64b67ff7b5
Model: fpadovani/tur-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
24079 lines
661 KiB
JSON
24079 lines
661 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1995301644424452,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.91241865158081,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 15.25,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.0786,
|
|
"mean_token_accuracy": 0.0003821215010248125,
|
|
"num_tokens": 8821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.92625322341919,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 15.3125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.1925,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18288.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.931429767608643,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 17.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1343,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 28664.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.981450891494751,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 18.375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.8816,
|
|
"mean_token_accuracy": 0.00011641443707048893,
|
|
"num_tokens": 37807.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.120096206665039,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 24.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.594,
|
|
"mean_token_accuracy": 7.418397581204772e-05,
|
|
"num_tokens": 48086.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.490445184707641,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 29.75,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 12.8914,
|
|
"mean_token_accuracy": 0.00022277416428551078,
|
|
"num_tokens": 57427.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.356700134277344,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 19.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.7365,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 66662.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.28960599899292,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.813,
|
|
"mean_token_accuracy": 0.0036690699635073543,
|
|
"num_tokens": 77388.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.716344833374023,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6278,
|
|
"mean_token_accuracy": 0.018409140314906834,
|
|
"num_tokens": 86093.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.73198299407959,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5419,
|
|
"mean_token_accuracy": 0.01724100988358259,
|
|
"num_tokens": 96097.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.63021240234375,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3987,
|
|
"mean_token_accuracy": 0.016340368427336216,
|
|
"num_tokens": 106328.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.640047836303712,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1971,
|
|
"mean_token_accuracy": 0.019724822044372557,
|
|
"num_tokens": 114822.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.70162353515625,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.1508,
|
|
"mean_token_accuracy": 0.019687474332749845,
|
|
"num_tokens": 124984.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.702993392944336,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 10.0193,
|
|
"mean_token_accuracy": 0.043946553766727445,
|
|
"num_tokens": 134054.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.67766580581665,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9853,
|
|
"mean_token_accuracy": 0.04433684386312962,
|
|
"num_tokens": 144561.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.662795639038086,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.9556,
|
|
"mean_token_accuracy": 0.04047659859061241,
|
|
"num_tokens": 153701.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.647140789031983,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.8424,
|
|
"mean_token_accuracy": 0.045346667617559434,
|
|
"num_tokens": 164291.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.631444549560547,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.8041,
|
|
"mean_token_accuracy": 0.048126301541924474,
|
|
"num_tokens": 174136.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.60820140838623,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.7185,
|
|
"mean_token_accuracy": 0.05448371171951294,
|
|
"num_tokens": 184368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.577119731903077,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.6957,
|
|
"mean_token_accuracy": 0.053209440782666206,
|
|
"num_tokens": 194659.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.547229385375976,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.5748,
|
|
"mean_token_accuracy": 0.050935184210538866,
|
|
"num_tokens": 204875.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.515561866760255,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.5761,
|
|
"mean_token_accuracy": 0.05177152454853058,
|
|
"num_tokens": 217033.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.471278762817382,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.3897,
|
|
"mean_token_accuracy": 0.05110491365194321,
|
|
"num_tokens": 225946.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.367455768585206,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.3339,
|
|
"mean_token_accuracy": 0.047009650617837906,
|
|
"num_tokens": 235413.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.327684879302979,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.3556,
|
|
"mean_token_accuracy": 0.041035909205675125,
|
|
"num_tokens": 247913.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.27382516860962,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.2148,
|
|
"mean_token_accuracy": 0.05273361578583717,
|
|
"num_tokens": 258486.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.201590824127198,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 9.1446,
|
|
"mean_token_accuracy": 0.052062534168362616,
|
|
"num_tokens": 268027.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.166050720214844,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 9.0516,
|
|
"mean_token_accuracy": 0.058280370011925695,
|
|
"num_tokens": 277470.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.048835277557373,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.9804,
|
|
"mean_token_accuracy": 0.055930846557021144,
|
|
"num_tokens": 286891.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.00039358139038,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.8799,
|
|
"mean_token_accuracy": 0.06509376168251038,
|
|
"num_tokens": 295636.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.860487079620361,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.8335,
|
|
"mean_token_accuracy": 0.06008245907723904,
|
|
"num_tokens": 306542.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.832607650756836,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.7586,
|
|
"mean_token_accuracy": 0.055786200985312465,
|
|
"num_tokens": 315956.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.66825180053711,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.7179,
|
|
"mean_token_accuracy": 0.058467098698019984,
|
|
"num_tokens": 325500.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.602266311645508,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.694,
|
|
"mean_token_accuracy": 0.05908621363341808,
|
|
"num_tokens": 335194.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.40921688079834,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.6446,
|
|
"mean_token_accuracy": 0.0567587573081255,
|
|
"num_tokens": 344717.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.355875492095947,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.5415,
|
|
"mean_token_accuracy": 0.058611446246504786,
|
|
"num_tokens": 354476.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.278519535064698,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.583,
|
|
"mean_token_accuracy": 0.05657804422080517,
|
|
"num_tokens": 363939.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.173566627502442,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.6021,
|
|
"mean_token_accuracy": 0.056013180688023564,
|
|
"num_tokens": 373187.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 9.077548694610595,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.5318,
|
|
"mean_token_accuracy": 0.057455115392804144,
|
|
"num_tokens": 382999.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 9.053006076812744,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.5703,
|
|
"mean_token_accuracy": 0.0567587573081255,
|
|
"num_tokens": 392639.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 9.040444278717041,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.5588,
|
|
"mean_token_accuracy": 0.05599666722118855,
|
|
"num_tokens": 403089.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.963880825042725,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.5074,
|
|
"mean_token_accuracy": 0.057358425855636594,
|
|
"num_tokens": 412321.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.893467998504638,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.5434,
|
|
"mean_token_accuracy": 0.05354794263839722,
|
|
"num_tokens": 421599.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.862988948822021,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.5194,
|
|
"mean_token_accuracy": 0.0537799846380949,
|
|
"num_tokens": 432012.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.87530450820923,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.4841,
|
|
"mean_token_accuracy": 0.06368993148207665,
|
|
"num_tokens": 441989.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.893553352355957,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4783,
|
|
"mean_token_accuracy": 0.058648154512047766,
|
|
"num_tokens": 451532.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.84007387161255,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.4902,
|
|
"mean_token_accuracy": 0.05833564437925816,
|
|
"num_tokens": 461815.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.851331996917725,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.5479,
|
|
"mean_token_accuracy": 0.05575990378856659,
|
|
"num_tokens": 470860.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.771306705474853,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.517,
|
|
"mean_token_accuracy": 0.05667851753532886,
|
|
"num_tokens": 480649.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.83043212890625,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4491,
|
|
"mean_token_accuracy": 0.06127909794449806,
|
|
"num_tokens": 489969.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.718154525756836,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.4681,
|
|
"mean_token_accuracy": 0.05937696918845177,
|
|
"num_tokens": 500000.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.808709049224854,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.4517,
|
|
"mean_token_accuracy": 0.06048737429082394,
|
|
"num_tokens": 510013.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.73866376876831,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.4782,
|
|
"mean_token_accuracy": 0.05986591465771198,
|
|
"num_tokens": 519698.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.757024574279786,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.4976,
|
|
"mean_token_accuracy": 0.05905666761100292,
|
|
"num_tokens": 531631.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.725329685211182,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.4571,
|
|
"mean_token_accuracy": 0.06441094093024731,
|
|
"num_tokens": 542204.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.754269123077393,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.383,
|
|
"mean_token_accuracy": 0.05882711634039879,
|
|
"num_tokens": 552269.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.679509162902832,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.3972,
|
|
"mean_token_accuracy": 0.05945455729961395,
|
|
"num_tokens": 561907.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.714503383636474,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.4968,
|
|
"mean_token_accuracy": 0.06066646538674832,
|
|
"num_tokens": 571283.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.684092807769776,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3882,
|
|
"mean_token_accuracy": 0.06541323848068714,
|
|
"num_tokens": 579896.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.677871990203858,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.3593,
|
|
"mean_token_accuracy": 0.07032604105770587,
|
|
"num_tokens": 588856.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.640351676940918,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.3892,
|
|
"mean_token_accuracy": 0.06575401201844215,
|
|
"num_tokens": 598910.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.718158340454101,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.4433,
|
|
"mean_token_accuracy": 0.062070992588996884,
|
|
"num_tokens": 609248.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.671941089630128,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.4592,
|
|
"mean_token_accuracy": 0.06366059742867947,
|
|
"num_tokens": 619352.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.706588459014892,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.4661,
|
|
"mean_token_accuracy": 0.06272411942481995,
|
|
"num_tokens": 628300.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.747008895874023,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.4018,
|
|
"mean_token_accuracy": 0.06640003323554992,
|
|
"num_tokens": 637969.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.643924903869628,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.3336,
|
|
"mean_token_accuracy": 0.0662142876535654,
|
|
"num_tokens": 647518.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.71212978363037,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.4995,
|
|
"mean_token_accuracy": 0.06047630980610848,
|
|
"num_tokens": 658292.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.704450511932373,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.3777,
|
|
"mean_token_accuracy": 0.06684980280697346,
|
|
"num_tokens": 667872.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.679888439178466,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.2947,
|
|
"mean_token_accuracy": 0.0693135604262352,
|
|
"num_tokens": 676976.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.639434337615967,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.3251,
|
|
"mean_token_accuracy": 0.06586846001446248,
|
|
"num_tokens": 686149.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.610470199584961,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.2287,
|
|
"mean_token_accuracy": 0.07368465512990952,
|
|
"num_tokens": 696439.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.60836582183838,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.2631,
|
|
"mean_token_accuracy": 0.07091691121459007,
|
|
"num_tokens": 705902.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.526141834259032,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.4111,
|
|
"mean_token_accuracy": 0.06636230871081353,
|
|
"num_tokens": 715973.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.639653873443603,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.3087,
|
|
"mean_token_accuracy": 0.06943082325160503,
|
|
"num_tokens": 725463.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.648558807373046,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.3425,
|
|
"mean_token_accuracy": 0.06693257950246334,
|
|
"num_tokens": 734941.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.635571098327636,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.3602,
|
|
"mean_token_accuracy": 0.06358583979308605,
|
|
"num_tokens": 744302.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.627023029327393,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.2859,
|
|
"mean_token_accuracy": 0.07252865135669709,
|
|
"num_tokens": 754341.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.77175464630127,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.4077,
|
|
"mean_token_accuracy": 0.06557657048106194,
|
|
"num_tokens": 764087.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.606595134735107,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.3433,
|
|
"mean_token_accuracy": 0.06623501852154731,
|
|
"num_tokens": 773728.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.625543308258056,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.3526,
|
|
"mean_token_accuracy": 0.06745064929127693,
|
|
"num_tokens": 784839.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.703261470794677,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.3402,
|
|
"mean_token_accuracy": 0.07067949250340462,
|
|
"num_tokens": 794514.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.594697570800781,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.3258,
|
|
"mean_token_accuracy": 0.07445940934121609,
|
|
"num_tokens": 805254.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.560181427001954,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.2289,
|
|
"mean_token_accuracy": 0.07385558374226094,
|
|
"num_tokens": 814135.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.59696340560913,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.2591,
|
|
"mean_token_accuracy": 0.07281342111527919,
|
|
"num_tokens": 823531.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.521518802642822,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.1938,
|
|
"mean_token_accuracy": 0.073985905200243,
|
|
"num_tokens": 832833.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.501078224182129,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.189,
|
|
"mean_token_accuracy": 0.07162816822528839,
|
|
"num_tokens": 841541.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.522215366363525,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.2042,
|
|
"mean_token_accuracy": 0.07523961365222931,
|
|
"num_tokens": 850689.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.53344202041626,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.1527,
|
|
"mean_token_accuracy": 0.08227219060063362,
|
|
"num_tokens": 860573.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.544331645965576,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.2541,
|
|
"mean_token_accuracy": 0.07364307269454003,
|
|
"num_tokens": 869784.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.543445301055907,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.216,
|
|
"mean_token_accuracy": 0.07438447847962379,
|
|
"num_tokens": 878716.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.488540935516358,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.2861,
|
|
"mean_token_accuracy": 0.07369314283132553,
|
|
"num_tokens": 888334.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.54775972366333,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.2092,
|
|
"mean_token_accuracy": 0.0723773218691349,
|
|
"num_tokens": 897701.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.553479957580567,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.1875,
|
|
"mean_token_accuracy": 0.07418999038636684,
|
|
"num_tokens": 907278.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.54272518157959,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.2054,
|
|
"mean_token_accuracy": 0.07134300135076047,
|
|
"num_tokens": 916194.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.520616245269775,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.207,
|
|
"mean_token_accuracy": 0.07744368985295295,
|
|
"num_tokens": 926743.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.551657390594482,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.2412,
|
|
"mean_token_accuracy": 0.07283293902873993,
|
|
"num_tokens": 936059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.39524564743042,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.1493,
|
|
"mean_token_accuracy": 0.07938387766480445,
|
|
"num_tokens": 945990.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.566281795501709,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.2333,
|
|
"mean_token_accuracy": 0.07900915294885635,
|
|
"num_tokens": 956626.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.450263595581054,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.179,
|
|
"mean_token_accuracy": 0.07676386944949627,
|
|
"num_tokens": 966200.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.555145835876464,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.1396,
|
|
"mean_token_accuracy": 0.07628392353653908,
|
|
"num_tokens": 975651.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.38605089187622,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 8.1242,
|
|
"mean_token_accuracy": 0.08255173414945602,
|
|
"num_tokens": 985264.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.503427410125733,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.1561,
|
|
"mean_token_accuracy": 0.07891211658716202,
|
|
"num_tokens": 996723.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.348312091827392,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.1596,
|
|
"mean_token_accuracy": 0.07888874784111977,
|
|
"num_tokens": 1006098.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.483654975891113,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.1879,
|
|
"mean_token_accuracy": 0.07833293974399566,
|
|
"num_tokens": 1016595.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.348458003997802,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.0453,
|
|
"mean_token_accuracy": 0.08186679258942604,
|
|
"num_tokens": 1026281.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.519502449035645,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.146,
|
|
"mean_token_accuracy": 0.083558601886034,
|
|
"num_tokens": 1036697.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.291908359527588,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.1041,
|
|
"mean_token_accuracy": 0.07858130112290382,
|
|
"num_tokens": 1047433.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.540676879882813,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.1544,
|
|
"mean_token_accuracy": 0.0775446780025959,
|
|
"num_tokens": 1056774.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.399338245391846,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 8.0729,
|
|
"mean_token_accuracy": 0.0837493509054184,
|
|
"num_tokens": 1068056.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.35708408355713,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 8.0637,
|
|
"mean_token_accuracy": 0.08658572286367416,
|
|
"num_tokens": 1077698.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.371122455596923,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 8.024,
|
|
"mean_token_accuracy": 0.08619759157299996,
|
|
"num_tokens": 1086485.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.344655513763428,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.0981,
|
|
"mean_token_accuracy": 0.07644926160573959,
|
|
"num_tokens": 1097329.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.330466938018798,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 8.0422,
|
|
"mean_token_accuracy": 0.08308784440159797,
|
|
"num_tokens": 1107990.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.35728998184204,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.9942,
|
|
"mean_token_accuracy": 0.09085135459899903,
|
|
"num_tokens": 1117798.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.300171279907227,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 8.1129,
|
|
"mean_token_accuracy": 0.08207414373755455,
|
|
"num_tokens": 1126976.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.369365787506103,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 8.0323,
|
|
"mean_token_accuracy": 0.08670488931238651,
|
|
"num_tokens": 1136410.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.333628749847412,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.0802,
|
|
"mean_token_accuracy": 0.08314882963895798,
|
|
"num_tokens": 1147162.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.32247953414917,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 8.0381,
|
|
"mean_token_accuracy": 0.08616725653409958,
|
|
"num_tokens": 1157578.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.34740982055664,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.951,
|
|
"mean_token_accuracy": 0.09069004505872727,
|
|
"num_tokens": 1166914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.420492267608642,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 8.1052,
|
|
"mean_token_accuracy": 0.07346431724727154,
|
|
"num_tokens": 1176740.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.245788764953613,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 8.0109,
|
|
"mean_token_accuracy": 0.08016561791300773,
|
|
"num_tokens": 1185497.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.463874912261963,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 8.1356,
|
|
"mean_token_accuracy": 0.07826456874608993,
|
|
"num_tokens": 1197390.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.216155338287354,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 8.0019,
|
|
"mean_token_accuracy": 0.08540406599640846,
|
|
"num_tokens": 1208293.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.2839524269104,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.9785,
|
|
"mean_token_accuracy": 0.08736005201935768,
|
|
"num_tokens": 1217860.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.30297269821167,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.9677,
|
|
"mean_token_accuracy": 0.0873529352247715,
|
|
"num_tokens": 1227259.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.173470211029052,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.8852,
|
|
"mean_token_accuracy": 0.09442147463560105,
|
|
"num_tokens": 1236775.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.359477519989014,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 8.016,
|
|
"mean_token_accuracy": 0.08664593175053596,
|
|
"num_tokens": 1246307.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 8.253477573394775,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.9653,
|
|
"mean_token_accuracy": 0.0844787299633026,
|
|
"num_tokens": 1255197.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.19736557006836,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.9582,
|
|
"mean_token_accuracy": 0.08905794695019723,
|
|
"num_tokens": 1265056.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.316370296478272,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.9362,
|
|
"mean_token_accuracy": 0.0887321688234806,
|
|
"num_tokens": 1274718.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.240344905853272,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 8.0083,
|
|
"mean_token_accuracy": 0.08291322365403175,
|
|
"num_tokens": 1284364.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.259224700927735,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.9941,
|
|
"mean_token_accuracy": 0.08638291731476784,
|
|
"num_tokens": 1294186.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.232594108581543,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.9088,
|
|
"mean_token_accuracy": 0.08878451958298683,
|
|
"num_tokens": 1303393.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.080247354507446,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.9236,
|
|
"mean_token_accuracy": 0.08766417391598225,
|
|
"num_tokens": 1312819.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.31481409072876,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.9491,
|
|
"mean_token_accuracy": 0.08286305814981461,
|
|
"num_tokens": 1323001.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.191842365264893,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.9247,
|
|
"mean_token_accuracy": 0.0884876474738121,
|
|
"num_tokens": 1333260.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 8.234783840179443,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.9158,
|
|
"mean_token_accuracy": 0.09147168770432472,
|
|
"num_tokens": 1342696.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.155243015289306,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.8796,
|
|
"mean_token_accuracy": 0.09066492915153504,
|
|
"num_tokens": 1353104.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.149154233932496,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.94,
|
|
"mean_token_accuracy": 0.08528364300727845,
|
|
"num_tokens": 1362871.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 8.276353740692139,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.9276,
|
|
"mean_token_accuracy": 0.0848144493997097,
|
|
"num_tokens": 1373622.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 8.046894645690918,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.8097,
|
|
"mean_token_accuracy": 0.0927486002445221,
|
|
"num_tokens": 1382707.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 8.174900817871094,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8886,
|
|
"mean_token_accuracy": 0.08790072128176689,
|
|
"num_tokens": 1392048.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 8.099133968353271,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.7641,
|
|
"mean_token_accuracy": 0.09442322701215744,
|
|
"num_tokens": 1401387.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 8.091927433013916,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.8821,
|
|
"mean_token_accuracy": 0.08691308051347732,
|
|
"num_tokens": 1411404.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 8.135170125961304,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.8546,
|
|
"mean_token_accuracy": 0.08999823704361916,
|
|
"num_tokens": 1420292.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 8.09806661605835,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.8309,
|
|
"mean_token_accuracy": 0.09208463206887245,
|
|
"num_tokens": 1429990.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 8.13855881690979,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.8628,
|
|
"mean_token_accuracy": 0.08753219097852707,
|
|
"num_tokens": 1440148.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 8.03170199394226,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7852,
|
|
"mean_token_accuracy": 0.08861454948782921,
|
|
"num_tokens": 1450015.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 8.133480024337768,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.8103,
|
|
"mean_token_accuracy": 0.08842997774481773,
|
|
"num_tokens": 1459582.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 8.07224726676941,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.8624,
|
|
"mean_token_accuracy": 0.08552923649549485,
|
|
"num_tokens": 1468151.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 8.003483009338378,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.7729,
|
|
"mean_token_accuracy": 0.09006534814834595,
|
|
"num_tokens": 1479099.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 8.126268005371093,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.873,
|
|
"mean_token_accuracy": 0.09025009647011757,
|
|
"num_tokens": 1488060.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 8.105157661437989,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.8384,
|
|
"mean_token_accuracy": 0.08615945875644684,
|
|
"num_tokens": 1498230.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 8.004671478271485,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.8242,
|
|
"mean_token_accuracy": 0.08832557871937752,
|
|
"num_tokens": 1507962.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 8.232299852371217,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.9545,
|
|
"mean_token_accuracy": 0.08387064412236214,
|
|
"num_tokens": 1518607.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 8.105499935150146,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.7776,
|
|
"mean_token_accuracy": 0.0910347007215023,
|
|
"num_tokens": 1527166.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 8.119454288482666,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.8703,
|
|
"mean_token_accuracy": 0.08840905651450157,
|
|
"num_tokens": 1536683.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 8.03728346824646,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.7568,
|
|
"mean_token_accuracy": 0.09142104163765907,
|
|
"num_tokens": 1546243.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 8.057508659362792,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.7846,
|
|
"mean_token_accuracy": 0.0889986164867878,
|
|
"num_tokens": 1555916.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.945902585983276,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6987,
|
|
"mean_token_accuracy": 0.094569893181324,
|
|
"num_tokens": 1566617.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.919804286956787,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7405,
|
|
"mean_token_accuracy": 0.08826911225914955,
|
|
"num_tokens": 1575413.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 8.038426303863526,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7465,
|
|
"mean_token_accuracy": 0.09363904744386672,
|
|
"num_tokens": 1586863.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 8.045948362350464,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.8292,
|
|
"mean_token_accuracy": 0.09168099835515023,
|
|
"num_tokens": 1597685.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 8.02879524230957,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.7286,
|
|
"mean_token_accuracy": 0.0919680006802082,
|
|
"num_tokens": 1607103.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 8.00586986541748,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.7797,
|
|
"mean_token_accuracy": 0.09101953282952309,
|
|
"num_tokens": 1617919.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 8.015330362319947,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.8094,
|
|
"mean_token_accuracy": 0.09074466563761234,
|
|
"num_tokens": 1627293.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 8.053974103927612,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.8196,
|
|
"mean_token_accuracy": 0.08691304028034211,
|
|
"num_tokens": 1638440.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.915004444122315,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.7225,
|
|
"mean_token_accuracy": 0.09402119815349579,
|
|
"num_tokens": 1648148.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.9461534976959225,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.75,
|
|
"mean_token_accuracy": 0.0946639321744442,
|
|
"num_tokens": 1658334.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 8.101148223876953,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.7948,
|
|
"mean_token_accuracy": 0.08722254931926728,
|
|
"num_tokens": 1667963.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.956143712997436,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.6999,
|
|
"mean_token_accuracy": 0.09139039814472198,
|
|
"num_tokens": 1677270.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.8967897415161135,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6758,
|
|
"mean_token_accuracy": 0.09658752381801605,
|
|
"num_tokens": 1686770.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.969452381134033,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.7521,
|
|
"mean_token_accuracy": 0.09170125946402549,
|
|
"num_tokens": 1697507.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.872890663146973,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.6841,
|
|
"mean_token_accuracy": 0.09290253594517708,
|
|
"num_tokens": 1708253.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 8.000007724761963,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.7539,
|
|
"mean_token_accuracy": 0.08929965049028396,
|
|
"num_tokens": 1717827.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.832028770446778,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5521,
|
|
"mean_token_accuracy": 0.10026744902133941,
|
|
"num_tokens": 1726678.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.88534722328186,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.7009,
|
|
"mean_token_accuracy": 0.09250150695443153,
|
|
"num_tokens": 1737518.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.921040725708008,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5908,
|
|
"mean_token_accuracy": 0.10193264484405518,
|
|
"num_tokens": 1746338.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.840936279296875,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6714,
|
|
"mean_token_accuracy": 0.09223530441522598,
|
|
"num_tokens": 1756538.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.921091079711914,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.6709,
|
|
"mean_token_accuracy": 0.09273412451148033,
|
|
"num_tokens": 1766722.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.847049188613892,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.6012,
|
|
"mean_token_accuracy": 0.09680447876453399,
|
|
"num_tokens": 1777039.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.876219177246094,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.7057,
|
|
"mean_token_accuracy": 0.09129747226834298,
|
|
"num_tokens": 1787621.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.934077644348145,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.7262,
|
|
"mean_token_accuracy": 0.09550910741090775,
|
|
"num_tokens": 1798345.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.863957357406616,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6484,
|
|
"mean_token_accuracy": 0.09627768769860268,
|
|
"num_tokens": 1807994.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.814187479019165,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.6025,
|
|
"mean_token_accuracy": 0.09041696637868882,
|
|
"num_tokens": 1817965.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.898249673843384,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.651,
|
|
"mean_token_accuracy": 0.09574145302176476,
|
|
"num_tokens": 1827094.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.875781297683716,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.62,
|
|
"mean_token_accuracy": 0.09457285776734352,
|
|
"num_tokens": 1837754.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.698305368423462,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.607,
|
|
"mean_token_accuracy": 0.09555240049958229,
|
|
"num_tokens": 1847500.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.8827156066894535,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.6649,
|
|
"mean_token_accuracy": 0.08770858943462372,
|
|
"num_tokens": 1857663.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.890668249130249,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.7266,
|
|
"mean_token_accuracy": 0.09187851324677468,
|
|
"num_tokens": 1867752.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.822569274902344,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.6389,
|
|
"mean_token_accuracy": 0.09240206554532052,
|
|
"num_tokens": 1877479.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.813203954696656,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6736,
|
|
"mean_token_accuracy": 0.09363591149449349,
|
|
"num_tokens": 1887944.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.859562635421753,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5872,
|
|
"mean_token_accuracy": 0.09667022675275802,
|
|
"num_tokens": 1896991.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.771055555343628,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.5995,
|
|
"mean_token_accuracy": 0.10148105099797249,
|
|
"num_tokens": 1907216.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.911443471908569,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.6083,
|
|
"mean_token_accuracy": 0.09393106177449226,
|
|
"num_tokens": 1917206.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.743614768981933,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.6854,
|
|
"mean_token_accuracy": 0.09089522212743759,
|
|
"num_tokens": 1929669.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.8640203952789305,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.5627,
|
|
"mean_token_accuracy": 0.09610607698559762,
|
|
"num_tokens": 1939881.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.689713811874389,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.5888,
|
|
"mean_token_accuracy": 0.09820158705115319,
|
|
"num_tokens": 1949423.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.818390989303589,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.6107,
|
|
"mean_token_accuracy": 0.09391192570328713,
|
|
"num_tokens": 1959214.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.867146348953247,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5943,
|
|
"mean_token_accuracy": 0.09512368217110634,
|
|
"num_tokens": 1968963.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.708599042892456,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.5637,
|
|
"mean_token_accuracy": 0.0960096038877964,
|
|
"num_tokens": 1979551.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.774115419387817,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.5299,
|
|
"mean_token_accuracy": 0.09881004914641381,
|
|
"num_tokens": 1988432.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.747634410858154,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.5714,
|
|
"mean_token_accuracy": 0.09639670103788375,
|
|
"num_tokens": 1997509.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.858575534820557,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.7288,
|
|
"mean_token_accuracy": 0.09117813184857368,
|
|
"num_tokens": 2007406.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.8197108745574955,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.5532,
|
|
"mean_token_accuracy": 0.09217148125171662,
|
|
"num_tokens": 2016760.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.714381504058838,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.5862,
|
|
"mean_token_accuracy": 0.0973098672926426,
|
|
"num_tokens": 2027776.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.711545372009278,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.525,
|
|
"mean_token_accuracy": 0.09987044408917427,
|
|
"num_tokens": 2036955.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.708169794082641,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.4481,
|
|
"mean_token_accuracy": 0.09874232336878777,
|
|
"num_tokens": 2046118.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.663513088226319,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.5182,
|
|
"mean_token_accuracy": 0.09265113547444344,
|
|
"num_tokens": 2056266.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.766235733032227,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.5564,
|
|
"mean_token_accuracy": 0.09874644502997398,
|
|
"num_tokens": 2067416.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.742217063903809,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.5323,
|
|
"mean_token_accuracy": 0.09508499130606651,
|
|
"num_tokens": 2076926.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.7295256614685055,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.5473,
|
|
"mean_token_accuracy": 0.10004104599356652,
|
|
"num_tokens": 2088017.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.6699363708496096,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.5634,
|
|
"mean_token_accuracy": 0.09938672706484794,
|
|
"num_tokens": 2097249.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.716280460357666,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.4976,
|
|
"mean_token_accuracy": 0.09836835712194443,
|
|
"num_tokens": 2105778.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.753679323196411,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.5311,
|
|
"mean_token_accuracy": 0.09935536906123162,
|
|
"num_tokens": 2114710.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.64402494430542,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.4801,
|
|
"mean_token_accuracy": 0.09851668924093246,
|
|
"num_tokens": 2124002.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.777598571777344,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.5611,
|
|
"mean_token_accuracy": 0.09994415789842606,
|
|
"num_tokens": 2134592.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.567396640777588,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.4156,
|
|
"mean_token_accuracy": 0.10332436636090278,
|
|
"num_tokens": 2143641.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.74939751625061,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.5304,
|
|
"mean_token_accuracy": 0.09657632037997246,
|
|
"num_tokens": 2154738.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.590510129928589,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.4692,
|
|
"mean_token_accuracy": 0.10435619726777076,
|
|
"num_tokens": 2164365.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.6218901634216305,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.3518,
|
|
"mean_token_accuracy": 0.1033005841076374,
|
|
"num_tokens": 2173185.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.6353357315063475,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.4808,
|
|
"mean_token_accuracy": 0.1050780363380909,
|
|
"num_tokens": 2184717.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.639813375473023,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.4457,
|
|
"mean_token_accuracy": 0.10765890702605248,
|
|
"num_tokens": 2193681.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.63369607925415,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.4596,
|
|
"mean_token_accuracy": 0.09970392286777496,
|
|
"num_tokens": 2203366.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.701994895935059,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.459,
|
|
"mean_token_accuracy": 0.10135932490229607,
|
|
"num_tokens": 2213982.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.644823122024536,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.4974,
|
|
"mean_token_accuracy": 0.09790250882506371,
|
|
"num_tokens": 2222897.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.627260303497314,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.446,
|
|
"mean_token_accuracy": 0.10249497219920159,
|
|
"num_tokens": 2232472.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.57940993309021,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.489,
|
|
"mean_token_accuracy": 0.10549622848629951,
|
|
"num_tokens": 2242666.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.741400814056396,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.568,
|
|
"mean_token_accuracy": 0.09314922839403153,
|
|
"num_tokens": 2254586.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.5815185546875,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.3888,
|
|
"mean_token_accuracy": 0.10329079777002334,
|
|
"num_tokens": 2264619.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.781215858459473,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.4773,
|
|
"mean_token_accuracy": 0.0925179947167635,
|
|
"num_tokens": 2274114.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.433381843566894,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.3847,
|
|
"mean_token_accuracy": 0.10573233887553216,
|
|
"num_tokens": 2283887.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.647586059570313,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.3971,
|
|
"mean_token_accuracy": 0.1060848891735077,
|
|
"num_tokens": 2293090.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.600371837615967,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.5024,
|
|
"mean_token_accuracy": 0.09858990088105202,
|
|
"num_tokens": 2302828.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.6886982917785645,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.3914,
|
|
"mean_token_accuracy": 0.10518279448151588,
|
|
"num_tokens": 2311415.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.562065887451172,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.4684,
|
|
"mean_token_accuracy": 0.09992958679795265,
|
|
"num_tokens": 2321512.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.6449196338653564,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.3802,
|
|
"mean_token_accuracy": 0.10009320005774498,
|
|
"num_tokens": 2331398.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.582540845870971,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.378,
|
|
"mean_token_accuracy": 0.10733285993337631,
|
|
"num_tokens": 2341751.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.647002792358398,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.3963,
|
|
"mean_token_accuracy": 0.09711159616708756,
|
|
"num_tokens": 2352538.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.58666090965271,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.4581,
|
|
"mean_token_accuracy": 0.09764329642057419,
|
|
"num_tokens": 2362433.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.584440898895264,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.4382,
|
|
"mean_token_accuracy": 0.09720063619315625,
|
|
"num_tokens": 2372431.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.566992712020874,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.4337,
|
|
"mean_token_accuracy": 0.10857149809598923,
|
|
"num_tokens": 2382483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.723560905456543,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.4276,
|
|
"mean_token_accuracy": 0.09219059199094773,
|
|
"num_tokens": 2392835.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.536263561248779,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.3764,
|
|
"mean_token_accuracy": 0.09699192494153977,
|
|
"num_tokens": 2402305.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.461746692657471,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.3208,
|
|
"mean_token_accuracy": 0.10833752900362015,
|
|
"num_tokens": 2412093.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.578193950653076,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.2861,
|
|
"mean_token_accuracy": 0.10602069944143296,
|
|
"num_tokens": 2421349.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.4720502376556395,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.2871,
|
|
"mean_token_accuracy": 0.11482211500406266,
|
|
"num_tokens": 2430672.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.4783854484558105,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.3577,
|
|
"mean_token_accuracy": 0.10103069022297859,
|
|
"num_tokens": 2439355.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.5710039138793945,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.3519,
|
|
"mean_token_accuracy": 0.10859728455543519,
|
|
"num_tokens": 2448860.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.42594199180603,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.3812,
|
|
"mean_token_accuracy": 0.10127258449792861,
|
|
"num_tokens": 2458276.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.5558329105377195,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.2995,
|
|
"mean_token_accuracy": 0.10753061398863792,
|
|
"num_tokens": 2467791.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.481610918045044,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.4297,
|
|
"mean_token_accuracy": 0.10026444271206855,
|
|
"num_tokens": 2477549.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.551158761978149,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.3405,
|
|
"mean_token_accuracy": 0.09958168342709542,
|
|
"num_tokens": 2487549.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.575411987304688,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.3359,
|
|
"mean_token_accuracy": 0.10639088824391366,
|
|
"num_tokens": 2496799.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.616192436218261,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.4325,
|
|
"mean_token_accuracy": 0.10289375483989716,
|
|
"num_tokens": 2505795.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.4822615623474125,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.2474,
|
|
"mean_token_accuracy": 0.10294352620840072,
|
|
"num_tokens": 2515289.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.597700119018555,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.4296,
|
|
"mean_token_accuracy": 0.09725573807954788,
|
|
"num_tokens": 2524563.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.434320259094238,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.3241,
|
|
"mean_token_accuracy": 0.10576057732105255,
|
|
"num_tokens": 2534057.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.505590295791626,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.3078,
|
|
"mean_token_accuracy": 0.10811854675412177,
|
|
"num_tokens": 2544646.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.574274253845215,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.3776,
|
|
"mean_token_accuracy": 0.10291878581047058,
|
|
"num_tokens": 2553843.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.4811914443969725,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.4132,
|
|
"mean_token_accuracy": 0.09877474531531334,
|
|
"num_tokens": 2564061.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.492168235778808,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.2787,
|
|
"mean_token_accuracy": 0.10895716845989227,
|
|
"num_tokens": 2574758.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.485337257385254,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.35,
|
|
"mean_token_accuracy": 0.10393542721867562,
|
|
"num_tokens": 2585213.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.545273399353027,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.3947,
|
|
"mean_token_accuracy": 0.10360251069068908,
|
|
"num_tokens": 2595511.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.474040794372558,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.3246,
|
|
"mean_token_accuracy": 0.1028148852288723,
|
|
"num_tokens": 2605930.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.545388984680176,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.2089,
|
|
"mean_token_accuracy": 0.11397390365600586,
|
|
"num_tokens": 2614224.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.5077166080474855,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.421,
|
|
"mean_token_accuracy": 0.09980487525463104,
|
|
"num_tokens": 2624879.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.493503904342651,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.2739,
|
|
"mean_token_accuracy": 0.10615406557917595,
|
|
"num_tokens": 2633836.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.377463626861572,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.3316,
|
|
"mean_token_accuracy": 0.10316964089870453,
|
|
"num_tokens": 2643754.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.616025114059449,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.3922,
|
|
"mean_token_accuracy": 0.09743982404470444,
|
|
"num_tokens": 2652708.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.4626898765563965,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.352,
|
|
"mean_token_accuracy": 0.1009536899626255,
|
|
"num_tokens": 2662353.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.507920217514038,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.2551,
|
|
"mean_token_accuracy": 0.10801847130060196,
|
|
"num_tokens": 2672376.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.4212922096252445,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.3581,
|
|
"mean_token_accuracy": 0.10042979195713997,
|
|
"num_tokens": 2682115.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.520157718658448,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.3351,
|
|
"mean_token_accuracy": 0.10273827612400055,
|
|
"num_tokens": 2692429.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.495982551574707,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.2832,
|
|
"mean_token_accuracy": 0.10646675527095795,
|
|
"num_tokens": 2701373.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.59482774734497,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.4542,
|
|
"mean_token_accuracy": 0.10424424782395363,
|
|
"num_tokens": 2710717.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.465184688568115,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.315,
|
|
"mean_token_accuracy": 0.10450968667864799,
|
|
"num_tokens": 2720936.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.52575716972351,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.2724,
|
|
"mean_token_accuracy": 0.11038048714399337,
|
|
"num_tokens": 2730504.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.384076833724976,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.2831,
|
|
"mean_token_accuracy": 0.1060723252594471,
|
|
"num_tokens": 2739069.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.52955813407898,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.3542,
|
|
"mean_token_accuracy": 0.09965510442852973,
|
|
"num_tokens": 2748941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.469629859924316,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.3046,
|
|
"mean_token_accuracy": 0.10589431822299958,
|
|
"num_tokens": 2758915.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.496847534179688,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.3413,
|
|
"mean_token_accuracy": 0.10205910354852676,
|
|
"num_tokens": 2768972.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.4970423698425295,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.1917,
|
|
"mean_token_accuracy": 0.10759721770882606,
|
|
"num_tokens": 2777989.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.3449572086334225,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.2963,
|
|
"mean_token_accuracy": 0.10734140872955322,
|
|
"num_tokens": 2788227.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.547876358032227,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.2899,
|
|
"mean_token_accuracy": 0.10559340417385102,
|
|
"num_tokens": 2797729.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.433524799346924,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.2836,
|
|
"mean_token_accuracy": 0.10649279952049255,
|
|
"num_tokens": 2807215.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.472461366653443,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.202,
|
|
"mean_token_accuracy": 0.10329415574669838,
|
|
"num_tokens": 2816945.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.3642683029174805,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.2831,
|
|
"mean_token_accuracy": 0.10314463749527931,
|
|
"num_tokens": 2827072.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.438300848007202,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.2172,
|
|
"mean_token_accuracy": 0.1053712360560894,
|
|
"num_tokens": 2837928.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.362199783325195,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.2508,
|
|
"mean_token_accuracy": 0.10845730304718018,
|
|
"num_tokens": 2847861.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.463563776016235,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.248,
|
|
"mean_token_accuracy": 0.10768592208623887,
|
|
"num_tokens": 2857885.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.49535756111145,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.2817,
|
|
"mean_token_accuracy": 0.1021933138370514,
|
|
"num_tokens": 2867004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.361451148986816,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 7.1422,
|
|
"mean_token_accuracy": 0.10897669419646264,
|
|
"num_tokens": 2876285.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.437837982177735,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.2794,
|
|
"mean_token_accuracy": 0.10400166437029838,
|
|
"num_tokens": 2886967.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.400296020507812,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 7.2407,
|
|
"mean_token_accuracy": 0.10448872894048691,
|
|
"num_tokens": 2897137.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.402553701400757,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.2226,
|
|
"mean_token_accuracy": 0.11351158022880554,
|
|
"num_tokens": 2907658.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.393366098403931,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.2207,
|
|
"mean_token_accuracy": 0.10734575539827347,
|
|
"num_tokens": 2917801.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.441537857055664,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.2977,
|
|
"mean_token_accuracy": 0.10554568693041802,
|
|
"num_tokens": 2927188.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.3817533493042,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.1798,
|
|
"mean_token_accuracy": 0.10319826304912567,
|
|
"num_tokens": 2936781.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.3468931198120115,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.1681,
|
|
"mean_token_accuracy": 0.10979624688625336,
|
|
"num_tokens": 2946426.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.339980173110962,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.2007,
|
|
"mean_token_accuracy": 0.10412992984056473,
|
|
"num_tokens": 2956246.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.4069291114807125,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.2068,
|
|
"mean_token_accuracy": 0.1070282831788063,
|
|
"num_tokens": 2965930.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.319704008102417,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 7.1387,
|
|
"mean_token_accuracy": 0.11144708767533303,
|
|
"num_tokens": 2975975.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.368978881835938,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 7.1486,
|
|
"mean_token_accuracy": 0.10778968706727028,
|
|
"num_tokens": 2985343.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.321302700042724,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 7.1615,
|
|
"mean_token_accuracy": 0.11044318154454232,
|
|
"num_tokens": 2994420.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.383437299728394,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.2869,
|
|
"mean_token_accuracy": 0.10852601900696754,
|
|
"num_tokens": 3004447.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.49035234451294,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 7.177,
|
|
"mean_token_accuracy": 0.10626579597592353,
|
|
"num_tokens": 3014596.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.332225370407104,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 7.111,
|
|
"mean_token_accuracy": 0.1120404727756977,
|
|
"num_tokens": 3024528.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.32868595123291,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 7.2234,
|
|
"mean_token_accuracy": 0.10404160246253014,
|
|
"num_tokens": 3035233.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.376626300811767,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.2365,
|
|
"mean_token_accuracy": 0.10801902562379836,
|
|
"num_tokens": 3045890.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.326313638687134,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 7.1306,
|
|
"mean_token_accuracy": 0.11243928968906403,
|
|
"num_tokens": 3056640.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.366794013977051,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 7.1631,
|
|
"mean_token_accuracy": 0.11329249888658524,
|
|
"num_tokens": 3066938.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.35032844543457,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.236,
|
|
"mean_token_accuracy": 0.11088693737983704,
|
|
"num_tokens": 3076791.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.395107746124268,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 7.1203,
|
|
"mean_token_accuracy": 0.10925953909754753,
|
|
"num_tokens": 3087532.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.281245279312134,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 7.2466,
|
|
"mean_token_accuracy": 0.10709367841482162,
|
|
"num_tokens": 3097465.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.441256141662597,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.1655,
|
|
"mean_token_accuracy": 0.10919474661350251,
|
|
"num_tokens": 3107162.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.253028106689453,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 7.1456,
|
|
"mean_token_accuracy": 0.11203786730766296,
|
|
"num_tokens": 3117154.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.32353892326355,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 7.1594,
|
|
"mean_token_accuracy": 0.10915421843528747,
|
|
"num_tokens": 3127635.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.413996791839599,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 7.1971,
|
|
"mean_token_accuracy": 0.10433795824646949,
|
|
"num_tokens": 3137806.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.3293005466461185,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 7.2291,
|
|
"mean_token_accuracy": 0.10129423663020135,
|
|
"num_tokens": 3147704.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.344339752197266,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.177,
|
|
"mean_token_accuracy": 0.10396260619163514,
|
|
"num_tokens": 3158486.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.358778429031372,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.1816,
|
|
"mean_token_accuracy": 0.11292050555348396,
|
|
"num_tokens": 3168518.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.306634759902954,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 7.093,
|
|
"mean_token_accuracy": 0.11131592839956284,
|
|
"num_tokens": 3177502.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.302649450302124,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 7.132,
|
|
"mean_token_accuracy": 0.11160676255822181,
|
|
"num_tokens": 3187408.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.337405490875244,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.182,
|
|
"mean_token_accuracy": 0.11259776130318641,
|
|
"num_tokens": 3196812.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.335812187194824,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 7.0628,
|
|
"mean_token_accuracy": 0.11406400948762893,
|
|
"num_tokens": 3206159.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.254757928848266,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 7.0451,
|
|
"mean_token_accuracy": 0.11323473453521729,
|
|
"num_tokens": 3217329.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.261689615249634,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 7.1639,
|
|
"mean_token_accuracy": 0.11070609316229821,
|
|
"num_tokens": 3227558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.421111106872559,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.2582,
|
|
"mean_token_accuracy": 0.10368104577064514,
|
|
"num_tokens": 3237719.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.341942644119262,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.1627,
|
|
"mean_token_accuracy": 0.11192248985171319,
|
|
"num_tokens": 3246483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.233231067657471,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 7.0634,
|
|
"mean_token_accuracy": 0.11377293840050698,
|
|
"num_tokens": 3256955.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.347592067718506,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 7.1488,
|
|
"mean_token_accuracy": 0.10765791982412339,
|
|
"num_tokens": 3266799.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.334767866134643,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 7.1478,
|
|
"mean_token_accuracy": 0.10780449137091637,
|
|
"num_tokens": 3276595.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.245278692245483,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 7.0769,
|
|
"mean_token_accuracy": 0.10730566009879113,
|
|
"num_tokens": 3286047.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.316799879074097,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 7.1646,
|
|
"mean_token_accuracy": 0.10785932466387749,
|
|
"num_tokens": 3295364.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.33067831993103,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 7.0745,
|
|
"mean_token_accuracy": 0.11385716944932937,
|
|
"num_tokens": 3305319.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.214070272445679,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 7.0871,
|
|
"mean_token_accuracy": 0.11497763246297836,
|
|
"num_tokens": 3315349.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.287170171737671,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 7.1709,
|
|
"mean_token_accuracy": 0.10371953621506691,
|
|
"num_tokens": 3325603.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.254241466522217,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 7.0624,
|
|
"mean_token_accuracy": 0.11126351356506348,
|
|
"num_tokens": 3334693.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.293223333358765,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 7.0913,
|
|
"mean_token_accuracy": 0.10409749746322632,
|
|
"num_tokens": 3345259.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.280128622055054,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.11194226369261742,
|
|
"num_tokens": 3354072.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.393798208236694,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 7.1109,
|
|
"mean_token_accuracy": 0.1075687400996685,
|
|
"num_tokens": 3364881.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.227674198150635,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 7.0544,
|
|
"mean_token_accuracy": 0.11126514673233032,
|
|
"num_tokens": 3374030.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.292581796646118,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 7.0712,
|
|
"mean_token_accuracy": 0.10977467969059944,
|
|
"num_tokens": 3384009.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.3453587055206295,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 7.1764,
|
|
"mean_token_accuracy": 0.10677952840924262,
|
|
"num_tokens": 3393660.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.311243486404419,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 7.2011,
|
|
"mean_token_accuracy": 0.11048303991556167,
|
|
"num_tokens": 3404364.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.421372318267823,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 7.0974,
|
|
"mean_token_accuracy": 0.10910709127783776,
|
|
"num_tokens": 3412990.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.14683895111084,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 7.0533,
|
|
"mean_token_accuracy": 0.1123741738498211,
|
|
"num_tokens": 3422339.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.241878366470337,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 7.0462,
|
|
"mean_token_accuracy": 0.11458217501640319,
|
|
"num_tokens": 3433093.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.317088603973389,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 7.1223,
|
|
"mean_token_accuracy": 0.11018144264817238,
|
|
"num_tokens": 3443464.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.248693656921387,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 7.079,
|
|
"mean_token_accuracy": 0.10889410227537155,
|
|
"num_tokens": 3453380.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.283649063110351,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 7.1213,
|
|
"mean_token_accuracy": 0.10985768139362335,
|
|
"num_tokens": 3463583.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.192403268814087,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 7.0285,
|
|
"mean_token_accuracy": 0.11696212887763976,
|
|
"num_tokens": 3473640.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.219367408752442,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 7.0867,
|
|
"mean_token_accuracy": 0.10979457870125771,
|
|
"num_tokens": 3483827.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.295134878158569,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 7.0601,
|
|
"mean_token_accuracy": 0.11907404363155365,
|
|
"num_tokens": 3493763.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.286717557907105,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 7.1599,
|
|
"mean_token_accuracy": 0.10770777985453606,
|
|
"num_tokens": 3503119.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.266967391967773,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 7.0697,
|
|
"mean_token_accuracy": 0.11251412183046341,
|
|
"num_tokens": 3513235.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.309150743484497,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.1909,
|
|
"mean_token_accuracy": 0.10825281664729118,
|
|
"num_tokens": 3523633.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.242037582397461,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 7.0344,
|
|
"mean_token_accuracy": 0.10948573946952819,
|
|
"num_tokens": 3532888.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.249222183227539,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 7.0524,
|
|
"mean_token_accuracy": 0.11693340837955475,
|
|
"num_tokens": 3541942.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.217988681793213,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 7.0303,
|
|
"mean_token_accuracy": 0.11028838530182838,
|
|
"num_tokens": 3551544.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.225018787384033,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 7.0354,
|
|
"mean_token_accuracy": 0.11371938288211822,
|
|
"num_tokens": 3561024.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.231437492370605,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 7.0097,
|
|
"mean_token_accuracy": 0.11793867349624634,
|
|
"num_tokens": 3570962.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.105706644058228,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 7.013,
|
|
"mean_token_accuracy": 0.1166162334382534,
|
|
"num_tokens": 3580669.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.306497097015381,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 7.0338,
|
|
"mean_token_accuracy": 0.11162179484963416,
|
|
"num_tokens": 3590627.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.187291955947876,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 7.0953,
|
|
"mean_token_accuracy": 0.10703551173210143,
|
|
"num_tokens": 3599872.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.294304513931275,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 7.0767,
|
|
"mean_token_accuracy": 0.11386150121688843,
|
|
"num_tokens": 3609809.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.298921871185303,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 7.0807,
|
|
"mean_token_accuracy": 0.11436494663357735,
|
|
"num_tokens": 3619385.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.1236320495605465,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.9365,
|
|
"mean_token_accuracy": 0.1221968486905098,
|
|
"num_tokens": 3628867.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.1869734764099125,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.957,
|
|
"mean_token_accuracy": 0.12176943942904472,
|
|
"num_tokens": 3637528.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.262745809555054,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 7.0832,
|
|
"mean_token_accuracy": 0.11131772547960281,
|
|
"num_tokens": 3648011.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.221261215209961,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 7.0548,
|
|
"mean_token_accuracy": 0.11538778394460678,
|
|
"num_tokens": 3657648.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.252969884872437,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.1120391070842743,
|
|
"num_tokens": 3666965.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.268553447723389,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 7.0761,
|
|
"mean_token_accuracy": 0.10713672935962677,
|
|
"num_tokens": 3676609.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.212067604064941,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.958,
|
|
"mean_token_accuracy": 0.11653830632567405,
|
|
"num_tokens": 3685884.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.169482707977295,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 7.0926,
|
|
"mean_token_accuracy": 0.11437800228595733,
|
|
"num_tokens": 3695436.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.212578773498535,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.9474,
|
|
"mean_token_accuracy": 0.12130062356591224,
|
|
"num_tokens": 3704806.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.132661199569702,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 7.0117,
|
|
"mean_token_accuracy": 0.1149711400270462,
|
|
"num_tokens": 3713927.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.325976610183716,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 7.0869,
|
|
"mean_token_accuracy": 0.10872976779937744,
|
|
"num_tokens": 3723685.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.113046550750733,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 7.0462,
|
|
"mean_token_accuracy": 0.11273184865713119,
|
|
"num_tokens": 3733918.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.19275393486023,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 7.0139,
|
|
"mean_token_accuracy": 0.10976849347352982,
|
|
"num_tokens": 3744466.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.280959558486939,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.9644,
|
|
"mean_token_accuracy": 0.11463172510266303,
|
|
"num_tokens": 3754082.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.130083608627319,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.11847582682967187,
|
|
"num_tokens": 3763111.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.268581295013428,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 7.0493,
|
|
"mean_token_accuracy": 0.11117423921823502,
|
|
"num_tokens": 3772555.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.268717622756958,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 7.0815,
|
|
"mean_token_accuracy": 0.111016134172678,
|
|
"num_tokens": 3783073.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.111140966415405,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 7.0262,
|
|
"mean_token_accuracy": 0.11531205549836158,
|
|
"num_tokens": 3792277.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.230959272384643,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.9675,
|
|
"mean_token_accuracy": 0.11661996394395828,
|
|
"num_tokens": 3801098.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.192171192169189,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 7.0099,
|
|
"mean_token_accuracy": 0.11187705099582672,
|
|
"num_tokens": 3810614.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.157060289382935,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.9944,
|
|
"mean_token_accuracy": 0.11400014832615853,
|
|
"num_tokens": 3818989.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.1906585693359375,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 7.024,
|
|
"mean_token_accuracy": 0.11215802431106567,
|
|
"num_tokens": 3829319.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.190929889678955,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 7.0554,
|
|
"mean_token_accuracy": 0.11058950945734977,
|
|
"num_tokens": 3839545.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.1641429424285885,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.9876,
|
|
"mean_token_accuracy": 0.11402552798390389,
|
|
"num_tokens": 3849029.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.209018182754517,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 7.0268,
|
|
"mean_token_accuracy": 0.11167576164007187,
|
|
"num_tokens": 3859463.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.266246891021728,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 7.072,
|
|
"mean_token_accuracy": 0.1130496896803379,
|
|
"num_tokens": 3869695.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.197639513015747,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 7.0303,
|
|
"mean_token_accuracy": 0.11531598567962646,
|
|
"num_tokens": 3879608.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.166806554794311,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.942,
|
|
"mean_token_accuracy": 0.11460894122719764,
|
|
"num_tokens": 3888709.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.064781713485718,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.9031,
|
|
"mean_token_accuracy": 0.11336119174957275,
|
|
"num_tokens": 3898392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.218285322189331,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 7.1152,
|
|
"mean_token_accuracy": 0.1025274470448494,
|
|
"num_tokens": 3909508.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.13175253868103,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.9752,
|
|
"mean_token_accuracy": 0.11452259048819542,
|
|
"num_tokens": 3918155.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.231250333786011,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 7.0059,
|
|
"mean_token_accuracy": 0.11461703926324844,
|
|
"num_tokens": 3928478.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.109054040908814,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 7.0509,
|
|
"mean_token_accuracy": 0.11921404525637627,
|
|
"num_tokens": 3938126.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.078082656860351,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.8813,
|
|
"mean_token_accuracy": 0.1193962648510933,
|
|
"num_tokens": 3948176.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.241360139846802,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.9992,
|
|
"mean_token_accuracy": 0.11483975872397423,
|
|
"num_tokens": 3958983.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.210058927536011,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.11502718180418015,
|
|
"num_tokens": 3968766.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.144572973251343,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.9732,
|
|
"mean_token_accuracy": 0.11400391906499863,
|
|
"num_tokens": 3979487.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.132036590576172,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.948,
|
|
"mean_token_accuracy": 0.11947876140475273,
|
|
"num_tokens": 3988450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.156334114074707,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.9566,
|
|
"mean_token_accuracy": 0.11755107268691063,
|
|
"num_tokens": 3997492.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.110681772232056,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.9394,
|
|
"mean_token_accuracy": 0.12227256521582604,
|
|
"num_tokens": 4007298.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.190283393859863,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.9835,
|
|
"mean_token_accuracy": 0.1158505879342556,
|
|
"num_tokens": 4017727.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.130951261520385,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.979,
|
|
"mean_token_accuracy": 0.11403572708368301,
|
|
"num_tokens": 4027618.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.089246463775635,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 7.0016,
|
|
"mean_token_accuracy": 0.11411673203110695,
|
|
"num_tokens": 4038831.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.18756742477417,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.9477,
|
|
"mean_token_accuracy": 0.1187774159014225,
|
|
"num_tokens": 4048736.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.13449182510376,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.8957,
|
|
"mean_token_accuracy": 0.11968778371810913,
|
|
"num_tokens": 4057633.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.130615329742431,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 7.011,
|
|
"mean_token_accuracy": 0.12041295915842057,
|
|
"num_tokens": 4067883.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.19430775642395,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.8841,
|
|
"mean_token_accuracy": 0.12097653448581695,
|
|
"num_tokens": 4078147.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.091365003585816,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.8675,
|
|
"mean_token_accuracy": 0.11910612732172013,
|
|
"num_tokens": 4087130.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.035022354125976,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.9829,
|
|
"mean_token_accuracy": 0.1219471551477909,
|
|
"num_tokens": 4096840.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.219481992721557,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.9685,
|
|
"mean_token_accuracy": 0.11537734568119049,
|
|
"num_tokens": 4105842.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.076082324981689,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.9031,
|
|
"mean_token_accuracy": 0.12017038688063622,
|
|
"num_tokens": 4114865.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.1540521621704105,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 7.0211,
|
|
"mean_token_accuracy": 0.11174777895212173,
|
|
"num_tokens": 4124954.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.097948169708252,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.12242434993386268,
|
|
"num_tokens": 4134091.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.188031768798828,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.9732,
|
|
"mean_token_accuracy": 0.11344101205468178,
|
|
"num_tokens": 4143566.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.129412221908569,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.9414,
|
|
"mean_token_accuracy": 0.11348962932825088,
|
|
"num_tokens": 4153053.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.159371280670166,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.9182,
|
|
"mean_token_accuracy": 0.1212809957563877,
|
|
"num_tokens": 4162925.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.011229467391968,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.8495,
|
|
"mean_token_accuracy": 0.12126544713974,
|
|
"num_tokens": 4172077.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.090507984161377,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.11842376366257668,
|
|
"num_tokens": 4182134.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.2148134231567385,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.9533,
|
|
"mean_token_accuracy": 0.11436854675412178,
|
|
"num_tokens": 4191963.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.040346622467041,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.9051,
|
|
"mean_token_accuracy": 0.1191865548491478,
|
|
"num_tokens": 4202180.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.15973048210144,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.11763255894184113,
|
|
"num_tokens": 4211874.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.0943811416625975,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.11530448347330094,
|
|
"num_tokens": 4221610.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.956639623641967,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.8427,
|
|
"mean_token_accuracy": 0.12943953052163124,
|
|
"num_tokens": 4230610.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 7.111695718765259,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.9587,
|
|
"mean_token_accuracy": 0.11384863331913948,
|
|
"num_tokens": 4241389.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.122995376586914,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.11816137433052062,
|
|
"num_tokens": 4250617.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 7.05834994316101,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.11939359828829765,
|
|
"num_tokens": 4260000.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.071297264099121,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.8335,
|
|
"mean_token_accuracy": 0.12091447785496712,
|
|
"num_tokens": 4269751.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.092474317550659,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.8873,
|
|
"mean_token_accuracy": 0.11750671342015266,
|
|
"num_tokens": 4279210.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.095043182373047,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.8667,
|
|
"mean_token_accuracy": 0.1229426383972168,
|
|
"num_tokens": 4288573.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.082563734054565,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.8855,
|
|
"mean_token_accuracy": 0.11777178645133972,
|
|
"num_tokens": 4298438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 7.016525602340698,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.8181,
|
|
"mean_token_accuracy": 0.12750059515237808,
|
|
"num_tokens": 4307174.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.152014636993409,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.9784,
|
|
"mean_token_accuracy": 0.11399625465273858,
|
|
"num_tokens": 4317220.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 7.140341758728027,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.12417919039726258,
|
|
"num_tokens": 4326496.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.062141704559326,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.9008,
|
|
"mean_token_accuracy": 0.12094885706901551,
|
|
"num_tokens": 4335705.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.156447696685791,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.9136,
|
|
"mean_token_accuracy": 0.12432578578591347,
|
|
"num_tokens": 4344711.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.058556938171387,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.9247,
|
|
"mean_token_accuracy": 0.11726782843470573,
|
|
"num_tokens": 4355448.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 7.016918325424195,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.12222934365272523,
|
|
"num_tokens": 4365104.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 7.023652172088623,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.7861,
|
|
"mean_token_accuracy": 0.12437113225460053,
|
|
"num_tokens": 4375219.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.107285213470459,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.9092,
|
|
"mean_token_accuracy": 0.11431368067860603,
|
|
"num_tokens": 4385294.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.0897664546966555,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.8791,
|
|
"mean_token_accuracy": 0.11411814317107201,
|
|
"num_tokens": 4394305.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.091776275634766,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.8152,
|
|
"mean_token_accuracy": 0.12024855241179466,
|
|
"num_tokens": 4403732.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.080003881454468,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.11582587286829948,
|
|
"num_tokens": 4413730.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.186346435546875,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.9858,
|
|
"mean_token_accuracy": 0.11293879821896553,
|
|
"num_tokens": 4423051.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.135729503631592,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.9801,
|
|
"mean_token_accuracy": 0.11710119098424912,
|
|
"num_tokens": 4433363.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.126741695404053,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.9249,
|
|
"mean_token_accuracy": 0.11564962193369865,
|
|
"num_tokens": 4442984.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 7.115010404586792,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.876,
|
|
"mean_token_accuracy": 0.11640706211328507,
|
|
"num_tokens": 4452364.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.1195290088653564,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.8947,
|
|
"mean_token_accuracy": 0.11545171216130257,
|
|
"num_tokens": 4461904.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.064880800247193,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.8496,
|
|
"mean_token_accuracy": 0.12019126564264297,
|
|
"num_tokens": 4470633.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.072769355773926,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.8757,
|
|
"mean_token_accuracy": 0.11745303049683571,
|
|
"num_tokens": 4480673.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.083282518386841,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.8558,
|
|
"mean_token_accuracy": 0.11386666968464851,
|
|
"num_tokens": 4489923.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 7.023565435409546,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.8231,
|
|
"mean_token_accuracy": 0.11956952810287476,
|
|
"num_tokens": 4501007.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.002195882797241,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.11942060068249702,
|
|
"num_tokens": 4510460.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.076708078384399,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.9317,
|
|
"mean_token_accuracy": 0.11818542778491974,
|
|
"num_tokens": 4521026.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.057536029815674,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.8402,
|
|
"mean_token_accuracy": 0.12432301193475723,
|
|
"num_tokens": 4530818.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.965789461135865,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.8025,
|
|
"mean_token_accuracy": 0.12702578529715539,
|
|
"num_tokens": 4539512.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.114251947402954,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.9636,
|
|
"mean_token_accuracy": 0.1128588818013668,
|
|
"num_tokens": 4549030.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 7.038267183303833,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.8147,
|
|
"mean_token_accuracy": 0.12493672892451287,
|
|
"num_tokens": 4559347.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 7.0613970279693605,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.8676,
|
|
"mean_token_accuracy": 0.11753461137413979,
|
|
"num_tokens": 4568721.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 7.050783443450928,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.8684,
|
|
"mean_token_accuracy": 0.1190462976694107,
|
|
"num_tokens": 4578265.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 7.009930086135864,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.8525,
|
|
"mean_token_accuracy": 0.12626971676945686,
|
|
"num_tokens": 4588694.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 7.092075347900391,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.8315,
|
|
"mean_token_accuracy": 0.12784341126680374,
|
|
"num_tokens": 4597754.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.026864671707154,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.8521,
|
|
"mean_token_accuracy": 0.12023111805319786,
|
|
"num_tokens": 4606874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.982235383987427,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.7391,
|
|
"mean_token_accuracy": 0.12449168413877487,
|
|
"num_tokens": 4615588.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.959120845794677,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.8909,
|
|
"mean_token_accuracy": 0.12301145270466804,
|
|
"num_tokens": 4625919.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 7.058623456954956,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.8355,
|
|
"mean_token_accuracy": 0.11596318781375885,
|
|
"num_tokens": 4635539.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.008761596679688,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.8361,
|
|
"mean_token_accuracy": 0.11988401189446449,
|
|
"num_tokens": 4645833.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.989094305038452,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.9397,
|
|
"mean_token_accuracy": 0.12021735459566116,
|
|
"num_tokens": 4655166.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.0768798828125,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.8216,
|
|
"mean_token_accuracy": 0.11937851533293724,
|
|
"num_tokens": 4664884.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 7.013132905960083,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.11891724541783333,
|
|
"num_tokens": 4675172.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.094194173812866,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.8083,
|
|
"mean_token_accuracy": 0.12721233293414116,
|
|
"num_tokens": 4684588.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 7.038353013992309,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.9273,
|
|
"mean_token_accuracy": 0.11809542998671532,
|
|
"num_tokens": 4694434.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 7.012913179397583,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.8729,
|
|
"mean_token_accuracy": 0.1202128566801548,
|
|
"num_tokens": 4705080.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.109264183044433,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.9413,
|
|
"mean_token_accuracy": 0.11637584567070007,
|
|
"num_tokens": 4714466.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 7.006923818588257,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.8346,
|
|
"mean_token_accuracy": 0.12132125496864318,
|
|
"num_tokens": 4724047.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 7.0618185043334964,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.8815,
|
|
"mean_token_accuracy": 0.11511459723114967,
|
|
"num_tokens": 4733153.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.07546854019165,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.7452,
|
|
"mean_token_accuracy": 0.12942711487412453,
|
|
"num_tokens": 4743239.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.986814689636231,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.8139,
|
|
"mean_token_accuracy": 0.12030862644314766,
|
|
"num_tokens": 4753128.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.173285341262817,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 7.0347,
|
|
"mean_token_accuracy": 0.1086900345981121,
|
|
"num_tokens": 4764056.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 7.03861436843872,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.8678,
|
|
"mean_token_accuracy": 0.11879493892192841,
|
|
"num_tokens": 4773354.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.988547229766846,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.8062,
|
|
"mean_token_accuracy": 0.11831172928214073,
|
|
"num_tokens": 4783367.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.978290653228759,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.7079,
|
|
"mean_token_accuracy": 0.1302500769495964,
|
|
"num_tokens": 4793028.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 7.027144050598144,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.8748,
|
|
"mean_token_accuracy": 0.11989556774497032,
|
|
"num_tokens": 4804032.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 7.083219337463379,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.9002,
|
|
"mean_token_accuracy": 0.12228977680206299,
|
|
"num_tokens": 4813294.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.98912935256958,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.807,
|
|
"mean_token_accuracy": 0.12156101688742638,
|
|
"num_tokens": 4823461.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.951521015167236,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.12493078187108039,
|
|
"num_tokens": 4832464.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 7.01842360496521,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.8186,
|
|
"mean_token_accuracy": 0.12038722783327102,
|
|
"num_tokens": 4842697.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.077435159683228,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.12191974818706512,
|
|
"num_tokens": 4853129.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 7.058256053924561,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.908,
|
|
"mean_token_accuracy": 0.11191392317414284,
|
|
"num_tokens": 4864048.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.903012084960937,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.8637,
|
|
"mean_token_accuracy": 0.12203898876905442,
|
|
"num_tokens": 4874368.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 7.099834775924682,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.12041815221309662,
|
|
"num_tokens": 4884813.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 7.00856614112854,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.8915,
|
|
"mean_token_accuracy": 0.1209457166492939,
|
|
"num_tokens": 4895594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.982333946228027,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.781,
|
|
"mean_token_accuracy": 0.12502407133579255,
|
|
"num_tokens": 4904922.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 7.018849563598633,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.7902,
|
|
"mean_token_accuracy": 0.12333055436611176,
|
|
"num_tokens": 4915009.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 7.075725412368774,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.918,
|
|
"mean_token_accuracy": 0.11689607426524162,
|
|
"num_tokens": 4924916.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 7.0010294914245605,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.8258,
|
|
"mean_token_accuracy": 0.11776653751730919,
|
|
"num_tokens": 4935127.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 7.039859199523926,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.8401,
|
|
"mean_token_accuracy": 0.12345104441046714,
|
|
"num_tokens": 4944749.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.964186906814575,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.7002,
|
|
"mean_token_accuracy": 0.1314247652888298,
|
|
"num_tokens": 4953868.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.972427940368652,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.12143997326493264,
|
|
"num_tokens": 4963282.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.901938772201538,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.6345,
|
|
"mean_token_accuracy": 0.13661187663674354,
|
|
"num_tokens": 4973099.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 7.017197799682617,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.11694255024194718,
|
|
"num_tokens": 4983771.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.881151914596558,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.12338883578777313,
|
|
"num_tokens": 4993648.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.960689496994019,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.8234,
|
|
"mean_token_accuracy": 0.12306213602423668,
|
|
"num_tokens": 5002821.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 7.070871496200562,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.8332,
|
|
"mean_token_accuracy": 0.12124887555837631,
|
|
"num_tokens": 5012655.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.9131255626678465,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.8003,
|
|
"mean_token_accuracy": 0.12324445545673371,
|
|
"num_tokens": 5023649.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.994232654571533,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.754,
|
|
"mean_token_accuracy": 0.1276788279414177,
|
|
"num_tokens": 5031945.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 7.038708591461182,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.8319,
|
|
"mean_token_accuracy": 0.11983529329299927,
|
|
"num_tokens": 5042036.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.972916555404663,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.8136,
|
|
"mean_token_accuracy": 0.11984457820653915,
|
|
"num_tokens": 5050986.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.988238525390625,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.12704542875289918,
|
|
"num_tokens": 5061408.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.902217388153076,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.7192,
|
|
"mean_token_accuracy": 0.12395873069763183,
|
|
"num_tokens": 5071646.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.9063128471374515,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.8173,
|
|
"mean_token_accuracy": 0.1257748030126095,
|
|
"num_tokens": 5083185.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 7.0397814273834225,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.7881,
|
|
"mean_token_accuracy": 0.12251957878470421,
|
|
"num_tokens": 5092993.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.979730272293091,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.8354,
|
|
"mean_token_accuracy": 0.117799261957407,
|
|
"num_tokens": 5102709.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 7.008151340484619,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.11763950660824776,
|
|
"num_tokens": 5112858.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 7.046616935729981,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.6954,
|
|
"mean_token_accuracy": 0.12784051820635794,
|
|
"num_tokens": 5123573.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.8589095115661625,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.8639,
|
|
"mean_token_accuracy": 0.11722040623426437,
|
|
"num_tokens": 5132908.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 7.009056949615479,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.755,
|
|
"mean_token_accuracy": 0.1255860634148121,
|
|
"num_tokens": 5142331.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 7.080911350250244,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.8289,
|
|
"mean_token_accuracy": 0.1180228516459465,
|
|
"num_tokens": 5152517.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.921509647369385,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.7802,
|
|
"mean_token_accuracy": 0.12336174324154854,
|
|
"num_tokens": 5162418.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.944567775726318,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.797,
|
|
"mean_token_accuracy": 0.12096343412995339,
|
|
"num_tokens": 5171948.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 7.008423233032227,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.7226,
|
|
"mean_token_accuracy": 0.12412903606891632,
|
|
"num_tokens": 5180963.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.923210000991821,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.8323,
|
|
"mean_token_accuracy": 0.12230520248413086,
|
|
"num_tokens": 5192305.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 7.007975339889526,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.12070221900939941,
|
|
"num_tokens": 5201503.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.982429170608521,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.6724,
|
|
"mean_token_accuracy": 0.1253625251352787,
|
|
"num_tokens": 5210206.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.814099502563477,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.7081,
|
|
"mean_token_accuracy": 0.12672959715127946,
|
|
"num_tokens": 5220256.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.92271785736084,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.12912995740771294,
|
|
"num_tokens": 5229128.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.972404956817627,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.6754,
|
|
"mean_token_accuracy": 0.12550344914197922,
|
|
"num_tokens": 5239468.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.915175199508667,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.769,
|
|
"mean_token_accuracy": 0.12083193883299828,
|
|
"num_tokens": 5247957.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.947061824798584,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.7875,
|
|
"mean_token_accuracy": 0.11905844509601593,
|
|
"num_tokens": 5257960.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.928300905227661,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.6633,
|
|
"mean_token_accuracy": 0.1272826075553894,
|
|
"num_tokens": 5266696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.9380433559417725,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.1306777834892273,
|
|
"num_tokens": 5275619.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.8965309143066404,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.12241848036646844,
|
|
"num_tokens": 5284884.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.951219177246093,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.13157505616545678,
|
|
"num_tokens": 5293909.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.885016298294067,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.7472,
|
|
"mean_token_accuracy": 0.11952828168869019,
|
|
"num_tokens": 5303142.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.935619926452636,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.6925,
|
|
"mean_token_accuracy": 0.12288326397538185,
|
|
"num_tokens": 5313055.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.9312550067901615,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.8109,
|
|
"mean_token_accuracy": 0.11529392302036286,
|
|
"num_tokens": 5323773.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.812974977493286,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.13647473528981208,
|
|
"num_tokens": 5334613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.891908311843872,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.6816,
|
|
"mean_token_accuracy": 0.12988344877958297,
|
|
"num_tokens": 5344151.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.891177415847778,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.13222801834344863,
|
|
"num_tokens": 5352425.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.880789041519165,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.8408,
|
|
"mean_token_accuracy": 0.1188066765666008,
|
|
"num_tokens": 5361811.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.9263018608093265,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.786,
|
|
"mean_token_accuracy": 0.11447468400001526,
|
|
"num_tokens": 5371463.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.908780908584594,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.6502,
|
|
"mean_token_accuracy": 0.12994811981916427,
|
|
"num_tokens": 5381464.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.861965656280518,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.7194,
|
|
"mean_token_accuracy": 0.12399204149842262,
|
|
"num_tokens": 5391012.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.97508602142334,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.8309,
|
|
"mean_token_accuracy": 0.12259437888860703,
|
|
"num_tokens": 5401198.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 7.017956781387329,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.7654,
|
|
"mean_token_accuracy": 0.12429968118667603,
|
|
"num_tokens": 5410592.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.83931188583374,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.7505,
|
|
"mean_token_accuracy": 0.1281308613717556,
|
|
"num_tokens": 5420878.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.955085563659668,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.7523,
|
|
"mean_token_accuracy": 0.12567364796996117,
|
|
"num_tokens": 5431199.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.932239675521851,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.12451341077685356,
|
|
"num_tokens": 5441661.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.778904724121094,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.132535882294178,
|
|
"num_tokens": 5451863.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.936461877822876,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.7345,
|
|
"mean_token_accuracy": 0.12622895315289498,
|
|
"num_tokens": 5461600.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 7.027527093887329,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.7576,
|
|
"mean_token_accuracy": 0.12218005806207657,
|
|
"num_tokens": 5470097.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.948017263412476,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.8869,
|
|
"mean_token_accuracy": 0.11402522325515747,
|
|
"num_tokens": 5480906.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 7.057219552993774,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.7821,
|
|
"mean_token_accuracy": 0.11816998645663261,
|
|
"num_tokens": 5489732.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.840402030944825,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.13391595482826232,
|
|
"num_tokens": 5498422.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.822567796707153,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.12329033613204957,
|
|
"num_tokens": 5507958.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.983218050003051,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.761,
|
|
"mean_token_accuracy": 0.12427213788032532,
|
|
"num_tokens": 5516752.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.899249696731568,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.12306348532438278,
|
|
"num_tokens": 5527211.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.921328783035278,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.6782,
|
|
"mean_token_accuracy": 0.12412735596299171,
|
|
"num_tokens": 5536925.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.966558170318604,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.8369,
|
|
"mean_token_accuracy": 0.11656751185655594,
|
|
"num_tokens": 5546800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.868718194961548,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.697,
|
|
"mean_token_accuracy": 0.1250438630580902,
|
|
"num_tokens": 5557266.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.938524961471558,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.6673,
|
|
"mean_token_accuracy": 0.12535413205623627,
|
|
"num_tokens": 5566169.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.896262836456299,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.7617,
|
|
"mean_token_accuracy": 0.12486017644405364,
|
|
"num_tokens": 5575566.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.885776615142822,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.647,
|
|
"mean_token_accuracy": 0.12700871676206588,
|
|
"num_tokens": 5584804.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.893292379379273,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.7104,
|
|
"mean_token_accuracy": 0.12000066190958023,
|
|
"num_tokens": 5594361.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 7.01403489112854,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.6936,
|
|
"mean_token_accuracy": 0.1254715770483017,
|
|
"num_tokens": 5605682.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.884680128097534,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.7746,
|
|
"mean_token_accuracy": 0.11833036169409752,
|
|
"num_tokens": 5617251.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.8461815357208256,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.6684,
|
|
"mean_token_accuracy": 0.1276953287422657,
|
|
"num_tokens": 5627140.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.882718229293824,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.5987,
|
|
"mean_token_accuracy": 0.13200223743915557,
|
|
"num_tokens": 5635486.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.946580982208252,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.7686,
|
|
"mean_token_accuracy": 0.11976373195648193,
|
|
"num_tokens": 5645621.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.974322843551636,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.8311,
|
|
"mean_token_accuracy": 0.11587899774312974,
|
|
"num_tokens": 5655626.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.923132610321045,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.7721,
|
|
"mean_token_accuracy": 0.12438612058758736,
|
|
"num_tokens": 5664547.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.959670162200927,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.7344,
|
|
"mean_token_accuracy": 0.12106872946023942,
|
|
"num_tokens": 5674861.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.850112104415894,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.6879,
|
|
"mean_token_accuracy": 0.12462930828332901,
|
|
"num_tokens": 5684143.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.901785516738892,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.6542,
|
|
"mean_token_accuracy": 0.12453328371047974,
|
|
"num_tokens": 5693837.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.979707384109497,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.7457,
|
|
"mean_token_accuracy": 0.11954636201262474,
|
|
"num_tokens": 5704827.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.934035778045654,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.7828,
|
|
"mean_token_accuracy": 0.12128729447722435,
|
|
"num_tokens": 5714419.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.87302975654602,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.7059,
|
|
"mean_token_accuracy": 0.12609893232584,
|
|
"num_tokens": 5724983.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.862426519393921,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.13176713660359382,
|
|
"num_tokens": 5734471.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.90787901878357,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.12451120018959046,
|
|
"num_tokens": 5744801.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.892666482925415,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.7164,
|
|
"mean_token_accuracy": 0.12045061364769935,
|
|
"num_tokens": 5754267.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.792302894592285,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.6261,
|
|
"mean_token_accuracy": 0.13216007202863694,
|
|
"num_tokens": 5764466.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.894134426116944,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.11944599896669388,
|
|
"num_tokens": 5775158.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.95402045249939,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.13158607333898545,
|
|
"num_tokens": 5783320.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.822439527511596,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.12602196037769317,
|
|
"num_tokens": 5792980.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.934293985366821,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.7596,
|
|
"mean_token_accuracy": 0.12525345459580423,
|
|
"num_tokens": 5802338.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.895787000656128,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.6529,
|
|
"mean_token_accuracy": 0.12653236985206603,
|
|
"num_tokens": 5811388.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.873412609100342,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.6797,
|
|
"mean_token_accuracy": 0.12875316813588142,
|
|
"num_tokens": 5821108.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.890844678878784,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.7279,
|
|
"mean_token_accuracy": 0.11901220306754112,
|
|
"num_tokens": 5831389.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.821516752243042,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.6059,
|
|
"mean_token_accuracy": 0.13066981732845306,
|
|
"num_tokens": 5840392.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.8590656280517575,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.12876412868499756,
|
|
"num_tokens": 5850032.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.887386322021484,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.683,
|
|
"mean_token_accuracy": 0.12640040144324302,
|
|
"num_tokens": 5859204.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.845551586151123,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.6866,
|
|
"mean_token_accuracy": 0.1273339122533798,
|
|
"num_tokens": 5868582.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.876190519332885,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.6229,
|
|
"mean_token_accuracy": 0.13258609995245935,
|
|
"num_tokens": 5879601.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.681353775320272,
|
|
"eval_loss": 6.711971759796143,
|
|
"eval_mean_token_accuracy": 0.13082575049137093,
|
|
"eval_num_tokens": 5879601.0,
|
|
"eval_runtime": 18.5417,
|
|
"eval_samples_per_second": 1674.337,
|
|
"eval_steps_per_second": 209.312,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.860547161102295,
|
|
"epoch": 0.30039486179837055,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995454644392967,
|
|
"loss": 6.6828,
|
|
"mean_token_accuracy": 0.1199514240026474,
|
|
"num_tokens": 5890255.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.836520481109619,
|
|
"epoch": 0.30089468685959914,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995431942370087,
|
|
"loss": 6.7017,
|
|
"mean_token_accuracy": 0.13403721749782563,
|
|
"num_tokens": 5899965.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.850822114944458,
|
|
"epoch": 0.3013945119208277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995409183852718,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.1277392603456974,
|
|
"num_tokens": 5910082.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.81156644821167,
|
|
"epoch": 0.30189433698205626,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995386368841432,
|
|
"loss": 6.734,
|
|
"mean_token_accuracy": 0.12413607314229011,
|
|
"num_tokens": 5920267.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.92461085319519,
|
|
"epoch": 0.30239416204328484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995363497336802,
|
|
"loss": 6.7223,
|
|
"mean_token_accuracy": 0.1259683944284916,
|
|
"num_tokens": 5929275.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.916010570526123,
|
|
"epoch": 0.30289398710451343,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995340569339405,
|
|
"loss": 6.7331,
|
|
"mean_token_accuracy": 0.1227998599410057,
|
|
"num_tokens": 5939305.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.927875185012818,
|
|
"epoch": 0.303393812165742,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995317584849817,
|
|
"loss": 6.7798,
|
|
"mean_token_accuracy": 0.11840006709098816,
|
|
"num_tokens": 5950816.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.781100273132324,
|
|
"epoch": 0.30389363722697055,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995294543868615,
|
|
"loss": 6.59,
|
|
"mean_token_accuracy": 0.13672472536563873,
|
|
"num_tokens": 5959824.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.895697450637817,
|
|
"epoch": 0.30439346228819913,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995271446396382,
|
|
"loss": 6.6897,
|
|
"mean_token_accuracy": 0.12784379869699478,
|
|
"num_tokens": 5968752.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.861779737472534,
|
|
"epoch": 0.3048932873494277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995248292433697,
|
|
"loss": 6.6245,
|
|
"mean_token_accuracy": 0.12324162349104881,
|
|
"num_tokens": 5979085.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.854835796356201,
|
|
"epoch": 0.30539311241065625,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004995225081981142,
|
|
"loss": 6.6817,
|
|
"mean_token_accuracy": 0.12485206797719002,
|
|
"num_tokens": 5990378.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.831756448745727,
|
|
"epoch": 0.30589293747188484,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995201815039301,
|
|
"loss": 6.5649,
|
|
"mean_token_accuracy": 0.13644901737570764,
|
|
"num_tokens": 5999524.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.823571443557739,
|
|
"epoch": 0.3063927625331134,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995178491608762,
|
|
"loss": 6.6704,
|
|
"mean_token_accuracy": 0.12984049916267396,
|
|
"num_tokens": 6009928.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.7765707015991214,
|
|
"epoch": 0.30689258759434196,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995155111690107,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.13109827488660813,
|
|
"num_tokens": 6019683.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.891257190704346,
|
|
"epoch": 0.30739241265557055,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499513167528393,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.12392932772636414,
|
|
"num_tokens": 6030506.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.893397998809815,
|
|
"epoch": 0.30789223771679913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995108182390815,
|
|
"loss": 6.6541,
|
|
"mean_token_accuracy": 0.127655690908432,
|
|
"num_tokens": 6039720.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.714027976989746,
|
|
"epoch": 0.30839206277802766,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995084633011359,
|
|
"loss": 6.5128,
|
|
"mean_token_accuracy": 0.13731268048286438,
|
|
"num_tokens": 6049336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.769006967544556,
|
|
"epoch": 0.30889188783925625,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499506102714615,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.12772710919380187,
|
|
"num_tokens": 6059420.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.894221544265747,
|
|
"epoch": 0.30939171290048484,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995037364795782,
|
|
"loss": 6.6162,
|
|
"mean_token_accuracy": 0.13121913075447084,
|
|
"num_tokens": 6069035.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.8395720481872555,
|
|
"epoch": 0.3098915379617134,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995013645960853,
|
|
"loss": 6.6209,
|
|
"mean_token_accuracy": 0.1228025123476982,
|
|
"num_tokens": 6077863.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.796633720397949,
|
|
"epoch": 0.31039136302294196,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994989870641958,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.1278463914990425,
|
|
"num_tokens": 6088929.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.841479206085205,
|
|
"epoch": 0.31089118808417054,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994966038839695,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.1331371009349823,
|
|
"num_tokens": 6098673.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.811598491668701,
|
|
"epoch": 0.31139101314539913,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994942150554666,
|
|
"loss": 6.4808,
|
|
"mean_token_accuracy": 0.13783543109893798,
|
|
"num_tokens": 6107289.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.763007307052613,
|
|
"epoch": 0.31189083820662766,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994918205787468,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.1319437026977539,
|
|
"num_tokens": 6117811.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.808111715316772,
|
|
"epoch": 0.31239066326785625,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994894204538706,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.1224993959069252,
|
|
"num_tokens": 6127740.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.848862075805664,
|
|
"epoch": 0.31289048832908484,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994870146808984,
|
|
"loss": 6.6352,
|
|
"mean_token_accuracy": 0.12831297889351845,
|
|
"num_tokens": 6137253.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.829786729812622,
|
|
"epoch": 0.31339031339031337,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994846032598906,
|
|
"loss": 6.6579,
|
|
"mean_token_accuracy": 0.13139474987983704,
|
|
"num_tokens": 6147420.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.7944231033325195,
|
|
"epoch": 0.31389013845154196,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994821861909082,
|
|
"loss": 6.6002,
|
|
"mean_token_accuracy": 0.1344860926270485,
|
|
"num_tokens": 6156436.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.744538116455078,
|
|
"epoch": 0.31438996351277054,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994797634740114,
|
|
"loss": 6.5645,
|
|
"mean_token_accuracy": 0.1254199042916298,
|
|
"num_tokens": 6165526.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.916535568237305,
|
|
"epoch": 0.3148897885739991,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994773351092618,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.12227125912904739,
|
|
"num_tokens": 6176093.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.806874370574951,
|
|
"epoch": 0.31538961363522766,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049947490109672,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.13499117344617845,
|
|
"num_tokens": 6185373.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.813190174102783,
|
|
"epoch": 0.31588943869645625,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994724614364476,
|
|
"loss": 6.6969,
|
|
"mean_token_accuracy": 0.12468868568539619,
|
|
"num_tokens": 6196252.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.92350172996521,
|
|
"epoch": 0.31638926375768484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994700161285058,
|
|
"loss": 6.6138,
|
|
"mean_token_accuracy": 0.13101329877972603,
|
|
"num_tokens": 6206463.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.840941715240478,
|
|
"epoch": 0.31688908881891337,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499467565172956,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.13344849348068238,
|
|
"num_tokens": 6216676.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.770532560348511,
|
|
"epoch": 0.31738891388014195,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994651085698602,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.1266130104660988,
|
|
"num_tokens": 6227261.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.793110275268555,
|
|
"epoch": 0.31788873894137054,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049946264631928,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.1299448736011982,
|
|
"num_tokens": 6237468.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.730577278137207,
|
|
"epoch": 0.3183885640025991,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994601784212774,
|
|
"loss": 6.5273,
|
|
"mean_token_accuracy": 0.13367701396346093,
|
|
"num_tokens": 6247164.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.737555265426636,
|
|
"epoch": 0.31888838906382766,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994577048759144,
|
|
"loss": 6.6415,
|
|
"mean_token_accuracy": 0.12758639827370644,
|
|
"num_tokens": 6257635.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.885430097579956,
|
|
"epoch": 0.31938821412505625,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994552256832533,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.12833332344889642,
|
|
"num_tokens": 6266823.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.825052070617676,
|
|
"epoch": 0.3198880391862848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994527408433566,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.13387023508548737,
|
|
"num_tokens": 6276527.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.8343099594116214,
|
|
"epoch": 0.32038786424751337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994502503562865,
|
|
"loss": 6.6576,
|
|
"mean_token_accuracy": 0.1253943145275116,
|
|
"num_tokens": 6286499.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.796053409576416,
|
|
"epoch": 0.32088768930874195,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499447754222106,
|
|
"loss": 6.5799,
|
|
"mean_token_accuracy": 0.13133140057325363,
|
|
"num_tokens": 6296550.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.75276198387146,
|
|
"epoch": 0.3213875143699705,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994452524408777,
|
|
"loss": 6.6298,
|
|
"mean_token_accuracy": 0.1270774334669113,
|
|
"num_tokens": 6306951.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.909622716903686,
|
|
"epoch": 0.32188733943119907,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994427450126646,
|
|
"loss": 6.6741,
|
|
"mean_token_accuracy": 0.12139397338032723,
|
|
"num_tokens": 6316026.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.787709379196167,
|
|
"epoch": 0.32238716449242766,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994402319375298,
|
|
"loss": 6.6062,
|
|
"mean_token_accuracy": 0.13093544766306878,
|
|
"num_tokens": 6325064.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.815984630584717,
|
|
"epoch": 0.32288698955365625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994377132155366,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.12869550362229348,
|
|
"num_tokens": 6334443.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.859949779510498,
|
|
"epoch": 0.3233868146148848,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994351888467482,
|
|
"loss": 6.6326,
|
|
"mean_token_accuracy": 0.13534025177359582,
|
|
"num_tokens": 6346103.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.761764478683472,
|
|
"epoch": 0.32388663967611336,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994326588312282,
|
|
"loss": 6.6102,
|
|
"mean_token_accuracy": 0.12837436720728873,
|
|
"num_tokens": 6356576.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.906105613708496,
|
|
"epoch": 0.32438646473734195,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994301231690403,
|
|
"loss": 6.6192,
|
|
"mean_token_accuracy": 0.13152617439627648,
|
|
"num_tokens": 6364796.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.799127864837646,
|
|
"epoch": 0.3248862897985705,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994275818602482,
|
|
"loss": 6.6821,
|
|
"mean_token_accuracy": 0.1256471887230873,
|
|
"num_tokens": 6374951.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.742057371139526,
|
|
"epoch": 0.32538611485979907,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994250349049159,
|
|
"loss": 6.5718,
|
|
"mean_token_accuracy": 0.13147338405251502,
|
|
"num_tokens": 6384230.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.799435615539551,
|
|
"epoch": 0.32588593992102766,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994224823031075,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.1292741797864437,
|
|
"num_tokens": 6394070.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.759094667434693,
|
|
"epoch": 0.3263857649822562,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994199240548873,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.13265890926122664,
|
|
"num_tokens": 6403968.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.856962633132935,
|
|
"epoch": 0.3268855900434848,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994173601603194,
|
|
"loss": 6.6802,
|
|
"mean_token_accuracy": 0.1274121530354023,
|
|
"num_tokens": 6413254.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.788355588912964,
|
|
"epoch": 0.32738541510471336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994147906194684,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.13717470020055772,
|
|
"num_tokens": 6421266.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.83143458366394,
|
|
"epoch": 0.3278852401659419,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994122154323992,
|
|
"loss": 6.6223,
|
|
"mean_token_accuracy": 0.12834875658154488,
|
|
"num_tokens": 6429596.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.835178375244141,
|
|
"epoch": 0.3283850652271705,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994096345991763,
|
|
"loss": 6.6205,
|
|
"mean_token_accuracy": 0.12660129144787788,
|
|
"num_tokens": 6440825.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.777733182907104,
|
|
"epoch": 0.32888489028839907,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994070481198649,
|
|
"loss": 6.5846,
|
|
"mean_token_accuracy": 0.13142892420291902,
|
|
"num_tokens": 6450576.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.816314220428467,
|
|
"epoch": 0.32938471534962765,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994044559945296,
|
|
"loss": 6.589,
|
|
"mean_token_accuracy": 0.13519199714064598,
|
|
"num_tokens": 6459673.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.723920822143555,
|
|
"epoch": 0.3298845404108562,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994018582232361,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.12928077429533005,
|
|
"num_tokens": 6469353.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.785896730422974,
|
|
"epoch": 0.3303843654720848,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993992548060497,
|
|
"loss": 6.5928,
|
|
"mean_token_accuracy": 0.13344419449567796,
|
|
"num_tokens": 6479610.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.78511905670166,
|
|
"epoch": 0.33088419053331336,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993966457430357,
|
|
"loss": 6.6206,
|
|
"mean_token_accuracy": 0.13322013840079308,
|
|
"num_tokens": 6488866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.786275625228882,
|
|
"epoch": 0.3313840155945419,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993940310342598,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.13620288148522378,
|
|
"num_tokens": 6498396.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.727838087081909,
|
|
"epoch": 0.3318838406557705,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993914106797879,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.13454839885234832,
|
|
"num_tokens": 6508347.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.876163816452026,
|
|
"epoch": 0.33238366571699907,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993887846796858,
|
|
"loss": 6.65,
|
|
"mean_token_accuracy": 0.12700310945510865,
|
|
"num_tokens": 6518369.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.742571544647217,
|
|
"epoch": 0.3328834907782276,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993861530340196,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.13208815306425095,
|
|
"num_tokens": 6527477.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.752882671356201,
|
|
"epoch": 0.3333833158394562,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993835157428555,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.13668068647384643,
|
|
"num_tokens": 6536271.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.79825119972229,
|
|
"epoch": 0.33388314090068477,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993808728062599,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.13273728266358376,
|
|
"num_tokens": 6546295.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.847344255447387,
|
|
"epoch": 0.3343829659619133,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993782242242994,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.13553625270724295,
|
|
"num_tokens": 6557338.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.706897592544555,
|
|
"epoch": 0.3348827910231419,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993755699970404,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.12940239012241364,
|
|
"num_tokens": 6567916.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.779553318023682,
|
|
"epoch": 0.3353826160843705,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993729101245498,
|
|
"loss": 6.6852,
|
|
"mean_token_accuracy": 0.12738192081451416,
|
|
"num_tokens": 6577821.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.829365348815918,
|
|
"epoch": 0.33588244114559906,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993702446068945,
|
|
"loss": 6.5491,
|
|
"mean_token_accuracy": 0.13510767072439195,
|
|
"num_tokens": 6587674.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.7904322147369385,
|
|
"epoch": 0.3363822662068276,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993675734441416,
|
|
"loss": 6.6434,
|
|
"mean_token_accuracy": 0.13473183438181877,
|
|
"num_tokens": 6597292.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.728825855255127,
|
|
"epoch": 0.3368820912680562,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993648966363583,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.13414635956287385,
|
|
"num_tokens": 6608698.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.781323480606079,
|
|
"epoch": 0.33738191632928477,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499362214183612,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.12938414216041566,
|
|
"num_tokens": 6617914.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.70294418334961,
|
|
"epoch": 0.3378817413905133,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049935952608597,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.13585723638534547,
|
|
"num_tokens": 6627457.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.795602464675904,
|
|
"epoch": 0.3383815664517419,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993568323435002,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.13577620610594748,
|
|
"num_tokens": 6636511.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.775119304656982,
|
|
"epoch": 0.3388813915129705,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993541329562702,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.132101146876812,
|
|
"num_tokens": 6647028.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.763808059692383,
|
|
"epoch": 0.339381216574199,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993514279243477,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.1340196780860424,
|
|
"num_tokens": 6656407.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.755914354324341,
|
|
"epoch": 0.3398810416354276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993487172478012,
|
|
"loss": 6.5301,
|
|
"mean_token_accuracy": 0.13331264555454253,
|
|
"num_tokens": 6665554.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.7822106838226315,
|
|
"epoch": 0.3403808666966562,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993460009266988,
|
|
"loss": 6.6045,
|
|
"mean_token_accuracy": 0.12475471571087837,
|
|
"num_tokens": 6675730.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.704963254928589,
|
|
"epoch": 0.3408806917578847,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993432789611086,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.14141545966267585,
|
|
"num_tokens": 6685871.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.789458560943603,
|
|
"epoch": 0.3413805168191133,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993405513510992,
|
|
"loss": 6.7274,
|
|
"mean_token_accuracy": 0.11894873753190041,
|
|
"num_tokens": 6697503.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.851514005661011,
|
|
"epoch": 0.3418803418803419,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993378180967394,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.13509066253900529,
|
|
"num_tokens": 6708022.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.717868328094482,
|
|
"epoch": 0.3423801669415705,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993350791980978,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.1329593650996685,
|
|
"num_tokens": 6717510.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.827261590957642,
|
|
"epoch": 0.342879992002799,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993323346552433,
|
|
"loss": 6.6277,
|
|
"mean_token_accuracy": 0.1324178047478199,
|
|
"num_tokens": 6726538.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.815475749969482,
|
|
"epoch": 0.3433798170640276,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993295844682449,
|
|
"loss": 6.5374,
|
|
"mean_token_accuracy": 0.13447542414069175,
|
|
"num_tokens": 6736750.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.732570314407349,
|
|
"epoch": 0.3438796421252562,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499326828637172,
|
|
"loss": 6.5741,
|
|
"mean_token_accuracy": 0.12793689221143723,
|
|
"num_tokens": 6746366.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.713649702072144,
|
|
"epoch": 0.3443794671864847,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993240671620938,
|
|
"loss": 6.5817,
|
|
"mean_token_accuracy": 0.1281355671584606,
|
|
"num_tokens": 6755887.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.808232307434082,
|
|
"epoch": 0.3448792922477133,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993213000430797,
|
|
"loss": 6.5953,
|
|
"mean_token_accuracy": 0.13886945098638534,
|
|
"num_tokens": 6764434.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.837958335876465,
|
|
"epoch": 0.3453791173089419,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993185272801995,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.1220993809401989,
|
|
"num_tokens": 6774237.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.84452862739563,
|
|
"epoch": 0.3458789423701704,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993157488735228,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.13282398506999016,
|
|
"num_tokens": 6784537.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.731106948852539,
|
|
"epoch": 0.346378767431399,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993129648231197,
|
|
"loss": 6.5347,
|
|
"mean_token_accuracy": 0.13576256334781647,
|
|
"num_tokens": 6794223.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.668006038665771,
|
|
"epoch": 0.3468785924926276,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049931017512906,
|
|
"loss": 6.5587,
|
|
"mean_token_accuracy": 0.13244524151086806,
|
|
"num_tokens": 6803680.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.864859914779663,
|
|
"epoch": 0.3473784175538562,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993073797914141,
|
|
"loss": 6.5638,
|
|
"mean_token_accuracy": 0.12987205013632774,
|
|
"num_tokens": 6812853.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.728725004196167,
|
|
"epoch": 0.3478782426150847,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993045788102522,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.13237608522176741,
|
|
"num_tokens": 6822104.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.773728656768799,
|
|
"epoch": 0.3483780676763133,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993017721856449,
|
|
"loss": 6.6079,
|
|
"mean_token_accuracy": 0.12588487043976784,
|
|
"num_tokens": 6832683.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.836304140090943,
|
|
"epoch": 0.3488778927375419,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004992989599176626,
|
|
"loss": 6.5798,
|
|
"mean_token_accuracy": 0.12687501460313796,
|
|
"num_tokens": 6843191.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.726966524124146,
|
|
"epoch": 0.3493777177987704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992961420063763,
|
|
"loss": 6.5633,
|
|
"mean_token_accuracy": 0.13255376368761063,
|
|
"num_tokens": 6852205.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.660494184494018,
|
|
"epoch": 0.349877542859999,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992933184518567,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.13458824530243874,
|
|
"num_tokens": 6863052.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.7441253662109375,
|
|
"epoch": 0.3503773679212276,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992904892541749,
|
|
"loss": 6.5506,
|
|
"mean_token_accuracy": 0.13711895644664765,
|
|
"num_tokens": 6872717.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.75137300491333,
|
|
"epoch": 0.3508771929824561,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992876544134022,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.14251541569828988,
|
|
"num_tokens": 6881351.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.7535230159759525,
|
|
"epoch": 0.3513770180436847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992848139296098,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.13545247092843055,
|
|
"num_tokens": 6891353.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.783826398849487,
|
|
"epoch": 0.3518768431049133,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992819678028692,
|
|
"loss": 6.6245,
|
|
"mean_token_accuracy": 0.12173576429486274,
|
|
"num_tokens": 6902352.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.790583515167237,
|
|
"epoch": 0.3523766681661418,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499279116033252,
|
|
"loss": 6.6035,
|
|
"mean_token_accuracy": 0.12277116775512695,
|
|
"num_tokens": 6911950.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.737413740158081,
|
|
"epoch": 0.3528764932273704,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992762586208299,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.14421395510435103,
|
|
"num_tokens": 6921949.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.73858962059021,
|
|
"epoch": 0.353376318288599,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992733955656749,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.13170789256691934,
|
|
"num_tokens": 6932561.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.739193916320801,
|
|
"epoch": 0.3538761433498276,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992705268678589,
|
|
"loss": 6.5222,
|
|
"mean_token_accuracy": 0.13438423350453377,
|
|
"num_tokens": 6941663.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.728638219833374,
|
|
"epoch": 0.3543759684110561,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992676525274542,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.1283603638410568,
|
|
"num_tokens": 6952373.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.660042142868042,
|
|
"epoch": 0.3548757934722847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992647725445331,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.1381118729710579,
|
|
"num_tokens": 6961337.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.772459888458252,
|
|
"epoch": 0.3553756185335133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499261886919168,
|
|
"loss": 6.5129,
|
|
"mean_token_accuracy": 0.13579124957323074,
|
|
"num_tokens": 6971649.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.756059360504151,
|
|
"epoch": 0.3558754435947418,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992589956514316,
|
|
"loss": 6.5265,
|
|
"mean_token_accuracy": 0.13866043761372565,
|
|
"num_tokens": 6982261.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.710768413543701,
|
|
"epoch": 0.3563752686559704,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992560987413965,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.1314053662121296,
|
|
"num_tokens": 6991324.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.676396751403809,
|
|
"epoch": 0.356875093717199,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992531961891356,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.1360301211476326,
|
|
"num_tokens": 7001396.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.817516183853149,
|
|
"epoch": 0.35737491877842753,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992502879947222,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.13338373303413392,
|
|
"num_tokens": 7010354.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.7689660549163815,
|
|
"epoch": 0.3578747438396561,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992473741582291,
|
|
"loss": 6.5914,
|
|
"mean_token_accuracy": 0.12699368372559547,
|
|
"num_tokens": 7019835.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.715113496780395,
|
|
"epoch": 0.3583745689008847,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992444546797298,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.1373328983783722,
|
|
"num_tokens": 7030515.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.649649620056152,
|
|
"epoch": 0.35887439396211324,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992415295592977,
|
|
"loss": 6.5158,
|
|
"mean_token_accuracy": 0.13744487911462783,
|
|
"num_tokens": 7041248.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.78484878540039,
|
|
"epoch": 0.3593742190233418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992385987970064,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.13354873284697533,
|
|
"num_tokens": 7050578.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.768323993682861,
|
|
"epoch": 0.3598740440845704,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992356623929297,
|
|
"loss": 6.5624,
|
|
"mean_token_accuracy": 0.12766438275575637,
|
|
"num_tokens": 7060270.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.762470626831055,
|
|
"epoch": 0.360373869145799,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992327203471414,
|
|
"loss": 6.5953,
|
|
"mean_token_accuracy": 0.1289625272154808,
|
|
"num_tokens": 7070259.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.710714197158813,
|
|
"epoch": 0.36087369420702753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992297726597156,
|
|
"loss": 6.519,
|
|
"mean_token_accuracy": 0.13905792608857154,
|
|
"num_tokens": 7078784.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.717840957641601,
|
|
"epoch": 0.3613735192682561,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992268193307264,
|
|
"loss": 6.5689,
|
|
"mean_token_accuracy": 0.12597132846713066,
|
|
"num_tokens": 7088632.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.7258179664611815,
|
|
"epoch": 0.3618733443294847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992238603602481,
|
|
"loss": 6.5752,
|
|
"mean_token_accuracy": 0.13087578862905502,
|
|
"num_tokens": 7097703.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.725839757919312,
|
|
"epoch": 0.36237316939071323,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992208957483552,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.1383651688694954,
|
|
"num_tokens": 7107183.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.784894752502441,
|
|
"epoch": 0.3628729944519418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992179254951223,
|
|
"loss": 6.5919,
|
|
"mean_token_accuracy": 0.12946465089917183,
|
|
"num_tokens": 7118220.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.748425436019898,
|
|
"epoch": 0.3633728195131704,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499214949600624,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.1331576108932495,
|
|
"num_tokens": 7128322.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.653918504714966,
|
|
"epoch": 0.36387264457439894,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992119680649355,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.13750485628843306,
|
|
"num_tokens": 7137284.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.675596094131469,
|
|
"epoch": 0.3643724696356275,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992089808881313,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.13767508938908576,
|
|
"num_tokens": 7146598.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.866312026977539,
|
|
"epoch": 0.3648722946968561,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992059880702869,
|
|
"loss": 6.6153,
|
|
"mean_token_accuracy": 0.13753045871853828,
|
|
"num_tokens": 7156816.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.764746761322021,
|
|
"epoch": 0.36537211975808465,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992029896114775,
|
|
"loss": 6.544,
|
|
"mean_token_accuracy": 0.12656489610671998,
|
|
"num_tokens": 7166855.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.638649415969849,
|
|
"epoch": 0.36587194481931323,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991999855117787,
|
|
"loss": 6.4297,
|
|
"mean_token_accuracy": 0.1436794362962246,
|
|
"num_tokens": 7176477.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.724538660049438,
|
|
"epoch": 0.3663717698805418,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991969757712659,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.14060992375016212,
|
|
"num_tokens": 7186173.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.657022762298584,
|
|
"epoch": 0.3668715949417704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991939603900149,
|
|
"loss": 6.4397,
|
|
"mean_token_accuracy": 0.13965553045272827,
|
|
"num_tokens": 7195403.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.697231864929199,
|
|
"epoch": 0.36737142000299894,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991909393681015,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.1321679435670376,
|
|
"num_tokens": 7204179.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.6658265590667725,
|
|
"epoch": 0.3678712450642275,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991879127056017,
|
|
"loss": 6.4817,
|
|
"mean_token_accuracy": 0.1341702915728092,
|
|
"num_tokens": 7214159.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.720257186889649,
|
|
"epoch": 0.3683710701254561,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991848804025918,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.13838336020708084,
|
|
"num_tokens": 7224410.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.711658525466919,
|
|
"epoch": 0.36887089518668464,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499181842459148,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.14222702607512475,
|
|
"num_tokens": 7233740.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.743264961242676,
|
|
"epoch": 0.36937072024791323,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991787988753467,
|
|
"loss": 6.4795,
|
|
"mean_token_accuracy": 0.13322645500302316,
|
|
"num_tokens": 7242834.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.673091030120849,
|
|
"epoch": 0.3698705453091418,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991757496512645,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.1401118218898773,
|
|
"num_tokens": 7252098.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.800505828857422,
|
|
"epoch": 0.37037037037037035,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991726947869782,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.12465254962444305,
|
|
"num_tokens": 7261396.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.736898040771484,
|
|
"epoch": 0.37087019543159894,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991696342825645,
|
|
"loss": 6.5328,
|
|
"mean_token_accuracy": 0.12767770290374755,
|
|
"num_tokens": 7271138.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.699572229385376,
|
|
"epoch": 0.3713700204928275,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991665681381005,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.14116159528493882,
|
|
"num_tokens": 7280164.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.73060040473938,
|
|
"epoch": 0.37186984555405606,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991634963536633,
|
|
"loss": 6.5326,
|
|
"mean_token_accuracy": 0.13450543880462645,
|
|
"num_tokens": 7288830.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.705532169342041,
|
|
"epoch": 0.37236967061528464,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991604189293303,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.13030011355876922,
|
|
"num_tokens": 7298955.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.736779451370239,
|
|
"epoch": 0.37286949567651323,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991573358651787,
|
|
"loss": 6.4787,
|
|
"mean_token_accuracy": 0.13266245201230048,
|
|
"num_tokens": 7309829.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.7341827869415285,
|
|
"epoch": 0.3733693207377418,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991542471612864,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.13345155641436576,
|
|
"num_tokens": 7319654.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.760975885391235,
|
|
"epoch": 0.37386914579897035,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991511528177307,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.13128891512751578,
|
|
"num_tokens": 7330415.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.749932193756104,
|
|
"epoch": 0.37436897086019894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991480528345898,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.13012148514389993,
|
|
"num_tokens": 7339511.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.790622043609619,
|
|
"epoch": 0.3748687959214275,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991449472119416,
|
|
"loss": 6.5456,
|
|
"mean_token_accuracy": 0.1296324238181114,
|
|
"num_tokens": 7348488.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.642946577072143,
|
|
"epoch": 0.37536862098265605,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991418359498642,
|
|
"loss": 6.4815,
|
|
"mean_token_accuracy": 0.1372799627482891,
|
|
"num_tokens": 7357804.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.701333522796631,
|
|
"epoch": 0.37586844604388464,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991387190484358,
|
|
"loss": 6.5423,
|
|
"mean_token_accuracy": 0.1304772190749645,
|
|
"num_tokens": 7367644.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.756773376464844,
|
|
"epoch": 0.37636827110511323,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000499135596507735,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.1307382293045521,
|
|
"num_tokens": 7377357.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.724325847625733,
|
|
"epoch": 0.37686809616634176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991324683278402,
|
|
"loss": 6.577,
|
|
"mean_token_accuracy": 0.1285243198275566,
|
|
"num_tokens": 7387306.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.758603239059449,
|
|
"epoch": 0.37736792122757035,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991293345088301,
|
|
"loss": 6.5133,
|
|
"mean_token_accuracy": 0.13067101538181305,
|
|
"num_tokens": 7397472.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.617776775360108,
|
|
"epoch": 0.37786774628879893,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991261950507837,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.1306978516280651,
|
|
"num_tokens": 7408786.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.744413614273071,
|
|
"epoch": 0.37836757135002747,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049912304995378,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.12564446777105331,
|
|
"num_tokens": 7417857.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.673680448532105,
|
|
"epoch": 0.37886739641125605,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991198992178979,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.13097197264432908,
|
|
"num_tokens": 7427007.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.706555986404419,
|
|
"epoch": 0.37936722147248464,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991167428432168,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.13801468461751937,
|
|
"num_tokens": 7437090.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.698903608322143,
|
|
"epoch": 0.3798670465337132,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991135808298162,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.1340007059276104,
|
|
"num_tokens": 7446249.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.741633558273316,
|
|
"epoch": 0.38036687159494176,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991104131777755,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.1311210051178932,
|
|
"num_tokens": 7455838.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.660193824768067,
|
|
"epoch": 0.38086669665617034,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991072398871746,
|
|
"loss": 6.5587,
|
|
"mean_token_accuracy": 0.1313708506524563,
|
|
"num_tokens": 7466057.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.7265625,
|
|
"epoch": 0.38136652171739893,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991040609580932,
|
|
"loss": 6.5192,
|
|
"mean_token_accuracy": 0.13103291466832162,
|
|
"num_tokens": 7475174.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.7295308113098145,
|
|
"epoch": 0.38186634677862746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991008763906112,
|
|
"loss": 6.4491,
|
|
"mean_token_accuracy": 0.13873595148324966,
|
|
"num_tokens": 7484635.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.666983318328858,
|
|
"epoch": 0.38236617183985605,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004990976861848087,
|
|
"loss": 6.515,
|
|
"mean_token_accuracy": 0.1301315173506737,
|
|
"num_tokens": 7496428.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.697428941726685,
|
|
"epoch": 0.38286599690108464,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990944903407663,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.1339688517153263,
|
|
"num_tokens": 7506581.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.703534173965454,
|
|
"epoch": 0.38336582196231317,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990912888585641,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.13956890478730202,
|
|
"num_tokens": 7515809.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.582537078857422,
|
|
"epoch": 0.38386564702354176,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990880817382828,
|
|
"loss": 6.4487,
|
|
"mean_token_accuracy": 0.13839477449655532,
|
|
"num_tokens": 7525800.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.724882745742798,
|
|
"epoch": 0.38436547208477034,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499084868980003,
|
|
"loss": 6.5484,
|
|
"mean_token_accuracy": 0.13364261463284494,
|
|
"num_tokens": 7536903.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.653644990921021,
|
|
"epoch": 0.3848652971459989,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990816505838054,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.13110204860568048,
|
|
"num_tokens": 7546004.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.701745176315308,
|
|
"epoch": 0.38536512220722746,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990784265497713,
|
|
"loss": 6.6273,
|
|
"mean_token_accuracy": 0.13158790543675422,
|
|
"num_tokens": 7555971.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.806903934478759,
|
|
"epoch": 0.38586494726845605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990751968779817,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.13267250657081603,
|
|
"num_tokens": 7564569.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.700612878799438,
|
|
"epoch": 0.38636477232968464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990719615685176,
|
|
"loss": 6.5169,
|
|
"mean_token_accuracy": 0.13525842130184174,
|
|
"num_tokens": 7574134.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.706356191635132,
|
|
"epoch": 0.38686459739091317,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990687206214608,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.13645146638154984,
|
|
"num_tokens": 7583631.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.578931379318237,
|
|
"epoch": 0.38736442245214175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990654740368925,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.13898524791002273,
|
|
"num_tokens": 7593281.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.586987400054932,
|
|
"epoch": 0.38786424751337034,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990622218148947,
|
|
"loss": 6.5022,
|
|
"mean_token_accuracy": 0.1368226744234562,
|
|
"num_tokens": 7603735.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.741074800491333,
|
|
"epoch": 0.3883640725745989,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990589639555489,
|
|
"loss": 6.4537,
|
|
"mean_token_accuracy": 0.13325776383280755,
|
|
"num_tokens": 7613126.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.7218067169189455,
|
|
"epoch": 0.38886389763582746,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990557004589373,
|
|
"loss": 6.4928,
|
|
"mean_token_accuracy": 0.12952338755130768,
|
|
"num_tokens": 7623191.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.6596495628356935,
|
|
"epoch": 0.38936372269705605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990524313251419,
|
|
"loss": 6.4842,
|
|
"mean_token_accuracy": 0.13738488107919694,
|
|
"num_tokens": 7634118.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.650729846954346,
|
|
"epoch": 0.3898635477582846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990491565542449,
|
|
"loss": 6.3543,
|
|
"mean_token_accuracy": 0.1455010548233986,
|
|
"num_tokens": 7643228.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.6171557903289795,
|
|
"epoch": 0.39036337281951317,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990458761463289,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.1334925673902035,
|
|
"num_tokens": 7652578.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.657894039154053,
|
|
"epoch": 0.39086319788074175,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990425901014763,
|
|
"loss": 6.4395,
|
|
"mean_token_accuracy": 0.13238203674554824,
|
|
"num_tokens": 7661617.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.688712120056152,
|
|
"epoch": 0.3913630229419703,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990392984197697,
|
|
"loss": 6.4495,
|
|
"mean_token_accuracy": 0.14183069318532943,
|
|
"num_tokens": 7670864.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.667213869094849,
|
|
"epoch": 0.39186284800319887,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990360011012921,
|
|
"loss": 6.5015,
|
|
"mean_token_accuracy": 0.13075718954205512,
|
|
"num_tokens": 7681528.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.694702577590943,
|
|
"epoch": 0.39236267306442746,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990326981461264,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.13443247824907303,
|
|
"num_tokens": 7690398.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.602849674224854,
|
|
"epoch": 0.39286249812565605,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990293895543555,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.1385771796107292,
|
|
"num_tokens": 7699843.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.64528980255127,
|
|
"epoch": 0.3933623231868846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499026075326063,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.13632732927799224,
|
|
"num_tokens": 7710181.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.684283971786499,
|
|
"epoch": 0.39386214824811316,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499022755461332,
|
|
"loss": 6.4264,
|
|
"mean_token_accuracy": 0.1344867043197155,
|
|
"num_tokens": 7719148.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.568447685241699,
|
|
"epoch": 0.39436197330934175,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499019429960246,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.1449710302054882,
|
|
"num_tokens": 7728551.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.676558256149292,
|
|
"epoch": 0.3948617983705703,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990160988228888,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.13119087666273116,
|
|
"num_tokens": 7739083.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.736115837097168,
|
|
"epoch": 0.39536162343179887,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990127620493444,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.13509285524487497,
|
|
"num_tokens": 7749684.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.620078229904175,
|
|
"epoch": 0.39586144849302746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990094196396964,
|
|
"loss": 6.3841,
|
|
"mean_token_accuracy": 0.14306461289525033,
|
|
"num_tokens": 7759281.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.6140861988067625,
|
|
"epoch": 0.396361273554256,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499006071594029,
|
|
"loss": 6.4625,
|
|
"mean_token_accuracy": 0.13693887293338775,
|
|
"num_tokens": 7768612.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.637713766098022,
|
|
"epoch": 0.3968610986154846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990027179124266,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.1362014554440975,
|
|
"num_tokens": 7778333.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.751733779907227,
|
|
"epoch": 0.39736092367671316,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989993585949733,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.13205100148916243,
|
|
"num_tokens": 7787547.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.617351293563843,
|
|
"epoch": 0.3978607487379417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989959936417541,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.1332288607954979,
|
|
"num_tokens": 7798407.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.667150354385376,
|
|
"epoch": 0.3983605737991703,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498992623052853,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.14540825933218002,
|
|
"num_tokens": 7807879.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.625219011306763,
|
|
"epoch": 0.39886039886039887,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989892468283553,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.13793101608753205,
|
|
"num_tokens": 7817210.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.7313008308410645,
|
|
"epoch": 0.39936022392162746,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989858649683457,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.1238260805606842,
|
|
"num_tokens": 7827845.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.762821054458618,
|
|
"epoch": 0.399860048982856,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989824774729094,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.13847627490758896,
|
|
"num_tokens": 7836994.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.673427867889404,
|
|
"epoch": 0.4003598740440846,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989790843421317,
|
|
"loss": 6.5034,
|
|
"mean_token_accuracy": 0.1325397364795208,
|
|
"num_tokens": 7846733.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.590197944641114,
|
|
"epoch": 0.40085969910531316,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989756855760979,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.13929353132843972,
|
|
"num_tokens": 7856393.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.6574195384979244,
|
|
"epoch": 0.4013595241665417,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989722811748934,
|
|
"loss": 6.5026,
|
|
"mean_token_accuracy": 0.13468595445156098,
|
|
"num_tokens": 7866394.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.721140623092651,
|
|
"epoch": 0.4018593492277703,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989688711386039,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.1279691606760025,
|
|
"num_tokens": 7877084.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.686622381210327,
|
|
"epoch": 0.40235917428899887,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989654554673152,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.13242175728082656,
|
|
"num_tokens": 7887289.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.593886280059815,
|
|
"epoch": 0.4028589993502274,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004989620341611133,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.1394074648618698,
|
|
"num_tokens": 7897315.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.801152086257934,
|
|
"epoch": 0.403358824411456,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989586072200843,
|
|
"loss": 6.5745,
|
|
"mean_token_accuracy": 0.1294828787446022,
|
|
"num_tokens": 7905913.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.677629613876343,
|
|
"epoch": 0.40385864947268457,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989551746443143,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.13915923833847046,
|
|
"num_tokens": 7914879.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.615264940261841,
|
|
"epoch": 0.4043584745339131,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989517364338899,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.13616302162408828,
|
|
"num_tokens": 7925163.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.697507905960083,
|
|
"epoch": 0.4048582995951417,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989482925888974,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.14133367091417312,
|
|
"num_tokens": 7934380.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.639877605438232,
|
|
"epoch": 0.4053581246563703,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989448431094233,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.13517219424247742,
|
|
"num_tokens": 7944600.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.560222148895264,
|
|
"epoch": 0.40585794971759886,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989413879955548,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.14073312729597093,
|
|
"num_tokens": 7953545.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.617502450942993,
|
|
"epoch": 0.4063577747788274,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989379272473785,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.13185736313462257,
|
|
"num_tokens": 7962931.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.704211950302124,
|
|
"epoch": 0.406857599840056,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004989344608649815,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.14036257043480874,
|
|
"num_tokens": 7973090.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.703934240341186,
|
|
"epoch": 0.40735742490128457,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989309888484511,
|
|
"loss": 6.5557,
|
|
"mean_token_accuracy": 0.12565968558192253,
|
|
"num_tokens": 7982208.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.6350264072418215,
|
|
"epoch": 0.4078572499625131,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989275111978748,
|
|
"loss": 6.5028,
|
|
"mean_token_accuracy": 0.1372723951935768,
|
|
"num_tokens": 7993389.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.646020364761353,
|
|
"epoch": 0.4083570750237417,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989240279133398,
|
|
"loss": 6.3965,
|
|
"mean_token_accuracy": 0.13715113922953606,
|
|
"num_tokens": 8002749.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.662372016906739,
|
|
"epoch": 0.4088569000849703,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004989205389949339,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.13935092315077782,
|
|
"num_tokens": 8011552.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.555446004867553,
|
|
"epoch": 0.4093567251461988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989170444427448,
|
|
"loss": 6.4099,
|
|
"mean_token_accuracy": 0.1370534487068653,
|
|
"num_tokens": 8020622.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.62073335647583,
|
|
"epoch": 0.4098565502074274,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989135442568606,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.14659582301974297,
|
|
"num_tokens": 8030356.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.641555976867676,
|
|
"epoch": 0.410356375268656,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989100384373693,
|
|
"loss": 6.4754,
|
|
"mean_token_accuracy": 0.13209769874811172,
|
|
"num_tokens": 8039903.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.603917455673217,
|
|
"epoch": 0.4108562003298845,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989065269843588,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.1381150096654892,
|
|
"num_tokens": 8050488.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.666340446472168,
|
|
"epoch": 0.4113560253911131,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498903009897918,
|
|
"loss": 6.4326,
|
|
"mean_token_accuracy": 0.13442504778504372,
|
|
"num_tokens": 8060179.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.620138263702392,
|
|
"epoch": 0.4118558504523417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988994871781349,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.1340521678328514,
|
|
"num_tokens": 8070915.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.59868803024292,
|
|
"epoch": 0.4123556755135703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988959588250983,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.13991266041994094,
|
|
"num_tokens": 8080203.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.6721686840057375,
|
|
"epoch": 0.4128555005747988,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498892424838897,
|
|
"loss": 6.4287,
|
|
"mean_token_accuracy": 0.13809964507818223,
|
|
"num_tokens": 8090552.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.655696296691895,
|
|
"epoch": 0.4133553256360274,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988888852196199,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.14456716924905777,
|
|
"num_tokens": 8099947.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.5789977550506595,
|
|
"epoch": 0.413855150697256,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004988853399673562,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.1324965015053749,
|
|
"num_tokens": 8110502.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.675621604919433,
|
|
"epoch": 0.4143549757584845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988817890821948,
|
|
"loss": 6.5021,
|
|
"mean_token_accuracy": 0.13082315623760224,
|
|
"num_tokens": 8118762.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.6797792434692385,
|
|
"epoch": 0.4148548008197131,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988782325642252,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.1341571941971779,
|
|
"num_tokens": 8129072.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.607687711715698,
|
|
"epoch": 0.4153546258809417,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498874670413537,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.13247276917099954,
|
|
"num_tokens": 8138504.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.736753463745117,
|
|
"epoch": 0.4158544509421702,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988711026302197,
|
|
"loss": 6.5054,
|
|
"mean_token_accuracy": 0.1319202721118927,
|
|
"num_tokens": 8148534.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.692439222335816,
|
|
"epoch": 0.4163542760033988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988675292143629,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.12958220466971399,
|
|
"num_tokens": 8160272.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.681442308425903,
|
|
"epoch": 0.4168541010646274,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988639501660568,
|
|
"loss": 6.4159,
|
|
"mean_token_accuracy": 0.13566980212926866,
|
|
"num_tokens": 8170053.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.647701978683472,
|
|
"epoch": 0.4173539261258559,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988603654853913,
|
|
"loss": 6.4502,
|
|
"mean_token_accuracy": 0.1307328499853611,
|
|
"num_tokens": 8179425.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.6206447124481205,
|
|
"epoch": 0.4178537511870845,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988567751724565,
|
|
"loss": 6.4464,
|
|
"mean_token_accuracy": 0.13175366893410684,
|
|
"num_tokens": 8189846.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.649720954895019,
|
|
"epoch": 0.4183535762483131,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498853179227343,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.1355961926281452,
|
|
"num_tokens": 8198596.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.697376537322998,
|
|
"epoch": 0.4188534013095417,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498849577650141,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.13727675452828408,
|
|
"num_tokens": 8206849.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.626776218414307,
|
|
"epoch": 0.4193532263707702,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988459704409413,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.13869191706180573,
|
|
"num_tokens": 8216260.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.64318881034851,
|
|
"epoch": 0.4198530514319988,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988423575998345,
|
|
"loss": 6.4381,
|
|
"mean_token_accuracy": 0.1396738849580288,
|
|
"num_tokens": 8224650.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.550717401504516,
|
|
"epoch": 0.4203528764932274,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004988387391269117,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.1449220821261406,
|
|
"num_tokens": 8235276.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.668815469741821,
|
|
"epoch": 0.4208527015544559,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988351150222638,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.14007834419608117,
|
|
"num_tokens": 8244687.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.6584413051605225,
|
|
"epoch": 0.4213525266156845,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004988314852859819,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.13266218602657318,
|
|
"num_tokens": 8255091.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.602011442184448,
|
|
"epoch": 0.4218523516769131,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004988278499181575,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.150519697368145,
|
|
"num_tokens": 8265172.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.64949631690979,
|
|
"epoch": 0.4223521767381416,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498824208918882,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.1386836938560009,
|
|
"num_tokens": 8275625.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.592551565170288,
|
|
"epoch": 0.4228520017993702,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498820562288247,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.13505590111017227,
|
|
"num_tokens": 8284343.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.647990703582764,
|
|
"epoch": 0.4233518268605988,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988169100263442,
|
|
"loss": 6.4615,
|
|
"mean_token_accuracy": 0.13546039909124374,
|
|
"num_tokens": 8293430.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.573033809661865,
|
|
"epoch": 0.4238516519218274,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988132521332656,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.13175069764256478,
|
|
"num_tokens": 8302925.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.604532527923584,
|
|
"epoch": 0.4243514769830559,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988095886091031,
|
|
"loss": 6.3947,
|
|
"mean_token_accuracy": 0.1372518755495548,
|
|
"num_tokens": 8312134.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.673155021667481,
|
|
"epoch": 0.4248513020442845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988059194539489,
|
|
"loss": 6.3981,
|
|
"mean_token_accuracy": 0.13447411358356476,
|
|
"num_tokens": 8320942.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.658750391006469,
|
|
"epoch": 0.4253511271055131,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988022446678954,
|
|
"loss": 6.431,
|
|
"mean_token_accuracy": 0.1357377290725708,
|
|
"num_tokens": 8331898.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.5866392135620115,
|
|
"epoch": 0.4258509521667416,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987985642510352,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.13870286643505098,
|
|
"num_tokens": 8341728.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.6022340774536135,
|
|
"epoch": 0.4263507772279702,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987948782034605,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.14205716848373412,
|
|
"num_tokens": 8351611.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.610146760940552,
|
|
"epoch": 0.4268506022891988,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987911865252644,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.14113254994153976,
|
|
"num_tokens": 8360528.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.5951155662536625,
|
|
"epoch": 0.42735042735042733,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987874892165395,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.13764438405632973,
|
|
"num_tokens": 8369898.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.65561056137085,
|
|
"epoch": 0.4278502524116559,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498783786277379,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.14095073267817498,
|
|
"num_tokens": 8379928.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.630190896987915,
|
|
"epoch": 0.4283500774728845,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987800777078759,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.1403922386467457,
|
|
"num_tokens": 8389208.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.600115442276001,
|
|
"epoch": 0.42884990253411304,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987763635081238,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.1389320746064186,
|
|
"num_tokens": 8398364.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.616777992248535,
|
|
"epoch": 0.4293497275953416,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498772643678216,
|
|
"loss": 6.426,
|
|
"mean_token_accuracy": 0.13474786952137946,
|
|
"num_tokens": 8408756.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.624324798583984,
|
|
"epoch": 0.4298495526565702,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987689182182459,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.13658897206187248,
|
|
"num_tokens": 8418318.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.55518684387207,
|
|
"epoch": 0.4303493777177988,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987651871283075,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.13088221698999405,
|
|
"num_tokens": 8427709.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.624454736709595,
|
|
"epoch": 0.43084920277902733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987614504084946,
|
|
"loss": 6.4344,
|
|
"mean_token_accuracy": 0.1318454049527645,
|
|
"num_tokens": 8437848.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.619418668746948,
|
|
"epoch": 0.4313490278402559,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987577080589012,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1383514918386936,
|
|
"num_tokens": 8447466.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.609916496276855,
|
|
"epoch": 0.4318488529014845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987539600796213,
|
|
"loss": 6.3771,
|
|
"mean_token_accuracy": 0.14249589070677757,
|
|
"num_tokens": 8456651.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.6440176486969,
|
|
"epoch": 0.43234867796271303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987502064707494,
|
|
"loss": 6.4151,
|
|
"mean_token_accuracy": 0.1384366989135742,
|
|
"num_tokens": 8466421.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.564423274993897,
|
|
"epoch": 0.4328485030239416,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987464472323799,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.13625019490718843,
|
|
"num_tokens": 8476419.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.629364919662476,
|
|
"epoch": 0.4333483280851702,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987426823646074,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.138084876537323,
|
|
"num_tokens": 8486652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.592283439636231,
|
|
"epoch": 0.43384815314639874,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987389118675266,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.13976754546165465,
|
|
"num_tokens": 8495965.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.643533372879029,
|
|
"epoch": 0.4343479782076273,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987351357412322,
|
|
"loss": 6.4346,
|
|
"mean_token_accuracy": 0.13415250182151794,
|
|
"num_tokens": 8506018.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.5735618591308596,
|
|
"epoch": 0.4348478032688559,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987313539858196,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.14260436818003655,
|
|
"num_tokens": 8516178.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.684410095214844,
|
|
"epoch": 0.43534762833008445,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987275666013836,
|
|
"loss": 6.4593,
|
|
"mean_token_accuracy": 0.13695967346429824,
|
|
"num_tokens": 8525548.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.666143608093262,
|
|
"epoch": 0.43584745339131303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987237735880195,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.13141249120235443,
|
|
"num_tokens": 8535941.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.541698360443116,
|
|
"epoch": 0.4363472784525416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987199749458229,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.14433649852871894,
|
|
"num_tokens": 8545381.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.605207014083862,
|
|
"epoch": 0.4368471035137702,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987161706748893,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.14123242646455764,
|
|
"num_tokens": 8555827.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.597718715667725,
|
|
"epoch": 0.43734692857499874,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987123607753144,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.1482037529349327,
|
|
"num_tokens": 8565508.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.673507833480835,
|
|
"epoch": 0.4378467536362273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498708545247194,
|
|
"loss": 6.4947,
|
|
"mean_token_accuracy": 0.1310153126716614,
|
|
"num_tokens": 8576273.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.629042768478394,
|
|
"epoch": 0.4383465786974559,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987047240906243,
|
|
"loss": 6.4501,
|
|
"mean_token_accuracy": 0.1355544313788414,
|
|
"num_tokens": 8585488.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.564994192123413,
|
|
"epoch": 0.43884640375868444,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987008973057012,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.1362445756793022,
|
|
"num_tokens": 8595299.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.620970106124878,
|
|
"epoch": 0.43934622881991303,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986970648925211,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.13859717845916747,
|
|
"num_tokens": 8604910.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.654837131500244,
|
|
"epoch": 0.4398460538811416,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986932268511804,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.13972875252366065,
|
|
"num_tokens": 8614966.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.545269775390625,
|
|
"epoch": 0.44034587894237015,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986893831817758,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.13854756355285644,
|
|
"num_tokens": 8624539.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.509920120239258,
|
|
"epoch": 0.44084570400359874,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986855338844038,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.14724286496639252,
|
|
"num_tokens": 8633775.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.56339020729065,
|
|
"epoch": 0.4413455290648273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986816789591613,
|
|
"loss": 6.4095,
|
|
"mean_token_accuracy": 0.13371871337294577,
|
|
"num_tokens": 8643798.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.492765331268311,
|
|
"epoch": 0.44184535412605586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986778184061453,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.14173724576830865,
|
|
"num_tokens": 8653695.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.590259456634522,
|
|
"epoch": 0.44234517918728444,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986739522254529,
|
|
"loss": 6.3567,
|
|
"mean_token_accuracy": 0.13940617591142654,
|
|
"num_tokens": 8663521.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.698655128479004,
|
|
"epoch": 0.44284500424851303,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986700804171816,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.1347972996532917,
|
|
"num_tokens": 8673108.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.648994207382202,
|
|
"epoch": 0.4433448293097416,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986662029814285,
|
|
"loss": 6.3525,
|
|
"mean_token_accuracy": 0.13953598588705063,
|
|
"num_tokens": 8682917.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.631197166442871,
|
|
"epoch": 0.44384465437097015,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986623199182913,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.1323112390935421,
|
|
"num_tokens": 8692436.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.584388208389282,
|
|
"epoch": 0.44434447943219874,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986584312278678,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.1443377584218979,
|
|
"num_tokens": 8702627.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.6175868034362795,
|
|
"epoch": 0.4448443044934273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986545369102556,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.13404581397771836,
|
|
"num_tokens": 8711697.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.665869951248169,
|
|
"epoch": 0.44534412955465585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986506369655528,
|
|
"loss": 6.4091,
|
|
"mean_token_accuracy": 0.13579729869961737,
|
|
"num_tokens": 8721449.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.579997920989991,
|
|
"epoch": 0.44584395461588444,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986467313938575,
|
|
"loss": 6.3916,
|
|
"mean_token_accuracy": 0.13501101806759835,
|
|
"num_tokens": 8731829.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.5675280570983885,
|
|
"epoch": 0.44634377967711303,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498642820195268,
|
|
"loss": 6.1992,
|
|
"mean_token_accuracy": 0.15529305040836333,
|
|
"num_tokens": 8741768.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.636408710479737,
|
|
"epoch": 0.44684360473834156,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986389033698827,
|
|
"loss": 6.4843,
|
|
"mean_token_accuracy": 0.13215626254677773,
|
|
"num_tokens": 8751473.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.642395257949829,
|
|
"epoch": 0.44734342979957015,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986349809178002,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.13525526225566864,
|
|
"num_tokens": 8761229.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.516204404830932,
|
|
"epoch": 0.44784325486079873,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986310528391192,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.13831223249435426,
|
|
"num_tokens": 8770670.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.610432577133179,
|
|
"epoch": 0.44834307992202727,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986271191339383,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.1379597954452038,
|
|
"num_tokens": 8780816.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.7023273468017575,
|
|
"epoch": 0.44884290498325585,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986231798023566,
|
|
"loss": 6.453,
|
|
"mean_token_accuracy": 0.133901596814394,
|
|
"num_tokens": 8790304.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.608483982086182,
|
|
"epoch": 0.44934273004448444,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986192348444734,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.138035336881876,
|
|
"num_tokens": 8799188.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.620791435241699,
|
|
"epoch": 0.449842555105713,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986152842603877,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.13701629638671875,
|
|
"num_tokens": 8810194.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.654542922973633,
|
|
"epoch": 0.45034238016694156,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004986113280501989,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.13809545636177062,
|
|
"num_tokens": 8820394.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.5758332252502445,
|
|
"epoch": 0.45084220522817015,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986073662140068,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.1426957719027996,
|
|
"num_tokens": 8831308.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.546499872207642,
|
|
"epoch": 0.45134203028939873,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986033987519109,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.14570676535367966,
|
|
"num_tokens": 8841461.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.623135137557983,
|
|
"epoch": 0.45184185535062726,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985994256640108,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.13716485276818274,
|
|
"num_tokens": 8850356.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.6305742263793945,
|
|
"epoch": 0.45234168041185585,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985954469504069,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.13241086900234222,
|
|
"num_tokens": 8859863.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.591443014144898,
|
|
"epoch": 0.45284150547308444,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985914626111991,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.13501992896199227,
|
|
"num_tokens": 8869887.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.644174385070801,
|
|
"epoch": 0.45334133053431297,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004985874726464875,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.13741553351283073,
|
|
"num_tokens": 8879950.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.595855188369751,
|
|
"epoch": 0.45384115559554156,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985834770563727,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.14475732445716857,
|
|
"num_tokens": 8888304.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.548413562774658,
|
|
"epoch": 0.45434098065677014,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985794758409552,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.15353648960590363,
|
|
"num_tokens": 8898642.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.558280944824219,
|
|
"epoch": 0.4548408057179987,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004985754690003354,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.12900075316429138,
|
|
"num_tokens": 8909202.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.53426423072815,
|
|
"epoch": 0.45534063077922726,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985714565346145,
|
|
"loss": 6.2979,
|
|
"mean_token_accuracy": 0.14765509963035583,
|
|
"num_tokens": 8918844.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.6262125968933105,
|
|
"epoch": 0.45584045584045585,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985674384438933,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.13535004779696463,
|
|
"num_tokens": 8928706.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.586584234237671,
|
|
"epoch": 0.45634028090168444,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985634147282729,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.14519940838217735,
|
|
"num_tokens": 8939293.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.545429801940918,
|
|
"epoch": 0.45684010596291297,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985593853878544,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.13739223405718803,
|
|
"num_tokens": 8947922.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.523553657531738,
|
|
"epoch": 0.45733993102414155,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004985553504227394,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.14679670631885527,
|
|
"num_tokens": 8957745.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.619437170028687,
|
|
"epoch": 0.45783975608537014,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985513098330293,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.13493750542402266,
|
|
"num_tokens": 8968331.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.565895652770996,
|
|
"epoch": 0.4583395811465987,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985472636188257,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.14844054132699966,
|
|
"num_tokens": 8977752.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.563983058929443,
|
|
"epoch": 0.45883940620782726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985432117802305,
|
|
"loss": 6.3748,
|
|
"mean_token_accuracy": 0.1358737416565418,
|
|
"num_tokens": 8986701.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.539378309249878,
|
|
"epoch": 0.45933923126905585,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985391543173456,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.13833511471748353,
|
|
"num_tokens": 8996192.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.603825378417969,
|
|
"epoch": 0.4598390563302844,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000498535091230273,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.13897524774074554,
|
|
"num_tokens": 9007059.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.509483575820923,
|
|
"epoch": 0.46033888139151297,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985310225191152,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.14229824393987656,
|
|
"num_tokens": 9016923.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.550838804244995,
|
|
"epoch": 0.46083870645274155,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985269481839744,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.13663146793842315,
|
|
"num_tokens": 9026034.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.6666419506073,
|
|
"epoch": 0.4613385315139701,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985228682249529,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.13819245621562004,
|
|
"num_tokens": 9036773.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.615478610992431,
|
|
"epoch": 0.46183835657519867,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985187826421538,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.13985020890831948,
|
|
"num_tokens": 9047825.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.605540132522583,
|
|
"epoch": 0.46233818163642726,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985146914356795,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.13437833040952682,
|
|
"num_tokens": 9056295.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.567204523086548,
|
|
"epoch": 0.46283800669765585,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498510594605633,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.13963764011859894,
|
|
"num_tokens": 9067245.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.562276315689087,
|
|
"epoch": 0.4633378317588844,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985064921521177,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.1408180572092533,
|
|
"num_tokens": 9077528.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.5792008399963375,
|
|
"epoch": 0.46383765682011296,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985023840752364,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.1445113755762577,
|
|
"num_tokens": 9086015.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.59324164390564,
|
|
"epoch": 0.46433748188134155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984982703750926,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.13380938321352004,
|
|
"num_tokens": 9095963.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.499166440963745,
|
|
"epoch": 0.4648373069425701,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984941510517899,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.1417975626885891,
|
|
"num_tokens": 9105819.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.51986083984375,
|
|
"epoch": 0.46533713200379867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984900261054319,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.14423037990927695,
|
|
"num_tokens": 9114574.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.584482288360595,
|
|
"epoch": 0.46583695706502726,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984858955361224,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.13324421420693397,
|
|
"num_tokens": 9125490.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.667818784713745,
|
|
"epoch": 0.4663367821262558,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984817593439651,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.1395638443529606,
|
|
"num_tokens": 9134886.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.554930877685547,
|
|
"epoch": 0.4668366071874844,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984776175290643,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.14410901069641113,
|
|
"num_tokens": 9143598.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.527012729644776,
|
|
"epoch": 0.46733643224871296,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984734700915242,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.12662543207406998,
|
|
"num_tokens": 9153051.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.633116388320923,
|
|
"epoch": 0.4678362573099415,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498469317031449,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.13861129581928253,
|
|
"num_tokens": 9162472.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.560390043258667,
|
|
"epoch": 0.4683360823711701,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984651583489434,
|
|
"loss": 6.3929,
|
|
"mean_token_accuracy": 0.14095161855220795,
|
|
"num_tokens": 9171453.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.4846728324890135,
|
|
"epoch": 0.46883590743239867,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984609940441119,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.14540164768695832,
|
|
"num_tokens": 9181104.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.635798645019531,
|
|
"epoch": 0.46933573249362726,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984568241170593,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.14489806294441224,
|
|
"num_tokens": 9190403.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.560534811019897,
|
|
"epoch": 0.4698355575548558,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984526485678905,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.14175272434949876,
|
|
"num_tokens": 9199132.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.551282072067261,
|
|
"epoch": 0.4703353826160844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984484673967105,
|
|
"loss": 6.4355,
|
|
"mean_token_accuracy": 0.12911114916205407,
|
|
"num_tokens": 9208274.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.535216426849365,
|
|
"epoch": 0.47083520767731296,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984442806036246,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.14726507514715195,
|
|
"num_tokens": 9218513.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.620094060897827,
|
|
"epoch": 0.4713350327385415,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984400881887381,
|
|
"loss": 6.4078,
|
|
"mean_token_accuracy": 0.1369947798550129,
|
|
"num_tokens": 9229197.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.5997944355010985,
|
|
"epoch": 0.4718348577997701,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984358901521565,
|
|
"loss": 6.2626,
|
|
"mean_token_accuracy": 0.13775440230965613,
|
|
"num_tokens": 9239465.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.548333263397216,
|
|
"epoch": 0.47233468286099867,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984316864939853,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.14078133404254914,
|
|
"num_tokens": 9250112.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.604399347305298,
|
|
"epoch": 0.4728345079222272,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984274772143304,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.14028800427913665,
|
|
"num_tokens": 9259406.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.602729749679566,
|
|
"epoch": 0.4733343329834558,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984232623132977,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.1402455322444439,
|
|
"num_tokens": 9269462.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.5745021343231205,
|
|
"epoch": 0.4738341580446844,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984190417909932,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.13758225739002228,
|
|
"num_tokens": 9280291.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.6031004905700685,
|
|
"epoch": 0.4743339831059129,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984148156475231,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.13424651324748993,
|
|
"num_tokens": 9289680.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.549824571609497,
|
|
"epoch": 0.4748338081671415,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004984105838829937,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.13878616392612458,
|
|
"num_tokens": 9301043.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.504221487045288,
|
|
"epoch": 0.4753336332283701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984063464975116,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.14260153621435165,
|
|
"num_tokens": 9311851.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.688992118835449,
|
|
"epoch": 0.47583345828959867,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984021034911833,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.1412937067449093,
|
|
"num_tokens": 9320886.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.530198335647583,
|
|
"epoch": 0.4763332833508272,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983978548641154,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.13919110372662544,
|
|
"num_tokens": 9330518.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.459668684005737,
|
|
"epoch": 0.4768331084120558,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983936006164151,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.1423420637845993,
|
|
"num_tokens": 9339703.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.655837297439575,
|
|
"epoch": 0.47733293347328437,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983893407481892,
|
|
"loss": 6.4787,
|
|
"mean_token_accuracy": 0.12985201105475425,
|
|
"num_tokens": 9349931.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.573695421218872,
|
|
"epoch": 0.4778327585345129,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983850752595451,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.1428273394703865,
|
|
"num_tokens": 9358984.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.566775989532471,
|
|
"epoch": 0.4783325835957415,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983808041505898,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.1458449773490429,
|
|
"num_tokens": 9368081.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.606782245635986,
|
|
"epoch": 0.4788324086569701,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983765274214311,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.1329596996307373,
|
|
"num_tokens": 9377346.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.489269161224366,
|
|
"epoch": 0.4793322337181986,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983722450721764,
|
|
"loss": 6.3827,
|
|
"mean_token_accuracy": 0.14182444736361505,
|
|
"num_tokens": 9387493.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.586794662475586,
|
|
"epoch": 0.4798320587794272,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983679571029336,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.13902711272239685,
|
|
"num_tokens": 9397154.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.584662008285522,
|
|
"epoch": 0.4803318838406558,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004983636635138103,
|
|
"loss": 6.4353,
|
|
"mean_token_accuracy": 0.13636839836835862,
|
|
"num_tokens": 9406705.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.566107749938965,
|
|
"epoch": 0.4808317089018843,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983593643049148,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.14564415365457534,
|
|
"num_tokens": 9416850.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.5056829929351805,
|
|
"epoch": 0.4813315339631129,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983550594763552,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.14114589616656303,
|
|
"num_tokens": 9425841.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.478992176055908,
|
|
"epoch": 0.4818313590243415,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983507490282397,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.14144658893346787,
|
|
"num_tokens": 9436748.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.53460545539856,
|
|
"epoch": 0.4823311840855701,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983464329606768,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.13899094834923745,
|
|
"num_tokens": 9446043.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.577762937545776,
|
|
"epoch": 0.4828310091467986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983421112737752,
|
|
"loss": 6.3859,
|
|
"mean_token_accuracy": 0.13852088823914527,
|
|
"num_tokens": 9455480.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.574634170532226,
|
|
"epoch": 0.4833308342080272,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983377839676435,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.13791154623031615,
|
|
"num_tokens": 9464412.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.558297443389892,
|
|
"epoch": 0.4838306592692558,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983334510423906,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.14104320779442786,
|
|
"num_tokens": 9475639.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.547320747375489,
|
|
"epoch": 0.4843304843304843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983291124981257,
|
|
"loss": 6.2932,
|
|
"mean_token_accuracy": 0.14363638833165168,
|
|
"num_tokens": 9484721.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.443142366409302,
|
|
"epoch": 0.4848303093917129,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983247683349576,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.1503700517117977,
|
|
"num_tokens": 9494594.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.46635479927063,
|
|
"epoch": 0.4853301344529415,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983204185529959,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.14452256560325621,
|
|
"num_tokens": 9503707.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.545555448532104,
|
|
"epoch": 0.48582995951417,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983160631523499,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.14395815283060073,
|
|
"num_tokens": 9512473.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.554967308044434,
|
|
"epoch": 0.4863297845753986,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983117021331293,
|
|
"loss": 6.3862,
|
|
"mean_token_accuracy": 0.14062849804759026,
|
|
"num_tokens": 9523253.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.561938142776489,
|
|
"epoch": 0.4868296096366272,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983073354954436,
|
|
"loss": 6.3295,
|
|
"mean_token_accuracy": 0.14637787491083146,
|
|
"num_tokens": 9531938.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.580343294143677,
|
|
"epoch": 0.4873294346978557,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983029632394029,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.13762582391500472,
|
|
"num_tokens": 9541542.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.470240068435669,
|
|
"epoch": 0.4878292597590843,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498298585365117,
|
|
"loss": 6.2741,
|
|
"mean_token_accuracy": 0.14422172009944917,
|
|
"num_tokens": 9551521.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.565884351730347,
|
|
"epoch": 0.4883290848203129,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982942018726963,
|
|
"loss": 6.3989,
|
|
"mean_token_accuracy": 0.1435948356986046,
|
|
"num_tokens": 9561605.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.541082859039307,
|
|
"epoch": 0.4888289098815415,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982898127622508,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.14238758534193038,
|
|
"num_tokens": 9571591.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.473294067382812,
|
|
"epoch": 0.48932873494277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004982854180338911,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.14472779035568237,
|
|
"num_tokens": 9580994.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.593008279800415,
|
|
"epoch": 0.4898285600039986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982810176877279,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.14055697545409201,
|
|
"num_tokens": 9589268.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.509798383712768,
|
|
"epoch": 0.4903283850652272,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004982766117238716,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.1377256415784359,
|
|
"num_tokens": 9599461.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.540691280364991,
|
|
"epoch": 0.4908282101264557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982722001424331,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.137178722769022,
|
|
"num_tokens": 9609629.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.519233322143554,
|
|
"epoch": 0.4913280351876843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982677829435236,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.14501211196184158,
|
|
"num_tokens": 9619618.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.549957799911499,
|
|
"epoch": 0.4918278602489129,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982633601272543,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.14338547959923745,
|
|
"num_tokens": 9629042.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.523736381530762,
|
|
"epoch": 0.4923276853101414,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982589316937361,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.14397076070308684,
|
|
"num_tokens": 9638596.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.579415369033813,
|
|
"epoch": 0.49282751037137,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982544976430808,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.1363321416079998,
|
|
"num_tokens": 9648505.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.497425556182861,
|
|
"epoch": 0.4933273354325986,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982500579753995,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.1440951094031334,
|
|
"num_tokens": 9658113.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.518186235427857,
|
|
"epoch": 0.49382716049382713,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982456126908044,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.14415861368179322,
|
|
"num_tokens": 9668075.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.607472991943359,
|
|
"epoch": 0.4943269855550557,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982411617894071,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.13661205396056175,
|
|
"num_tokens": 9678139.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.545077991485596,
|
|
"epoch": 0.4948268106162843,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982367052713196,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.13556177616119386,
|
|
"num_tokens": 9687328.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.510440540313721,
|
|
"epoch": 0.4953266356775129,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982322431366541,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.14261072650551795,
|
|
"num_tokens": 9697536.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.545744609832764,
|
|
"epoch": 0.4958264607387414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982277753855227,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.1451621651649475,
|
|
"num_tokens": 9706804.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.570737266540528,
|
|
"epoch": 0.49632628579997,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498223302018038,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.14873917400836945,
|
|
"num_tokens": 9716868.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.478694915771484,
|
|
"epoch": 0.4968261108611986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982188230343124,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.1420037865638733,
|
|
"num_tokens": 9728790.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.569926643371582,
|
|
"epoch": 0.49732593592242713,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982143384344587,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.13710157945752144,
|
|
"num_tokens": 9739118.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.5901134490966795,
|
|
"epoch": 0.4978257609836557,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982098482185897,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.13986100181937217,
|
|
"num_tokens": 9749347.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.617333459854126,
|
|
"epoch": 0.4983255860448843,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982053523868182,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.1376863457262516,
|
|
"num_tokens": 9759432.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.486593627929688,
|
|
"epoch": 0.49882541110611284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982008509392576,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.1378074787557125,
|
|
"num_tokens": 9768666.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.454793882369995,
|
|
"epoch": 0.4993252361673414,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498196343876021,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.15229423493146896,
|
|
"num_tokens": 9778699.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.51581883430481,
|
|
"epoch": 0.49982506122857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981918311972219,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.14056676626205444,
|
|
"num_tokens": 9788156.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.4820068359375,
|
|
"epoch": 0.5003248862897985,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981873129029737,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.15172883123159409,
|
|
"num_tokens": 9797293.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.512367153167725,
|
|
"epoch": 0.5008247113510271,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049818278899339,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.1474616900086403,
|
|
"num_tokens": 9806962.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.53746771812439,
|
|
"epoch": 0.5013245364122557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498178259468585,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.14440343901515007,
|
|
"num_tokens": 9816689.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.5377936363220215,
|
|
"epoch": 0.5018243614734843,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981737243286722,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.1420392207801342,
|
|
"num_tokens": 9826321.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.598534393310547,
|
|
"epoch": 0.5023241865347129,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981691835737661,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.13818110153079033,
|
|
"num_tokens": 9836054.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.597829532623291,
|
|
"epoch": 0.5028240115959414,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981646372039807,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.14267103597521782,
|
|
"num_tokens": 9846516.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.5271446228027346,
|
|
"epoch": 0.50332383665717,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004981600852194305,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.1508418709039688,
|
|
"num_tokens": 9856599.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.526463222503662,
|
|
"epoch": 0.5038236617183985,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00049815552762023,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.14515673294663428,
|
|
"num_tokens": 9866922.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.503176164627075,
|
|
"epoch": 0.5043234867796271,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981509644064937,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.14172665774822235,
|
|
"num_tokens": 9876174.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.502034282684326,
|
|
"epoch": 0.5048233118408557,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981463955783367,
|
|
"loss": 6.2333,
|
|
"mean_token_accuracy": 0.14824968129396437,
|
|
"num_tokens": 9886208.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.506152486801147,
|
|
"epoch": 0.5053231369020843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981418211358736,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.14375177547335624,
|
|
"num_tokens": 9896522.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.476954555511474,
|
|
"epoch": 0.5058229619633129,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981372410792199,
|
|
"loss": 6.2869,
|
|
"mean_token_accuracy": 0.1476489081978798,
|
|
"num_tokens": 9905753.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.563267803192138,
|
|
"epoch": 0.5063227870245414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981326554084906,
|
|
"loss": 6.3867,
|
|
"mean_token_accuracy": 0.1415315695106983,
|
|
"num_tokens": 9916566.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.518082952499389,
|
|
"epoch": 0.50682261208577,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981280641238011,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.1354844018816948,
|
|
"num_tokens": 9926126.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.509505987167358,
|
|
"epoch": 0.5073224371469985,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981234672252669,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.13671267479658128,
|
|
"num_tokens": 9937666.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.586646032333374,
|
|
"epoch": 0.5078222622082271,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981188647130037,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.14464337527751922,
|
|
"num_tokens": 9947107.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.536127424240112,
|
|
"epoch": 0.5083220872694557,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981142565871272,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.14032416194677352,
|
|
"num_tokens": 9956484.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.411437845230102,
|
|
"epoch": 0.5088219123306843,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981096428477535,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.14039676412940025,
|
|
"num_tokens": 9966731.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.527744388580322,
|
|
"epoch": 0.5093217373919128,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981050234949986,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.14204144924879075,
|
|
"num_tokens": 9976491.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.54841194152832,
|
|
"epoch": 0.5098215624531414,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981003985289786,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.14918500632047654,
|
|
"num_tokens": 9985248.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.405408000946045,
|
|
"epoch": 0.51032138751437,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980957679498101,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.14638384506106378,
|
|
"num_tokens": 9995578.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.603743314743042,
|
|
"epoch": 0.5108212125755985,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004980911317576095,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.1395988643169403,
|
|
"num_tokens": 10006078.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.616304540634156,
|
|
"epoch": 0.5113210376368271,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980864899524933,
|
|
"loss": 6.3676,
|
|
"mean_token_accuracy": 0.13535810634493828,
|
|
"num_tokens": 10015943.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.512275314331054,
|
|
"epoch": 0.5118208626980557,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980818425345786,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.13668338134884833,
|
|
"num_tokens": 10025738.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.558469629287719,
|
|
"epoch": 0.5123206877592843,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498077189503982,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.13545635789632798,
|
|
"num_tokens": 10035032.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.552367782592773,
|
|
"epoch": 0.5128205128205128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980725308608208,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.14596602320671082,
|
|
"num_tokens": 10044201.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.467952394485474,
|
|
"epoch": 0.5133203378817414,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980678666052121,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.14746638312935828,
|
|
"num_tokens": 10054163.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.475956392288208,
|
|
"epoch": 0.51382016294297,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004980631967372733,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.13951059877872468,
|
|
"num_tokens": 10065225.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.56135663986206,
|
|
"epoch": 0.5143199880041985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980585212571218,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.14300507456064224,
|
|
"num_tokens": 10074776.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.592345428466797,
|
|
"epoch": 0.5148198130654271,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980538401648753,
|
|
"loss": 6.4348,
|
|
"mean_token_accuracy": 0.13887105882167816,
|
|
"num_tokens": 10085917.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.540498685836792,
|
|
"epoch": 0.5153196381266557,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980491534606517,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.14526643380522727,
|
|
"num_tokens": 10094727.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.5178173065185545,
|
|
"epoch": 0.5158194631878842,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980444611445686,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.14883555024862288,
|
|
"num_tokens": 10104839.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.502590131759644,
|
|
"epoch": 0.5163192882491128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980397632167444,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.14643971472978592,
|
|
"num_tokens": 10114501.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.524584770202637,
|
|
"epoch": 0.5168191133103414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980350596772971,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.14097927510738373,
|
|
"num_tokens": 10124597.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.46236367225647,
|
|
"epoch": 0.51731893837157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004980303505263451,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14542513117194175,
|
|
"num_tokens": 10135695.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.426722526550293,
|
|
"epoch": 0.5178187634327985,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980256357640069,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.13918386474251748,
|
|
"num_tokens": 10146107.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.554210901260376,
|
|
"epoch": 0.5183185884940271,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980209153904011,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.14753025025129318,
|
|
"num_tokens": 10155983.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.556188344955444,
|
|
"epoch": 0.5188184135552557,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980161894056464,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.13928946629166603,
|
|
"num_tokens": 10166183.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.492159461975097,
|
|
"epoch": 0.5193182386164842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980114578098618,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.14736593440175055,
|
|
"num_tokens": 10175524.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.4928689956665036,
|
|
"epoch": 0.5198180636777128,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004980067206031663,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.13515107408165933,
|
|
"num_tokens": 10186235.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.609361410140991,
|
|
"epoch": 0.5203178887389414,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004980019777856791,
|
|
"loss": 6.3547,
|
|
"mean_token_accuracy": 0.13849088698625564,
|
|
"num_tokens": 10196166.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.537497663497925,
|
|
"epoch": 0.52081771380017,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004979972293575195,
|
|
"loss": 6.2671,
|
|
"mean_token_accuracy": 0.14175921231508254,
|
|
"num_tokens": 10205691.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.448285150527954,
|
|
"epoch": 0.5213175388613985,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979924753188069,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.14872171580791474,
|
|
"num_tokens": 10216224.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.477010059356689,
|
|
"epoch": 0.5218173639226271,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004979877156696612,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.1434367462992668,
|
|
"num_tokens": 10226468.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.640393924713135,
|
|
"epoch": 0.5223171889838556,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979829504102018,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.14011741280555726,
|
|
"num_tokens": 10235932.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.601132106781006,
|
|
"epoch": 0.5228170140450842,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004979781795405488,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.13735318332910537,
|
|
"num_tokens": 10246052.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.6360596179962155,
|
|
"epoch": 0.5233168391063128,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979734030608222,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.14410310834646226,
|
|
"num_tokens": 10255056.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.509991121292114,
|
|
"epoch": 0.5238166641675414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979686209711422,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.14153314307332038,
|
|
"num_tokens": 10265403.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.446553039550781,
|
|
"epoch": 0.5243164892287699,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497963833271629,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.15151776224374772,
|
|
"num_tokens": 10275148.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.532001113891601,
|
|
"epoch": 0.5248163142899985,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979590399624031,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.14435537084937095,
|
|
"num_tokens": 10285083.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.466645240783691,
|
|
"epoch": 0.5253161393512271,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979542410435852,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.13771927729249,
|
|
"num_tokens": 10294466.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.556583213806152,
|
|
"epoch": 0.5258159644124556,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979494365152959,
|
|
"loss": 6.3436,
|
|
"mean_token_accuracy": 0.1370968833565712,
|
|
"num_tokens": 10304333.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.59895806312561,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979446263776562,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.1343003660440445,
|
|
"num_tokens": 10314880.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.51984429359436,
|
|
"epoch": 0.5268156145349128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497939810630787,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.14585166946053504,
|
|
"num_tokens": 10324060.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.459022140502929,
|
|
"epoch": 0.5273154395961414,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004979349892748096,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.1419714942574501,
|
|
"num_tokens": 10335248.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.556001758575439,
|
|
"epoch": 0.5278152646573699,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979301623098452,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.15221127420663833,
|
|
"num_tokens": 10343974.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.493832206726074,
|
|
"epoch": 0.5283150897185985,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004979253297360153,
|
|
"loss": 6.2725,
|
|
"mean_token_accuracy": 0.14151808470487595,
|
|
"num_tokens": 10354037.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.507943105697632,
|
|
"epoch": 0.528814914779827,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004979204915534415,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.14203192293643951,
|
|
"num_tokens": 10364714.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.521287488937378,
|
|
"epoch": 0.5293147398410556,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979156477622454,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.1444737546145916,
|
|
"num_tokens": 10373972.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.473849773406982,
|
|
"epoch": 0.5298145649022842,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004979107983625491,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.14477100670337678,
|
|
"num_tokens": 10382882.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.434201002120972,
|
|
"epoch": 0.5303143899635128,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979059433544744,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.14759512692689897,
|
|
"num_tokens": 10392257.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.511396884918213,
|
|
"epoch": 0.5308142150247414,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979010827381435,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.1426718309521675,
|
|
"num_tokens": 10401055.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.5877152442932125,
|
|
"epoch": 0.5313140400859699,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978962165136787,
|
|
"loss": 6.4083,
|
|
"mean_token_accuracy": 0.13451818153262138,
|
|
"num_tokens": 10411443.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.5525330066680905,
|
|
"epoch": 0.5318138651471985,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978913446812025,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.14053457006812095,
|
|
"num_tokens": 10422142.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.532049703598022,
|
|
"epoch": 0.532313690208427,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978864672408374,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.14145327657461165,
|
|
"num_tokens": 10432454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.519385290145874,
|
|
"epoch": 0.5328135152696556,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004978815841927061,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.14249399900436402,
|
|
"num_tokens": 10443625.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.581267213821411,
|
|
"epoch": 0.5333133403308842,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978766955369315,
|
|
"loss": 6.333,
|
|
"mean_token_accuracy": 0.14542470797896384,
|
|
"num_tokens": 10454055.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.424762296676636,
|
|
"epoch": 0.5338131653921128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978718012736367,
|
|
"loss": 6.1928,
|
|
"mean_token_accuracy": 0.14896668791770934,
|
|
"num_tokens": 10462683.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.441015005111694,
|
|
"epoch": 0.5343129904533414,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978669014029446,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.15022287964820863,
|
|
"num_tokens": 10471699.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.428078031539917,
|
|
"epoch": 0.5348128155145699,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004978619959249787,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.15191919580101967,
|
|
"num_tokens": 10480790.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.457252931594849,
|
|
"epoch": 0.5353126405757984,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978570848398623,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.13901477977633475,
|
|
"num_tokens": 10490202.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.4627772808074955,
|
|
"epoch": 0.535812465637027,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497852168147719,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.14239349961280823,
|
|
"num_tokens": 10499690.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.525272560119629,
|
|
"epoch": 0.5363122906982556,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978472458486724,
|
|
"loss": 6.277,
|
|
"mean_token_accuracy": 0.14200210124254226,
|
|
"num_tokens": 10510120.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.528937101364136,
|
|
"epoch": 0.5368121157594842,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978423179428466,
|
|
"loss": 6.4073,
|
|
"mean_token_accuracy": 0.13670619055628777,
|
|
"num_tokens": 10520521.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.417565059661865,
|
|
"epoch": 0.5373119408207128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978373844303653,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.15266377255320548,
|
|
"num_tokens": 10530233.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.450378799438477,
|
|
"epoch": 0.5378117658819414,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978324453113528,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.14494828879833221,
|
|
"num_tokens": 10539683.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.41905026435852,
|
|
"epoch": 0.5383115909431699,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978275005859333,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.14378251880407333,
|
|
"num_tokens": 10549483.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.558788394927978,
|
|
"epoch": 0.5388114160043984,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978225502542313,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.13704988956451417,
|
|
"num_tokens": 10560464.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.523187303543091,
|
|
"epoch": 0.539311241065627,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978175943163712,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.14209336638450623,
|
|
"num_tokens": 10568660.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.503925466537476,
|
|
"epoch": 0.5398110661268556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978126327724777,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.14399428367614747,
|
|
"num_tokens": 10577304.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.495206689834594,
|
|
"epoch": 0.5403108911880842,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978076656226758,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.15970669090747833,
|
|
"num_tokens": 10587591.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.49522180557251,
|
|
"epoch": 0.5408107162493128,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004978026928670902,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.14627155065536498,
|
|
"num_tokens": 10598591.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.453034162521362,
|
|
"epoch": 0.5413105413105413,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004977977145058463,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.14603489339351655,
|
|
"num_tokens": 10608842.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.435686779022217,
|
|
"epoch": 0.5418103663717699,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004977927305390693,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.14656710401177406,
|
|
"num_tokens": 10618812.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.520738649368286,
|
|
"epoch": 0.5423101914329984,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977877409668845,
|
|
"loss": 6.3954,
|
|
"mean_token_accuracy": 0.13775839656591415,
|
|
"num_tokens": 10629244.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.57886700630188,
|
|
"epoch": 0.542810016494227,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977827457894174,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.13544595316052438,
|
|
"num_tokens": 10638931.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.487677431106567,
|
|
"epoch": 0.5433098415554556,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977777450067937,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.14867637306451797,
|
|
"num_tokens": 10648754.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.439542055130005,
|
|
"epoch": 0.5438096666166842,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977727386191393,
|
|
"loss": 6.1901,
|
|
"mean_token_accuracy": 0.15131721571087836,
|
|
"num_tokens": 10657716.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.451899003982544,
|
|
"epoch": 0.5443094916779128,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004977677266265802,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.14816371202468873,
|
|
"num_tokens": 10667621.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.4599203109741214,
|
|
"epoch": 0.5448093167391413,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977627090292424,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.14214157089591026,
|
|
"num_tokens": 10676640.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.460400629043579,
|
|
"epoch": 0.5453091418003698,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977576858272521,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.13580250442028047,
|
|
"num_tokens": 10687034.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.4517356872558596,
|
|
"epoch": 0.5458089668615984,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977526570207358,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.15036468356847763,
|
|
"num_tokens": 10696234.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.435783767700196,
|
|
"epoch": 0.546308791922827,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977476226098199,
|
|
"loss": 6.2255,
|
|
"mean_token_accuracy": 0.15388489365577698,
|
|
"num_tokens": 10705733.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.508023118972778,
|
|
"epoch": 0.5468086169840556,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977425825946312,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.14530422240495683,
|
|
"num_tokens": 10714628.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.52370138168335,
|
|
"epoch": 0.5473084420452842,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004977375369752964,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.13399826884269714,
|
|
"num_tokens": 10726120.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.486573028564453,
|
|
"epoch": 0.5478082671065128,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977324857519425,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.14302257671952248,
|
|
"num_tokens": 10735976.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.521982479095459,
|
|
"epoch": 0.5483080921677413,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977274289246967,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.13969054594635963,
|
|
"num_tokens": 10745730.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.486727333068847,
|
|
"epoch": 0.5488079172289698,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977223664936859,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.14279983043670655,
|
|
"num_tokens": 10755435.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.426490116119385,
|
|
"epoch": 0.5493077422901984,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977172984590378,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.15165309607982635,
|
|
"num_tokens": 10765483.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.423614263534546,
|
|
"epoch": 0.549807567351427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977122248208798,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.1458958640694618,
|
|
"num_tokens": 10775034.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.389389324188232,
|
|
"epoch": 0.5503073924126556,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004977071455793394,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.14586547762155533,
|
|
"num_tokens": 10784799.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.483004093170166,
|
|
"epoch": 0.5508072174738842,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977020607345445,
|
|
"loss": 6.2986,
|
|
"mean_token_accuracy": 0.13670646920800208,
|
|
"num_tokens": 10794907.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.463555002212525,
|
|
"epoch": 0.5513070425351128,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004976969702866231,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.14932522252202035,
|
|
"num_tokens": 10804374.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.457903718948364,
|
|
"epoch": 0.5518068675963412,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976918742357033,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.14583136066794394,
|
|
"num_tokens": 10814245.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.414517402648926,
|
|
"epoch": 0.5523066926575698,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976867725819133,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.1433719888329506,
|
|
"num_tokens": 10824667.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.4435950756073,
|
|
"epoch": 0.5528065177187984,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976816653253813,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.14657047092914582,
|
|
"num_tokens": 10834890.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.444228839874268,
|
|
"epoch": 0.553306342780027,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004976765524662359,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.15016230940818787,
|
|
"num_tokens": 10844751.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.538416528701783,
|
|
"epoch": 0.5538061678412556,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976714340046058,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.14701344817876816,
|
|
"num_tokens": 10854113.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.473024225234985,
|
|
"epoch": 0.5543059929024842,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976663099406196,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.14653860181570053,
|
|
"num_tokens": 10863468.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.43930025100708,
|
|
"epoch": 0.5548058179637128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976611802744066,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.15181547924876213,
|
|
"num_tokens": 10873381.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.480038213729858,
|
|
"epoch": 0.5553056430249412,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004976560450060954,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.15241528004407884,
|
|
"num_tokens": 10883457.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.36265115737915,
|
|
"epoch": 0.5558054680861698,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976509041358154,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.14695338681340217,
|
|
"num_tokens": 10892822.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.401890563964844,
|
|
"epoch": 0.5563052931473984,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497645757663696,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.15708919018507003,
|
|
"num_tokens": 10901935.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.42699408531189,
|
|
"epoch": 0.556805118208627,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976406055898665,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.14264499321579932,
|
|
"num_tokens": 10911863.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.435345411300659,
|
|
"epoch": 0.5573049432698556,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976354479144568,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.1457000732421875,
|
|
"num_tokens": 10921196.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.4638190269470215,
|
|
"epoch": 0.5578047683310842,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976302846375965,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.14406682699918746,
|
|
"num_tokens": 10931374.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.543346357345581,
|
|
"epoch": 0.5583045933923126,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004976251157594155,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.1396176964044571,
|
|
"num_tokens": 10941002.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.525654315948486,
|
|
"epoch": 0.5588044184535412,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976199412800437,
|
|
"loss": 6.2445,
|
|
"mean_token_accuracy": 0.14187017381191253,
|
|
"num_tokens": 10950602.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.439078330993652,
|
|
"epoch": 0.5593042435147698,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976147611996118,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.14701986610889434,
|
|
"num_tokens": 10960363.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.456356191635132,
|
|
"epoch": 0.5598040685759984,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976095755182496,
|
|
"loss": 6.3192,
|
|
"mean_token_accuracy": 0.1390128515660763,
|
|
"num_tokens": 10970179.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.452031373977661,
|
|
"epoch": 0.560303893637227,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976043842360877,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.14139995276927947,
|
|
"num_tokens": 10980446.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.496991300582886,
|
|
"epoch": 0.5608037186984556,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497599187353257,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.14295857772231102,
|
|
"num_tokens": 10990883.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.483784151077271,
|
|
"epoch": 0.5613035437596842,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004975939848698879,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.15214839875698088,
|
|
"num_tokens": 11000956.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.399802303314209,
|
|
"epoch": 0.5618033688209126,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004975887767861113,
|
|
"loss": 6.2314,
|
|
"mean_token_accuracy": 0.14712525606155397,
|
|
"num_tokens": 11010873.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.460791444778442,
|
|
"epoch": 0.5623031938821412,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975835631020585,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.14298221096396446,
|
|
"num_tokens": 11020192.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.43976526260376,
|
|
"epoch": 0.5628030189433698,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975783438178605,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.14295758530497552,
|
|
"num_tokens": 11030466.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.4148193359375,
|
|
"epoch": 0.5633028440045984,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004975731189336487,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.14819499254226684,
|
|
"num_tokens": 11040309.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.474888038635254,
|
|
"epoch": 0.563802669065827,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004975678884495544,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.14439230635762215,
|
|
"num_tokens": 11049560.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.541922092437744,
|
|
"epoch": 0.5643024941270556,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975626523657093,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.1359780639410019,
|
|
"num_tokens": 11059352.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.513946151733398,
|
|
"epoch": 0.564802319188284,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975574106822451,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.14432844072580336,
|
|
"num_tokens": 11069159.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.466729259490966,
|
|
"epoch": 0.5653021442495126,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004975521633992938,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.1374719813466072,
|
|
"num_tokens": 11078960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.440870189666748,
|
|
"epoch": 0.5658019693107412,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004975469105169873,
|
|
"loss": 6.1564,
|
|
"mean_token_accuracy": 0.15519137680530548,
|
|
"num_tokens": 11089408.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.502084970474243,
|
|
"epoch": 0.5663017943719698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975416520354579,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.1416455015540123,
|
|
"num_tokens": 11099485.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.488633298873902,
|
|
"epoch": 0.5668016194331984,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975363879548377,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.15036003440618514,
|
|
"num_tokens": 11109568.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.595293807983398,
|
|
"epoch": 0.567301444494427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004975311182752592,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.13346163257956506,
|
|
"num_tokens": 11119433.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.518634510040283,
|
|
"epoch": 0.5678012695556556,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975258429968551,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.14116447940468788,
|
|
"num_tokens": 11130060.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.53895378112793,
|
|
"epoch": 0.568301094616884,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975205621197581,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.1381514325737953,
|
|
"num_tokens": 11140417.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.548374509811401,
|
|
"epoch": 0.5688009196781126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975152756441009,
|
|
"loss": 6.3091,
|
|
"mean_token_accuracy": 0.14686904475092888,
|
|
"num_tokens": 11150830.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.4534149169921875,
|
|
"epoch": 0.5693007447393412,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975099835700166,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.15294980704784394,
|
|
"num_tokens": 11161057.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.389756917953491,
|
|
"epoch": 0.5698005698005698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975046858976386,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.14236015751957892,
|
|
"num_tokens": 11170182.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.429002809524536,
|
|
"epoch": 0.5703003948617984,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974993826270997,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.14572951421141625,
|
|
"num_tokens": 11179962.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.443261194229126,
|
|
"epoch": 0.570800219923027,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974940737585337,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.16185080111026764,
|
|
"num_tokens": 11189341.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.375280284881592,
|
|
"epoch": 0.5713000449842555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497488759292074,
|
|
"loss": 6.2314,
|
|
"mean_token_accuracy": 0.15144093856215476,
|
|
"num_tokens": 11199264.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.370076894760132,
|
|
"epoch": 0.571799870045484,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974834392278545,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.1498553931713104,
|
|
"num_tokens": 11209257.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.490721845626831,
|
|
"epoch": 0.5722996951067126,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974781135660088,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.1498432382941246,
|
|
"num_tokens": 11218294.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.38384485244751,
|
|
"epoch": 0.5727995201679412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974727823066709,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.15196659713983535,
|
|
"num_tokens": 11227684.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.496408081054687,
|
|
"epoch": 0.5732993452291698,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974674454499753,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.13989517614245414,
|
|
"num_tokens": 11237195.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.566801404953003,
|
|
"epoch": 0.5737991702903984,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004974621029960559,
|
|
"loss": 6.2743,
|
|
"mean_token_accuracy": 0.14605024456977844,
|
|
"num_tokens": 11246871.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.501814126968384,
|
|
"epoch": 0.574298995351627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974567549450472,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.14634861648082734,
|
|
"num_tokens": 11256298.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.519607639312744,
|
|
"epoch": 0.5747988204128555,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974514012970839,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.14612126499414443,
|
|
"num_tokens": 11265857.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.406342601776123,
|
|
"epoch": 0.575298645474084,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004974460420523005,
|
|
"loss": 6.1104,
|
|
"mean_token_accuracy": 0.15408238172531127,
|
|
"num_tokens": 11275406.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.429341506958008,
|
|
"epoch": 0.5757984705353126,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004974406772108319,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.1535745695233345,
|
|
"num_tokens": 11283910.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.420456981658935,
|
|
"epoch": 0.5762982955965412,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004974353067728132,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.14322038739919662,
|
|
"num_tokens": 11293808.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.477599334716797,
|
|
"epoch": 0.5767981206577698,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974299307383794,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.14640988409519196,
|
|
"num_tokens": 11302519.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.511928415298462,
|
|
"epoch": 0.5772979457189984,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974245491076656,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.1391863778233528,
|
|
"num_tokens": 11312609.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.465887546539307,
|
|
"epoch": 0.5777977707802269,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974191618808075,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.14593261554837228,
|
|
"num_tokens": 11322471.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.519799470901489,
|
|
"epoch": 0.5782975958414555,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974137690579405,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.14685750231146813,
|
|
"num_tokens": 11333332.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.456929111480713,
|
|
"epoch": 0.578797420902684,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974083706392004,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.1434884212911129,
|
|
"num_tokens": 11342952.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.503396272659302,
|
|
"epoch": 0.5792972459639126,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004974029666247228,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.1391166031360626,
|
|
"num_tokens": 11353509.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.575589942932129,
|
|
"epoch": 0.5797970710251412,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004973975570146438,
|
|
"loss": 6.3316,
|
|
"mean_token_accuracy": 0.14068508967757226,
|
|
"num_tokens": 11363065.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.346537685394287,
|
|
"epoch": 0.5802968960863698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973921418090997,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.14828286319971085,
|
|
"num_tokens": 11373720.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.3362135887146,
|
|
"epoch": 0.5807967211475984,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973867210082263,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.14823839366436004,
|
|
"num_tokens": 11384432.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.486730480194092,
|
|
"epoch": 0.5812965462088269,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973812946121603,
|
|
"loss": 6.3628,
|
|
"mean_token_accuracy": 0.14108474254608155,
|
|
"num_tokens": 11394100.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.429854249954223,
|
|
"epoch": 0.5817963712700555,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004973758626210382,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.14420912861824037,
|
|
"num_tokens": 11403359.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.507780313491821,
|
|
"epoch": 0.582296196331284,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973704250349965,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.14223186522722245,
|
|
"num_tokens": 11412921.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.4520446300506595,
|
|
"epoch": 0.5827960213925126,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973649818541722,
|
|
"loss": 6.2231,
|
|
"mean_token_accuracy": 0.1455032780766487,
|
|
"num_tokens": 11422459.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.4262919425964355,
|
|
"epoch": 0.5832958464537412,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973595330787022,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.14993923529982567,
|
|
"num_tokens": 11431517.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.463098049163818,
|
|
"epoch": 0.5837956715149698,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973540787087235,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.14541814848780632,
|
|
"num_tokens": 11440662.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.387221336364746,
|
|
"epoch": 0.5842954965761983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973486187443734,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.15907835215330124,
|
|
"num_tokens": 11449762.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.3439528465271,
|
|
"epoch": 0.5847953216374269,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973431531857893,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.16193536221981047,
|
|
"num_tokens": 11459963.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.43265290260315,
|
|
"epoch": 0.5852951466986555,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004973376820331087,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.14007008746266364,
|
|
"num_tokens": 11469063.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.453941440582275,
|
|
"epoch": 0.585794971759884,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973322052864692,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.15193006098270417,
|
|
"num_tokens": 11477651.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.515561580657959,
|
|
"epoch": 0.5862947968211126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973267229460087,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.13993054628372192,
|
|
"num_tokens": 11487248.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.470349407196045,
|
|
"epoch": 0.5867946218823412,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497321235011865,
|
|
"loss": 6.3225,
|
|
"mean_token_accuracy": 0.14390917420387267,
|
|
"num_tokens": 11497066.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.580075263977051,
|
|
"epoch": 0.5872944469435698,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004973157414841763,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.13790747299790382,
|
|
"num_tokens": 11508490.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.497212743759155,
|
|
"epoch": 0.5877942720047983,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973102423630806,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.1481941357254982,
|
|
"num_tokens": 11518851.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.405769014358521,
|
|
"epoch": 0.5882940970660269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973047376487166,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14822361022233962,
|
|
"num_tokens": 11529102.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.408405399322509,
|
|
"epoch": 0.5887939221272555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004972992273412224,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.142403294891119,
|
|
"num_tokens": 11540563.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.40832405090332,
|
|
"epoch": 0.589293747188484,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972937114407369,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.1527942955493927,
|
|
"num_tokens": 11549955.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.436826133728028,
|
|
"epoch": 0.5897935722497126,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000497288189947399,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14903123825788497,
|
|
"num_tokens": 11558932.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.3486456871032715,
|
|
"epoch": 0.5902933973109412,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004972826628613472,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.1497093379497528,
|
|
"num_tokens": 11568901.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.454030275344849,
|
|
"epoch": 0.5907932223721697,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004972771301827209,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.14531795531511307,
|
|
"num_tokens": 11579738.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.459357833862304,
|
|
"epoch": 0.5912930474333983,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972715919116592,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.15216088593006133,
|
|
"num_tokens": 11590293.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.435681533813477,
|
|
"epoch": 0.5917928724946269,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972660480483015,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.14078980907797814,
|
|
"num_tokens": 11599745.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.4635560512542725,
|
|
"epoch": 0.5922926975558555,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972604985927871,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.13868655562400817,
|
|
"num_tokens": 11609958.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.517204332351684,
|
|
"epoch": 0.592792522617084,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004972549435452558,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.14023516029119493,
|
|
"num_tokens": 11619941.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.470420980453492,
|
|
"epoch": 0.5932923476783126,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972493829058474,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.15700115114450455,
|
|
"num_tokens": 11630287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.445519828796387,
|
|
"epoch": 0.5937921727395412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972438166747016,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.15244002118706704,
|
|
"num_tokens": 11639806.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.421046781539917,
|
|
"epoch": 0.5942919978007697,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004972382448519586,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.14387975931167601,
|
|
"num_tokens": 11650132.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.441921186447144,
|
|
"epoch": 0.5947918228619983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972326674377586,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14634337425231933,
|
|
"num_tokens": 11659670.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.465638208389282,
|
|
"epoch": 0.5952916479232269,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004972270844322418,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.14842158406972886,
|
|
"num_tokens": 11669998.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.477115774154663,
|
|
"epoch": 0.5957914729844555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972214958355488,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.1426238439977169,
|
|
"num_tokens": 11679052.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.463780546188355,
|
|
"epoch": 0.596291298045684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972159016478201,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.14764349311590194,
|
|
"num_tokens": 11687957.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.4369134426116945,
|
|
"epoch": 0.5967911231069126,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972103018691965,
|
|
"loss": 6.1688,
|
|
"mean_token_accuracy": 0.14828080162405968,
|
|
"num_tokens": 11696922.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.378879165649414,
|
|
"epoch": 0.5972909481681411,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972046964998189,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.1520995616912842,
|
|
"num_tokens": 11706600.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.403307819366455,
|
|
"epoch": 0.5977907732293697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971990855398283,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.14440116733312608,
|
|
"num_tokens": 11715933.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.42338547706604,
|
|
"epoch": 0.5982905982905983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971934689893658,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.15346132069826127,
|
|
"num_tokens": 11724807.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.465043926239014,
|
|
"epoch": 0.5987904233518269,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004971878468485729,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.14487154707312583,
|
|
"num_tokens": 11734985.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.395099639892578,
|
|
"epoch": 0.5992902484130554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497182219117591,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.1446204327046871,
|
|
"num_tokens": 11743418.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.437512397766113,
|
|
"epoch": 0.599790073474284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004971765857965615,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1459173545241356,
|
|
"num_tokens": 11752953.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.599790073474284,
|
|
"eval_entropy": 6.235621366203523,
|
|
"eval_loss": 6.238680362701416,
|
|
"eval_mean_token_accuracy": 0.15221030916850672,
|
|
"eval_num_tokens": 11752953.0,
|
|
"eval_runtime": 18.1768,
|
|
"eval_samples_per_second": 1707.944,
|
|
"eval_steps_per_second": 213.514,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.46585750579834,
|
|
"epoch": 0.6002898985355126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004971709468856263,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.145554082095623,
|
|
"num_tokens": 11763260.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.3714714527130125,
|
|
"epoch": 0.6007897235967411,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004971653023849274,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.16545616760849952,
|
|
"num_tokens": 11773255.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.436368799209594,
|
|
"epoch": 0.6012895486579697,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971596522946065,
|
|
"loss": 6.1963,
|
|
"mean_token_accuracy": 0.1476260207593441,
|
|
"num_tokens": 11783443.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.36988525390625,
|
|
"epoch": 0.6017893737191983,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004971539966148059,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.14593764320015906,
|
|
"num_tokens": 11791932.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.3834803104400635,
|
|
"epoch": 0.6022891987804269,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004971483353456681,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.15279377549886702,
|
|
"num_tokens": 11801420.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.460667896270752,
|
|
"epoch": 0.6027890238416554,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971426684873352,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.14521490186452865,
|
|
"num_tokens": 11810977.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.374953651428223,
|
|
"epoch": 0.603288848902884,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971369960399499,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.1554199203848839,
|
|
"num_tokens": 11821016.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.443546724319458,
|
|
"epoch": 0.6037886739641125,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497131318003655,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.1437994658946991,
|
|
"num_tokens": 11831157.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.401700639724732,
|
|
"epoch": 0.6042884990253411,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971256343785932,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.1525086373090744,
|
|
"num_tokens": 11840319.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.463356351852417,
|
|
"epoch": 0.6047883240865697,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971199451649078,
|
|
"loss": 6.2764,
|
|
"mean_token_accuracy": 0.1432381361722946,
|
|
"num_tokens": 11850808.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.517700624465943,
|
|
"epoch": 0.6052881491477983,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004971142503627415,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.1434370681643486,
|
|
"num_tokens": 11861123.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.336001253128051,
|
|
"epoch": 0.6057879742090269,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497108549972238,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.1537317529320717,
|
|
"num_tokens": 11870308.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.47981972694397,
|
|
"epoch": 0.6062877992702554,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971028439935404,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.14339130222797394,
|
|
"num_tokens": 11880254.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.442069435119629,
|
|
"epoch": 0.606787624331484,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970971324267925,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.15201347097754478,
|
|
"num_tokens": 11891272.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.365389680862426,
|
|
"epoch": 0.6072874493927125,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970914152721378,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.14827411770820617,
|
|
"num_tokens": 11901176.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.469020891189575,
|
|
"epoch": 0.6077872744539411,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004970856925297204,
|
|
"loss": 6.2335,
|
|
"mean_token_accuracy": 0.14073792845010757,
|
|
"num_tokens": 11910820.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.467056035995483,
|
|
"epoch": 0.6082870995151697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497079964199684,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.14642472118139266,
|
|
"num_tokens": 11920458.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.363491773605347,
|
|
"epoch": 0.6087869245763983,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004970742302821729,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.15776306986808777,
|
|
"num_tokens": 11931150.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.40634241104126,
|
|
"epoch": 0.6092867496376269,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970684907773312,
|
|
"loss": 6.1726,
|
|
"mean_token_accuracy": 0.1461140662431717,
|
|
"num_tokens": 11939960.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.5120614528656,
|
|
"epoch": 0.6097865746988554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970627456853036,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.14566329270601272,
|
|
"num_tokens": 11950781.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.482526063919067,
|
|
"epoch": 0.6102863997600839,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970569950062343,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.14931279718875884,
|
|
"num_tokens": 11960489.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.470678186416626,
|
|
"epoch": 0.6107862248213125,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004970512387402682,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.14969441890716553,
|
|
"num_tokens": 11970651.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.384146356582642,
|
|
"epoch": 0.6112860498825411,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004970454768875501,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.15012350156903267,
|
|
"num_tokens": 11980349.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.426074695587158,
|
|
"epoch": 0.6117858749437697,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970397094482249,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.15233335122466088,
|
|
"num_tokens": 11990076.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.377290058135986,
|
|
"epoch": 0.6122857000049983,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004970339364224378,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.15152915865182875,
|
|
"num_tokens": 11999515.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.450072336196899,
|
|
"epoch": 0.6127855250662269,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004970281578103339,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.14416319876909256,
|
|
"num_tokens": 12009224.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.408392477035522,
|
|
"epoch": 0.6132853501274554,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004970223736120587,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.1531042866408825,
|
|
"num_tokens": 12019295.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.45149188041687,
|
|
"epoch": 0.6137851751886839,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004970165838277578,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.14003654047846795,
|
|
"num_tokens": 12029130.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.417482852935791,
|
|
"epoch": 0.6142850002499125,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970107884575767,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14834195747971535,
|
|
"num_tokens": 12038676.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.431208896636963,
|
|
"epoch": 0.6147848253111411,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970049875016613,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.15883677303791047,
|
|
"num_tokens": 12048089.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.427967071533203,
|
|
"epoch": 0.6152846503723697,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004969991809601576,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.14690154194831848,
|
|
"num_tokens": 12059531.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.468362808227539,
|
|
"epoch": 0.6157844754335983,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969933688332115,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.14071761146187783,
|
|
"num_tokens": 12070103.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.372881078720093,
|
|
"epoch": 0.6162843004948269,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969875511209694,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.14632972478866577,
|
|
"num_tokens": 12078481.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.459029245376587,
|
|
"epoch": 0.6167841255560553,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004969817278235777,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.14507190212607385,
|
|
"num_tokens": 12088875.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.4829957485198975,
|
|
"epoch": 0.6172839506172839,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969758989411829,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.14632299542427063,
|
|
"num_tokens": 12099769.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.485964775085449,
|
|
"epoch": 0.6177837756785125,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969700644739315,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.150674507021904,
|
|
"num_tokens": 12109334.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.420757293701172,
|
|
"epoch": 0.6182836007397411,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969642244219705,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.14781033396720886,
|
|
"num_tokens": 12119017.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.3539855003356935,
|
|
"epoch": 0.6187834258009697,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969583787854467,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15940816029906274,
|
|
"num_tokens": 12128002.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.428264427185058,
|
|
"epoch": 0.6192832508621983,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004969525275645071,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.14578869566321373,
|
|
"num_tokens": 12137802.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.361740159988403,
|
|
"epoch": 0.6197830759234269,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004969466707592991,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.1514109715819359,
|
|
"num_tokens": 12147270.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.39790563583374,
|
|
"epoch": 0.6202829009846553,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049694080836997,
|
|
"loss": 6.1985,
|
|
"mean_token_accuracy": 0.15247814059257508,
|
|
"num_tokens": 12157358.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.488137102127075,
|
|
"epoch": 0.6207827260458839,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969349403966672,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.14677564278244973,
|
|
"num_tokens": 12166159.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.426560926437378,
|
|
"epoch": 0.6212825511071125,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969290668395385,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.1473272331058979,
|
|
"num_tokens": 12176405.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.475098896026611,
|
|
"epoch": 0.6217823761683411,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969231876987315,
|
|
"loss": 6.2672,
|
|
"mean_token_accuracy": 0.14321921691298484,
|
|
"num_tokens": 12186021.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.41944580078125,
|
|
"epoch": 0.6222822012295697,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969173029743942,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.15480018258094788,
|
|
"num_tokens": 12195222.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.385243272781372,
|
|
"epoch": 0.6227820262907983,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969114126666746,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.1526782840490341,
|
|
"num_tokens": 12205443.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.4909021854400635,
|
|
"epoch": 0.6232818513520267,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969055167757211,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.14764367789030075,
|
|
"num_tokens": 12215181.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.434947967529297,
|
|
"epoch": 0.6237816764132553,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968996153016819,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.14859371781349182,
|
|
"num_tokens": 12224327.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.4243059158325195,
|
|
"epoch": 0.6242815014744839,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004968937082447054,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.15060742422938347,
|
|
"num_tokens": 12234962.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.455028104782104,
|
|
"epoch": 0.6247813265357125,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968877956049403,
|
|
"loss": 6.2741,
|
|
"mean_token_accuracy": 0.14332959055900574,
|
|
"num_tokens": 12245883.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.481830692291259,
|
|
"epoch": 0.6252811515969411,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968818773825355,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.1421663448214531,
|
|
"num_tokens": 12254412.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.346131229400635,
|
|
"epoch": 0.6257809766581697,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004968759535776396,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.14878410547971727,
|
|
"num_tokens": 12264894.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.425607395172119,
|
|
"epoch": 0.6262808017193983,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004968700241904018,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.14812298566102983,
|
|
"num_tokens": 12274557.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.4023716926574705,
|
|
"epoch": 0.6267806267806267,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968640892209714,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.15128899812698365,
|
|
"num_tokens": 12283696.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.338653564453125,
|
|
"epoch": 0.6272804518418553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968581486694975,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.15529007241129875,
|
|
"num_tokens": 12292981.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.401558542251587,
|
|
"epoch": 0.6277802769030839,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968522025361297,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15605232864618301,
|
|
"num_tokens": 12302865.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.376195764541626,
|
|
"epoch": 0.6282801019643125,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004968462508210176,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1534101739525795,
|
|
"num_tokens": 12313099.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.410076427459717,
|
|
"epoch": 0.6287799270255411,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968402935243109,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.14855726137757302,
|
|
"num_tokens": 12324155.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.354358911514282,
|
|
"epoch": 0.6292797520867697,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968343306461595,
|
|
"loss": 6.0698,
|
|
"mean_token_accuracy": 0.156469689309597,
|
|
"num_tokens": 12334082.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.363330554962158,
|
|
"epoch": 0.6297795771479981,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968283621867134,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.1514860585331917,
|
|
"num_tokens": 12344673.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.441592025756836,
|
|
"epoch": 0.6302794022092267,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968223881461227,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.14587515890598296,
|
|
"num_tokens": 12355149.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.427363920211792,
|
|
"epoch": 0.6307792272704553,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496816408524538,
|
|
"loss": 6.0841,
|
|
"mean_token_accuracy": 0.15343114286661147,
|
|
"num_tokens": 12364043.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.421494817733764,
|
|
"epoch": 0.6312790523316839,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968104233221094,
|
|
"loss": 6.2772,
|
|
"mean_token_accuracy": 0.14720324650406838,
|
|
"num_tokens": 12373591.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.393746757507325,
|
|
"epoch": 0.6317788773929125,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968044325389877,
|
|
"loss": 6.2028,
|
|
"mean_token_accuracy": 0.15082022398710251,
|
|
"num_tokens": 12383570.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.5201396465301515,
|
|
"epoch": 0.6322787024541411,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967984361753235,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.1459848552942276,
|
|
"num_tokens": 12393682.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.47806134223938,
|
|
"epoch": 0.6327785275153697,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004967924342312677,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.1485290229320526,
|
|
"num_tokens": 12403478.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.37299542427063,
|
|
"epoch": 0.6332783525765981,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967864267069713,
|
|
"loss": 6.2055,
|
|
"mean_token_accuracy": 0.1482327714562416,
|
|
"num_tokens": 12412810.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.35264368057251,
|
|
"epoch": 0.6337781776378267,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967804136025856,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.15365379601716994,
|
|
"num_tokens": 12422209.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.413401174545288,
|
|
"epoch": 0.6342780026990553,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004967743949182617,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14988465309143068,
|
|
"num_tokens": 12431569.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.347585582733155,
|
|
"epoch": 0.6347778277602839,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967683706541511,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.16711846143007278,
|
|
"num_tokens": 12441607.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.357980728149414,
|
|
"epoch": 0.6352776528215125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967623408104054,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.14344130605459213,
|
|
"num_tokens": 12451072.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.435903024673462,
|
|
"epoch": 0.6357774778827411,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967563053871762,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.1481225535273552,
|
|
"num_tokens": 12460798.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.331244993209839,
|
|
"epoch": 0.6362773029439696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967502643846155,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15049599409103392,
|
|
"num_tokens": 12471891.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.371154546737671,
|
|
"epoch": 0.6367771280051981,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496744217802875,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.15096227675676346,
|
|
"num_tokens": 12482212.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.406865739822388,
|
|
"epoch": 0.6372769530664267,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004967381656421073,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.1488061361014843,
|
|
"num_tokens": 12492517.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.384095191955566,
|
|
"epoch": 0.6377767781276553,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004967321079024643,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.1496433362364769,
|
|
"num_tokens": 12502521.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.4173485279083256,
|
|
"epoch": 0.6382766031888839,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967260445840985,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.14466459453105926,
|
|
"num_tokens": 12513195.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.402704095840454,
|
|
"epoch": 0.6387764282501125,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967199756871624,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.16343617886304856,
|
|
"num_tokens": 12521640.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.389385509490967,
|
|
"epoch": 0.6392762533113411,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967139012118088,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.15508382469415666,
|
|
"num_tokens": 12530807.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.45805025100708,
|
|
"epoch": 0.6397760783725696,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967078211581907,
|
|
"loss": 6.2439,
|
|
"mean_token_accuracy": 0.14960914403200148,
|
|
"num_tokens": 12542049.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.469855642318725,
|
|
"epoch": 0.6402759034337981,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967017355264606,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.1545007884502411,
|
|
"num_tokens": 12551699.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.419739007949829,
|
|
"epoch": 0.6407757284950267,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496695644316772,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.14401657059788703,
|
|
"num_tokens": 12561414.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.465617513656616,
|
|
"epoch": 0.6412755535562553,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004966895475292781,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.1499449759721756,
|
|
"num_tokens": 12571950.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.505334711074829,
|
|
"epoch": 0.6417753786174839,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004966834451641322,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.14724814668297767,
|
|
"num_tokens": 12581264.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.4650954246521,
|
|
"epoch": 0.6422752036787125,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966773372214878,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.14929757118225098,
|
|
"num_tokens": 12590950.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.460349035263062,
|
|
"epoch": 0.642775028739941,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966712237014987,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.14689367413520812,
|
|
"num_tokens": 12599766.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.41261100769043,
|
|
"epoch": 0.6432748538011696,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004966651046043186,
|
|
"loss": 6.1773,
|
|
"mean_token_accuracy": 0.1511249229311943,
|
|
"num_tokens": 12610074.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.318903493881225,
|
|
"epoch": 0.6437746788623981,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004966589799301016,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.16128139197826385,
|
|
"num_tokens": 12619117.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.479786109924317,
|
|
"epoch": 0.6442745039236267,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004966528496790015,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.14388450905680655,
|
|
"num_tokens": 12627993.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.419493818283081,
|
|
"epoch": 0.6447743289848553,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966467138511729,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.14940599948167801,
|
|
"num_tokens": 12637787.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.464951753616333,
|
|
"epoch": 0.6452741540460839,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049664057244677,
|
|
"loss": 6.2913,
|
|
"mean_token_accuracy": 0.14467113614082336,
|
|
"num_tokens": 12648409.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.367974758148193,
|
|
"epoch": 0.6457739791073125,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966344254659473,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.15173483937978743,
|
|
"num_tokens": 12658391.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.422540616989136,
|
|
"epoch": 0.646273804168541,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966282729088595,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14910729303956033,
|
|
"num_tokens": 12669926.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.3959547996521,
|
|
"epoch": 0.6467736292297696,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966221147756615,
|
|
"loss": 6.2108,
|
|
"mean_token_accuracy": 0.15013228505849838,
|
|
"num_tokens": 12679176.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.4099202156066895,
|
|
"epoch": 0.6472734542909981,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004966159510665079,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.1515546627342701,
|
|
"num_tokens": 12688954.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.397485303878784,
|
|
"epoch": 0.6477732793522267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004966097817815542,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.15111466944217683,
|
|
"num_tokens": 12697577.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.367500734329224,
|
|
"epoch": 0.6482731044134553,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966036069209552,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.14086623266339302,
|
|
"num_tokens": 12708153.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.43664698600769,
|
|
"epoch": 0.6487729294746839,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965974264848666,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.15022410601377487,
|
|
"num_tokens": 12717329.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.500986814498901,
|
|
"epoch": 0.6492727545359124,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965912404734438,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.14851651713252068,
|
|
"num_tokens": 12726528.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.451917314529419,
|
|
"epoch": 0.649772579597141,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004965850488868424,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.1411927618086338,
|
|
"num_tokens": 12737341.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.401538610458374,
|
|
"epoch": 0.6502724046583696,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965788517252181,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.15477316528558732,
|
|
"num_tokens": 12746973.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.503889846801758,
|
|
"epoch": 0.6507722297195981,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496572648988727,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.154511921107769,
|
|
"num_tokens": 12756176.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.428466033935547,
|
|
"epoch": 0.6512720547808267,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000496566440677525,
|
|
"loss": 6.1364,
|
|
"mean_token_accuracy": 0.14951808080077172,
|
|
"num_tokens": 12766349.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.319422817230224,
|
|
"epoch": 0.6517718798420553,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965602267917685,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.1548992156982422,
|
|
"num_tokens": 12775857.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.411621141433716,
|
|
"epoch": 0.6522717049032839,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965540073316136,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14810678362846375,
|
|
"num_tokens": 12786376.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.419033622741699,
|
|
"epoch": 0.6527715299645124,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004965477822972169,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.14401675313711165,
|
|
"num_tokens": 12795719.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.418721675872803,
|
|
"epoch": 0.653271355025741,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965415516887349,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.14873905181884767,
|
|
"num_tokens": 12806742.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.323797941207886,
|
|
"epoch": 0.6537711800869695,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004965353155063246,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.14897419661283492,
|
|
"num_tokens": 12817362.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.313902473449707,
|
|
"epoch": 0.6542710051481981,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965290737501427,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.16033125445246696,
|
|
"num_tokens": 12826516.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.393736982345581,
|
|
"epoch": 0.6547708302094267,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965228264203464,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.1403120458126068,
|
|
"num_tokens": 12836321.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.406529712677002,
|
|
"epoch": 0.6552706552706553,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004965165735170928,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.15599434971809387,
|
|
"num_tokens": 12845955.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.404567909240723,
|
|
"epoch": 0.6557704803318838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496510315040539,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.1463264048099518,
|
|
"num_tokens": 12854749.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.417236471176148,
|
|
"epoch": 0.6562703053931124,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004965040509908429,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.1478302776813507,
|
|
"num_tokens": 12865145.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.38645191192627,
|
|
"epoch": 0.656770130454341,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004964977813681618,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.1566852644085884,
|
|
"num_tokens": 12876109.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.4392931938171385,
|
|
"epoch": 0.6572699555155695,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964915061726534,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.145036219060421,
|
|
"num_tokens": 12886813.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.375727796554566,
|
|
"epoch": 0.6577697805767981,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004964852254044759,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.14892916679382323,
|
|
"num_tokens": 12897991.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.406149911880493,
|
|
"epoch": 0.6582696056380267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964789390637871,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.1381581112742424,
|
|
"num_tokens": 12907354.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.477312326431274,
|
|
"epoch": 0.6587694306992553,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964726471507451,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.15529901385307313,
|
|
"num_tokens": 12917187.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.359694576263427,
|
|
"epoch": 0.6592692557604838,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964663496655083,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.15640944093465806,
|
|
"num_tokens": 12926470.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.401365423202515,
|
|
"epoch": 0.6597690808217124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964600466082351,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.1551777422428131,
|
|
"num_tokens": 12936609.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.400619602203369,
|
|
"epoch": 0.660268905882941,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964537379790842,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.15821731835603714,
|
|
"num_tokens": 12946286.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.403859806060791,
|
|
"epoch": 0.6607687309441695,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964474237782141,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.15230389237403869,
|
|
"num_tokens": 12955881.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.4244283676147464,
|
|
"epoch": 0.6612685560053981,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004964411040057839,
|
|
"loss": 6.2145,
|
|
"mean_token_accuracy": 0.1501467764377594,
|
|
"num_tokens": 12966273.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.352776050567627,
|
|
"epoch": 0.6617683810666267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004964347786619524,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.14457590207457544,
|
|
"num_tokens": 12975300.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.395555114746093,
|
|
"epoch": 0.6622682061278552,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964284477468791,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.15942828506231307,
|
|
"num_tokens": 12985291.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.404913139343262,
|
|
"epoch": 0.6627680311890838,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004964221112607228,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.15730291604995728,
|
|
"num_tokens": 12995935.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.393776798248291,
|
|
"epoch": 0.6632678562503124,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964157692036432,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.1551939904689789,
|
|
"num_tokens": 13006916.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.482045745849609,
|
|
"epoch": 0.663767681311541,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964094215757998,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.1344801217317581,
|
|
"num_tokens": 13017247.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.410199975967407,
|
|
"epoch": 0.6642675063727695,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004964030683773525,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.15629311949014663,
|
|
"num_tokens": 13026038.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.4183793544769285,
|
|
"epoch": 0.6647673314339981,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963967096084608,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.1398528054356575,
|
|
"num_tokens": 13036436.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.465635871887207,
|
|
"epoch": 0.6652671564952267,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963903452692849,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.14933979362249375,
|
|
"num_tokens": 13045594.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.435950040817261,
|
|
"epoch": 0.6657669815564552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963839753599848,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.14927535206079484,
|
|
"num_tokens": 13056023.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.4585912227630615,
|
|
"epoch": 0.6662668066176838,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000496377599880721,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.1534339167177677,
|
|
"num_tokens": 13064230.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.347588777542114,
|
|
"epoch": 0.6667666316789124,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004963712188316537,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.1597050353884697,
|
|
"num_tokens": 13073767.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.316200017929077,
|
|
"epoch": 0.667266456740141,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963648322129435,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.154131942987442,
|
|
"num_tokens": 13083026.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.398050832748413,
|
|
"epoch": 0.6677662818013695,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000496358440024751,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.15409237891435623,
|
|
"num_tokens": 13092029.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.4708263874053955,
|
|
"epoch": 0.6682661068625981,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004963520422672372,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.1461144804954529,
|
|
"num_tokens": 13101859.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.393950891494751,
|
|
"epoch": 0.6687659319238266,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496345638940563,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.1542508229613304,
|
|
"num_tokens": 13111007.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.340293741226196,
|
|
"epoch": 0.6692657569850552,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963392300448894,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.15422316640615463,
|
|
"num_tokens": 13120662.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.373708629608155,
|
|
"epoch": 0.6697655820462838,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963328155803778,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.14732048362493516,
|
|
"num_tokens": 13130263.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.411378669738769,
|
|
"epoch": 0.6702654071075124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963263955471895,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.1530996486544609,
|
|
"num_tokens": 13139821.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.298514461517334,
|
|
"epoch": 0.670765232168741,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496319969945486,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.15401810631155968,
|
|
"num_tokens": 13149731.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.345810794830323,
|
|
"epoch": 0.6712650572299695,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496313538775429,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.15483235716819763,
|
|
"num_tokens": 13160689.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.387895011901856,
|
|
"epoch": 0.6717648822911981,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004963071020371803,
|
|
"loss": 6.2893,
|
|
"mean_token_accuracy": 0.147469175606966,
|
|
"num_tokens": 13170694.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.4619217872619625,
|
|
"epoch": 0.6722647073524266,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963006597309019,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.1465860716998577,
|
|
"num_tokens": 13180514.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.359937715530395,
|
|
"epoch": 0.6727645324136552,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962942118567559,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.15511937737464904,
|
|
"num_tokens": 13190144.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.405026292800903,
|
|
"epoch": 0.6732643574748838,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962877584149043,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.14447804391384125,
|
|
"num_tokens": 13199640.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.401241827011108,
|
|
"epoch": 0.6737641825361124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962812994055098,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1594453051686287,
|
|
"num_tokens": 13208824.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.30706787109375,
|
|
"epoch": 0.674264007597341,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962748348287347,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.16513512879610062,
|
|
"num_tokens": 13219305.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.333461284637451,
|
|
"epoch": 0.6747638326585695,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962683646847416,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.15698383003473282,
|
|
"num_tokens": 13227727.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.388839864730835,
|
|
"epoch": 0.675263657719798,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004962618889736936,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.1546965755522251,
|
|
"num_tokens": 13237522.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.366639804840088,
|
|
"epoch": 0.6757634827810266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962554076957533,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.14975305944681166,
|
|
"num_tokens": 13247155.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.362000322341919,
|
|
"epoch": 0.6762633078422552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962489208510838,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.14469285011291505,
|
|
"num_tokens": 13257324.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.351904487609863,
|
|
"epoch": 0.6767631329034838,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962424284398484,
|
|
"loss": 6.1811,
|
|
"mean_token_accuracy": 0.14799242913722993,
|
|
"num_tokens": 13267025.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.387102508544922,
|
|
"epoch": 0.6772629579647124,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962359304622105,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.15986717939376832,
|
|
"num_tokens": 13276709.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.3475823402404785,
|
|
"epoch": 0.677762783025941,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962294269183335,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.14890932962298392,
|
|
"num_tokens": 13286029.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.400726699829102,
|
|
"epoch": 0.6782626080871695,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496222917808381,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.13871833980083464,
|
|
"num_tokens": 13296367.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.4817811965942385,
|
|
"epoch": 0.678762433148398,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962164031325169,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.14910077154636384,
|
|
"num_tokens": 13305186.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.391106224060058,
|
|
"epoch": 0.6792622582096266,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496209882890905,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.15676940083503724,
|
|
"num_tokens": 13314512.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.392285966873169,
|
|
"epoch": 0.6797620832708552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962033570837094,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.14896375089883804,
|
|
"num_tokens": 13324423.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.408303451538086,
|
|
"epoch": 0.6802619083320838,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961968257110941,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.145650053024292,
|
|
"num_tokens": 13334133.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.47266149520874,
|
|
"epoch": 0.6807617333933124,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004961902887732236,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.15050871446728706,
|
|
"num_tokens": 13344017.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.336544322967529,
|
|
"epoch": 0.681261558454541,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961837462702626,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.16171526312828063,
|
|
"num_tokens": 13353922.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.366875553131104,
|
|
"epoch": 0.6817613835157694,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004961771982023752,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.15015759319067,
|
|
"num_tokens": 13363890.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.359401702880859,
|
|
"epoch": 0.682261208576998,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961706445697265,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.1544269695878029,
|
|
"num_tokens": 13373726.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.317543268203735,
|
|
"epoch": 0.6827610336382266,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961640853724813,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.16124315410852433,
|
|
"num_tokens": 13382049.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.277030563354492,
|
|
"epoch": 0.6832608586994552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004961575206108046,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.1637004792690277,
|
|
"num_tokens": 13390977.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.410705041885376,
|
|
"epoch": 0.6837606837606838,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961509502848616,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.15287146344780922,
|
|
"num_tokens": 13400165.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.39957103729248,
|
|
"epoch": 0.6842605088219124,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961443743948177,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.148889921605587,
|
|
"num_tokens": 13410201.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.3598854541778564,
|
|
"epoch": 0.684760333883141,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496137792940838,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.15562955886125565,
|
|
"num_tokens": 13421074.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.353109312057495,
|
|
"epoch": 0.6852601589443694,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961312059230885,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.1597494289278984,
|
|
"num_tokens": 13430387.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.333962249755859,
|
|
"epoch": 0.685759984005598,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961246133417348,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.1581158310174942,
|
|
"num_tokens": 13439497.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.400959205627442,
|
|
"epoch": 0.6862598090668266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004961180151969427,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.14569994658231736,
|
|
"num_tokens": 13450543.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.330302476882935,
|
|
"epoch": 0.6867596341280552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961114114888782,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.15468398481607437,
|
|
"num_tokens": 13459996.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.356401968002319,
|
|
"epoch": 0.6872594591892838,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961048022177074,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.15578799843788146,
|
|
"num_tokens": 13469141.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.319010782241821,
|
|
"epoch": 0.6877592842505124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960981873835968,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.16249615401029588,
|
|
"num_tokens": 13478349.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.309292840957641,
|
|
"epoch": 0.6882591093117408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960915669867126,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.15508376955986022,
|
|
"num_tokens": 13487417.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.473600006103515,
|
|
"epoch": 0.6887589343729694,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004960849410272216,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.14608558565378188,
|
|
"num_tokens": 13497607.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.430092811584473,
|
|
"epoch": 0.689258759434198,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960783095052903,
|
|
"loss": 6.2172,
|
|
"mean_token_accuracy": 0.14428661093115808,
|
|
"num_tokens": 13508222.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.296179342269897,
|
|
"epoch": 0.6897585844954266,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004960716724210856,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.1658175066113472,
|
|
"num_tokens": 13519593.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.499619579315185,
|
|
"epoch": 0.6902584095566552,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960650297747746,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.14199733808636666,
|
|
"num_tokens": 13531089.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.3842894554138185,
|
|
"epoch": 0.6907582346178838,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960583815665242,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.15265306904911996,
|
|
"num_tokens": 13539897.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.38850998878479,
|
|
"epoch": 0.6912580596791124,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004960517277965018,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.1421434462070465,
|
|
"num_tokens": 13549986.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.4226827144622805,
|
|
"epoch": 0.6917578847403408,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960450684648749,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.1504869803786278,
|
|
"num_tokens": 13559866.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.4762866497039795,
|
|
"epoch": 0.6922577098015694,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496038403571811,
|
|
"loss": 6.2073,
|
|
"mean_token_accuracy": 0.14401910826563835,
|
|
"num_tokens": 13569789.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.427924871444702,
|
|
"epoch": 0.692757534862798,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004960317331174777,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14649601578712462,
|
|
"num_tokens": 13579121.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.339105701446533,
|
|
"epoch": 0.6932573599240266,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004960250571020428,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.15387641042470931,
|
|
"num_tokens": 13589281.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.452700519561768,
|
|
"epoch": 0.6937571849852552,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004960183755256744,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.15480642318725585,
|
|
"num_tokens": 13598312.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.358840465545654,
|
|
"epoch": 0.6942570100464838,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960116883885406,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.15427826941013337,
|
|
"num_tokens": 13608164.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.3677284717559814,
|
|
"epoch": 0.6947568351077124,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960049956908095,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.15066410452127457,
|
|
"num_tokens": 13618314.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.391674280166626,
|
|
"epoch": 0.6952566601689408,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004959982974326496,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.1516549788415432,
|
|
"num_tokens": 13628846.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.3451238632202145,
|
|
"epoch": 0.6957564852301694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959915936142294,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.1632595956325531,
|
|
"num_tokens": 13637941.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.3916404247283936,
|
|
"epoch": 0.696256310291398,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959848842357175,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1518751010298729,
|
|
"num_tokens": 13647734.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.327761697769165,
|
|
"epoch": 0.6967561353526266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959781692972829,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.15482066050171853,
|
|
"num_tokens": 13657929.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.395666074752808,
|
|
"epoch": 0.6972559604138552,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959714487990943,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.14907077848911285,
|
|
"num_tokens": 13668258.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.4012397766113285,
|
|
"epoch": 0.6977557854750838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495964722741321,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.15827775746583939,
|
|
"num_tokens": 13677515.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.372984170913696,
|
|
"epoch": 0.6982556105363122,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959579911241322,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.15468469709157945,
|
|
"num_tokens": 13686865.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.3944355010986325,
|
|
"epoch": 0.6987554355975408,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959512539476971,
|
|
"loss": 6.2101,
|
|
"mean_token_accuracy": 0.1496955059468746,
|
|
"num_tokens": 13696683.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.400767517089844,
|
|
"epoch": 0.6992552606587694,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004959445112121853,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.14558056443929673,
|
|
"num_tokens": 13706452.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.361153602600098,
|
|
"epoch": 0.699755085719998,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959377629177665,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.15986247658729552,
|
|
"num_tokens": 13717474.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.3601658821105955,
|
|
"epoch": 0.7002549107812266,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959310090646104,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.16291055232286453,
|
|
"num_tokens": 13726723.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.45692286491394,
|
|
"epoch": 0.7007547358424552,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004959242496528869,
|
|
"loss": 6.2851,
|
|
"mean_token_accuracy": 0.14390696436166764,
|
|
"num_tokens": 13736432.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.3902373790740965,
|
|
"epoch": 0.7012545609036838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959174846827663,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.1531929723918438,
|
|
"num_tokens": 13745767.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.451144218444824,
|
|
"epoch": 0.7017543859649122,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959107141544186,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.15571997165679932,
|
|
"num_tokens": 13756035.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.344784784317016,
|
|
"epoch": 0.7022542110261408,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495903938068014,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.16333325505256652,
|
|
"num_tokens": 13765715.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.365966033935547,
|
|
"epoch": 0.7027540360873694,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004958971564237233,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.1469478726387024,
|
|
"num_tokens": 13775987.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.3115802764892575,
|
|
"epoch": 0.703253861148598,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000495890369221717,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.15399834662675857,
|
|
"num_tokens": 13785095.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.442880582809448,
|
|
"epoch": 0.7037536862098266,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004958835764621657,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.14771572798490523,
|
|
"num_tokens": 13794777.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.355412101745605,
|
|
"epoch": 0.7042535112710552,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958767781452406,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.15076218247413636,
|
|
"num_tokens": 13803534.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.348436689376831,
|
|
"epoch": 0.7047533363322837,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004958699742711126,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.14913366734981537,
|
|
"num_tokens": 13813941.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.374467229843139,
|
|
"epoch": 0.7052531613935122,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004958631648399528,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.1534392163157463,
|
|
"num_tokens": 13823611.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.441148948669434,
|
|
"epoch": 0.7057529864547408,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004958563498519327,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.14845563992857932,
|
|
"num_tokens": 13833047.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.368374872207641,
|
|
"epoch": 0.7062528115159694,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004958495293072235,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.15331770479679108,
|
|
"num_tokens": 13843524.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.3521583557128904,
|
|
"epoch": 0.706752636577198,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958427032059971,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.15610503256320954,
|
|
"num_tokens": 13852188.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.324339771270752,
|
|
"epoch": 0.7072524616384266,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004958358715484251,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.1498229146003723,
|
|
"num_tokens": 13863540.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.447328853607178,
|
|
"epoch": 0.7077522866996552,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004958290343346795,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.15378015339374543,
|
|
"num_tokens": 13871828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.39950270652771,
|
|
"epoch": 0.7082521117608837,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495822191564932,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.15130583196878433,
|
|
"num_tokens": 13882222.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.404683589935303,
|
|
"epoch": 0.7087519368221122,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004958153432393553,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.14860968366265298,
|
|
"num_tokens": 13891689.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.338508415222168,
|
|
"epoch": 0.7092517618833408,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495808489358121,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.1544829338788986,
|
|
"num_tokens": 13901310.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.319579458236694,
|
|
"epoch": 0.7097515869445694,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958016299214022,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.15065168738365173,
|
|
"num_tokens": 13910350.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.3466075420379635,
|
|
"epoch": 0.710251412005798,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004957947649293712,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.14743608981370926,
|
|
"num_tokens": 13920481.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.427731990814209,
|
|
"epoch": 0.7107512370670266,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004957878943822006,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14863065779209136,
|
|
"num_tokens": 13931232.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.4239678382873535,
|
|
"epoch": 0.7112510621282551,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957810182800634,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.14625515341758727,
|
|
"num_tokens": 13940717.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.389589262008667,
|
|
"epoch": 0.7117508871894836,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957741366231327,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.15782224684953688,
|
|
"num_tokens": 13949918.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.359981822967529,
|
|
"epoch": 0.7122507122507122,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957672494115815,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.15367264151573182,
|
|
"num_tokens": 13959914.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.365821027755738,
|
|
"epoch": 0.7127505373119408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495760356645583,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.15741909444332122,
|
|
"num_tokens": 13970054.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.292272472381592,
|
|
"epoch": 0.7132503623731694,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957534583253108,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1655389443039894,
|
|
"num_tokens": 13980339.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.287518644332886,
|
|
"epoch": 0.713750187434398,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004957465544509384,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.14967343881726264,
|
|
"num_tokens": 13990466.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.3970856189727785,
|
|
"epoch": 0.7142500124956266,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957396450226395,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.1484213002026081,
|
|
"num_tokens": 13999822.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.4514576435089115,
|
|
"epoch": 0.7147498375568551,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957327300405879,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.15095962956547737,
|
|
"num_tokens": 14008939.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.36820878982544,
|
|
"epoch": 0.7152496626180836,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957258095049577,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.1432138055562973,
|
|
"num_tokens": 14019005.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.350853681564331,
|
|
"epoch": 0.7157494876793122,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957188834159229,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.1641040027141571,
|
|
"num_tokens": 14029390.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.351580429077148,
|
|
"epoch": 0.7162493127405408,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957119517736577,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.15496953576803207,
|
|
"num_tokens": 14038613.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.288190937042236,
|
|
"epoch": 0.7167491378017694,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004957050145783366,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.15048024505376817,
|
|
"num_tokens": 14048144.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.273267412185669,
|
|
"epoch": 0.717248962862998,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956980718301342,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.16615069806575775,
|
|
"num_tokens": 14056894.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.365176820755005,
|
|
"epoch": 0.7177487879242265,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004956911235292251,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.1520610496401787,
|
|
"num_tokens": 14066024.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.2935586929321286,
|
|
"epoch": 0.7182486129854551,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956841696757841,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.15400634557008744,
|
|
"num_tokens": 14075805.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.3335480213165285,
|
|
"epoch": 0.7187484380466836,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004956772102699862,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.15522269904613495,
|
|
"num_tokens": 14085229.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.426359987258911,
|
|
"epoch": 0.7192482631079122,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004956702453120064,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.15459308326244353,
|
|
"num_tokens": 14094594.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.33559627532959,
|
|
"epoch": 0.7197480881691408,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004956632748020201,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.1556967779994011,
|
|
"num_tokens": 14104373.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.273628854751587,
|
|
"epoch": 0.7202479132303694,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956562987402026,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.15983724147081374,
|
|
"num_tokens": 14113918.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.465671348571777,
|
|
"epoch": 0.720747738291598,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956493171267293,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.14312312826514245,
|
|
"num_tokens": 14123711.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.4386381149292,
|
|
"epoch": 0.7212475633528265,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495642329961776,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.15941580682992934,
|
|
"num_tokens": 14132994.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.3032402992248535,
|
|
"epoch": 0.7217473884140551,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004956353372455185,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.15604784935712815,
|
|
"num_tokens": 14143398.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.341692399978638,
|
|
"epoch": 0.7222472134752836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956283389781327,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.1548337534070015,
|
|
"num_tokens": 14152374.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.382602167129517,
|
|
"epoch": 0.7227470385365122,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956213351597946,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.15727116912603378,
|
|
"num_tokens": 14162123.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.42876181602478,
|
|
"epoch": 0.7232468635977408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956143257906805,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.15249986946582794,
|
|
"num_tokens": 14172004.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.304404592514038,
|
|
"epoch": 0.7237466886589694,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956073108709667,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.1527062639594078,
|
|
"num_tokens": 14181659.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.29217300415039,
|
|
"epoch": 0.7242465137201979,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956002904008298,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1551188573241234,
|
|
"num_tokens": 14191051.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.426984691619873,
|
|
"epoch": 0.7247463387814265,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004955932643804463,
|
|
"loss": 6.1864,
|
|
"mean_token_accuracy": 0.14595220237970352,
|
|
"num_tokens": 14201232.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.358117580413818,
|
|
"epoch": 0.7252461638426551,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495586232809993,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.1496300518512726,
|
|
"num_tokens": 14210426.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.266166162490845,
|
|
"epoch": 0.7257459889038836,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004955791956896469,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.15686025768518447,
|
|
"num_tokens": 14220013.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.374533748626709,
|
|
"epoch": 0.7262458139651122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495572153019585,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.1499778851866722,
|
|
"num_tokens": 14229249.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.395423746109008,
|
|
"epoch": 0.7267456390263408,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004955651047999844,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.1600521206855774,
|
|
"num_tokens": 14238370.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.268012380599975,
|
|
"epoch": 0.7272454640875694,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004955580510310226,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.16599784791469574,
|
|
"num_tokens": 14248037.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.321020889282226,
|
|
"epoch": 0.7277452891487979,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955509917128771,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.14789412021636963,
|
|
"num_tokens": 14257480.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.37284836769104,
|
|
"epoch": 0.7282451142100265,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004955439268457252,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.1492689773440361,
|
|
"num_tokens": 14266114.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.297130918502807,
|
|
"epoch": 0.728744939271255,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004955368564297449,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.156357142329216,
|
|
"num_tokens": 14276048.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.336635732650757,
|
|
"epoch": 0.7292447643324836,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004955297804651142,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.16252694725990297,
|
|
"num_tokens": 14285225.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.457760000228882,
|
|
"epoch": 0.7297445893937122,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004955226989520107,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.15450618490576745,
|
|
"num_tokens": 14295566.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.357035064697266,
|
|
"epoch": 0.7302444144549408,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000495515611890613,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.1518037036061287,
|
|
"num_tokens": 14305072.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.234553813934326,
|
|
"epoch": 0.7307442395161693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004955085192810993,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.16198152750730516,
|
|
"num_tokens": 14315273.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.357436466217041,
|
|
"epoch": 0.7312440645773979,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004955014211236479,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.148907670378685,
|
|
"num_tokens": 14324818.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.398277330398559,
|
|
"epoch": 0.7317438896386265,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004954943174184375,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.14729854017496108,
|
|
"num_tokens": 14335129.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.3896379470825195,
|
|
"epoch": 0.732243714699855,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004954872081656469,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.1471581920981407,
|
|
"num_tokens": 14344339.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.385218143463135,
|
|
"epoch": 0.7327435397610836,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954800933654548,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.14939822256565094,
|
|
"num_tokens": 14353391.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.466739797592163,
|
|
"epoch": 0.7332433648223122,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004954729730180403,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.14671093598008156,
|
|
"num_tokens": 14363684.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.383737993240357,
|
|
"epoch": 0.7337431898835408,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954658471235825,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.15718478560447693,
|
|
"num_tokens": 14372802.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.3937585830688475,
|
|
"epoch": 0.7342430149447693,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954587156822607,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.14622166603803635,
|
|
"num_tokens": 14382665.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.3785542964935305,
|
|
"epoch": 0.7347428400059979,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004954515786942544,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.14995825439691543,
|
|
"num_tokens": 14393631.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.368095350265503,
|
|
"epoch": 0.7352426650672265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000495444436159743,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.15527340024709702,
|
|
"num_tokens": 14402713.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.4901505470275875,
|
|
"epoch": 0.735742490128455,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004954372880789064,
|
|
"loss": 6.2335,
|
|
"mean_token_accuracy": 0.1488625578582287,
|
|
"num_tokens": 14412777.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.416183853149414,
|
|
"epoch": 0.7362423151896836,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954301344519244,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.15214701741933823,
|
|
"num_tokens": 14422839.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.2740966796875,
|
|
"epoch": 0.7367421402509122,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004954229752789769,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.15730472505092621,
|
|
"num_tokens": 14433239.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.405355930328369,
|
|
"epoch": 0.7372419653121407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954158105602441,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14881424009799957,
|
|
"num_tokens": 14442907.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.321631526947021,
|
|
"epoch": 0.7377417903733693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004954086402959061,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.15384451597929,
|
|
"num_tokens": 14452492.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.359379386901855,
|
|
"epoch": 0.7382416154345979,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004954014644861435,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.1500435747206211,
|
|
"num_tokens": 14461353.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.3073262691497805,
|
|
"epoch": 0.7387414404958265,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953942831311367,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1685504212975502,
|
|
"num_tokens": 14470579.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.298497533798217,
|
|
"epoch": 0.739241265557055,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004953870962310666,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.16526476442813873,
|
|
"num_tokens": 14481608.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.33706226348877,
|
|
"epoch": 0.7397410906182836,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953799037861138,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.15208917409181594,
|
|
"num_tokens": 14493074.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.3495124816894535,
|
|
"epoch": 0.7402409156795122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953727057964594,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.16100960224866867,
|
|
"num_tokens": 14502469.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.322280216217041,
|
|
"epoch": 0.7407407407407407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953655022622843,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.15022923797369003,
|
|
"num_tokens": 14512939.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.35167760848999,
|
|
"epoch": 0.7412405658019693,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004953582931837699,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.15059924721717835,
|
|
"num_tokens": 14522681.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.380117559432984,
|
|
"epoch": 0.7417403908631979,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953510785610976,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.1634833335876465,
|
|
"num_tokens": 14532115.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.3472569465637205,
|
|
"epoch": 0.7422402159244265,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953438583944487,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.1547413095831871,
|
|
"num_tokens": 14541147.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.339827632904052,
|
|
"epoch": 0.742740040985655,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004953366326840052,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.15764619559049606,
|
|
"num_tokens": 14550373.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.41272611618042,
|
|
"epoch": 0.7432398660468836,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953294014299486,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.15989745557308196,
|
|
"num_tokens": 14559396.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.408972358703613,
|
|
"epoch": 0.7437396911081121,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953221646324611,
|
|
"loss": 6.1768,
|
|
"mean_token_accuracy": 0.15163759887218475,
|
|
"num_tokens": 14570292.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.339803791046142,
|
|
"epoch": 0.7442395161693407,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004953149222917245,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15516375601291657,
|
|
"num_tokens": 14579887.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.3852581024169925,
|
|
"epoch": 0.7447393412305693,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004953076744079213,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.14993379563093184,
|
|
"num_tokens": 14590260.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.3677795886993405,
|
|
"epoch": 0.7452391662917979,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953004209812335,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.15240892246365548,
|
|
"num_tokens": 14599812.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.298649024963379,
|
|
"epoch": 0.7457389913530265,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004952931620118439,
|
|
"loss": 6.009,
|
|
"mean_token_accuracy": 0.16149093210697174,
|
|
"num_tokens": 14609147.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.375099802017212,
|
|
"epoch": 0.746238816414255,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004952858974999351,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1476011499762535,
|
|
"num_tokens": 14618834.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.310449934005737,
|
|
"epoch": 0.7467386414754836,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004952786274456896,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.16517005413770675,
|
|
"num_tokens": 14628556.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.328486633300781,
|
|
"epoch": 0.7472384665367121,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004952713518492907,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.15241181701421738,
|
|
"num_tokens": 14637486.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.324020147323608,
|
|
"epoch": 0.7477382915979407,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004952640707109213,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.15444162636995315,
|
|
"num_tokens": 14647599.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.358633708953858,
|
|
"epoch": 0.7482381166591693,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004952567840307644,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.1563905507326126,
|
|
"num_tokens": 14656246.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.333115482330323,
|
|
"epoch": 0.7487379417203979,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952494918090036,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.15353814512491226,
|
|
"num_tokens": 14665550.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.369959306716919,
|
|
"epoch": 0.7492377667816265,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004952421940458222,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.15390245839953423,
|
|
"num_tokens": 14676462.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.291474771499634,
|
|
"epoch": 0.749737591842855,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952348907414039,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.1592863120138645,
|
|
"num_tokens": 14685963.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.2951575756073,
|
|
"epoch": 0.7502374169040835,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952275818959325,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.15469097197055817,
|
|
"num_tokens": 14695764.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.345249271392822,
|
|
"epoch": 0.7507372419653121,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952202675095916,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.1603232964873314,
|
|
"num_tokens": 14705839.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.333761215209961,
|
|
"epoch": 0.7512370670265407,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952129475825657,
|
|
"loss": 6.0316,
|
|
"mean_token_accuracy": 0.15530915260314943,
|
|
"num_tokens": 14714801.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.368722724914551,
|
|
"epoch": 0.7517368920877693,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004952056221150385,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.1523699216544628,
|
|
"num_tokens": 14723803.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.318247127532959,
|
|
"epoch": 0.7522367171489979,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004951982911071945,
|
|
"loss": 6.034,
|
|
"mean_token_accuracy": 0.16145545095205308,
|
|
"num_tokens": 14732598.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.351654386520385,
|
|
"epoch": 0.7527365422102265,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004951909545592183,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.1562404751777649,
|
|
"num_tokens": 14742598.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.358648872375488,
|
|
"epoch": 0.753236367271455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004951836124712942,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.15901827663183213,
|
|
"num_tokens": 14751434.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.368652820587158,
|
|
"epoch": 0.7537361923326835,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951762648436073,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.14980801790952683,
|
|
"num_tokens": 14760661.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.348774051666259,
|
|
"epoch": 0.7542360173939121,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951689116763419,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.14993853271007537,
|
|
"num_tokens": 14770431.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.353184986114502,
|
|
"epoch": 0.7547358424551407,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004951615529696835,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.1467999368906021,
|
|
"num_tokens": 14780066.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.362098121643067,
|
|
"epoch": 0.7552356675163693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004951541887238172,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.1566444903612137,
|
|
"num_tokens": 14789531.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.338529968261719,
|
|
"epoch": 0.7557354925775979,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004951468189389281,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.1536315642297268,
|
|
"num_tokens": 14799000.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.343132019042969,
|
|
"epoch": 0.7562353176388265,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004951394436152016,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.15519018173217775,
|
|
"num_tokens": 14808991.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.327774238586426,
|
|
"epoch": 0.7567351427000549,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004951320627528234,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.16200356930494308,
|
|
"num_tokens": 14819351.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.310733795166016,
|
|
"epoch": 0.7572349677612835,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004951246763519791,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1514159321784973,
|
|
"num_tokens": 14828924.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.487410974502564,
|
|
"epoch": 0.7577347928225121,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004951172844128546,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.13553070202469825,
|
|
"num_tokens": 14841077.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.453035879135132,
|
|
"epoch": 0.7582346178837407,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004951098869356358,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14519087523221968,
|
|
"num_tokens": 14851223.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.338871002197266,
|
|
"epoch": 0.7587344429449693,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495102483920509,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.157693912088871,
|
|
"num_tokens": 14861003.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.3789122104644775,
|
|
"epoch": 0.7592342680061979,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004950950753676603,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.14835447520017625,
|
|
"num_tokens": 14870207.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.301839351654053,
|
|
"epoch": 0.7597340930674265,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950876612772763,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.15509497597813607,
|
|
"num_tokens": 14879886.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.298347282409668,
|
|
"epoch": 0.7602339181286549,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950802416495431,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15882294327020646,
|
|
"num_tokens": 14889275.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.375413656234741,
|
|
"epoch": 0.7607337431898835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004950728164846478,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.15026083290576936,
|
|
"num_tokens": 14898317.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.302619886398316,
|
|
"epoch": 0.7612335682511121,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004950653857827771,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.15734130442142485,
|
|
"num_tokens": 14907183.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.327234601974487,
|
|
"epoch": 0.7617333933123407,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950579495441177,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.14951879382133484,
|
|
"num_tokens": 14917564.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.371053886413574,
|
|
"epoch": 0.7622332183735693,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950505077688572,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.15921780318021775,
|
|
"num_tokens": 14927102.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.259738349914551,
|
|
"epoch": 0.7627330434347979,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004950430604571824,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.1736061081290245,
|
|
"num_tokens": 14937934.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.333322763442993,
|
|
"epoch": 0.7632328684960263,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004950356076092808,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.15417497605085373,
|
|
"num_tokens": 14948109.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.358225870132446,
|
|
"epoch": 0.7637326935572549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049502814922534,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.14735992774367332,
|
|
"num_tokens": 14956971.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.360690975189209,
|
|
"epoch": 0.7642325186184835,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004950206853055475,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.15772800594568254,
|
|
"num_tokens": 14967046.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.393977880477905,
|
|
"epoch": 0.7647323436797121,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004950132158500913,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.14841361716389656,
|
|
"num_tokens": 14976234.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.255156803131103,
|
|
"epoch": 0.7652321687409407,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004950057408591591,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.16525048315525054,
|
|
"num_tokens": 14985205.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.262028789520263,
|
|
"epoch": 0.7657319938021693,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949982603329391,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.15609192624688148,
|
|
"num_tokens": 14994233.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.318466663360596,
|
|
"epoch": 0.7662318188633979,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004949907742716195,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.1550212100148201,
|
|
"num_tokens": 15004001.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.439916181564331,
|
|
"epoch": 0.7667316439246263,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949832826753886,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.14778689593076705,
|
|
"num_tokens": 15015046.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.303813123703003,
|
|
"epoch": 0.7672314689858549,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000494975785544435,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.15167940855026246,
|
|
"num_tokens": 15025404.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.35413761138916,
|
|
"epoch": 0.7677312940470835,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949682828789472,
|
|
"loss": 6.107,
|
|
"mean_token_accuracy": 0.14957534670829772,
|
|
"num_tokens": 15036160.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.320992803573608,
|
|
"epoch": 0.7682311191083121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494960774679114,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.16119422018527985,
|
|
"num_tokens": 15046356.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.320734977722168,
|
|
"epoch": 0.7687309441695407,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004949532609451242,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.15622462034225465,
|
|
"num_tokens": 15056101.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.348245620727539,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004949457416771671,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.1623734086751938,
|
|
"num_tokens": 15065726.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.317084169387817,
|
|
"epoch": 0.7697305942919977,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949382168754316,
|
|
"loss": 6.0388,
|
|
"mean_token_accuracy": 0.1640765145421028,
|
|
"num_tokens": 15075211.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.2661572933197025,
|
|
"epoch": 0.7702304193532263,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004949306865401073,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.15901511460542678,
|
|
"num_tokens": 15085525.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.349509191513062,
|
|
"epoch": 0.7707302444144549,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004949231506713833,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.15093438774347306,
|
|
"num_tokens": 15093851.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.438135766983033,
|
|
"epoch": 0.7712300694756835,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004949156092694496,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.14524950087070465,
|
|
"num_tokens": 15104066.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.350125503540039,
|
|
"epoch": 0.7717298945369121,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004949080623344958,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.1590372070670128,
|
|
"num_tokens": 15114047.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.322095108032227,
|
|
"epoch": 0.7722297195981407,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004949005098667117,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.15758729875087737,
|
|
"num_tokens": 15123719.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.346479749679565,
|
|
"epoch": 0.7727295446593693,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948929518662873,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1600412458181381,
|
|
"num_tokens": 15133978.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.355271816253662,
|
|
"epoch": 0.7732293697205977,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004948853883334129,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.15229474753141403,
|
|
"num_tokens": 15145058.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.418582105636597,
|
|
"epoch": 0.7737291947818263,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948778192682787,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.15038572251796722,
|
|
"num_tokens": 15155400.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.315107536315918,
|
|
"epoch": 0.7742290198430549,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494870244671075,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.1674094408750534,
|
|
"num_tokens": 15164969.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.316328525543213,
|
|
"epoch": 0.7747288449042835,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004948626645419926,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.1667407527565956,
|
|
"num_tokens": 15173840.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.357839727401734,
|
|
"epoch": 0.7752286699655121,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004948550788812222,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.14474273845553398,
|
|
"num_tokens": 15184541.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.34360785484314,
|
|
"epoch": 0.7757284950267407,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004948474876889545,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.15687183141708375,
|
|
"num_tokens": 15195060.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.403780698776245,
|
|
"epoch": 0.7762283200879692,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948398909653806,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.14697161540389062,
|
|
"num_tokens": 15206093.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.376169061660766,
|
|
"epoch": 0.7767281451491977,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004948322887106917,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.15045107305049896,
|
|
"num_tokens": 15215359.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.31698317527771,
|
|
"epoch": 0.7772279702104263,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004948246809250788,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.1537777900695801,
|
|
"num_tokens": 15225283.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.289384937286377,
|
|
"epoch": 0.7777277952716549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004948170676087338,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.1611175060272217,
|
|
"num_tokens": 15234319.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.322017574310303,
|
|
"epoch": 0.7782276203328835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948094487618476,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.1634511888027191,
|
|
"num_tokens": 15244410.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.3062560081481935,
|
|
"epoch": 0.7787274453941121,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004948018243846126,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.1593460828065872,
|
|
"num_tokens": 15253431.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.328841352462769,
|
|
"epoch": 0.7792272704553407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947941944772199,
|
|
"loss": 6.0655,
|
|
"mean_token_accuracy": 0.15655386596918106,
|
|
"num_tokens": 15262566.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.424752712249756,
|
|
"epoch": 0.7797270955165692,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000494786559039862,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.1512213408946991,
|
|
"num_tokens": 15272122.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.374563121795655,
|
|
"epoch": 0.7802269205777977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004947789180727308,
|
|
"loss": 6.1104,
|
|
"mean_token_accuracy": 0.14912727624177932,
|
|
"num_tokens": 15281165.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.281117677688599,
|
|
"epoch": 0.7807267456390263,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004947712715760186,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15215574949979782,
|
|
"num_tokens": 15290992.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.42008786201477,
|
|
"epoch": 0.7812265707002549,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947636195499177,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.15412439107894899,
|
|
"num_tokens": 15300454.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.367960453033447,
|
|
"epoch": 0.7817263957614835,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947559619946207,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.16236582249403,
|
|
"num_tokens": 15310471.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.36067476272583,
|
|
"epoch": 0.7822262208227121,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004947482989103203,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.150112184882164,
|
|
"num_tokens": 15320554.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.33453893661499,
|
|
"epoch": 0.7827260458839406,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004947406302972092,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.15288945585489272,
|
|
"num_tokens": 15331623.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.396679544448853,
|
|
"epoch": 0.7832258709451692,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947329561554804,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15599678754806517,
|
|
"num_tokens": 15340954.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.352474308013916,
|
|
"epoch": 0.7837256960063977,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947252764853269,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.1548044927418232,
|
|
"num_tokens": 15350858.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.357823276519776,
|
|
"epoch": 0.7842255210676263,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947175912869421,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.15271322131156922,
|
|
"num_tokens": 15360382.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.360582780838013,
|
|
"epoch": 0.7847253461288549,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004947099005605191,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.15477154329419135,
|
|
"num_tokens": 15370626.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.371226644515991,
|
|
"epoch": 0.7852251711900835,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947022043062517,
|
|
"loss": 6.0871,
|
|
"mean_token_accuracy": 0.15329956635832787,
|
|
"num_tokens": 15379582.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.3223960399627686,
|
|
"epoch": 0.7857249962513121,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004946945025243333,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.16119557172060012,
|
|
"num_tokens": 15390168.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.216022109985351,
|
|
"epoch": 0.7862248213125406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946867952149577,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.1690938338637352,
|
|
"num_tokens": 15400979.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.356059169769287,
|
|
"epoch": 0.7867246463737692,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946790823783189,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.158439601957798,
|
|
"num_tokens": 15409954.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.310535097122193,
|
|
"epoch": 0.7872244714349977,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000494671364014611,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.15261083096265793,
|
|
"num_tokens": 15419539.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.258672666549683,
|
|
"epoch": 0.7877242964962263,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000494663640124028,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.15462627187371253,
|
|
"num_tokens": 15428751.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.320603656768799,
|
|
"epoch": 0.7882241215574549,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946559107067643,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.1596684604883194,
|
|
"num_tokens": 15438466.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.328545141220093,
|
|
"epoch": 0.7887239466186835,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946481757630146,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.1580088883638382,
|
|
"num_tokens": 15448395.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.344852066040039,
|
|
"epoch": 0.789223771679912,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004946404352929732,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.14948575645685197,
|
|
"num_tokens": 15457986.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.344309520721436,
|
|
"epoch": 0.7897235967411406,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000494632689296835,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.15723001658916474,
|
|
"num_tokens": 15467989.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.334513759613037,
|
|
"epoch": 0.7902234218023692,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946249377747947,
|
|
"loss": 5.9607,
|
|
"mean_token_accuracy": 0.16250821352005004,
|
|
"num_tokens": 15477537.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.354229974746704,
|
|
"epoch": 0.7907232468635977,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004946171807270476,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.15882723778486252,
|
|
"num_tokens": 15488007.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.328631067276001,
|
|
"epoch": 0.7912230719248263,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004946094181537887,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.15875689685344696,
|
|
"num_tokens": 15498122.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.351136350631714,
|
|
"epoch": 0.7917228969860549,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946016500552134,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.15321754813194274,
|
|
"num_tokens": 15507585.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.351750278472901,
|
|
"epoch": 0.7922227220472835,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004945938764315171,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.16057391911745073,
|
|
"num_tokens": 15516260.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.379032468795776,
|
|
"epoch": 0.792722547108512,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004945860972828954,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.15382259786129,
|
|
"num_tokens": 15527372.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.315398454666138,
|
|
"epoch": 0.7932223721697406,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945783126095439,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.1528909057378769,
|
|
"num_tokens": 15537244.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.43246865272522,
|
|
"epoch": 0.7937221972309692,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945705224116586,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.15014927536249162,
|
|
"num_tokens": 15546512.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.2727875232696535,
|
|
"epoch": 0.7942220222921977,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945627266894354,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.15795076489448548,
|
|
"num_tokens": 15557381.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.326065349578857,
|
|
"epoch": 0.7947218473534263,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945549254430707,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.14939350187778472,
|
|
"num_tokens": 15565806.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.319204092025757,
|
|
"epoch": 0.7952216724146549,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945471186727603,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15233103036880494,
|
|
"num_tokens": 15577059.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.417460632324219,
|
|
"epoch": 0.7957214974758834,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945393063787011,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.14103016182780265,
|
|
"num_tokens": 15587827.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.4459022045135494,
|
|
"epoch": 0.796221322537112,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945314885610894,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.1510389395058155,
|
|
"num_tokens": 15598232.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.31694221496582,
|
|
"epoch": 0.7967211475983406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945236652201219,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.15895196795463562,
|
|
"num_tokens": 15606896.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.273259067535401,
|
|
"epoch": 0.7972209726595691,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945158363559955,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.16047601997852326,
|
|
"num_tokens": 15616868.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.328847742080688,
|
|
"epoch": 0.7977207977207977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945080019689071,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.15540412366390227,
|
|
"num_tokens": 15626521.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.313483047485351,
|
|
"epoch": 0.7982206227820263,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945001620590538,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.165322382748127,
|
|
"num_tokens": 15635901.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.353866624832153,
|
|
"epoch": 0.7987204478432549,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000494492316626633,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.15146649330854417,
|
|
"num_tokens": 15645672.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.415690517425537,
|
|
"epoch": 0.7992202729044834,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004944844656718419,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.152686657756567,
|
|
"num_tokens": 15656668.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.3465392112731935,
|
|
"epoch": 0.799720097965712,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944766091948783,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.16045805513858796,
|
|
"num_tokens": 15666176.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.316654968261719,
|
|
"epoch": 0.8002199230269406,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004944687471959395,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.1564193531870842,
|
|
"num_tokens": 15676162.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.387695264816284,
|
|
"epoch": 0.8007197480881691,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004944608796752237,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.161932110786438,
|
|
"num_tokens": 15685393.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.330781888961792,
|
|
"epoch": 0.8012195731493977,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004944530066329284,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.1627380758523941,
|
|
"num_tokens": 15694944.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.373159551620484,
|
|
"epoch": 0.8017193982106263,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004944451280692521,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.1525207683444023,
|
|
"num_tokens": 15704410.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.364796924591064,
|
|
"epoch": 0.8022192232718548,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944372439843927,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.15973300039768218,
|
|
"num_tokens": 15713663.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.34503321647644,
|
|
"epoch": 0.8027190483330834,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004944293543785489,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.16243622004985808,
|
|
"num_tokens": 15722662.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.337097978591919,
|
|
"epoch": 0.803218873394312,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944214592519188,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.14615035504102708,
|
|
"num_tokens": 15732615.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.356634330749512,
|
|
"epoch": 0.8037186984555406,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004944135586047014,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.16407724916934968,
|
|
"num_tokens": 15741569.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.347867822647094,
|
|
"epoch": 0.8042185235167691,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944056524370953,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.16192770302295684,
|
|
"num_tokens": 15750734.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.3771974563598635,
|
|
"epoch": 0.8047183485779977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004943977407492994,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.15936525613069535,
|
|
"num_tokens": 15761664.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.283066511154175,
|
|
"epoch": 0.8052181736392263,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004943898235415128,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.1661711812019348,
|
|
"num_tokens": 15771159.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.353420734405518,
|
|
"epoch": 0.8057179987004548,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004943819008139347,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.15416169315576553,
|
|
"num_tokens": 15781429.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.372888422012329,
|
|
"epoch": 0.8062178237616834,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943739725667644,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15405321270227432,
|
|
"num_tokens": 15791361.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.364490413665772,
|
|
"epoch": 0.806717648822912,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943660388002014,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.14680706486105918,
|
|
"num_tokens": 15802020.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.2646417140960695,
|
|
"epoch": 0.8072174738841406,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943580995144454,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.16641053855419158,
|
|
"num_tokens": 15811319.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.358747053146362,
|
|
"epoch": 0.8077172989453691,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943501547096961,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.15363794565200806,
|
|
"num_tokens": 15821337.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.367038059234619,
|
|
"epoch": 0.8082171240065977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004943422043861531,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.15800345242023467,
|
|
"num_tokens": 15832234.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.357004451751709,
|
|
"epoch": 0.8087169490678262,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004943342485440169,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.16090811491012574,
|
|
"num_tokens": 15841797.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.312534952163697,
|
|
"epoch": 0.8092167741290548,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004943262871834874,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.15150876194238663,
|
|
"num_tokens": 15851031.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.347748422622681,
|
|
"epoch": 0.8097165991902834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943183203047649,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.14989572912454605,
|
|
"num_tokens": 15861297.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.353136682510376,
|
|
"epoch": 0.810216424251512,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004943103479080499,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.15555044859647751,
|
|
"num_tokens": 15871066.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.372951459884644,
|
|
"epoch": 0.8107162493127406,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494302369993543,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.15368365943431855,
|
|
"num_tokens": 15880395.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.323442125320435,
|
|
"epoch": 0.8112160743739691,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004942943865614449,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.16135157495737076,
|
|
"num_tokens": 15889937.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.356968116760254,
|
|
"epoch": 0.8117158994351977,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004942863976119565,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.1533365249633789,
|
|
"num_tokens": 15899894.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.239344787597656,
|
|
"epoch": 0.8122157244964262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004942784031452788,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.17576976865530014,
|
|
"num_tokens": 15909038.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.306358909606933,
|
|
"epoch": 0.8127155495576548,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004942704031616127,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15730501413345338,
|
|
"num_tokens": 15917891.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.404510068893432,
|
|
"epoch": 0.8132153746188834,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004942623976611598,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.1437299445271492,
|
|
"num_tokens": 15928079.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.336041450500488,
|
|
"epoch": 0.813715199680112,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004942543866441215,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.1558523252606392,
|
|
"num_tokens": 15938065.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.279840803146362,
|
|
"epoch": 0.8142150247413406,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004942463701106992,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.15661945715546607,
|
|
"num_tokens": 15947650.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.279820299148559,
|
|
"epoch": 0.8147148498025691,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942383480610946,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.15910924226045609,
|
|
"num_tokens": 15957194.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.353277349472046,
|
|
"epoch": 0.8152146748637976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942303204955096,
|
|
"loss": 6.0058,
|
|
"mean_token_accuracy": 0.1525981068611145,
|
|
"num_tokens": 15966068.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.328863477706909,
|
|
"epoch": 0.8157144999250262,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004942222874141461,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.1565055899322033,
|
|
"num_tokens": 15975672.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.331948280334473,
|
|
"epoch": 0.8162143249862548,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942142488172063,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1589051067829132,
|
|
"num_tokens": 15986216.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.279346895217896,
|
|
"epoch": 0.8167141500474834,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942062047048924,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.1637604370713234,
|
|
"num_tokens": 15994673.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.278978538513184,
|
|
"epoch": 0.817213975108712,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941981550774068,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.16159429252147675,
|
|
"num_tokens": 16003576.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.219257783889771,
|
|
"epoch": 0.8177138001699406,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004941900999349521,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.1629066564142704,
|
|
"num_tokens": 16013334.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.363968849182129,
|
|
"epoch": 0.8182136252311691,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004941820392777307,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.157041934132576,
|
|
"num_tokens": 16023101.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.289866352081299,
|
|
"epoch": 0.8187134502923976,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941739731059457,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15517905876040458,
|
|
"num_tokens": 16034189.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.325851821899414,
|
|
"epoch": 0.8192132753536262,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004941659014198,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.16243064403533936,
|
|
"num_tokens": 16044008.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.378225517272949,
|
|
"epoch": 0.8197131004148548,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004941578242194965,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.157520392537117,
|
|
"num_tokens": 16053557.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.34628849029541,
|
|
"epoch": 0.8202129254760834,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941497415052387,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.16494817435741424,
|
|
"num_tokens": 16063191.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.275260496139526,
|
|
"epoch": 0.820712750537312,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004941416532772296,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.1579779177904129,
|
|
"num_tokens": 16072482.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.264672565460205,
|
|
"epoch": 0.8212125755985406,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000494133559535673,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.16216217279434203,
|
|
"num_tokens": 16082848.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.430441522598267,
|
|
"epoch": 0.821712400659769,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941254602807724,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.15594725906848908,
|
|
"num_tokens": 16091604.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.418979597091675,
|
|
"epoch": 0.8222122257209976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941173555127315,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1573072925209999,
|
|
"num_tokens": 16101427.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.2760858058929445,
|
|
"epoch": 0.8227120507822262,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004941092452317546,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.16387312561273576,
|
|
"num_tokens": 16112206.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.389609622955322,
|
|
"epoch": 0.8232118758434548,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941011294380452,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.15831712558865546,
|
|
"num_tokens": 16122652.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.320662260055542,
|
|
"epoch": 0.8237117009046834,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004940930081318079,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15809359550476074,
|
|
"num_tokens": 16132976.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.367689418792724,
|
|
"epoch": 0.824211525965912,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004940848813132469,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.1614730328321457,
|
|
"num_tokens": 16143514.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.359382963180542,
|
|
"epoch": 0.8247113510271405,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004940767489825666,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.15422015637159348,
|
|
"num_tokens": 16154235.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.312224721908569,
|
|
"epoch": 0.825211176088369,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004940686111399716,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.15710938796401025,
|
|
"num_tokens": 16164251.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.271993112564087,
|
|
"epoch": 0.8257110011495976,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004940604677856669,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.1678191229701042,
|
|
"num_tokens": 16172780.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.22545895576477,
|
|
"epoch": 0.8262108262108262,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000494052318919857,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.16943707168102265,
|
|
"num_tokens": 16182443.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.3193761825561525,
|
|
"epoch": 0.8267106512720548,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004940441645427473,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.15817681401968003,
|
|
"num_tokens": 16192515.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.329217863082886,
|
|
"epoch": 0.8272104763332834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940360046545427,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.15585372000932693,
|
|
"num_tokens": 16201615.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.3338240623474125,
|
|
"epoch": 0.827710301394512,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004940278392554486,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.15715113505721093,
|
|
"num_tokens": 16210461.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.264766359329224,
|
|
"epoch": 0.8282101264557404,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004940196683456704,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.15522116869688035,
|
|
"num_tokens": 16220293.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.276094675064087,
|
|
"epoch": 0.828709951516969,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940114919254137,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.1632644221186638,
|
|
"num_tokens": 16230020.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.314875221252441,
|
|
"epoch": 0.8292097765781976,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940033099948843,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15687973350286483,
|
|
"num_tokens": 16240187.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.298923110961914,
|
|
"epoch": 0.8297096016394262,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939951225542879,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.15905750691890716,
|
|
"num_tokens": 16250200.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.315143966674805,
|
|
"epoch": 0.8302094267006548,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004939869296038306,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.1560800239443779,
|
|
"num_tokens": 16259396.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.369123268127441,
|
|
"epoch": 0.8307092517618834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004939787311437185,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.1463489644229412,
|
|
"num_tokens": 16270033.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.409291172027588,
|
|
"epoch": 0.831209076823112,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939705271741579,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.15849734097719193,
|
|
"num_tokens": 16281464.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.37066068649292,
|
|
"epoch": 0.8317089018843404,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004939623176953551,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.15250220745801926,
|
|
"num_tokens": 16292125.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.280330514907837,
|
|
"epoch": 0.832208726945569,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004939541027075168,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.15650486648082734,
|
|
"num_tokens": 16302993.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.3125328540802,
|
|
"epoch": 0.8327085520067976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939458822108496,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.15871484875679015,
|
|
"num_tokens": 16311287.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.336609554290772,
|
|
"epoch": 0.8332083770680262,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939376562055602,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.15882525444030762,
|
|
"num_tokens": 16320701.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.303063488006591,
|
|
"epoch": 0.8337082021292548,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939294246918558,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.16013622060418128,
|
|
"num_tokens": 16329834.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.274789524078369,
|
|
"epoch": 0.8342080271904834,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004939211876699435,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.15697502493858337,
|
|
"num_tokens": 16339043.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.38935170173645,
|
|
"epoch": 0.8347078522517118,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939129451400305,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.15153319835662843,
|
|
"num_tokens": 16348774.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.335216093063354,
|
|
"epoch": 0.8352076773129404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493904697102324,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.1559519499540329,
|
|
"num_tokens": 16357999.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.32489013671875,
|
|
"epoch": 0.835707502374169,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004938964435570317,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.1566874586045742,
|
|
"num_tokens": 16369308.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.219276380538941,
|
|
"epoch": 0.8362073274353976,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004938881845043612,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.1575685992836952,
|
|
"num_tokens": 16378001.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.410024976730346,
|
|
"epoch": 0.8367071524966262,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938799199445202,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.15064250826835632,
|
|
"num_tokens": 16387925.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.420650672912598,
|
|
"epoch": 0.8372069775578548,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004938716498777169,
|
|
"loss": 6.1099,
|
|
"mean_token_accuracy": 0.1486400470137596,
|
|
"num_tokens": 16398200.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.251035404205322,
|
|
"epoch": 0.8377068026190834,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004938633743041592,
|
|
"loss": 5.9048,
|
|
"mean_token_accuracy": 0.16335107684135436,
|
|
"num_tokens": 16407874.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.351597261428833,
|
|
"epoch": 0.8382066276803118,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938550932240552,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.16021281331777573,
|
|
"num_tokens": 16417825.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.313519906997681,
|
|
"epoch": 0.8387064527415404,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004938468066376134,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.1588287577033043,
|
|
"num_tokens": 16427265.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.219474124908447,
|
|
"epoch": 0.839206277802769,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004938385145450423,
|
|
"loss": 5.9335,
|
|
"mean_token_accuracy": 0.16904399394989014,
|
|
"num_tokens": 16436639.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.3209210395812985,
|
|
"epoch": 0.8397061028639976,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938302169465505,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15923720598220825,
|
|
"num_tokens": 16446411.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.329742097854615,
|
|
"epoch": 0.8402059279252262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938219138423467,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.1569899618625641,
|
|
"num_tokens": 16455784.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.254296159744262,
|
|
"epoch": 0.8407057529864548,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938136052326399,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.1652514010667801,
|
|
"num_tokens": 16464411.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.33018012046814,
|
|
"epoch": 0.8412055780476833,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938052911176392,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.15236517563462257,
|
|
"num_tokens": 16473299.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.236158561706543,
|
|
"epoch": 0.8417054031089118,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004937969714975534,
|
|
"loss": 5.8978,
|
|
"mean_token_accuracy": 0.1701076254248619,
|
|
"num_tokens": 16483040.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.307992315292358,
|
|
"epoch": 0.8422052281701404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004937886463725923,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.1591356337070465,
|
|
"num_tokens": 16492608.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.386041641235352,
|
|
"epoch": 0.842705053231369,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004937803157429651,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.152254805713892,
|
|
"num_tokens": 16503139.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.274320459365844,
|
|
"epoch": 0.8432048782925976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004937719796088815,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.16632994264364243,
|
|
"num_tokens": 16511584.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.229552412033081,
|
|
"epoch": 0.8437047033538262,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004937636379705511,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.1586647227406502,
|
|
"num_tokens": 16522407.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.266093635559082,
|
|
"epoch": 0.8442045284150548,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004937552908281839,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.15468461513519288,
|
|
"num_tokens": 16532351.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.380763959884644,
|
|
"epoch": 0.8447043534762833,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004937469381819899,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.15118208080530166,
|
|
"num_tokens": 16541673.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.316137981414795,
|
|
"epoch": 0.8452041785375118,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937385800321792,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.16469220519065858,
|
|
"num_tokens": 16551622.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.323038625717163,
|
|
"epoch": 0.8457040035987404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004937302163789621,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.16254176050424576,
|
|
"num_tokens": 16559074.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.292465686798096,
|
|
"epoch": 0.846203828659969,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004937218472225491,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.16847988665103913,
|
|
"num_tokens": 16568650.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.3299661636352536,
|
|
"epoch": 0.8467036537211976,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004937134725631506,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1615317791700363,
|
|
"num_tokens": 16578696.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.333920335769653,
|
|
"epoch": 0.8472034787824262,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004937050924009775,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.15477089658379556,
|
|
"num_tokens": 16589014.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.311668968200683,
|
|
"epoch": 0.8477033038436548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004936967067362406,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.1608669266104698,
|
|
"num_tokens": 16598319.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.3801312923431395,
|
|
"epoch": 0.8482031289048833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936883155691507,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.15383087694644929,
|
|
"num_tokens": 16607941.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.300627613067627,
|
|
"epoch": 0.8487029539661118,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004936799188999192,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.15645340755581855,
|
|
"num_tokens": 16618398.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.3287097930908205,
|
|
"epoch": 0.8492027790273404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004936715167287571,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.15087620839476584,
|
|
"num_tokens": 16628953.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.376377201080322,
|
|
"epoch": 0.849702604088569,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000493663109055876,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.15419138818979264,
|
|
"num_tokens": 16638783.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.320876359939575,
|
|
"epoch": 0.8502024291497976,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004936546958814873,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.15921728909015656,
|
|
"num_tokens": 16647432.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.339123201370239,
|
|
"epoch": 0.8507022542110262,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004936462772058026,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.1491931989789009,
|
|
"num_tokens": 16656839.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.356180667877197,
|
|
"epoch": 0.8512020792722547,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004936378530290339,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.15205063074827194,
|
|
"num_tokens": 16667054.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.333870506286621,
|
|
"epoch": 0.8517019043334833,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004936294233513931,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15879931226372718,
|
|
"num_tokens": 16676851.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.350597715377807,
|
|
"epoch": 0.8522017293947118,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936209881730922,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.1549105763435364,
|
|
"num_tokens": 16686433.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.283620977401734,
|
|
"epoch": 0.8527015544559404,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004936125474943436,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.1670728474855423,
|
|
"num_tokens": 16695859.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.307900285720825,
|
|
"epoch": 0.853201379517169,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004936041013153596,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.16403653621673583,
|
|
"num_tokens": 16704391.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.326267385482788,
|
|
"epoch": 0.8537012045783976,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004935956496363525,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14513936787843704,
|
|
"num_tokens": 16715316.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.4946760654449465,
|
|
"epoch": 0.8542010296396262,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004935871924575352,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14828586131334304,
|
|
"num_tokens": 16726215.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.3403096199035645,
|
|
"epoch": 0.8547008547008547,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935787297791204,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.15677949488162995,
|
|
"num_tokens": 16735768.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.26854944229126,
|
|
"epoch": 0.8552006797620832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935702616013209,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.17068031281232834,
|
|
"num_tokens": 16744265.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.296561145782471,
|
|
"epoch": 0.8557005048233118,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049356178792435,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.15913574397563934,
|
|
"num_tokens": 16753713.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.349815416336059,
|
|
"epoch": 0.8562003298845404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935533087484207,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.15839519053697587,
|
|
"num_tokens": 16763670.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.243776512145996,
|
|
"epoch": 0.856700154945769,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004935448240737464,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.1591751366853714,
|
|
"num_tokens": 16773504.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.263789653778076,
|
|
"epoch": 0.8571999800069976,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004935363339005405,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.1548612654209137,
|
|
"num_tokens": 16784181.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.372800493240357,
|
|
"epoch": 0.8576998050682261,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004935278382290168,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.1553930178284645,
|
|
"num_tokens": 16793610.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.364020681381225,
|
|
"epoch": 0.8581996301294547,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004935193370593887,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.14924698770046235,
|
|
"num_tokens": 16804068.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.295427656173706,
|
|
"epoch": 0.8586994551906832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935108303918705,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.15623578131198884,
|
|
"num_tokens": 16813769.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.285124444961548,
|
|
"epoch": 0.8591992802519118,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004935023182266761,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.1577179491519928,
|
|
"num_tokens": 16822859.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.408170318603515,
|
|
"epoch": 0.8596991053131404,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004934938005640194,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.1459698349237442,
|
|
"num_tokens": 16834839.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.408890676498413,
|
|
"epoch": 0.860198930374369,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493485277404115,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15306514650583267,
|
|
"num_tokens": 16845205.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.3744221210479735,
|
|
"epoch": 0.8606987554355976,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004934767487471772,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.15598127841949463,
|
|
"num_tokens": 16854874.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.284731149673462,
|
|
"epoch": 0.8611985804968261,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004934682145934207,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.16285969763994218,
|
|
"num_tokens": 16864771.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.297547101974487,
|
|
"epoch": 0.8616984055580547,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049345967494306,
|
|
"loss": 6.0227,
|
|
"mean_token_accuracy": 0.15545195192098618,
|
|
"num_tokens": 16874227.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.272792339324951,
|
|
"epoch": 0.8621982306192832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934511297963102,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.1649970218539238,
|
|
"num_tokens": 16883895.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.296281480789185,
|
|
"epoch": 0.8626980556805118,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004934425791533861,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.16428372263908386,
|
|
"num_tokens": 16893012.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.322003316879273,
|
|
"epoch": 0.8631978807417404,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004934340230145031,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.16415923088788986,
|
|
"num_tokens": 16903831.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.387474012374878,
|
|
"epoch": 0.863697705802969,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934254613798761,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.1477980762720108,
|
|
"num_tokens": 16913649.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.293093967437744,
|
|
"epoch": 0.8641975308641975,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004934168942497207,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.15922494232654572,
|
|
"num_tokens": 16923063.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.363900852203369,
|
|
"epoch": 0.8646973559254261,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004934083216242526,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.15772690176963805,
|
|
"num_tokens": 16932901.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.361544799804688,
|
|
"epoch": 0.8651971809866547,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933997435036873,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.14874605387449263,
|
|
"num_tokens": 16942781.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.350284290313721,
|
|
"epoch": 0.8656970060478832,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004933911598882405,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.15804762989282609,
|
|
"num_tokens": 16952064.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.251397132873535,
|
|
"epoch": 0.8661968311091118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004933825707781284,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.15892206728458405,
|
|
"num_tokens": 16961528.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.309291696548462,
|
|
"epoch": 0.8666966561703404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933739761735671,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.15917915999889373,
|
|
"num_tokens": 16971066.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.346917390823364,
|
|
"epoch": 0.867196481231569,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004933653760747726,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.15533553212881088,
|
|
"num_tokens": 16981438.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.33717827796936,
|
|
"epoch": 0.8676963062927975,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004933567704819615,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.1681694880127907,
|
|
"num_tokens": 16990836.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.268847465515137,
|
|
"epoch": 0.8681961313540261,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004933481593953502,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.1634020611643791,
|
|
"num_tokens": 17000254.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.293424081802368,
|
|
"epoch": 0.8686959564152547,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004933395428151554,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.16054651886224747,
|
|
"num_tokens": 17010081.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.276514196395874,
|
|
"epoch": 0.8691957814764832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000493330920741594,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.165019690990448,
|
|
"num_tokens": 17018967.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.280643272399902,
|
|
"epoch": 0.8696956065377118,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933222931748827,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.15800123661756516,
|
|
"num_tokens": 17027615.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.284801483154297,
|
|
"epoch": 0.8701954315989404,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004933136601152387,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.16204793602228165,
|
|
"num_tokens": 17038446.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.322351312637329,
|
|
"epoch": 0.8706952566601689,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004933050215628793,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.15633762776851653,
|
|
"num_tokens": 17047787.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.298692893981934,
|
|
"epoch": 0.8711950817213975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932963775180216,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.15792082324624063,
|
|
"num_tokens": 17056842.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.270297479629517,
|
|
"epoch": 0.8716949067826261,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004932877279808833,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.1550676628947258,
|
|
"num_tokens": 17066217.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.404949092864991,
|
|
"epoch": 0.8721947318438547,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004932790729516818,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.14534684121608735,
|
|
"num_tokens": 17077760.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.297685146331787,
|
|
"epoch": 0.8726945569050832,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004932704124306352,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.16252171993255615,
|
|
"num_tokens": 17088251.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.362019681930542,
|
|
"epoch": 0.8731943819663118,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000493261746417961,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.15425260365009308,
|
|
"num_tokens": 17098192.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.328019714355468,
|
|
"epoch": 0.8736942070275404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004932530749138775,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.1566529244184494,
|
|
"num_tokens": 17107787.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.327110147476196,
|
|
"epoch": 0.8741940320887689,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004932443979186028,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.15814253240823745,
|
|
"num_tokens": 17118125.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.28403263092041,
|
|
"epoch": 0.8746938571499975,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004932357154323552,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.16689711958169937,
|
|
"num_tokens": 17127909.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.297478485107422,
|
|
"epoch": 0.8751936822112261,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932270274553531,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.16073320135474206,
|
|
"num_tokens": 17137672.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.27841534614563,
|
|
"epoch": 0.8756935072724547,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004932183339878153,
|
|
"loss": 5.9749,
|
|
"mean_token_accuracy": 0.16102777123451234,
|
|
"num_tokens": 17147151.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.295157766342163,
|
|
"epoch": 0.8761933323336832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932096350299602,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.16724041104316711,
|
|
"num_tokens": 17156615.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.307548189163208,
|
|
"epoch": 0.8766931573949118,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004932009305820069,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.16361405551433564,
|
|
"num_tokens": 17166089.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.315958881378174,
|
|
"epoch": 0.8771929824561403,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004931922206441743,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.15870085209608079,
|
|
"num_tokens": 17176565.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.221841144561767,
|
|
"epoch": 0.8776928075173689,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004931835052166817,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.1633104845881462,
|
|
"num_tokens": 17186987.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.281564521789551,
|
|
"epoch": 0.8781926325785975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004931747842997481,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.1614842638373375,
|
|
"num_tokens": 17196325.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.347506952285767,
|
|
"epoch": 0.8786924576398261,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004931660578935931,
|
|
"loss": 6.016,
|
|
"mean_token_accuracy": 0.16086701005697251,
|
|
"num_tokens": 17206210.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.275522136688233,
|
|
"epoch": 0.8791922827010547,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931573259984363,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.1625548392534256,
|
|
"num_tokens": 17216521.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.2953314781188965,
|
|
"epoch": 0.8796921077622832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931485886144972,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.163150092959404,
|
|
"num_tokens": 17225125.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.31622314453125,
|
|
"epoch": 0.8801919328235118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931398457419959,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.16008610874414445,
|
|
"num_tokens": 17234674.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.2657308101654055,
|
|
"epoch": 0.8806917578847403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004931310973811521,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.16115928292274476,
|
|
"num_tokens": 17244362.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.24544506072998,
|
|
"epoch": 0.8811915829459689,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000493122343532186,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.1613535575568676,
|
|
"num_tokens": 17253541.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.2896276950836185,
|
|
"epoch": 0.8816914080071975,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000493113584195318,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.1658151239156723,
|
|
"num_tokens": 17263214.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.326872110366821,
|
|
"epoch": 0.8821912330684261,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004931048193707681,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.1554119296371937,
|
|
"num_tokens": 17273991.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.2352180004119875,
|
|
"epoch": 0.8826910581296546,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004930960490587573,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.16835620999336243,
|
|
"num_tokens": 17283221.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.228054571151733,
|
|
"epoch": 0.8831908831908832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000493087273259506,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.16027445197105408,
|
|
"num_tokens": 17293520.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.301565551757813,
|
|
"epoch": 0.8836907082521117,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004930784919732349,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.15990298986434937,
|
|
"num_tokens": 17303881.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.281642818450928,
|
|
"epoch": 0.8841905333133403,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004930697052001651,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1712904006242752,
|
|
"num_tokens": 17314115.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.2910114288330075,
|
|
"epoch": 0.8846903583745689,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004930609129405177,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.15459459871053696,
|
|
"num_tokens": 17324517.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.293638467788696,
|
|
"epoch": 0.8851901834357975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004930521151945138,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.16115714162588118,
|
|
"num_tokens": 17334109.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.3327062129974365,
|
|
"epoch": 0.8856900084970261,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004930433119623749,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.15914444923400878,
|
|
"num_tokens": 17344602.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.27345757484436,
|
|
"epoch": 0.8861898335582546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930345032443221,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.170835642516613,
|
|
"num_tokens": 17354476.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.298273324966431,
|
|
"epoch": 0.8866896586194832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004930256890405777,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.16544063985347748,
|
|
"num_tokens": 17364748.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.293568468093872,
|
|
"epoch": 0.8871894836807117,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004930168693513627,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.15670243948698043,
|
|
"num_tokens": 17374162.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.304314184188843,
|
|
"epoch": 0.8876893087419403,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930080441768995,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.16098790019750595,
|
|
"num_tokens": 17384042.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.279111099243164,
|
|
"epoch": 0.8881891338031689,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049299921351741,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.1617957279086113,
|
|
"num_tokens": 17394181.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.299239730834961,
|
|
"epoch": 0.8886889588643975,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004929903773731164,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.1515504464507103,
|
|
"num_tokens": 17402983.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.36971082687378,
|
|
"epoch": 0.8891887839256261,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929815357442409,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.15176645442843437,
|
|
"num_tokens": 17413442.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.334700345993042,
|
|
"epoch": 0.8896886089868546,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004929726886310062,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.15787985026836396,
|
|
"num_tokens": 17423644.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.359425830841064,
|
|
"epoch": 0.8901884340480831,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004929638360336348,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.15729981660842896,
|
|
"num_tokens": 17433400.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.342666435241699,
|
|
"epoch": 0.8906882591093117,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004929549779523492,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.15617013797163964,
|
|
"num_tokens": 17443146.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.235498380661011,
|
|
"epoch": 0.8911880841705403,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004929461143873725,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.16772447377443314,
|
|
"num_tokens": 17452880.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.242399215698242,
|
|
"epoch": 0.8916879092317689,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004929372453389277,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.16290762424468994,
|
|
"num_tokens": 17461633.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.34659333229065,
|
|
"epoch": 0.8921877342929975,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004929283708072378,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.1571647822856903,
|
|
"num_tokens": 17470892.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.331136322021484,
|
|
"epoch": 0.8926875593542261,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004929194907925262,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.15679070204496384,
|
|
"num_tokens": 17481457.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.319706773757934,
|
|
"epoch": 0.8931873844154546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929106052950163,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.15017589926719666,
|
|
"num_tokens": 17490387.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.341036176681518,
|
|
"epoch": 0.8936872094766831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004929017143149317,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.16335285529494287,
|
|
"num_tokens": 17499478.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.341434621810913,
|
|
"epoch": 0.8941870345379117,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000492892817852496,
|
|
"loss": 6.0782,
|
|
"mean_token_accuracy": 0.15566957741975784,
|
|
"num_tokens": 17509396.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.296658039093018,
|
|
"epoch": 0.8946868595991403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000492883915907933,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.1627983994781971,
|
|
"num_tokens": 17519773.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.317468118667603,
|
|
"epoch": 0.8951866846603689,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004928750084814668,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.16174028366804122,
|
|
"num_tokens": 17529873.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.248566007614135,
|
|
"epoch": 0.8956865097215975,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004928660955733214,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.167071533203125,
|
|
"num_tokens": 17538642.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.298224258422851,
|
|
"epoch": 0.896186334782826,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004928571771837211,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.15473215132951737,
|
|
"num_tokens": 17546892.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.364128589630127,
|
|
"epoch": 0.8966861598440545,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004928482533128902,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.15607682317495347,
|
|
"num_tokens": 17556283.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.291881322860718,
|
|
"epoch": 0.8971859849052831,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004928393239610535,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.1568782977759838,
|
|
"num_tokens": 17567021.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.323279190063476,
|
|
"epoch": 0.8976858099665117,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004928303891284354,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.16249987930059434,
|
|
"num_tokens": 17575927.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.31244912147522,
|
|
"epoch": 0.8981856350277403,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004928214488152607,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.16090064644813537,
|
|
"num_tokens": 17585882.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.2501074314117435,
|
|
"epoch": 0.8986854600889689,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004928125030217545,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.16871493458747863,
|
|
"num_tokens": 17595998.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.370286464691162,
|
|
"epoch": 0.8991852851501975,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004928035517481416,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.16180001050233841,
|
|
"num_tokens": 17605177.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.332086515426636,
|
|
"epoch": 0.899685110211426,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004927945949946476,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15261444002389907,
|
|
"num_tokens": 17615089.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.899685110211426,
|
|
"eval_entropy": 6.091995080516868,
|
|
"eval_loss": 6.006189823150635,
|
|
"eval_mean_token_accuracy": 0.1658259522466431,
|
|
"eval_num_tokens": 17615089.0,
|
|
"eval_runtime": 18.3622,
|
|
"eval_samples_per_second": 1690.701,
|
|
"eval_steps_per_second": 211.358,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.319211149215699,
|
|
"epoch": 0.9001849352726545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927856327614975,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.16066382378339766,
|
|
"num_tokens": 17624708.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.320309829711914,
|
|
"epoch": 0.9006847603338831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492776665048917,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.16052087098360063,
|
|
"num_tokens": 17633639.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.24876823425293,
|
|
"epoch": 0.9011845853951117,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927676918571316,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.1569691739976406,
|
|
"num_tokens": 17643092.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.286394453048706,
|
|
"epoch": 0.9016844104563403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004927587131863671,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.15303539484739304,
|
|
"num_tokens": 17652698.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.275062799453735,
|
|
"epoch": 0.9021842355175689,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004927497290368493,
|
|
"loss": 5.8961,
|
|
"mean_token_accuracy": 0.16537746489048005,
|
|
"num_tokens": 17662654.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.297282314300537,
|
|
"epoch": 0.9026840605787975,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927407394088046,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.15799168795347213,
|
|
"num_tokens": 17672476.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.306432390213013,
|
|
"epoch": 0.9031838856400259,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004927317443024587,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.15369687229394913,
|
|
"num_tokens": 17682612.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.3743470191955565,
|
|
"epoch": 0.9036837107012545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927227437180382,
|
|
"loss": 6.0065,
|
|
"mean_token_accuracy": 0.15351989418268203,
|
|
"num_tokens": 17692020.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.303380012512207,
|
|
"epoch": 0.9041835357624831,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004927137376557696,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.1619989678263664,
|
|
"num_tokens": 17702677.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.229163551330567,
|
|
"epoch": 0.9046833608237117,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004927047261158793,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.1710870608687401,
|
|
"num_tokens": 17711753.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.287225294113159,
|
|
"epoch": 0.9051831858849403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004926957090985942,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.1570405438542366,
|
|
"num_tokens": 17721293.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.37217435836792,
|
|
"epoch": 0.9056830109461689,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004926866866041409,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.15806891322135924,
|
|
"num_tokens": 17732311.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.322846603393555,
|
|
"epoch": 0.9061828360073975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004926776586327467,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.1629113405942917,
|
|
"num_tokens": 17743040.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.253210973739624,
|
|
"epoch": 0.9066826610686259,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926686251846386,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.17474207878112794,
|
|
"num_tokens": 17752436.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.271312141418457,
|
|
"epoch": 0.9071824861298545,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926595862600439,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.15757881104946136,
|
|
"num_tokens": 17762043.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.244815063476563,
|
|
"epoch": 0.9076823111910831,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004926505418591901,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.1568921148777008,
|
|
"num_tokens": 17772065.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.2171916484832765,
|
|
"epoch": 0.9081821362523117,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004926414919823045,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.1630600333213806,
|
|
"num_tokens": 17781472.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.313794660568237,
|
|
"epoch": 0.9086819613135403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926324366296151,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.15891491174697875,
|
|
"num_tokens": 17789435.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.304472255706787,
|
|
"epoch": 0.9091817863747689,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926233758013494,
|
|
"loss": 5.9711,
|
|
"mean_token_accuracy": 0.15842942744493485,
|
|
"num_tokens": 17798367.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.304627752304077,
|
|
"epoch": 0.9096816114359974,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004926143094977359,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.164638015627861,
|
|
"num_tokens": 17807660.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.253454875946045,
|
|
"epoch": 0.9101814364972259,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004926052377190022,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.1660101182758808,
|
|
"num_tokens": 17816993.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.324965190887451,
|
|
"epoch": 0.9106812615584545,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004925961604653765,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.16099593937397003,
|
|
"num_tokens": 17826570.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.334753751754761,
|
|
"epoch": 0.9111810866196831,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004925870777370877,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.16466909050941467,
|
|
"num_tokens": 17835921.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.269651556015015,
|
|
"epoch": 0.9116809116809117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925779895343639,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.1671336054801941,
|
|
"num_tokens": 17845713.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.312954139709473,
|
|
"epoch": 0.9121807367421403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004925688958574339,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15697822272777556,
|
|
"num_tokens": 17855808.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.296477031707764,
|
|
"epoch": 0.9126805618033689,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004925597967065264,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.16216063797473906,
|
|
"num_tokens": 17865427.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.272869634628296,
|
|
"epoch": 0.9131803868645973,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004925506920818705,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.15422266572713852,
|
|
"num_tokens": 17876371.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.278209066390991,
|
|
"epoch": 0.9136802119258259,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925415819836951,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.16299416571855546,
|
|
"num_tokens": 17886050.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.315353441238403,
|
|
"epoch": 0.9141800369870545,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004925324664122294,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.16405436992645264,
|
|
"num_tokens": 17896509.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.394306707382202,
|
|
"epoch": 0.9146798620482831,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004925233453677029,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.1607755996286869,
|
|
"num_tokens": 17906242.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.269827556610108,
|
|
"epoch": 0.9151796871095117,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004925142188503451,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.1615909069776535,
|
|
"num_tokens": 17916261.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.26325364112854,
|
|
"epoch": 0.9156795121707403,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925050868603854,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.1623930349946022,
|
|
"num_tokens": 17926486.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.268542242050171,
|
|
"epoch": 0.9161793372319688,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004924959493980537,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.16016075313091277,
|
|
"num_tokens": 17936374.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.387264728546143,
|
|
"epoch": 0.9166791622931973,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004924868064635798,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.14479677900671958,
|
|
"num_tokens": 17946930.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.423554420471191,
|
|
"epoch": 0.9171789873544259,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492477658057194,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.15967584699392318,
|
|
"num_tokens": 17955760.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.310541820526123,
|
|
"epoch": 0.9176788124156545,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004924685041791262,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.1650274410843849,
|
|
"num_tokens": 17965871.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.197895669937134,
|
|
"epoch": 0.9181786374768831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924593448296068,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.16768270283937453,
|
|
"num_tokens": 17974551.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.32922625541687,
|
|
"epoch": 0.9186784625381117,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004924501800088662,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15901304483413697,
|
|
"num_tokens": 17983675.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.320379257202148,
|
|
"epoch": 0.9191782875993403,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004924410097171351,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.161191126704216,
|
|
"num_tokens": 17993299.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.314342403411866,
|
|
"epoch": 0.9196781126605688,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000492431833954644,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.1643039718270302,
|
|
"num_tokens": 18004755.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.345354270935059,
|
|
"epoch": 0.9201779377217973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924226527216241,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.14989715963602065,
|
|
"num_tokens": 18014908.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.306883716583252,
|
|
"epoch": 0.9206777627830259,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004924134660183061,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.16108319759368897,
|
|
"num_tokens": 18023919.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.277152729034424,
|
|
"epoch": 0.9211775878442545,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004924042738449212,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.16133492439985275,
|
|
"num_tokens": 18033706.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.34048867225647,
|
|
"epoch": 0.9216774129054831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923950762017008,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.14872289448976517,
|
|
"num_tokens": 18043171.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.284806537628174,
|
|
"epoch": 0.9221772379667117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004923858730888762,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.17093055695295334,
|
|
"num_tokens": 18052567.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.302040910720825,
|
|
"epoch": 0.9226770630279402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000492376664506679,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.16670629680156707,
|
|
"num_tokens": 18061648.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.2984199047088625,
|
|
"epoch": 0.9231768880891688,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004923674504553408,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.16013550013303757,
|
|
"num_tokens": 18071079.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.309845352172852,
|
|
"epoch": 0.9236767131503973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004923582309350935,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.15939266607165337,
|
|
"num_tokens": 18081162.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.374463319778442,
|
|
"epoch": 0.9241765382116259,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492349005946169,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.16179885268211364,
|
|
"num_tokens": 18090072.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.353137826919555,
|
|
"epoch": 0.9246763632728545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923397754887994,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1594219610095024,
|
|
"num_tokens": 18100565.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.278534746170044,
|
|
"epoch": 0.9251761883340831,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004923305395632172,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.1588011935353279,
|
|
"num_tokens": 18109795.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.363600254058838,
|
|
"epoch": 0.9256760133953117,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923212981696543,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.15104192048311232,
|
|
"num_tokens": 18118821.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.314014148712158,
|
|
"epoch": 0.9261758384565402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004923120513083436,
|
|
"loss": 6.0169,
|
|
"mean_token_accuracy": 0.1619693875312805,
|
|
"num_tokens": 18128709.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.267874670028687,
|
|
"epoch": 0.9266756635177688,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004923027989795175,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.15080320909619332,
|
|
"num_tokens": 18138134.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.295729064941407,
|
|
"epoch": 0.9271754885789973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492293541183409,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.16175611466169357,
|
|
"num_tokens": 18147455.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.291168880462647,
|
|
"epoch": 0.9276753136402259,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004922842779202509,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.16404477655887603,
|
|
"num_tokens": 18157787.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.203155040740967,
|
|
"epoch": 0.9281751387014545,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004922750091902763,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.16532714813947677,
|
|
"num_tokens": 18167607.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.299008798599243,
|
|
"epoch": 0.9286749637626831,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004922657349937183,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.15551928877830506,
|
|
"num_tokens": 18178927.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.259000301361084,
|
|
"epoch": 0.9291747888239116,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004922564553308103,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.16854237169027328,
|
|
"num_tokens": 18188907.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.328156423568726,
|
|
"epoch": 0.9296746138851402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000492247170201786,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.1687764123082161,
|
|
"num_tokens": 18198937.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.309473371505737,
|
|
"epoch": 0.9301744389463688,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004922378796068785,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.16050454676151277,
|
|
"num_tokens": 18209306.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.357786846160889,
|
|
"epoch": 0.9306742640075973,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492228583546322,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.1474974423646927,
|
|
"num_tokens": 18219665.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.310727310180664,
|
|
"epoch": 0.9311740890688259,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004922192820203502,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.16298379004001617,
|
|
"num_tokens": 18229044.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.281115770339966,
|
|
"epoch": 0.9316739141300545,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004922099750291972,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.17023476362228393,
|
|
"num_tokens": 18239373.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.279518747329712,
|
|
"epoch": 0.9321737391912831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922006625730971,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.16142186969518663,
|
|
"num_tokens": 18249195.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.289080429077148,
|
|
"epoch": 0.9326735642525116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921913446522843,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.16744708120822907,
|
|
"num_tokens": 18258399.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.275579977035522,
|
|
"epoch": 0.9331733893137402,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000492182021266993,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.17046610414981841,
|
|
"num_tokens": 18268952.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.308241987228394,
|
|
"epoch": 0.9336732143749688,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000492172692417458,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.16183677092194557,
|
|
"num_tokens": 18279482.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.264645004272461,
|
|
"epoch": 0.9341730394361973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492163358103914,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.16305636316537858,
|
|
"num_tokens": 18289069.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.249431562423706,
|
|
"epoch": 0.9346728644974259,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004921540183265957,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.16541763246059418,
|
|
"num_tokens": 18298333.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.317691516876221,
|
|
"epoch": 0.9351726895586545,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004921446730857383,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.15929910838603972,
|
|
"num_tokens": 18307661.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.326679372787476,
|
|
"epoch": 0.935672514619883,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004921353223815767,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15444227010011674,
|
|
"num_tokens": 18317786.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.322533082962036,
|
|
"epoch": 0.9361723396811116,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004921259662143463,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.15629378110170364,
|
|
"num_tokens": 18328430.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.311990976333618,
|
|
"epoch": 0.9366721647423402,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004921166045842825,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.15643913596868514,
|
|
"num_tokens": 18339800.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.39114146232605,
|
|
"epoch": 0.9371719898035688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921072374916208,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.15216109305620193,
|
|
"num_tokens": 18348819.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.266355848312378,
|
|
"epoch": 0.9376718148647973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920978649365968,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.16932181715965272,
|
|
"num_tokens": 18358189.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.252970361709595,
|
|
"epoch": 0.9381716399260259,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004920884869194463,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.16228022575378417,
|
|
"num_tokens": 18367571.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.248996639251709,
|
|
"epoch": 0.9386714649872545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920791034404054,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.16511135995388032,
|
|
"num_tokens": 18376699.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.225177669525147,
|
|
"epoch": 0.939171290048483,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004920697144997102,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.1642061799764633,
|
|
"num_tokens": 18386036.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.239754772186279,
|
|
"epoch": 0.9396711151097116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920603200975968,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.17044914811849593,
|
|
"num_tokens": 18395363.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.283936023712158,
|
|
"epoch": 0.9401709401709402,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004920509202343016,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.15649334639310836,
|
|
"num_tokens": 18404919.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.308973598480224,
|
|
"epoch": 0.9406707652321687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492041514910061,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.16177840381860734,
|
|
"num_tokens": 18413520.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.327735137939453,
|
|
"epoch": 0.9411705902933973,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004920321041251118,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.16363254487514495,
|
|
"num_tokens": 18422942.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.373079395294189,
|
|
"epoch": 0.9416704153546259,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920226878796908,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15781474709510804,
|
|
"num_tokens": 18432782.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.319165658950806,
|
|
"epoch": 0.9421702404158544,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004920132661740348,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.16029011309146882,
|
|
"num_tokens": 18443058.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.287378215789795,
|
|
"epoch": 0.942670065477083,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920038390083808,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.16289011538028716,
|
|
"num_tokens": 18453138.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.266214656829834,
|
|
"epoch": 0.9431698905383116,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000491994406382966,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.15762582570314407,
|
|
"num_tokens": 18463763.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.323658275604248,
|
|
"epoch": 0.9436697155995402,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919849682980278,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.16068675518035888,
|
|
"num_tokens": 18473391.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.302414131164551,
|
|
"epoch": 0.9441695406607687,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919755247538037,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.15908005982637405,
|
|
"num_tokens": 18483002.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.315402889251709,
|
|
"epoch": 0.9446693657219973,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004919660757505312,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.16382649466395377,
|
|
"num_tokens": 18493428.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.326154041290283,
|
|
"epoch": 0.9451691907832259,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004919566212884481,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.15803915411233901,
|
|
"num_tokens": 18502756.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.336827802658081,
|
|
"epoch": 0.9456690158444544,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004919471613677921,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.15630435049533845,
|
|
"num_tokens": 18512576.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.287117338180542,
|
|
"epoch": 0.946168840905683,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004919376959888015,
|
|
"loss": 5.8946,
|
|
"mean_token_accuracy": 0.1617352396249771,
|
|
"num_tokens": 18522271.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.214782953262329,
|
|
"epoch": 0.9466686659669116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919282251517142,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.16643785685300827,
|
|
"num_tokens": 18532738.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.34790358543396,
|
|
"epoch": 0.9471684910281402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004919187488567686,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.16215639263391496,
|
|
"num_tokens": 18543132.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.272147369384766,
|
|
"epoch": 0.9476683160893687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004919092671042031,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.16845880299806595,
|
|
"num_tokens": 18551777.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.2397387504577635,
|
|
"epoch": 0.9481681411505973,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004918997798942562,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.16377705931663514,
|
|
"num_tokens": 18561137.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.267127609252929,
|
|
"epoch": 0.9486679662118258,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004918902872271668,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.1607971578836441,
|
|
"num_tokens": 18571917.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.348388910293579,
|
|
"epoch": 0.9491677912730544,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004918807891031734,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.16225840151309967,
|
|
"num_tokens": 18581670.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.2437046527862545,
|
|
"epoch": 0.949667616334283,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004918712855225154,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.16519014686346054,
|
|
"num_tokens": 18590140.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.164170503616333,
|
|
"epoch": 0.9501674413955116,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918617764854314,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.16923921108245848,
|
|
"num_tokens": 18599496.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.259040212631225,
|
|
"epoch": 0.9506672664567402,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000491852261992161,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.16660645604133606,
|
|
"num_tokens": 18609415.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.315243244171143,
|
|
"epoch": 0.9511670915179687,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918427420429435,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.15893747210502623,
|
|
"num_tokens": 18619215.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.362841653823852,
|
|
"epoch": 0.9516669165791973,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004918332166380185,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.16086530983448027,
|
|
"num_tokens": 18629381.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.250789642333984,
|
|
"epoch": 0.9521667416404258,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918236857776254,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.1652715116739273,
|
|
"num_tokens": 18639049.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.29691219329834,
|
|
"epoch": 0.9526665667016544,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004918141494620042,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.15976498275995255,
|
|
"num_tokens": 18649096.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.298697519302368,
|
|
"epoch": 0.953166391762883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004918046076913949,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.16505347937345505,
|
|
"num_tokens": 18658747.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.312511777877807,
|
|
"epoch": 0.9536662168241116,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004917950604660374,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.15731937438249588,
|
|
"num_tokens": 18668538.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.322397994995117,
|
|
"epoch": 0.9541660418853402,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000491785507786172,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.16249953359365463,
|
|
"num_tokens": 18679241.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.277149963378906,
|
|
"epoch": 0.9546658669465687,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004917759496520388,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.16174120604991912,
|
|
"num_tokens": 18689405.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.347413158416748,
|
|
"epoch": 0.9551656920077972,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004917663860638787,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.1545250356197357,
|
|
"num_tokens": 18697989.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.217179775238037,
|
|
"epoch": 0.9556655170690258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917568170219321,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.15835018903017045,
|
|
"num_tokens": 18706992.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.239038562774658,
|
|
"epoch": 0.9561653421302544,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004917472425264397,
|
|
"loss": 5.954,
|
|
"mean_token_accuracy": 0.15670762509107589,
|
|
"num_tokens": 18716742.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.327638101577759,
|
|
"epoch": 0.956665167191483,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004917376625776425,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.14651284366846085,
|
|
"num_tokens": 18725955.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.319440412521362,
|
|
"epoch": 0.9571649922527116,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917280771757814,
|
|
"loss": 5.9911,
|
|
"mean_token_accuracy": 0.1598081722855568,
|
|
"num_tokens": 18735199.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.315985059738159,
|
|
"epoch": 0.9576648173139402,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004917184863210977,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.15414370596408844,
|
|
"num_tokens": 18745457.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.366096544265747,
|
|
"epoch": 0.9581646423751687,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004917088900138326,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.15633195638656616,
|
|
"num_tokens": 18753869.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.32596001625061,
|
|
"epoch": 0.9586644674363972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916992882542276,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.1638189285993576,
|
|
"num_tokens": 18763022.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.27228569984436,
|
|
"epoch": 0.9591642924976258,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916896810425244,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.1667642131447792,
|
|
"num_tokens": 18772827.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.255521297454834,
|
|
"epoch": 0.9596641175588544,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916800683789645,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.16418609917163848,
|
|
"num_tokens": 18782272.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.271367454528809,
|
|
"epoch": 0.960163942620083,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916704502637897,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.15618413537740708,
|
|
"num_tokens": 18792125.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.274318885803223,
|
|
"epoch": 0.9606637676813116,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004916608266972422,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.16815245598554612,
|
|
"num_tokens": 18801498.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.353711843490601,
|
|
"epoch": 0.9611635927425402,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004916511976795642,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15661515295505524,
|
|
"num_tokens": 18811904.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.305003976821899,
|
|
"epoch": 0.9616634178037686,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004916415632109977,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.1630036637187004,
|
|
"num_tokens": 18821388.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.338581609725952,
|
|
"epoch": 0.9621632428649972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004916319232917852,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.16478827148675917,
|
|
"num_tokens": 18831392.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.295579528808593,
|
|
"epoch": 0.9626630679262258,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004916222779221694,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.16178267151117326,
|
|
"num_tokens": 18841211.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.347203588485717,
|
|
"epoch": 0.9631628929874544,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004916126271023926,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.16324140578508378,
|
|
"num_tokens": 18851033.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.258472490310669,
|
|
"epoch": 0.963662718048683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000491602970832698,
|
|
"loss": 5.9949,
|
|
"mean_token_accuracy": 0.16093525290489197,
|
|
"num_tokens": 18861439.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.307986736297607,
|
|
"epoch": 0.9641625431099116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915933091133284,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.15441488921642305,
|
|
"num_tokens": 18872056.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.325292348861694,
|
|
"epoch": 0.9646623681711401,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004915836419445268,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.1681361436843872,
|
|
"num_tokens": 18881540.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.247510957717895,
|
|
"epoch": 0.9651621932323686,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004915739693265365,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.16275075525045396,
|
|
"num_tokens": 18890466.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.254362297058106,
|
|
"epoch": 0.9656620182935972,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004915642912596009,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.15671503096818923,
|
|
"num_tokens": 18901397.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.2999852180480955,
|
|
"epoch": 0.9661618433548258,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004915546077439634,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.16803510189056398,
|
|
"num_tokens": 18911357.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.242397880554199,
|
|
"epoch": 0.9666616684160544,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004915449187798677,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.17770696580410003,
|
|
"num_tokens": 18920901.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.299816608428955,
|
|
"epoch": 0.967161493477283,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915352243675576,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.15782807767391205,
|
|
"num_tokens": 18931012.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.315431785583496,
|
|
"epoch": 0.9676613185385116,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000491525524507277,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.15936478227376938,
|
|
"num_tokens": 18941222.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.351514101028442,
|
|
"epoch": 0.96816114359974,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004915158191992699,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.15829297676682472,
|
|
"num_tokens": 18951073.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.3209422588348385,
|
|
"epoch": 0.9686609686609686,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004915061084437805,
|
|
"loss": 5.9965,
|
|
"mean_token_accuracy": 0.1606003910303116,
|
|
"num_tokens": 18960996.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.336945819854736,
|
|
"epoch": 0.9691607937221972,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004914963922410531,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.15426791608333587,
|
|
"num_tokens": 18970451.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.247201919555664,
|
|
"epoch": 0.9696606187834258,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004914866705913322,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.16017961055040358,
|
|
"num_tokens": 18979781.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.3247088432312015,
|
|
"epoch": 0.9701604438446544,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004914769434948623,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.16198552995920182,
|
|
"num_tokens": 18989663.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.2786938667297365,
|
|
"epoch": 0.970660268905883,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004914672109518883,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.15743749290704728,
|
|
"num_tokens": 18999613.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.225006437301635,
|
|
"epoch": 0.9711600939671116,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000491457472962655,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.172476364672184,
|
|
"num_tokens": 19008976.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.27231011390686,
|
|
"epoch": 0.97165991902834,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004914477295274073,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.1651044949889183,
|
|
"num_tokens": 19019013.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.344321060180664,
|
|
"epoch": 0.9721597440895686,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914379806463905,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.1558752790093422,
|
|
"num_tokens": 19029252.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.291296720504761,
|
|
"epoch": 0.9726595691507972,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004914282263198498,
|
|
"loss": 5.9616,
|
|
"mean_token_accuracy": 0.15710996240377426,
|
|
"num_tokens": 19038563.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.299259853363037,
|
|
"epoch": 0.9731593942120258,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004914184665480305,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15925637632608414,
|
|
"num_tokens": 19048568.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.206225490570068,
|
|
"epoch": 0.9736592192732544,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004914087013311784,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.1747054398059845,
|
|
"num_tokens": 19057527.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.27301058769226,
|
|
"epoch": 0.974159044334483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004913989306695389,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.16284987181425095,
|
|
"num_tokens": 19067372.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.184207153320313,
|
|
"epoch": 0.9746588693957114,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004913891545633582,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.16800097227096558,
|
|
"num_tokens": 19077521.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.27860460281372,
|
|
"epoch": 0.97515869445694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000491379373012882,
|
|
"loss": 5.8951,
|
|
"mean_token_accuracy": 0.16490065157413483,
|
|
"num_tokens": 19086674.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.33745493888855,
|
|
"epoch": 0.9756585195181686,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913695860183563,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.15137081891298293,
|
|
"num_tokens": 19097586.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.335993814468384,
|
|
"epoch": 0.9761583445793972,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004913597935800276,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.15008579194545746,
|
|
"num_tokens": 19107763.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.294979810714722,
|
|
"epoch": 0.9766581696406258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004913499956981422,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.17213923633098602,
|
|
"num_tokens": 19117931.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.27452540397644,
|
|
"epoch": 0.9771579947018544,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004913401923729465,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.16334527283906936,
|
|
"num_tokens": 19127707.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.220709657669067,
|
|
"epoch": 0.977657819763083,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004913303836046873,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.16490644663572313,
|
|
"num_tokens": 19137633.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.297032165527344,
|
|
"epoch": 0.9781576448243114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913205693936112,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.16249869912862777,
|
|
"num_tokens": 19146247.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.186648607254028,
|
|
"epoch": 0.97865746988554,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004913107497399653,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.17878171801567078,
|
|
"num_tokens": 19156225.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.275798416137695,
|
|
"epoch": 0.9791572949467686,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004913009246439966,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.16221326142549514,
|
|
"num_tokens": 19165763.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.2858813285827635,
|
|
"epoch": 0.9796571200079972,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004912910941059525,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.16459544152021408,
|
|
"num_tokens": 19174116.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.290776920318604,
|
|
"epoch": 0.9801569450692258,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004912812581260799,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.152647016197443,
|
|
"num_tokens": 19184416.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.35810227394104,
|
|
"epoch": 0.9806567701304544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004912714167046265,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.15895965397357942,
|
|
"num_tokens": 19193356.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.249219036102295,
|
|
"epoch": 0.9811565951916829,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004912615698418399,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.17790618538856506,
|
|
"num_tokens": 19204257.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.327652788162231,
|
|
"epoch": 0.9816564202529114,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004912517175379679,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.16282433718442918,
|
|
"num_tokens": 19213889.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.3349356174469,
|
|
"epoch": 0.98215624531414,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004912418597932584,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.15698160082101822,
|
|
"num_tokens": 19224008.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.309502410888672,
|
|
"epoch": 0.9826560703753686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004912319966079592,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.16029830425977706,
|
|
"num_tokens": 19234247.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.3602294921875,
|
|
"epoch": 0.9831558954365972,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004912221279823187,
|
|
"loss": 6.0151,
|
|
"mean_token_accuracy": 0.16117426604032517,
|
|
"num_tokens": 19244838.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.2874195098876955,
|
|
"epoch": 0.9836557204978258,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004912122539165851,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.1653192162513733,
|
|
"num_tokens": 19254989.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.279850673675537,
|
|
"epoch": 0.9841555455590544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912023744110068,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.15936510264873505,
|
|
"num_tokens": 19264519.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.265829372406006,
|
|
"epoch": 0.9846553706202829,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911924894658324,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.1664997473359108,
|
|
"num_tokens": 19274153.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.246427297592163,
|
|
"epoch": 0.9851551956815114,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004911825990813107,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.16345445066690445,
|
|
"num_tokens": 19283383.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.249483346939087,
|
|
"epoch": 0.98565502074274,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004911727032576903,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.16487012207508087,
|
|
"num_tokens": 19292758.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.306307411193847,
|
|
"epoch": 0.9861548458039686,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004911628019952203,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15553745329380037,
|
|
"num_tokens": 19302339.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.259342241287231,
|
|
"epoch": 0.9866546708651972,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004911528952941499,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.17182450592517853,
|
|
"num_tokens": 19312560.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.260993242263794,
|
|
"epoch": 0.9871544959264258,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911429831547283,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.17111795842647554,
|
|
"num_tokens": 19322796.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.262640953063965,
|
|
"epoch": 0.9876543209876543,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004911330655772047,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.1609895870089531,
|
|
"num_tokens": 19332719.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.287845802307129,
|
|
"epoch": 0.9881541460488829,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000491123142561829,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.1614077642560005,
|
|
"num_tokens": 19342226.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.260968160629273,
|
|
"epoch": 0.9886539711101114,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004911132141088505,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.15654188990592957,
|
|
"num_tokens": 19351933.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.333012390136719,
|
|
"epoch": 0.98915379617134,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004911032802185192,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.15710337162017823,
|
|
"num_tokens": 19359900.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.298925828933716,
|
|
"epoch": 0.9896536212325686,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491093340891085,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.1622732937335968,
|
|
"num_tokens": 19369139.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.250660181045532,
|
|
"epoch": 0.9901534462937972,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910833961267979,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.16304486691951753,
|
|
"num_tokens": 19378765.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.314934778213501,
|
|
"epoch": 0.9906532713550258,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910734459259081,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.15936781466007233,
|
|
"num_tokens": 19389001.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.27076735496521,
|
|
"epoch": 0.9911530964162543,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910634902886662,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.17139992713928223,
|
|
"num_tokens": 19397990.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.131765270233155,
|
|
"epoch": 0.9916529214774829,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004910535292153224,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.170303837954998,
|
|
"num_tokens": 19408060.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.210762691497803,
|
|
"epoch": 0.9921527465387114,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910435627061273,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.16619687378406525,
|
|
"num_tokens": 19417675.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.283784055709839,
|
|
"epoch": 0.99265257159994,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004910335907613318,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.16708033084869384,
|
|
"num_tokens": 19426433.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.256158351898193,
|
|
"epoch": 0.9931523966611686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004910236133811867,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.17176613509654998,
|
|
"num_tokens": 19435459.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.24712495803833,
|
|
"epoch": 0.9936522217223972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910136305659432,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.16299450695514678,
|
|
"num_tokens": 19445329.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.267837190628052,
|
|
"epoch": 0.9941520467836257,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004910036423158523,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.17023808360099793,
|
|
"num_tokens": 19454417.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.286039590835571,
|
|
"epoch": 0.9946518718448543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909936486311653,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.1573632001876831,
|
|
"num_tokens": 19464274.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.304116439819336,
|
|
"epoch": 0.9951516969060828,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004909836495121336,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.16261430829763412,
|
|
"num_tokens": 19472455.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.332637786865234,
|
|
"epoch": 0.9956515219673114,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004909736449590091,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.1577175110578537,
|
|
"num_tokens": 19483320.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.311175394058227,
|
|
"epoch": 0.99615134702854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000490963634972043,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.16232099682092666,
|
|
"num_tokens": 19493644.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.234761381149292,
|
|
"epoch": 0.9966511720897686,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909536195514875,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.16916954815387725,
|
|
"num_tokens": 19503035.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.272039794921875,
|
|
"epoch": 0.9971509971509972,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004909435986975946,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.16535471081733705,
|
|
"num_tokens": 19512254.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.262616205215454,
|
|
"epoch": 0.9976508222122257,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004909335724106162,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.170557664334774,
|
|
"num_tokens": 19523114.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.277891397476196,
|
|
"epoch": 0.9981506472734543,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004909235406908047,
|
|
"loss": 5.9537,
|
|
"mean_token_accuracy": 0.15898052603006363,
|
|
"num_tokens": 19532940.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.233804845809937,
|
|
"epoch": 0.9986504723346828,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004909135035384126,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.1644645467400551,
|
|
"num_tokens": 19542807.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.210470294952392,
|
|
"epoch": 0.9991502973959114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909034609536922,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.1664857655763626,
|
|
"num_tokens": 19552099.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.283058404922485,
|
|
"epoch": 0.99965012245714,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004908934129368963,
|
|
"loss": 5.8846,
|
|
"mean_token_accuracy": 0.1699151486158371,
|
|
"num_tokens": 19561709.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.263562626308865,
|
|
"epoch": 1.0000999650122457,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004908833594882777,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.16419489019446903,
|
|
"num_tokens": 19571739.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.327613735198975,
|
|
"epoch": 1.0005997900734742,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004908733006080893,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16759713888168334,
|
|
"num_tokens": 19582084.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.217071151733398,
|
|
"epoch": 1.001099615134703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004908632362965842,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.1604842260479927,
|
|
"num_tokens": 19591889.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.328868293762207,
|
|
"epoch": 1.0015994401959314,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004908531665540158,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.16043253093957902,
|
|
"num_tokens": 19601998.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.251083660125732,
|
|
"epoch": 1.00209926525716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490843091380637,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.1771794304251671,
|
|
"num_tokens": 19611347.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.312647294998169,
|
|
"epoch": 1.0025990903183886,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004908330107767018,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.17213153094053268,
|
|
"num_tokens": 19621522.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.254507160186767,
|
|
"epoch": 1.003098915379617,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908229247424633,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.17775459736585617,
|
|
"num_tokens": 19630815.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.2791633129119875,
|
|
"epoch": 1.0035987404408457,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004908128332781758,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.1748511791229248,
|
|
"num_tokens": 19640811.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.2577183723449705,
|
|
"epoch": 1.0040985655020742,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004908027363840928,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.17004597187042236,
|
|
"num_tokens": 19651335.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.23187747001648,
|
|
"epoch": 1.004598390563303,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004907926340604686,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.17143816351890565,
|
|
"num_tokens": 19660242.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.2966334342956545,
|
|
"epoch": 1.0050982156245314,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004907825263075573,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.16222339123487473,
|
|
"num_tokens": 19670013.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.267981004714966,
|
|
"epoch": 1.00559804068576,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004907724131256129,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.17664390951395034,
|
|
"num_tokens": 19679479.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.209923648834229,
|
|
"epoch": 1.0060978657469886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004907622945148903,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16942853331565857,
|
|
"num_tokens": 19688603.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.238440704345703,
|
|
"epoch": 1.006597690808217,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004907521704756438,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.16366230845451354,
|
|
"num_tokens": 19698375.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.264004468917847,
|
|
"epoch": 1.0070975158694457,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004907420410081284,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.16740598231554032,
|
|
"num_tokens": 19708911.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.231882476806641,
|
|
"epoch": 1.0075973409306742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004907319061125986,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.1652328699827194,
|
|
"num_tokens": 19717733.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.186142492294311,
|
|
"epoch": 1.008097165991903,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004907217657893096,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.16232636719942092,
|
|
"num_tokens": 19727192.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.2018595218658445,
|
|
"epoch": 1.0085969910531314,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004907116200385165,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.17150129824876786,
|
|
"num_tokens": 19737937.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.254257535934448,
|
|
"epoch": 1.00909681611436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004907014688604745,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.1666605219244957,
|
|
"num_tokens": 19748270.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.157501983642578,
|
|
"epoch": 1.0095966411755886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906913122554391,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.18495073914527893,
|
|
"num_tokens": 19758328.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.199046325683594,
|
|
"epoch": 1.010096466236817,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004906811502236657,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.1738783448934555,
|
|
"num_tokens": 19767780.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.293070697784424,
|
|
"epoch": 1.0105962912980457,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004906709827654101,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.16269650012254716,
|
|
"num_tokens": 19777202.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.234905576705932,
|
|
"epoch": 1.0110961163592742,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906608098809281,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.16912003010511398,
|
|
"num_tokens": 19788341.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.298268556594849,
|
|
"epoch": 1.011595941420503,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906506315704756,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.1660432666540146,
|
|
"num_tokens": 19797511.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.30206618309021,
|
|
"epoch": 1.0120957664817314,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004906404478343087,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.1706247881054878,
|
|
"num_tokens": 19807639.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.400612306594849,
|
|
"epoch": 1.0125955915429599,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004906302586726837,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.1562906414270401,
|
|
"num_tokens": 19818379.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.214356470108032,
|
|
"epoch": 1.0130954166041886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906200640858567,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.17587951570749283,
|
|
"num_tokens": 19828706.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.241750478744507,
|
|
"epoch": 1.013595241665417,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004906098640740846,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.179512819647789,
|
|
"num_tokens": 19838361.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.2757568359375,
|
|
"epoch": 1.0140950667266457,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004905996586376236,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.1710798054933548,
|
|
"num_tokens": 19848205.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.264225578308105,
|
|
"epoch": 1.0145948917878742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905894477767308,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.1656733989715576,
|
|
"num_tokens": 19858490.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.282264471054077,
|
|
"epoch": 1.015094716849103,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004905792314916629,
|
|
"loss": 5.8874,
|
|
"mean_token_accuracy": 0.17004922926425933,
|
|
"num_tokens": 19867551.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.278075790405273,
|
|
"epoch": 1.0155945419103314,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004905690097826769,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.16662276536226273,
|
|
"num_tokens": 19877581.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.369448137283325,
|
|
"epoch": 1.0160943669715599,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004905587826500303,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.16173219084739685,
|
|
"num_tokens": 19887827.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.289686155319214,
|
|
"epoch": 1.0165941920327886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004905485500939801,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.16599084436893463,
|
|
"num_tokens": 19897395.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.23954291343689,
|
|
"epoch": 1.017094017094017,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004905383121147838,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.1634050726890564,
|
|
"num_tokens": 19906601.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.264119577407837,
|
|
"epoch": 1.0175938421552457,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905280687126991,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.17033000737428666,
|
|
"num_tokens": 19916422.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.323351621627808,
|
|
"epoch": 1.0180936672164742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905178198879837,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.16748514175415039,
|
|
"num_tokens": 19927182.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.312600994110108,
|
|
"epoch": 1.018593492277703,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004905075656408953,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.15898788422346116,
|
|
"num_tokens": 19936537.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.28385214805603,
|
|
"epoch": 1.0190933173389314,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000490497305971692,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.16742823272943497,
|
|
"num_tokens": 19946315.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.250877761840821,
|
|
"epoch": 1.0195931424001599,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000490487040880632,
|
|
"loss": 5.7795,
|
|
"mean_token_accuracy": 0.16757286787033082,
|
|
"num_tokens": 19956145.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.2867772579193115,
|
|
"epoch": 1.0200929674613886,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004904767703679735,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1618366777896881,
|
|
"num_tokens": 19966890.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.294345092773438,
|
|
"epoch": 1.020592792522617,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004904664944339748,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.1625969648361206,
|
|
"num_tokens": 19976156.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.240063714981079,
|
|
"epoch": 1.0210926175838457,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904562130788947,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.17214999198913575,
|
|
"num_tokens": 19985851.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.209962320327759,
|
|
"epoch": 1.0215924426450742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004904459263029916,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1713658407330513,
|
|
"num_tokens": 19996531.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.293245649337768,
|
|
"epoch": 1.0220922677063027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904356341065245,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.17652123421430588,
|
|
"num_tokens": 20006050.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.310912704467773,
|
|
"epoch": 1.0225920927675314,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904253364897521,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.16106410473585128,
|
|
"num_tokens": 20015997.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.329140281677246,
|
|
"epoch": 1.0230919178287599,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004904150334529339,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.1575968712568283,
|
|
"num_tokens": 20026682.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.287328624725342,
|
|
"epoch": 1.0235917428899886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004904047249963289,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.1656009688973427,
|
|
"num_tokens": 20036166.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.2610307216644285,
|
|
"epoch": 1.024091567951217,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004903944111201964,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.17885891497135162,
|
|
"num_tokens": 20045545.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.306422472000122,
|
|
"epoch": 1.0245913930124457,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004903840918247958,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.16581542938947677,
|
|
"num_tokens": 20055072.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.314145708084107,
|
|
"epoch": 1.0250912180736742,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000490373767110387,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1623193085193634,
|
|
"num_tokens": 20064227.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.29743390083313,
|
|
"epoch": 1.0255910431349027,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004903634369772296,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.17113954871892928,
|
|
"num_tokens": 20074833.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.273669099807739,
|
|
"epoch": 1.0260908681961314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903531014255835,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16053743809461593,
|
|
"num_tokens": 20084340.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.283122301101685,
|
|
"epoch": 1.0265906932573599,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004903427604557089,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.1716426745057106,
|
|
"num_tokens": 20094372.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.272064971923828,
|
|
"epoch": 1.0270905183185886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004903324140678658,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.1677790626883507,
|
|
"num_tokens": 20104015.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.282415866851807,
|
|
"epoch": 1.027590343379817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004903220622623146,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.16924111992120744,
|
|
"num_tokens": 20113570.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.323736715316772,
|
|
"epoch": 1.0280901684410457,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004903117050393157,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.16146879494190217,
|
|
"num_tokens": 20124147.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.2693640232086185,
|
|
"epoch": 1.0285899935022742,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004903013423991296,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.16235486119985582,
|
|
"num_tokens": 20134310.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.244448137283325,
|
|
"epoch": 1.0290898185635027,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004902909743420173,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.1670222222805023,
|
|
"num_tokens": 20143894.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.30369610786438,
|
|
"epoch": 1.0295896436247314,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004902806008682394,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.1713735431432724,
|
|
"num_tokens": 20154862.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.24873628616333,
|
|
"epoch": 1.0300894686859599,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490270221978057,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.17258377373218536,
|
|
"num_tokens": 20164109.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.291932249069214,
|
|
"epoch": 1.0305892937471886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004902598376717312,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.15959929451346397,
|
|
"num_tokens": 20173971.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.2705787181854244,
|
|
"epoch": 1.031089118808417,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004902494479495233,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.16017400175333024,
|
|
"num_tokens": 20183683.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.247957754135132,
|
|
"epoch": 1.0315889438696457,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004902390528116946,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16870912164449692,
|
|
"num_tokens": 20192945.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.278894472122192,
|
|
"epoch": 1.0320887689308742,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004902286522585068,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.1700470119714737,
|
|
"num_tokens": 20202919.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.25832724571228,
|
|
"epoch": 1.0325885939921027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902182462902215,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.17647095620632172,
|
|
"num_tokens": 20212377.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.231448936462402,
|
|
"epoch": 1.0330884190533314,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902078349071004,
|
|
"loss": 5.7593,
|
|
"mean_token_accuracy": 0.17787338942289352,
|
|
"num_tokens": 20221083.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.274268245697021,
|
|
"epoch": 1.0335882441145599,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004901974181094057,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.16650898456573487,
|
|
"num_tokens": 20229577.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.2623707294464115,
|
|
"epoch": 1.0340880691757885,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901869958973991,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.17573138177394867,
|
|
"num_tokens": 20238400.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.245430994033813,
|
|
"epoch": 1.034587894237017,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901765682713432,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.1685774117708206,
|
|
"num_tokens": 20248479.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.256780195236206,
|
|
"epoch": 1.0350877192982457,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901661352315003,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.16757914274930955,
|
|
"num_tokens": 20258268.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.278981733322143,
|
|
"epoch": 1.0355875443594742,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004901556967781327,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.1720331773161888,
|
|
"num_tokens": 20267924.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.296961784362793,
|
|
"epoch": 1.0360873694207027,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004901452529115031,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.16561548709869384,
|
|
"num_tokens": 20278173.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.218019247055054,
|
|
"epoch": 1.0365871944819314,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004901348036318743,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.17286520153284074,
|
|
"num_tokens": 20287557.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.286599349975586,
|
|
"epoch": 1.0370870195431598,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004901243489395093,
|
|
"loss": 5.9316,
|
|
"mean_token_accuracy": 0.16526877731084824,
|
|
"num_tokens": 20297517.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.273164892196656,
|
|
"epoch": 1.0375868446043885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000490113888834671,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.17497787326574327,
|
|
"num_tokens": 20308029.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.172546100616455,
|
|
"epoch": 1.038086669665617,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004901034233176227,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.17826071083545686,
|
|
"num_tokens": 20318962.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.305340766906738,
|
|
"epoch": 1.0385864947268455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004900929523886274,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.1605779528617859,
|
|
"num_tokens": 20328729.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.303232288360595,
|
|
"epoch": 1.0390863197880742,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000490082476047949,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.15879374295473098,
|
|
"num_tokens": 20339002.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.269267559051514,
|
|
"epoch": 1.0395861448493027,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004900719942958506,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.18102378249168397,
|
|
"num_tokens": 20347869.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.143037557601929,
|
|
"epoch": 1.0400859699105314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900615071325963,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.1793408513069153,
|
|
"num_tokens": 20356609.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.201200294494629,
|
|
"epoch": 1.0405857949717598,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049005101455845,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.1820556640625,
|
|
"num_tokens": 20368793.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.2268714427948,
|
|
"epoch": 1.0410856200329885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900405165736753,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.17418347746133805,
|
|
"num_tokens": 20379525.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.306217336654663,
|
|
"epoch": 1.041585445094217,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900300131785365,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.17308982759714125,
|
|
"num_tokens": 20388253.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.199152612686158,
|
|
"epoch": 1.0420852701554455,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000490019504373298,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.16624206006526948,
|
|
"num_tokens": 20398086.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.2411740779876705,
|
|
"epoch": 1.0425850952166742,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900089901582241,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.16309795379638672,
|
|
"num_tokens": 20408113.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.334460639953614,
|
|
"epoch": 1.0430849202779027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004899984705335792,
|
|
"loss": 5.8865,
|
|
"mean_token_accuracy": 0.16618934273719788,
|
|
"num_tokens": 20417717.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.251717901229858,
|
|
"epoch": 1.0435847453391314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004899879454996282,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.1715273901820183,
|
|
"num_tokens": 20428307.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.212405347824097,
|
|
"epoch": 1.0440845704003598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004899774150566358,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.1688426062464714,
|
|
"num_tokens": 20437493.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.252768421173096,
|
|
"epoch": 1.0445843954615885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489966879204867,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.16880786120891572,
|
|
"num_tokens": 20448218.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.311066961288452,
|
|
"epoch": 1.045084220522817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004899563379445869,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.17348773330450057,
|
|
"num_tokens": 20457478.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.235060453414917,
|
|
"epoch": 1.0455840455840455,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004899457912760605,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.1694750264286995,
|
|
"num_tokens": 20466776.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.214666032791138,
|
|
"epoch": 1.0460838706452742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004899352391995533,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.17123496979475022,
|
|
"num_tokens": 20476461.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.237836503982544,
|
|
"epoch": 1.0465836957065027,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004899246817153309,
|
|
"loss": 5.8306,
|
|
"mean_token_accuracy": 0.16609944254159928,
|
|
"num_tokens": 20487022.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.2352241516113285,
|
|
"epoch": 1.0470835207677314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899141188236587,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.17418751269578933,
|
|
"num_tokens": 20496326.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.280617094039917,
|
|
"epoch": 1.0475833458289598,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004899035505248027,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.1697205752134323,
|
|
"num_tokens": 20504933.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.2450292110443115,
|
|
"epoch": 1.0480831708901883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898929768190286,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.17024991810321807,
|
|
"num_tokens": 20513931.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.158873510360718,
|
|
"epoch": 1.048582995951417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898823977066024,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.17965759783983232,
|
|
"num_tokens": 20523176.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.248373746871948,
|
|
"epoch": 1.0490828210126455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898718131877906,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.1649852216243744,
|
|
"num_tokens": 20533049.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.25427565574646,
|
|
"epoch": 1.0495826460738742,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004898612232628591,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.17336229234933853,
|
|
"num_tokens": 20542132.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.208258628845215,
|
|
"epoch": 1.0500824711351027,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898506279320745,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.16856057345867156,
|
|
"num_tokens": 20551779.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.2366392612457275,
|
|
"epoch": 1.0505822961963314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004898400271957034,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.1659865453839302,
|
|
"num_tokens": 20560548.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.288300466537476,
|
|
"epoch": 1.0510821212575598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898294210540126,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.1620687499642372,
|
|
"num_tokens": 20570909.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.381335973739624,
|
|
"epoch": 1.0515819463187883,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004898188095072688,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.16336330771446228,
|
|
"num_tokens": 20580367.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.2470130443573,
|
|
"epoch": 1.052081771380017,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489808192555739,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.17436877489089966,
|
|
"num_tokens": 20589653.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.206426191329956,
|
|
"epoch": 1.0525815964412455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004897975701996903,
|
|
"loss": 5.7875,
|
|
"mean_token_accuracy": 0.17152190655469896,
|
|
"num_tokens": 20599530.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.178856945037841,
|
|
"epoch": 1.0530814215024742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004897869424393902,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.1701964721083641,
|
|
"num_tokens": 20607989.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.230736875534058,
|
|
"epoch": 1.0535812465637027,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004897763092751057,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.16974607110023499,
|
|
"num_tokens": 20618315.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.2671589851379395,
|
|
"epoch": 1.0540810716249314,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004897656707071045,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.16907307207584382,
|
|
"num_tokens": 20627554.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.2750263690948485,
|
|
"epoch": 1.0545808966861598,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004897550267356545,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.16907401531934738,
|
|
"num_tokens": 20636841.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.230516719818115,
|
|
"epoch": 1.0550807217473883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004897443773610231,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.17434533983469008,
|
|
"num_tokens": 20647129.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.291663599014282,
|
|
"epoch": 1.055580546808617,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004897337225834785,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.1602578803896904,
|
|
"num_tokens": 20657971.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.27039942741394,
|
|
"epoch": 1.0560803718698455,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004897230624032888,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.16521901786327362,
|
|
"num_tokens": 20666266.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.302093744277954,
|
|
"epoch": 1.0565801969310742,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004897123968207219,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.1697933182120323,
|
|
"num_tokens": 20676454.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.1858570098876955,
|
|
"epoch": 1.0570800219923027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897017258360465,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.16921870708465575,
|
|
"num_tokens": 20687333.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.2232424259185795,
|
|
"epoch": 1.0575798470535314,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896910494495308,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.1740138202905655,
|
|
"num_tokens": 20696530.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.25609655380249,
|
|
"epoch": 1.0580796721147598,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004896803676614436,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.16981466561555864,
|
|
"num_tokens": 20706674.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.186701822280884,
|
|
"epoch": 1.0585794971759883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896696804720536,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1887897878885269,
|
|
"num_tokens": 20715695.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.239008951187134,
|
|
"epoch": 1.059079322237217,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004896589878816297,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.16783483624458312,
|
|
"num_tokens": 20725763.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.215407466888427,
|
|
"epoch": 1.0595791472984455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896482898904409,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.16836044937372208,
|
|
"num_tokens": 20734944.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.191200542449951,
|
|
"epoch": 1.0600789723596742,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896375864987563,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.17724661082029342,
|
|
"num_tokens": 20744951.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.209975719451904,
|
|
"epoch": 1.0605787974209027,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004896268777068453,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.17513211071491241,
|
|
"num_tokens": 20754937.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.255759954452515,
|
|
"epoch": 1.0610786224821314,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004896161635149773,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.16492398530244828,
|
|
"num_tokens": 20767373.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.255920028686523,
|
|
"epoch": 1.0615784475433598,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896054439234217,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16927689611911773,
|
|
"num_tokens": 20777647.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.243734979629517,
|
|
"epoch": 1.0620782726045883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004895947189324486,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.17779533565044403,
|
|
"num_tokens": 20788598.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.214111471176148,
|
|
"epoch": 1.062578097665817,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895839885423273,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.17242391556501388,
|
|
"num_tokens": 20798586.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.180407476425171,
|
|
"epoch": 1.0630779227270455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895732527533283,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.17524779438972474,
|
|
"num_tokens": 20807447.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.189729833602906,
|
|
"epoch": 1.0635777477882742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895625115657215,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.16953641623258592,
|
|
"num_tokens": 20817889.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.214007329940796,
|
|
"epoch": 1.0640775728495027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000489551764979777,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.16847578883171083,
|
|
"num_tokens": 20827858.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.230929899215698,
|
|
"epoch": 1.0645773979107314,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004895410129957653,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.17301045209169388,
|
|
"num_tokens": 20837114.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.276710176467896,
|
|
"epoch": 1.0650772229719598,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004895302556139569,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.16485681384801865,
|
|
"num_tokens": 20846979.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.223991537094117,
|
|
"epoch": 1.0655770480331883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895194928346226,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.1710292652249336,
|
|
"num_tokens": 20856831.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.21241192817688,
|
|
"epoch": 1.066076873094417,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000489508724658033,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.17350685596466064,
|
|
"num_tokens": 20866203.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.233049392700195,
|
|
"epoch": 1.0665766981556455,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000489497951084459,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.17279461473226548,
|
|
"num_tokens": 20875813.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.284146928787232,
|
|
"epoch": 1.0670765232168742,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894871721141718,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.1714742049574852,
|
|
"num_tokens": 20884773.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.196823024749756,
|
|
"epoch": 1.0675763482781027,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004894763877474426,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.1778479188680649,
|
|
"num_tokens": 20894305.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.227887344360352,
|
|
"epoch": 1.0680761733393311,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004894655979845427,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.16607076823711395,
|
|
"num_tokens": 20903849.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.251866149902344,
|
|
"epoch": 1.0685759984005598,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004894548028257434,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.17764956057071685,
|
|
"num_tokens": 20913380.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.214001607894898,
|
|
"epoch": 1.0690758234617883,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004894440022713165,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.1690727397799492,
|
|
"num_tokens": 20923921.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.2489522933959964,
|
|
"epoch": 1.069575648523017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894331963215337,
|
|
"loss": 5.7784,
|
|
"mean_token_accuracy": 0.17218806594610214,
|
|
"num_tokens": 20934613.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.24279375076294,
|
|
"epoch": 1.0700754735842455,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000489422384976667,
|
|
"loss": 5.8126,
|
|
"mean_token_accuracy": 0.17170547395944596,
|
|
"num_tokens": 20944052.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.245179462432861,
|
|
"epoch": 1.0705752986454742,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004894115682369881,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.17444587498903275,
|
|
"num_tokens": 20953406.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.3129113674163815,
|
|
"epoch": 1.0710751237067027,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004894007461027693,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.16140294075012207,
|
|
"num_tokens": 20963425.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.308528757095337,
|
|
"epoch": 1.0715749487679311,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004893899185742828,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.1595531776547432,
|
|
"num_tokens": 20973777.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.214809846878052,
|
|
"epoch": 1.0720747738291598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004893790856518014,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.17718849033117295,
|
|
"num_tokens": 20983418.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.166527223587036,
|
|
"epoch": 1.0725745988903883,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004893682473355972,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.17622092515230178,
|
|
"num_tokens": 20993051.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.190851545333862,
|
|
"epoch": 1.073074423951617,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004893574036259432,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.18105995655059814,
|
|
"num_tokens": 21003439.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.294794416427612,
|
|
"epoch": 1.0735742490128455,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004893465545231119,
|
|
"loss": 5.807,
|
|
"mean_token_accuracy": 0.17442636787891388,
|
|
"num_tokens": 21013242.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.225676870346069,
|
|
"epoch": 1.074074074074074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004893357000273765,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.17102200388908387,
|
|
"num_tokens": 21022268.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.2257468700408936,
|
|
"epoch": 1.0745738991353027,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048932484013901,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.16639198809862138,
|
|
"num_tokens": 21032130.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.191459083557129,
|
|
"epoch": 1.0750737241965311,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004893139748582857,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.1805924728512764,
|
|
"num_tokens": 21041966.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.198584794998169,
|
|
"epoch": 1.0755735492577598,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000489303104185477,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.17963544130325318,
|
|
"num_tokens": 21051270.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.266377401351929,
|
|
"epoch": 1.0760733743189883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004892922281208573,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.163670913875103,
|
|
"num_tokens": 21060926.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.309466457366943,
|
|
"epoch": 1.076573199380217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892813466647002,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.15903206169605255,
|
|
"num_tokens": 21071367.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.236577081680298,
|
|
"epoch": 1.0770730244414455,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004892704598172797,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.16662590205669403,
|
|
"num_tokens": 21082775.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.308690738677979,
|
|
"epoch": 1.077572849502674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004892595675788696,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.17080232203006745,
|
|
"num_tokens": 21092018.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.258871936798096,
|
|
"epoch": 1.0780726745639027,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004892486699497439,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.17113939374685289,
|
|
"num_tokens": 21101246.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.223579978942871,
|
|
"epoch": 1.0785724996251311,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004892377669301766,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.170625002682209,
|
|
"num_tokens": 21110816.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.265489530563355,
|
|
"epoch": 1.0790723246863598,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892268585204423,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.16893169432878494,
|
|
"num_tokens": 21120228.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.202846527099609,
|
|
"epoch": 1.0795721497475883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004892159447208154,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.1792238935828209,
|
|
"num_tokens": 21129921.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.211715793609619,
|
|
"epoch": 1.080071974808817,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004892050255315705,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.16292364299297332,
|
|
"num_tokens": 21139605.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.192932367324829,
|
|
"epoch": 1.0805717998700455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004891941009529822,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.17424436211585997,
|
|
"num_tokens": 21149004.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.276833629608154,
|
|
"epoch": 1.081071624931274,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004891831709853255,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.1633531004190445,
|
|
"num_tokens": 21159013.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.191910886764527,
|
|
"epoch": 1.0815714499925027,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004891722356288752,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.16855013221502305,
|
|
"num_tokens": 21169432.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.162499904632568,
|
|
"epoch": 1.0820712750537311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004891612948839068,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.17431146800518035,
|
|
"num_tokens": 21179672.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.2348438739776615,
|
|
"epoch": 1.0825711001149598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891503487506951,
|
|
"loss": 5.8034,
|
|
"mean_token_accuracy": 0.17536928355693818,
|
|
"num_tokens": 21189562.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.2974936962127686,
|
|
"epoch": 1.0830709251761883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004891393972295159,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.16623277664184571,
|
|
"num_tokens": 21199538.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.2797407627105715,
|
|
"epoch": 1.083570750237417,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004891284403206444,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.16449850499629975,
|
|
"num_tokens": 21209355.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.198844623565674,
|
|
"epoch": 1.0840705752986455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004891174780243566,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.17303127497434617,
|
|
"num_tokens": 21218268.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.265059566497802,
|
|
"epoch": 1.084570400359874,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000489106510340928,
|
|
"loss": 5.8783,
|
|
"mean_token_accuracy": 0.1678723767399788,
|
|
"num_tokens": 21228376.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.256024980545044,
|
|
"epoch": 1.0850702254211027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890955372706348,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.17064887285232544,
|
|
"num_tokens": 21237781.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.187611389160156,
|
|
"epoch": 1.0855700504823311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004890845588137531,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.17789104729890823,
|
|
"num_tokens": 21247096.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.2688051700592045,
|
|
"epoch": 1.0860698755435598,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004890735749705587,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.1683254674077034,
|
|
"num_tokens": 21258645.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.281689643859863,
|
|
"epoch": 1.0865697006047883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004890625857413283,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.175262551009655,
|
|
"num_tokens": 21268634.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.220130681991577,
|
|
"epoch": 1.087069525666017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890515911263385,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.16964426040649414,
|
|
"num_tokens": 21278996.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.123250579833984,
|
|
"epoch": 1.0875693507272455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004890405911258656,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.1870664492249489,
|
|
"num_tokens": 21288689.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.228249454498291,
|
|
"epoch": 1.088069175788474,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004890295857401866,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.16209219992160798,
|
|
"num_tokens": 21298542.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.204158878326416,
|
|
"epoch": 1.0885690008497027,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004890185749695783,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.17128636538982392,
|
|
"num_tokens": 21308035.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.323642826080322,
|
|
"epoch": 1.0890688259109311,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004890075588143176,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.16104443073272706,
|
|
"num_tokens": 21317898.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.277179908752442,
|
|
"epoch": 1.0895686509721598,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004889965372746819,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.17013414651155473,
|
|
"num_tokens": 21327347.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.254640817642212,
|
|
"epoch": 1.0900684760333883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004889855103509484,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.16509313732385636,
|
|
"num_tokens": 21336592.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.241123676300049,
|
|
"epoch": 1.090568301094617,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004889744780433944,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.16431327909231186,
|
|
"num_tokens": 21345764.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.27710337638855,
|
|
"epoch": 1.0910681261558455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004889634403522976,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.16938268393278122,
|
|
"num_tokens": 21354423.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.258947372436523,
|
|
"epoch": 1.091567951217074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004889523972779359,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.17423128485679626,
|
|
"num_tokens": 21364407.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.316880369186402,
|
|
"epoch": 1.0920677762783026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004889413488205868,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.16458490043878554,
|
|
"num_tokens": 21374642.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.174249219894409,
|
|
"epoch": 1.0925676013395311,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004889302949805283,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.18140521496534348,
|
|
"num_tokens": 21384437.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.246318340301514,
|
|
"epoch": 1.0930674264007598,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004889192357580388,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.17451990991830826,
|
|
"num_tokens": 21393924.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.193145990371704,
|
|
"epoch": 1.0935672514619883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004889081711533964,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.1745892196893692,
|
|
"num_tokens": 21402924.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.265622234344482,
|
|
"epoch": 1.0940670765232168,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004888971011668793,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.16403852105140687,
|
|
"num_tokens": 21412422.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.257238721847534,
|
|
"epoch": 1.0945669015844455,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004888860257987662,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.1692691996693611,
|
|
"num_tokens": 21421830.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.254115915298462,
|
|
"epoch": 1.095066726645674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004888749450493358,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.17389518022537231,
|
|
"num_tokens": 21431602.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.27824854850769,
|
|
"epoch": 1.0955665517069026,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004888638589188669,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1707202434539795,
|
|
"num_tokens": 21441110.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.323570013046265,
|
|
"epoch": 1.0960663767681311,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004888527674076382,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.16480204164981843,
|
|
"num_tokens": 21450626.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.195952081680298,
|
|
"epoch": 1.0965662018293598,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488841670515929,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.17576131075620652,
|
|
"num_tokens": 21461174.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.198922729492187,
|
|
"epoch": 1.0970660268905883,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004888305682440183,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.17712664008140563,
|
|
"num_tokens": 21470895.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.1781947135925295,
|
|
"epoch": 1.0975658519518168,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888194605921855,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.17825542986392975,
|
|
"num_tokens": 21480192.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.32770848274231,
|
|
"epoch": 1.0980656770130455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004888083475607102,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.17480758875608443,
|
|
"num_tokens": 21489418.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.310274362564087,
|
|
"epoch": 1.098565502074274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004887972291498718,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.16378034055233,
|
|
"num_tokens": 21499228.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.234390211105347,
|
|
"epoch": 1.0990653271355026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004887861053599503,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.17493254393339158,
|
|
"num_tokens": 21509051.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.197753477096557,
|
|
"epoch": 1.0995651521967311,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004887749761912252,
|
|
"loss": 5.8247,
|
|
"mean_token_accuracy": 0.17029917389154434,
|
|
"num_tokens": 21518853.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.305419015884399,
|
|
"epoch": 1.1000649772579596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004887638416439768,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.16735292375087737,
|
|
"num_tokens": 21528547.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.338865661621094,
|
|
"epoch": 1.1005648023191883,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004887527017184851,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.166448412835598,
|
|
"num_tokens": 21538166.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.255938482284546,
|
|
"epoch": 1.1010646273804168,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004887415564150305,
|
|
"loss": 5.8083,
|
|
"mean_token_accuracy": 0.17265542298555375,
|
|
"num_tokens": 21548212.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.264417505264282,
|
|
"epoch": 1.1015644524416455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004887304057338934,
|
|
"loss": 5.8114,
|
|
"mean_token_accuracy": 0.16552966386079787,
|
|
"num_tokens": 21558809.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.201149749755859,
|
|
"epoch": 1.102064277502874,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000488719249675354,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.18228883296251297,
|
|
"num_tokens": 21567923.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.212414073944092,
|
|
"epoch": 1.1025641025641026,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004887080882396936,
|
|
"loss": 5.8114,
|
|
"mean_token_accuracy": 0.1742700457572937,
|
|
"num_tokens": 21578051.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.221178722381592,
|
|
"epoch": 1.1030639276253311,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004886969214271925,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.17298130244016646,
|
|
"num_tokens": 21586950.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.277770853042602,
|
|
"epoch": 1.1035637526865596,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004886857492381319,
|
|
"loss": 5.8454,
|
|
"mean_token_accuracy": 0.16654481440782548,
|
|
"num_tokens": 21596577.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.235443115234375,
|
|
"epoch": 1.1040635777477883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004886745716727928,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.1649480104446411,
|
|
"num_tokens": 21606474.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.173011112213135,
|
|
"epoch": 1.1045634028090168,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004886633887314565,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.18065697997808455,
|
|
"num_tokens": 21616277.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.303259563446045,
|
|
"epoch": 1.1050632278702455,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004886522004144044,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.15928865671157838,
|
|
"num_tokens": 21626096.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.311390542984009,
|
|
"epoch": 1.105563052931474,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004886410067219178,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.16457974091172217,
|
|
"num_tokens": 21635295.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.295399761199951,
|
|
"epoch": 1.1060628779927026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886298076542785,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.1556862026453018,
|
|
"num_tokens": 21645900.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.257891750335693,
|
|
"epoch": 1.1065627030539311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004886186032117682,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.168827585875988,
|
|
"num_tokens": 21654757.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.179678344726563,
|
|
"epoch": 1.1070625281151596,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004886073933946688,
|
|
"loss": 5.7327,
|
|
"mean_token_accuracy": 0.17951847463846207,
|
|
"num_tokens": 21665253.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.1760273456573485,
|
|
"epoch": 1.1075623531763883,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004885961782032624,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.1801806092262268,
|
|
"num_tokens": 21674345.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.202904605865479,
|
|
"epoch": 1.1080621782376168,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000488584957637831,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16823271214962005,
|
|
"num_tokens": 21683110.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.191036605834961,
|
|
"epoch": 1.1085620032988455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004885737316986571,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.17640413641929625,
|
|
"num_tokens": 21692141.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.306861066818238,
|
|
"epoch": 1.109061828360074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000488562500386023,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.17453643977642058,
|
|
"num_tokens": 21700945.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.129668140411377,
|
|
"epoch": 1.1095616534213026,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004885512637002115,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.18485974073410033,
|
|
"num_tokens": 21711630.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.281171417236328,
|
|
"epoch": 1.1100614784825311,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004885400216415051,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.16047487705945968,
|
|
"num_tokens": 21721673.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.31116795539856,
|
|
"epoch": 1.1105613035437596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004885287742101865,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.16895480901002885,
|
|
"num_tokens": 21731655.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.230019903182983,
|
|
"epoch": 1.1110611286049883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004885175214065392,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.17114319503307343,
|
|
"num_tokens": 21741465.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.201787757873535,
|
|
"epoch": 1.1115609536662168,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004885062632308457,
|
|
"loss": 5.8052,
|
|
"mean_token_accuracy": 0.17364954799413682,
|
|
"num_tokens": 21750313.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.320503997802734,
|
|
"epoch": 1.1120607787274455,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004884949996833898,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.1615891546010971,
|
|
"num_tokens": 21759842.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.271698665618897,
|
|
"epoch": 1.112560603788674,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004884837307644545,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.17639626413583756,
|
|
"num_tokens": 21770126.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.189914655685425,
|
|
"epoch": 1.1130604288499026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884724564743236,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.17795439958572387,
|
|
"num_tokens": 21779878.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.268693494796753,
|
|
"epoch": 1.1135602539111311,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004884611768132805,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.1662510633468628,
|
|
"num_tokens": 21790971.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.28279709815979,
|
|
"epoch": 1.1140600789723596,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004884498917816092,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.1699115201830864,
|
|
"num_tokens": 21800733.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.266932439804077,
|
|
"epoch": 1.1145599040335883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004884386013795935,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.17655783891677856,
|
|
"num_tokens": 21809840.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.206650638580323,
|
|
"epoch": 1.1150597290948168,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004884273056075175,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.17152158841490744,
|
|
"num_tokens": 21819539.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.222465133666992,
|
|
"epoch": 1.1155595541560455,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004884160044656654,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.17538567036390304,
|
|
"num_tokens": 21829488.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.339767360687256,
|
|
"epoch": 1.116059379217274,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004884046979543217,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.16800465881824495,
|
|
"num_tokens": 21839244.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.3228888511657715,
|
|
"epoch": 1.1165592042785026,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004883933860737706,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.16819968521595002,
|
|
"num_tokens": 21850102.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.326172494888306,
|
|
"epoch": 1.1170590293397311,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004883820688242968,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.1693290278315544,
|
|
"num_tokens": 21860409.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.2148072719573975,
|
|
"epoch": 1.1175588544009596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004883707462061851,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.16803167164325714,
|
|
"num_tokens": 21870055.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.244731903076172,
|
|
"epoch": 1.1180586794621883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004883594182197203,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.16955012828111649,
|
|
"num_tokens": 21879103.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.263385248184204,
|
|
"epoch": 1.1185585045234168,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004883480848651875,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.16961098909378053,
|
|
"num_tokens": 21890140.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.345611095428467,
|
|
"epoch": 1.1190583295846455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004883367461428716,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.15885659605264663,
|
|
"num_tokens": 21900917.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.329178142547607,
|
|
"epoch": 1.119558154645874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004883254020530582,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.1615317642688751,
|
|
"num_tokens": 21910476.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.222822475433349,
|
|
"epoch": 1.1200579797071024,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004883140525960327,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.16910630017518996,
|
|
"num_tokens": 21920219.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.243803071975708,
|
|
"epoch": 1.1205578047683311,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004883026977720803,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.1721772149205208,
|
|
"num_tokens": 21930592.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.3569450855255125,
|
|
"epoch": 1.1210576298295596,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000488291337581487,
|
|
"loss": 5.9822,
|
|
"mean_token_accuracy": 0.15910609364509581,
|
|
"num_tokens": 21939785.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.229021453857422,
|
|
"epoch": 1.1215574548907883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004882799720245385,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.17306355088949205,
|
|
"num_tokens": 21948243.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.265091276168823,
|
|
"epoch": 1.1220572799520168,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004882686011015208,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.16389791220426558,
|
|
"num_tokens": 21958523.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.260773229598999,
|
|
"epoch": 1.1225571050132455,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048825722481272006,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.1659949764609337,
|
|
"num_tokens": 21968685.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.285730028152466,
|
|
"epoch": 1.123056930074474,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004882458431584223,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.16807433366775512,
|
|
"num_tokens": 21979896.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.320944166183471,
|
|
"epoch": 1.1235567551357024,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004882344561389141,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.16892224699258804,
|
|
"num_tokens": 21989513.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.218240594863891,
|
|
"epoch": 1.124056580196931,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048822306375448176,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.17245302647352218,
|
|
"num_tokens": 21999238.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.210474824905395,
|
|
"epoch": 1.1245564052581596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004882116660054121,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.1697083204984665,
|
|
"num_tokens": 22008992.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.267267894744873,
|
|
"epoch": 1.1250562303193883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004882002628919917,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.1654445171356201,
|
|
"num_tokens": 22018333.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.235571432113647,
|
|
"epoch": 1.1255560553806168,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004881888544145076,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.17377929240465165,
|
|
"num_tokens": 22028003.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.266388177871704,
|
|
"epoch": 1.1260558804418452,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048817744057324673,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.16534410715103148,
|
|
"num_tokens": 22038318.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.26509804725647,
|
|
"epoch": 1.126555705503074,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048816602136849644,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.16874318271875383,
|
|
"num_tokens": 22048180.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.238232755661011,
|
|
"epoch": 1.1270555305643024,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048815459680054375,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.1630205139517784,
|
|
"num_tokens": 22057831.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.225462484359741,
|
|
"epoch": 1.127555355625531,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048814316686967635,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.17420931458473204,
|
|
"num_tokens": 22068569.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.330999040603638,
|
|
"epoch": 1.1280551806867596,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004881317315761817,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1655169367790222,
|
|
"num_tokens": 22079267.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.273836660385132,
|
|
"epoch": 1.1285550057479883,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048812029092034747,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.17429005801677705,
|
|
"num_tokens": 22089469.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.219615840911866,
|
|
"epoch": 1.1290548308092168,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048810884490246164,
|
|
"loss": 5.8135,
|
|
"mean_token_accuracy": 0.17265410870313644,
|
|
"num_tokens": 22099148.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.241853189468384,
|
|
"epoch": 1.1295546558704452,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000488097393522812,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.1718738079071045,
|
|
"num_tokens": 22107750.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.302599191665649,
|
|
"epoch": 1.130054480931674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004880859367816868,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.16429785788059234,
|
|
"num_tokens": 22118336.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.2793214321136475,
|
|
"epoch": 1.1305543059929024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004880744746793744,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.16912783086299896,
|
|
"num_tokens": 22128166.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.288586091995239,
|
|
"epoch": 1.131054131054131,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048806300721616295,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.16635790169239045,
|
|
"num_tokens": 22136810.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.239151525497436,
|
|
"epoch": 1.1315539561153596,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048805153439234107,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.17779517024755478,
|
|
"num_tokens": 22146398.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.2880572319030765,
|
|
"epoch": 1.1320537811765883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004880400562081974,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.1718975782394409,
|
|
"num_tokens": 22155161.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.178945875167846,
|
|
"epoch": 1.1325536062378168,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048802857266402075,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.17364808171987534,
|
|
"num_tokens": 22166486.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.209415912628174,
|
|
"epoch": 1.1330534312990452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004880170837601,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1736931785941124,
|
|
"num_tokens": 22176487.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.27110743522644,
|
|
"epoch": 1.133553256360274,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004880055894967242,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.16871814727783202,
|
|
"num_tokens": 22186513.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.2504260540008545,
|
|
"epoch": 1.1340530814215024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048799408987418264,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.17213933169841766,
|
|
"num_tokens": 22197325.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.305105590820313,
|
|
"epoch": 1.134552906482731,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048798258489276457,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.16994359642267226,
|
|
"num_tokens": 22207160.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.294708204269409,
|
|
"epoch": 1.1350527315439596,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004879710745527595,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.16861019879579545,
|
|
"num_tokens": 22216533.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.256913375854492,
|
|
"epoch": 1.1355525566051883,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048795955885445696,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.16477554887533188,
|
|
"num_tokens": 22226186.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.210027170181275,
|
|
"epoch": 1.1360523816664168,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004879480377981467,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.1706872761249542,
|
|
"num_tokens": 22236315.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.263529586791992,
|
|
"epoch": 1.1365522067276452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048793651138411866,
|
|
"loss": 5.7722,
|
|
"mean_token_accuracy": 0.1747501939535141,
|
|
"num_tokens": 22245250.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.324446344375611,
|
|
"epoch": 1.137052031788874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048792497961266273,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.16506577134132386,
|
|
"num_tokens": 22255093.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.149733257293701,
|
|
"epoch": 1.1375518568501024,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048791344248406916,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.17546809315681458,
|
|
"num_tokens": 22264680.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.226985073089599,
|
|
"epoch": 1.138051681911331,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048790189999862814,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.16071088165044783,
|
|
"num_tokens": 22273804.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.2333899974823,
|
|
"epoch": 1.1385515069725596,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048789035215663013,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16907813400030136,
|
|
"num_tokens": 22284302.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.27653398513794,
|
|
"epoch": 1.1390513320337883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048787879895836563,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.17305733561515807,
|
|
"num_tokens": 22293439.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.24802713394165,
|
|
"epoch": 1.1395511570950168,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004878672404041253,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.17345030903816222,
|
|
"num_tokens": 22303005.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.215104246139527,
|
|
"epoch": 1.1400509821562452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048785567649419994,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.17783190160989762,
|
|
"num_tokens": 22311962.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.22875714302063,
|
|
"epoch": 1.140550807217474,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004878441072288806,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.1654905468225479,
|
|
"num_tokens": 22320998.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.288541793823242,
|
|
"epoch": 1.1410506322787024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048783253260845826,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.17346089705824852,
|
|
"num_tokens": 22330977.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.282377624511719,
|
|
"epoch": 1.141550457339931,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004878209526332242,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.17225361615419388,
|
|
"num_tokens": 22341287.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.221504783630371,
|
|
"epoch": 1.1420502824011596,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048780936730346967,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.17612471878528596,
|
|
"num_tokens": 22350507.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.291998386383057,
|
|
"epoch": 1.1425501074623883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048779777661948627,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.16200181245803832,
|
|
"num_tokens": 22361202.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.330362749099732,
|
|
"epoch": 1.1430499325236168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004877861805815655,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.1782814085483551,
|
|
"num_tokens": 22370824.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.204641437530517,
|
|
"epoch": 1.1435497575848452,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004877745791899993,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1697494626045227,
|
|
"num_tokens": 22380857.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.266793251037598,
|
|
"epoch": 1.144049582646074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048776297244507936,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.16998178213834764,
|
|
"num_tokens": 22391354.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.265444231033325,
|
|
"epoch": 1.1445494077073024,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048775136034709784,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.17959411293268204,
|
|
"num_tokens": 22400656.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.269432926177979,
|
|
"epoch": 1.145049232768531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048773974289634676,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.1630958840250969,
|
|
"num_tokens": 22410887.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.280389595031738,
|
|
"epoch": 1.1455490578297596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004877281200931185,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.16653543412685395,
|
|
"num_tokens": 22420370.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.1748240947723385,
|
|
"epoch": 1.1460488828909883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048771649193770554,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.17691890746355057,
|
|
"num_tokens": 22430746.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.262000894546508,
|
|
"epoch": 1.1465487079522168,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004877048584304004,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.16979972273111343,
|
|
"num_tokens": 22440812.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.323226642608643,
|
|
"epoch": 1.1470485330134452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048769321957149557,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.16928282678127288,
|
|
"num_tokens": 22450460.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.2656348705291744,
|
|
"epoch": 1.147548358074674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004876815753612843,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.17479838877916337,
|
|
"num_tokens": 22460660.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.240720605850219,
|
|
"epoch": 1.1480481831359024,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004876699258000592,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.18298303931951523,
|
|
"num_tokens": 22469238.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.222022247314453,
|
|
"epoch": 1.148548008197131,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004876582708881135,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.17304242849349977,
|
|
"num_tokens": 22479685.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.212673568725586,
|
|
"epoch": 1.1490478332583596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004876466106257404,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.17844162732362748,
|
|
"num_tokens": 22489770.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.305364322662354,
|
|
"epoch": 1.149547658319588,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048763494501323333,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.17237702384591103,
|
|
"num_tokens": 22499957.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.274979066848755,
|
|
"epoch": 1.1500474833808167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048762327405088573,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.17261638194322587,
|
|
"num_tokens": 22508863.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.2944722175598145,
|
|
"epoch": 1.1505473084420452,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004876115977389913,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.16986357569694518,
|
|
"num_tokens": 22517563.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.074275350570678,
|
|
"epoch": 1.151047133503274,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048759991607784375,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.18551616370677948,
|
|
"num_tokens": 22527907.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.1677086353302,
|
|
"epoch": 1.1515469585645024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048758822906773706,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.17749823480844498,
|
|
"num_tokens": 22537373.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.309373950958252,
|
|
"epoch": 1.1520467836257309,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048757653670896523,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.16774735748767852,
|
|
"num_tokens": 22547851.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.3243390083312985,
|
|
"epoch": 1.1525466086869596,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004875648390018224,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.16754820346832275,
|
|
"num_tokens": 22558127.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.195788908004761,
|
|
"epoch": 1.153046433748188,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000487553135946603,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.1719558745622635,
|
|
"num_tokens": 22568151.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.255156421661377,
|
|
"epoch": 1.1535462588094167,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048754142754360135,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.1655258610844612,
|
|
"num_tokens": 22579772.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.255225419998169,
|
|
"epoch": 1.1540460838706452,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004875297137931121,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.17134880572557448,
|
|
"num_tokens": 22589551.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.2700553894042965,
|
|
"epoch": 1.154545908931874,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004875179946954298,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.16913386285305024,
|
|
"num_tokens": 22599139.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.319818687438965,
|
|
"epoch": 1.1550457339931024,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048750627025084955,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.15884836614131928,
|
|
"num_tokens": 22609413.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.311534976959228,
|
|
"epoch": 1.1555455590543309,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004874945404596662,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.16574495285749435,
|
|
"num_tokens": 22619395.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.186106967926025,
|
|
"epoch": 1.1560453841155596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048748280532217485,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.18382429331541061,
|
|
"num_tokens": 22629623.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.194806337356567,
|
|
"epoch": 1.156545209176788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004874710648386709,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.16533533483743668,
|
|
"num_tokens": 22639735.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.274449729919434,
|
|
"epoch": 1.1570450342380167,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004874593190094496,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.1714326784014702,
|
|
"num_tokens": 22648563.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.205196857452393,
|
|
"epoch": 1.1575448592992452,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004874475678348065,
|
|
"loss": 5.7586,
|
|
"mean_token_accuracy": 0.17455536723136902,
|
|
"num_tokens": 22657137.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.161261940002442,
|
|
"epoch": 1.158044684360474,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048743581131503716,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.17630813121795655,
|
|
"num_tokens": 22667987.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.221647691726685,
|
|
"epoch": 1.1585445094217024,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004874240494504376,
|
|
"loss": 5.8506,
|
|
"mean_token_accuracy": 0.1623756282031536,
|
|
"num_tokens": 22678830.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.3100134372711185,
|
|
"epoch": 1.1590443344829309,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048741228224130357,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.16596301645040512,
|
|
"num_tokens": 22690568.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.321016597747803,
|
|
"epoch": 1.1595441595441596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048740050968793116,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.1711629807949066,
|
|
"num_tokens": 22700150.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.168083524703979,
|
|
"epoch": 1.160043984605388,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004873887317906166,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.17220389544963838,
|
|
"num_tokens": 22709365.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.315095663070679,
|
|
"epoch": 1.1605438096666167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048737694854965617,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.16563279181718826,
|
|
"num_tokens": 22718636.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.312443542480469,
|
|
"epoch": 1.1610436347278452,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048736515996534644,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.16638314127922058,
|
|
"num_tokens": 22728713.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.187457036972046,
|
|
"epoch": 1.161543459789074,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004873533660379839,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.18549923747777938,
|
|
"num_tokens": 22739061.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.294662380218506,
|
|
"epoch": 1.1620432848503024,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048734156676786525,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.1656804010272026,
|
|
"num_tokens": 22748752.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.196762418746948,
|
|
"epoch": 1.1625431099115309,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004873297621552875,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.1760011285543442,
|
|
"num_tokens": 22758695.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.2705286026000975,
|
|
"epoch": 1.1630429349727596,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048731795220054755,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.171059188246727,
|
|
"num_tokens": 22768948.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.247175645828247,
|
|
"epoch": 1.163542760033988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004873061369039425,
|
|
"loss": 5.847,
|
|
"mean_token_accuracy": 0.16854735761880874,
|
|
"num_tokens": 22779446.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.225361108779907,
|
|
"epoch": 1.1640425850952167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004872943162657697,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.16996433734893798,
|
|
"num_tokens": 22789654.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.235994338989258,
|
|
"epoch": 1.1645424101564452,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004872824902863265,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.16916198432445526,
|
|
"num_tokens": 22798938.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.281712579727173,
|
|
"epoch": 1.165042235217674,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004872706589659106,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.16965549439191818,
|
|
"num_tokens": 22808279.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.237965059280396,
|
|
"epoch": 1.1655420602789024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048725882230481947,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.17423912584781648,
|
|
"num_tokens": 22817378.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.2992301940917965,
|
|
"epoch": 1.1660418853401309,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048724698030335096,
|
|
"loss": 5.8351,
|
|
"mean_token_accuracy": 0.16743778586387634,
|
|
"num_tokens": 22828652.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.2241904735565186,
|
|
"epoch": 1.1665417104013596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004872351329618031,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.17244124859571458,
|
|
"num_tokens": 22839156.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.282567548751831,
|
|
"epoch": 1.167041535462588,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048722328028047386,
|
|
"loss": 5.884,
|
|
"mean_token_accuracy": 0.1691733255982399,
|
|
"num_tokens": 22849004.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.259127283096314,
|
|
"epoch": 1.1675413605238167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048721142225966146,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.16561611443758012,
|
|
"num_tokens": 22858984.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.234065341949463,
|
|
"epoch": 1.1680411855850452,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004871995588996644,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.17211920395493507,
|
|
"num_tokens": 22869149.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.281470823287964,
|
|
"epoch": 1.168541010646274,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004871876902007809,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.1694742888212204,
|
|
"num_tokens": 22878522.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.269507789611817,
|
|
"epoch": 1.1690408357075024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048717581616330985,
|
|
"loss": 5.8155,
|
|
"mean_token_accuracy": 0.17013311237096787,
|
|
"num_tokens": 22888356.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.265830326080322,
|
|
"epoch": 1.1695406607687309,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048716393678754975,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.17006351947784423,
|
|
"num_tokens": 22897551.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.25987057685852,
|
|
"epoch": 1.1700404858299596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004871520520737996,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.17016163766384124,
|
|
"num_tokens": 22906480.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.186250686645508,
|
|
"epoch": 1.170540310891188,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004871401620223585,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.17924709618091583,
|
|
"num_tokens": 22916544.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.176890230178833,
|
|
"epoch": 1.1710401359524167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004871282666335255,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.1833168312907219,
|
|
"num_tokens": 22926083.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.322067928314209,
|
|
"epoch": 1.1715399610136452,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048711636590759985,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.1714811697602272,
|
|
"num_tokens": 22936127.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.224063777923584,
|
|
"epoch": 1.172039786074874,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048710445984488106,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.17265614122152328,
|
|
"num_tokens": 22946579.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.195921468734741,
|
|
"epoch": 1.1725396111361024,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004870925484456686,
|
|
"loss": 5.8073,
|
|
"mean_token_accuracy": 0.1732216313481331,
|
|
"num_tokens": 22956286.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.238073253631592,
|
|
"epoch": 1.1730394361973309,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004870806317102622,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.17092543542385102,
|
|
"num_tokens": 22965625.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.269776153564453,
|
|
"epoch": 1.1735392612585596,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004870687096389617,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.17275564074516297,
|
|
"num_tokens": 22975853.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.254664421081543,
|
|
"epoch": 1.174039086319788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000487056782232067,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.16675358563661574,
|
|
"num_tokens": 22985928.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.236872768402099,
|
|
"epoch": 1.1745389113810167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048704484948987824,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.17861782312393187,
|
|
"num_tokens": 22995222.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.262687540054321,
|
|
"epoch": 1.1750387364422452,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004870329114126956,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.17316104471683502,
|
|
"num_tokens": 23005735.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.268049430847168,
|
|
"epoch": 1.1755385615034737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004870209680008196,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1771699458360672,
|
|
"num_tokens": 23016198.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.252965593338013,
|
|
"epoch": 1.1760383865647024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004870090192545505,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.1611589103937149,
|
|
"num_tokens": 23025927.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.213923597335816,
|
|
"epoch": 1.1765382116259309,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000486997065174189,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.18170126527547836,
|
|
"num_tokens": 23034626.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.1884942054748535,
|
|
"epoch": 1.1770380366871596,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048698510576003593,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.17197567373514175,
|
|
"num_tokens": 23045773.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.224418878555298,
|
|
"epoch": 1.177537861748388,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048697314101239217,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.17286113202571868,
|
|
"num_tokens": 23056803.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.2601940631866455,
|
|
"epoch": 1.1780376868096165,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004869611709315587,
|
|
"loss": 5.8193,
|
|
"mean_token_accuracy": 0.165431010723114,
|
|
"num_tokens": 23066513.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.2795003890991214,
|
|
"epoch": 1.1785375118708452,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048694919551783665,
|
|
"loss": 5.8064,
|
|
"mean_token_accuracy": 0.16697267740964888,
|
|
"num_tokens": 23077309.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.177225971221924,
|
|
"epoch": 1.1790373369320737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048693721477152755,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.17845340222120284,
|
|
"num_tokens": 23088292.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.280026769638061,
|
|
"epoch": 1.1795371619933024,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048692522869293246,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.17034266293048858,
|
|
"num_tokens": 23098744.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.2487359046936035,
|
|
"epoch": 1.1800369870545309,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004869132372823533,
|
|
"loss": 5.7473,
|
|
"mean_token_accuracy": 0.17736131995916365,
|
|
"num_tokens": 23108223.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.237580823898315,
|
|
"epoch": 1.1805368121157596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048690124054009157,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.17137773036956788,
|
|
"num_tokens": 23118595.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.2237659931182865,
|
|
"epoch": 1.181036637176988,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004868892384664491,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.18594790399074554,
|
|
"num_tokens": 23127640.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.263938999176025,
|
|
"epoch": 1.1815364622382165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048687723106172805,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.16829336285591126,
|
|
"num_tokens": 23138409.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.191019010543823,
|
|
"epoch": 1.1820362872994452,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048686521832623026,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.17410077154636383,
|
|
"num_tokens": 23148427.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.190537548065185,
|
|
"epoch": 1.1825361123606737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004868532002602581,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.17895690947771073,
|
|
"num_tokens": 23157873.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.253702640533447,
|
|
"epoch": 1.1830359374219024,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000486841176864114,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.17860284447669983,
|
|
"num_tokens": 23166488.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.21856369972229,
|
|
"epoch": 1.1835357624831309,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048682914813810035,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.18270608633756638,
|
|
"num_tokens": 23176548.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.142065525054932,
|
|
"epoch": 1.1840355875443596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048681711408251986,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.16855593472719194,
|
|
"num_tokens": 23186269.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.242264032363892,
|
|
"epoch": 1.184535412605588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048680507469767533,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.1791372552514076,
|
|
"num_tokens": 23197181.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.2654155731201175,
|
|
"epoch": 1.1850352376668165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004867930299838696,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.1771192029118538,
|
|
"num_tokens": 23207391.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.3225829124450685,
|
|
"epoch": 1.1855350627280452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048678097994140566,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.16968509256839753,
|
|
"num_tokens": 23217510.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.146426153182984,
|
|
"epoch": 1.1860348877892737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048676892457058687,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.17826200574636458,
|
|
"num_tokens": 23226746.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.23757963180542,
|
|
"epoch": 1.1865347128505024,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004867568638717164,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.16646807342767717,
|
|
"num_tokens": 23236333.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.233410263061524,
|
|
"epoch": 1.1870345379117309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048674479784509766,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.17898917943239212,
|
|
"num_tokens": 23245071.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.217166376113892,
|
|
"epoch": 1.1875343629729596,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048673272649103435,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.17330993711948395,
|
|
"num_tokens": 23254225.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.231344556808471,
|
|
"epoch": 1.188034188034188,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048672064980983013,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.1774000883102417,
|
|
"num_tokens": 23264822.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.275156927108765,
|
|
"epoch": 1.1885340130954165,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048670856780178874,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.16764267385005951,
|
|
"num_tokens": 23274559.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.247850608825684,
|
|
"epoch": 1.1890338381566452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048669648046721436,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.1784386843442917,
|
|
"num_tokens": 23284431.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.267743158340454,
|
|
"epoch": 1.1895336632178737,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000486684387806411,
|
|
"loss": 5.8422,
|
|
"mean_token_accuracy": 0.16585779339075088,
|
|
"num_tokens": 23294814.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.3096842765808105,
|
|
"epoch": 1.1900334882791024,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048667228981968285,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.1652626320719719,
|
|
"num_tokens": 23304701.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.344409036636352,
|
|
"epoch": 1.1905333133403309,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048666018650733446,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.16449054926633835,
|
|
"num_tokens": 23314335.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.244540214538574,
|
|
"epoch": 1.1910331384015596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004866480778696702,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1697878807783127,
|
|
"num_tokens": 23324591.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.192378759384155,
|
|
"epoch": 1.191532963462788,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048663596390699477,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.17523031532764435,
|
|
"num_tokens": 23334682.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.304729700088501,
|
|
"epoch": 1.1920327885240165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004866238446196129,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.17512813359498977,
|
|
"num_tokens": 23343943.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.252923393249512,
|
|
"epoch": 1.1925326135852452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004866117200078296,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1714470237493515,
|
|
"num_tokens": 23354031.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.287362289428711,
|
|
"epoch": 1.1930324386464737,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048659959007194985,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.16731278598308563,
|
|
"num_tokens": 23363922.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.279626560211182,
|
|
"epoch": 1.1935322637077024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048658745481227884,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.16548400670289992,
|
|
"num_tokens": 23372552.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.15002031326294,
|
|
"epoch": 1.1940320887689309,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000486575314229122,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.183314773440361,
|
|
"num_tokens": 23383454.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.289122867584228,
|
|
"epoch": 1.1945319138301596,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004865631683227846,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.16752267330884935,
|
|
"num_tokens": 23393429.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.299776697158814,
|
|
"epoch": 1.195031738891388,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048655101709357243,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.17362553179264067,
|
|
"num_tokens": 23403742.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.210325813293457,
|
|
"epoch": 1.1955315639526165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000486538860541791,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.1711210384964943,
|
|
"num_tokens": 23412875.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.28693528175354,
|
|
"epoch": 1.1960313890138452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048652669866774636,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.16813606023788452,
|
|
"num_tokens": 23422838.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.324335670471191,
|
|
"epoch": 1.1965312140750737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004865145314717443,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.16648115813732148,
|
|
"num_tokens": 23431407.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.203433895111084,
|
|
"epoch": 1.1970310391363024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048650235895409115,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.18098316490650176,
|
|
"num_tokens": 23441580.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.25840129852295,
|
|
"epoch": 1.1975308641975309,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004864901811150931,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.16784808784723282,
|
|
"num_tokens": 23451508.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.278424882888794,
|
|
"epoch": 1.1980306892587596,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004864779979550564,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.1686504751443863,
|
|
"num_tokens": 23461928.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.266041946411133,
|
|
"epoch": 1.198530514319988,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004864658094742878,
|
|
"loss": 5.7716,
|
|
"mean_token_accuracy": 0.17719919979572296,
|
|
"num_tokens": 23471501.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.321413230895996,
|
|
"epoch": 1.1990303393812165,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048645361567309375,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.17601174265146255,
|
|
"num_tokens": 23481478.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.311269378662109,
|
|
"epoch": 1.1995301644424452,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004864414165517812,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.16686025857925416,
|
|
"num_tokens": 23491253.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1995301644424452,
|
|
"eval_entropy": 6.028489144184453,
|
|
"eval_loss": 5.860131740570068,
|
|
"eval_mean_token_accuracy": 0.1779402785878595,
|
|
"eval_num_tokens": 23491253.0,
|
|
"eval_runtime": 18.419,
|
|
"eval_samples_per_second": 1685.486,
|
|
"eval_steps_per_second": 210.706,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"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": 5528889990512640.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|