f21d0f2e85
Model: fpadovani/tur-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.599790073474284,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.791650009155274,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 11.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.2639,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.82121729850769,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 13.4375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2929,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18288.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.837881422042846,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 16.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1106,
|
|
"mean_token_accuracy": 0.0001669449033215642,
|
|
"num_tokens": 28664.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.054859638214111,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 25.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.5211,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 37807.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.8463219165802,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 21.375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.1102,
|
|
"mean_token_accuracy": 7.418397581204772e-05,
|
|
"num_tokens": 48086.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.3131178855896,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.84,
|
|
"mean_token_accuracy": 0.0007628825958818197,
|
|
"num_tokens": 57427.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.695811748504639,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.6279,
|
|
"mean_token_accuracy": 0.013821808062493801,
|
|
"num_tokens": 66662.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.684320831298828,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.4081,
|
|
"mean_token_accuracy": 0.020816447213292122,
|
|
"num_tokens": 77388.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.571028423309325,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1091,
|
|
"mean_token_accuracy": 0.028454202599823473,
|
|
"num_tokens": 86093.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.40514316558838,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0138,
|
|
"mean_token_accuracy": 0.04152352567762137,
|
|
"num_tokens": 96097.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.368546867370606,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9286,
|
|
"mean_token_accuracy": 0.03463506633415818,
|
|
"num_tokens": 106328.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.427862358093261,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.7561,
|
|
"mean_token_accuracy": 0.03965897653251886,
|
|
"num_tokens": 114822.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.424885177612305,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7727,
|
|
"mean_token_accuracy": 0.04571409597992897,
|
|
"num_tokens": 124984.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.377210521697998,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.6547,
|
|
"mean_token_accuracy": 0.042986732348799704,
|
|
"num_tokens": 134054.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.345882892608643,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.6148,
|
|
"mean_token_accuracy": 0.04352582097053528,
|
|
"num_tokens": 144561.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.32333002090454,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6092,
|
|
"mean_token_accuracy": 0.034140726551413536,
|
|
"num_tokens": 153701.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.304623126983643,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.463,
|
|
"mean_token_accuracy": 0.0478254497051239,
|
|
"num_tokens": 164291.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.249341011047363,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4218,
|
|
"mean_token_accuracy": 0.047897301986813544,
|
|
"num_tokens": 174136.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.243558979034423,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3489,
|
|
"mean_token_accuracy": 0.055490773916244504,
|
|
"num_tokens": 184368.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.187316131591796,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3329,
|
|
"mean_token_accuracy": 0.053723962232470515,
|
|
"num_tokens": 194659.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.174760437011718,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2164,
|
|
"mean_token_accuracy": 0.05385222285985947,
|
|
"num_tokens": 204875.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.10236120223999,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.2078,
|
|
"mean_token_accuracy": 0.05042871832847595,
|
|
"num_tokens": 217033.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.943318462371826,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0442,
|
|
"mean_token_accuracy": 0.059573306888341906,
|
|
"num_tokens": 225946.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.942243766784667,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9898,
|
|
"mean_token_accuracy": 0.05044227540493011,
|
|
"num_tokens": 235413.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.90278606414795,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.0153,
|
|
"mean_token_accuracy": 0.049924901127815245,
|
|
"num_tokens": 247913.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.790752792358399,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.8984,
|
|
"mean_token_accuracy": 0.055387107655406,
|
|
"num_tokens": 258486.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.678752231597901,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.8218,
|
|
"mean_token_accuracy": 0.05492280051112175,
|
|
"num_tokens": 268027.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.582042121887207,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.7463,
|
|
"mean_token_accuracy": 0.05840916000306606,
|
|
"num_tokens": 277470.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.53208656311035,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.7007,
|
|
"mean_token_accuracy": 0.05844452828168869,
|
|
"num_tokens": 286891.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.274843978881837,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.6317,
|
|
"mean_token_accuracy": 0.06578897573053837,
|
|
"num_tokens": 295636.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.232738018035889,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.6046,
|
|
"mean_token_accuracy": 0.06044535823166371,
|
|
"num_tokens": 306542.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.169378280639648,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.5522,
|
|
"mean_token_accuracy": 0.05850973688066006,
|
|
"num_tokens": 315956.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.077482509613038,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.556,
|
|
"mean_token_accuracy": 0.05588611029088497,
|
|
"num_tokens": 325500.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.019215297698974,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.5765,
|
|
"mean_token_accuracy": 0.061797235161066055,
|
|
"num_tokens": 335194.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.91619348526001,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.5278,
|
|
"mean_token_accuracy": 0.06026073396205902,
|
|
"num_tokens": 344717.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.963479804992676,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4478,
|
|
"mean_token_accuracy": 0.06314925663173199,
|
|
"num_tokens": 354476.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.849452114105224,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4974,
|
|
"mean_token_accuracy": 0.06487920247018338,
|
|
"num_tokens": 363939.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.840077209472657,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.5395,
|
|
"mean_token_accuracy": 0.059846711531281474,
|
|
"num_tokens": 373187.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.856325626373291,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.4639,
|
|
"mean_token_accuracy": 0.06266250982880592,
|
|
"num_tokens": 382999.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.76255006790161,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.5246,
|
|
"mean_token_accuracy": 0.055932244285941124,
|
|
"num_tokens": 392639.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.83744945526123,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.5051,
|
|
"mean_token_accuracy": 0.060099894925951955,
|
|
"num_tokens": 403089.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.76892318725586,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.4578,
|
|
"mean_token_accuracy": 0.06044381149113178,
|
|
"num_tokens": 412321.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.67372522354126,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.4975,
|
|
"mean_token_accuracy": 0.05988954678177834,
|
|
"num_tokens": 421599.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.718119621276855,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4825,
|
|
"mean_token_accuracy": 0.06165708601474762,
|
|
"num_tokens": 432012.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.79115982055664,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.4559,
|
|
"mean_token_accuracy": 0.0672556784003973,
|
|
"num_tokens": 441989.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.681735038757324,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4371,
|
|
"mean_token_accuracy": 0.06710335984826088,
|
|
"num_tokens": 451532.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.714591789245606,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.4554,
|
|
"mean_token_accuracy": 0.06041393578052521,
|
|
"num_tokens": 461815.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.641080474853515,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.5187,
|
|
"mean_token_accuracy": 0.0578727588057518,
|
|
"num_tokens": 470860.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.66689691543579,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4869,
|
|
"mean_token_accuracy": 0.0585276797413826,
|
|
"num_tokens": 480649.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.777419471740723,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4179,
|
|
"mean_token_accuracy": 0.06519291624426841,
|
|
"num_tokens": 489969.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.547350120544433,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.4388,
|
|
"mean_token_accuracy": 0.061872397735714915,
|
|
"num_tokens": 500000.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.71965675354004,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.4147,
|
|
"mean_token_accuracy": 0.06390333585441113,
|
|
"num_tokens": 510013.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.639085960388183,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.4423,
|
|
"mean_token_accuracy": 0.06236038282513619,
|
|
"num_tokens": 519698.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.607205486297607,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.4579,
|
|
"mean_token_accuracy": 0.06288496181368827,
|
|
"num_tokens": 531631.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.685933876037598,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.4181,
|
|
"mean_token_accuracy": 0.06637280248105526,
|
|
"num_tokens": 542204.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.591467189788819,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.3423,
|
|
"mean_token_accuracy": 0.06390709988772869,
|
|
"num_tokens": 552269.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.608537673950195,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.3414,
|
|
"mean_token_accuracy": 0.06816986836493015,
|
|
"num_tokens": 561907.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.648595142364503,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.4558,
|
|
"mean_token_accuracy": 0.06445144601166249,
|
|
"num_tokens": 571283.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.61089735031128,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3458,
|
|
"mean_token_accuracy": 0.06920457892119884,
|
|
"num_tokens": 579896.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.51350793838501,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.3036,
|
|
"mean_token_accuracy": 0.07353892996907234,
|
|
"num_tokens": 588856.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.551695823669434,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.3491,
|
|
"mean_token_accuracy": 0.0707152359187603,
|
|
"num_tokens": 598910.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.606128025054932,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.4008,
|
|
"mean_token_accuracy": 0.06663076654076576,
|
|
"num_tokens": 609248.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.602969741821289,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.4004,
|
|
"mean_token_accuracy": 0.07128242403268814,
|
|
"num_tokens": 619352.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.579054260253907,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.4079,
|
|
"mean_token_accuracy": 0.06752461530268192,
|
|
"num_tokens": 628300.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.591523170471191,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.3416,
|
|
"mean_token_accuracy": 0.07400070279836654,
|
|
"num_tokens": 637969.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.576322555541992,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.2732,
|
|
"mean_token_accuracy": 0.07148236110806465,
|
|
"num_tokens": 647518.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.6574538230896,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.4367,
|
|
"mean_token_accuracy": 0.06586230397224427,
|
|
"num_tokens": 658292.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.541346549987793,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.3214,
|
|
"mean_token_accuracy": 0.07294419221580029,
|
|
"num_tokens": 667872.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.493266773223876,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.2263,
|
|
"mean_token_accuracy": 0.07715460062026977,
|
|
"num_tokens": 676976.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.568483257293702,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.2417,
|
|
"mean_token_accuracy": 0.07718590386211872,
|
|
"num_tokens": 686149.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.499206447601319,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1559,
|
|
"mean_token_accuracy": 0.08460776209831238,
|
|
"num_tokens": 696439.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.419091320037841,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.191,
|
|
"mean_token_accuracy": 0.07839456871151924,
|
|
"num_tokens": 705902.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.40989990234375,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.3448,
|
|
"mean_token_accuracy": 0.07528226897120475,
|
|
"num_tokens": 715973.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.515093135833741,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.2424,
|
|
"mean_token_accuracy": 0.07501133531332016,
|
|
"num_tokens": 725463.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.500295448303223,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.2611,
|
|
"mean_token_accuracy": 0.07273164205253124,
|
|
"num_tokens": 734941.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.510288524627686,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.2799,
|
|
"mean_token_accuracy": 0.06865583658218384,
|
|
"num_tokens": 744302.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.47841272354126,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.2038,
|
|
"mean_token_accuracy": 0.07888807356357574,
|
|
"num_tokens": 754341.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.518750953674317,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.336,
|
|
"mean_token_accuracy": 0.06818274445831776,
|
|
"num_tokens": 764087.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.479927158355713,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.269,
|
|
"mean_token_accuracy": 0.07431223466992379,
|
|
"num_tokens": 773728.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.466327667236328,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.2881,
|
|
"mean_token_accuracy": 0.0715954463928938,
|
|
"num_tokens": 784839.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.545995807647705,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.2697,
|
|
"mean_token_accuracy": 0.07756833955645562,
|
|
"num_tokens": 794514.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.35866994857788,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.2412,
|
|
"mean_token_accuracy": 0.08144036792218685,
|
|
"num_tokens": 805254.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.43459873199463,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.1496,
|
|
"mean_token_accuracy": 0.07946307957172394,
|
|
"num_tokens": 814135.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.418154335021972,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.1839,
|
|
"mean_token_accuracy": 0.07811970189213753,
|
|
"num_tokens": 823531.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.321841144561768,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.1146,
|
|
"mean_token_accuracy": 0.07991140782833099,
|
|
"num_tokens": 832833.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.342794036865234,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.1112,
|
|
"mean_token_accuracy": 0.07684088721871377,
|
|
"num_tokens": 841541.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.320394039154053,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.1394,
|
|
"mean_token_accuracy": 0.0770353578031063,
|
|
"num_tokens": 850689.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.390166759490967,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.0773,
|
|
"mean_token_accuracy": 0.08421313390135765,
|
|
"num_tokens": 860573.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.347050094604493,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.1889,
|
|
"mean_token_accuracy": 0.07550015076994895,
|
|
"num_tokens": 869784.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.39032440185547,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.1487,
|
|
"mean_token_accuracy": 0.0786550410091877,
|
|
"num_tokens": 878716.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.328646183013916,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.2197,
|
|
"mean_token_accuracy": 0.077447821944952,
|
|
"num_tokens": 888334.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.372361946105958,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.1543,
|
|
"mean_token_accuracy": 0.07392257861793042,
|
|
"num_tokens": 897701.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.399530696868897,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.1317,
|
|
"mean_token_accuracy": 0.07822134792804718,
|
|
"num_tokens": 907278.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.294167709350585,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.1437,
|
|
"mean_token_accuracy": 0.07629175707697869,
|
|
"num_tokens": 916194.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.306899166107177,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.1509,
|
|
"mean_token_accuracy": 0.08040244802832604,
|
|
"num_tokens": 926743.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.370134830474854,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.1868,
|
|
"mean_token_accuracy": 0.0721151065081358,
|
|
"num_tokens": 936059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.221036243438721,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.1031,
|
|
"mean_token_accuracy": 0.08096854016184807,
|
|
"num_tokens": 945990.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.352540111541748,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.1913,
|
|
"mean_token_accuracy": 0.07854288667440415,
|
|
"num_tokens": 956626.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.371198749542236,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.1251,
|
|
"mean_token_accuracy": 0.0782523088157177,
|
|
"num_tokens": 966200.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.303024864196777,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0814,
|
|
"mean_token_accuracy": 0.08018661290407181,
|
|
"num_tokens": 975651.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.221511459350586,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 8.0613,
|
|
"mean_token_accuracy": 0.086454738676548,
|
|
"num_tokens": 985264.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.337020969390869,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.1059,
|
|
"mean_token_accuracy": 0.08457382321357727,
|
|
"num_tokens": 996723.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.217254400253296,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.0926,
|
|
"mean_token_accuracy": 0.0818971797823906,
|
|
"num_tokens": 1006098.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.273353767395019,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.1417,
|
|
"mean_token_accuracy": 0.07896760366857052,
|
|
"num_tokens": 1016595.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.265801811218262,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.0003,
|
|
"mean_token_accuracy": 0.0856276884675026,
|
|
"num_tokens": 1026281.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.255826377868653,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.1116,
|
|
"mean_token_accuracy": 0.08526691868901252,
|
|
"num_tokens": 1036697.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.168128395080567,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.0472,
|
|
"mean_token_accuracy": 0.08230854123830796,
|
|
"num_tokens": 1047433.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.279230976104737,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.1059,
|
|
"mean_token_accuracy": 0.07863970063626766,
|
|
"num_tokens": 1056774.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.211492776870728,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 8.0195,
|
|
"mean_token_accuracy": 0.08664621040225029,
|
|
"num_tokens": 1068056.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.15999402999878,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 8.0081,
|
|
"mean_token_accuracy": 0.0843143068253994,
|
|
"num_tokens": 1077698.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.228297233581543,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.948,
|
|
"mean_token_accuracy": 0.08828233480453491,
|
|
"num_tokens": 1086485.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.20526762008667,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.0437,
|
|
"mean_token_accuracy": 0.07942705936729907,
|
|
"num_tokens": 1097329.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.111399030685424,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9965,
|
|
"mean_token_accuracy": 0.08688130974769592,
|
|
"num_tokens": 1107990.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.083545064926147,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.9398,
|
|
"mean_token_accuracy": 0.09414497017860413,
|
|
"num_tokens": 1117798.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.12392086982727,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 8.0728,
|
|
"mean_token_accuracy": 0.08350903168320656,
|
|
"num_tokens": 1126976.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.238962268829345,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 8.0056,
|
|
"mean_token_accuracy": 0.08829480558633804,
|
|
"num_tokens": 1136410.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.136268615722656,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.0448,
|
|
"mean_token_accuracy": 0.08559292852878571,
|
|
"num_tokens": 1147162.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.142546319961548,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.9966,
|
|
"mean_token_accuracy": 0.0838573083281517,
|
|
"num_tokens": 1157578.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.119126796722412,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.9013,
|
|
"mean_token_accuracy": 0.09387225136160851,
|
|
"num_tokens": 1166914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.238367509841918,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 8.0695,
|
|
"mean_token_accuracy": 0.07503110878169536,
|
|
"num_tokens": 1176740.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.108829545974732,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.9774,
|
|
"mean_token_accuracy": 0.07893616035580635,
|
|
"num_tokens": 1185497.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.179529571533203,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 8.0667,
|
|
"mean_token_accuracy": 0.08129067718982697,
|
|
"num_tokens": 1197390.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.068883323669434,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.9543,
|
|
"mean_token_accuracy": 0.08870518133044243,
|
|
"num_tokens": 1208293.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.15115303993225,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.9508,
|
|
"mean_token_accuracy": 0.08918194845318794,
|
|
"num_tokens": 1217860.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.05653681755066,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.9353,
|
|
"mean_token_accuracy": 0.08667743131518364,
|
|
"num_tokens": 1227259.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.01396565437317,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.8609,
|
|
"mean_token_accuracy": 0.09146164059638977,
|
|
"num_tokens": 1236775.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.13114972114563,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.9588,
|
|
"mean_token_accuracy": 0.0877492293715477,
|
|
"num_tokens": 1246307.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 8.100008535385133,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.9329,
|
|
"mean_token_accuracy": 0.08653593435883522,
|
|
"num_tokens": 1255197.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.022264909744262,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.9269,
|
|
"mean_token_accuracy": 0.08907717168331146,
|
|
"num_tokens": 1265056.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.095293426513672,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8923,
|
|
"mean_token_accuracy": 0.0903382994234562,
|
|
"num_tokens": 1274718.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.11915626525879,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.9806,
|
|
"mean_token_accuracy": 0.08302460163831711,
|
|
"num_tokens": 1284364.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.03192071914673,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.9635,
|
|
"mean_token_accuracy": 0.08643308579921723,
|
|
"num_tokens": 1294186.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.06210789680481,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.8788,
|
|
"mean_token_accuracy": 0.09071523323655128,
|
|
"num_tokens": 1303393.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.958633279800415,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.869,
|
|
"mean_token_accuracy": 0.08798071406781674,
|
|
"num_tokens": 1312819.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.046775722503662,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.9151,
|
|
"mean_token_accuracy": 0.08215179368853569,
|
|
"num_tokens": 1323001.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.055660486221313,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.8848,
|
|
"mean_token_accuracy": 0.08770225271582603,
|
|
"num_tokens": 1333260.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.934985589981079,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.8751,
|
|
"mean_token_accuracy": 0.09213166236877442,
|
|
"num_tokens": 1342696.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.97315731048584,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.8557,
|
|
"mean_token_accuracy": 0.09062512218952179,
|
|
"num_tokens": 1353104.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.987550115585327,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.919,
|
|
"mean_token_accuracy": 0.08597041219472885,
|
|
"num_tokens": 1362871.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 8.106160926818848,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.9071,
|
|
"mean_token_accuracy": 0.08379044011235237,
|
|
"num_tokens": 1373622.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.853943729400635,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.7799,
|
|
"mean_token_accuracy": 0.09153937473893166,
|
|
"num_tokens": 1382707.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.994217348098755,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8429,
|
|
"mean_token_accuracy": 0.08916826024651528,
|
|
"num_tokens": 1392048.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.870188045501709,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.7336,
|
|
"mean_token_accuracy": 0.09760514721274376,
|
|
"num_tokens": 1401387.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.9647351741790775,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.8467,
|
|
"mean_token_accuracy": 0.0882681168615818,
|
|
"num_tokens": 1411404.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.9368860721588135,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.8307,
|
|
"mean_token_accuracy": 0.09069122523069381,
|
|
"num_tokens": 1420292.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.9168719291687015,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.8032,
|
|
"mean_token_accuracy": 0.09315077662467956,
|
|
"num_tokens": 1429990.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.91649284362793,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.8377,
|
|
"mean_token_accuracy": 0.08601107746362686,
|
|
"num_tokens": 1440148.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.9139933586120605,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7484,
|
|
"mean_token_accuracy": 0.09189097732305526,
|
|
"num_tokens": 1450015.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.917560863494873,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.7691,
|
|
"mean_token_accuracy": 0.08974878862500191,
|
|
"num_tokens": 1459582.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.895784044265747,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.8411,
|
|
"mean_token_accuracy": 0.08744788095355034,
|
|
"num_tokens": 1468151.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.8630622863769535,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.726,
|
|
"mean_token_accuracy": 0.09304906949400901,
|
|
"num_tokens": 1479099.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.873302745819092,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.8318,
|
|
"mean_token_accuracy": 0.09302263855934143,
|
|
"num_tokens": 1488060.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.948469638824463,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.8108,
|
|
"mean_token_accuracy": 0.0858851782977581,
|
|
"num_tokens": 1498230.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.869532060623169,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7938,
|
|
"mean_token_accuracy": 0.08861268982291222,
|
|
"num_tokens": 1507962.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 8.029801321029662,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.9144,
|
|
"mean_token_accuracy": 0.08749665692448616,
|
|
"num_tokens": 1518607.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.902935981750488,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.7459,
|
|
"mean_token_accuracy": 0.08882014006376267,
|
|
"num_tokens": 1527166.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.913458681106567,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.8457,
|
|
"mean_token_accuracy": 0.08774015679955482,
|
|
"num_tokens": 1536683.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.799791765213013,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.7383,
|
|
"mean_token_accuracy": 0.0890597477555275,
|
|
"num_tokens": 1546243.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.86862621307373,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.7593,
|
|
"mean_token_accuracy": 0.08828465566039086,
|
|
"num_tokens": 1555916.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.798974323272705,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6721,
|
|
"mean_token_accuracy": 0.09845857620239258,
|
|
"num_tokens": 1566617.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.832266473770142,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7156,
|
|
"mean_token_accuracy": 0.0884881392121315,
|
|
"num_tokens": 1575413.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.771887922286988,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7332,
|
|
"mean_token_accuracy": 0.09316859021782875,
|
|
"num_tokens": 1586863.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.834986591339112,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.8049,
|
|
"mean_token_accuracy": 0.09231851473450661,
|
|
"num_tokens": 1597685.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.867625284194946,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.6986,
|
|
"mean_token_accuracy": 0.09077956452965737,
|
|
"num_tokens": 1607103.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.832145357131958,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.7485,
|
|
"mean_token_accuracy": 0.08986216709017754,
|
|
"num_tokens": 1617919.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.794708204269409,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.768,
|
|
"mean_token_accuracy": 0.09404098391532897,
|
|
"num_tokens": 1627293.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.90134825706482,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.7922,
|
|
"mean_token_accuracy": 0.0896671935915947,
|
|
"num_tokens": 1638440.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.743810081481934,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.7189,
|
|
"mean_token_accuracy": 0.09339917823672295,
|
|
"num_tokens": 1648148.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.798413705825806,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.7344,
|
|
"mean_token_accuracy": 0.09364142566919327,
|
|
"num_tokens": 1658334.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.8422918796539305,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.7699,
|
|
"mean_token_accuracy": 0.08807238787412644,
|
|
"num_tokens": 1667963.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.815905141830444,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.6715,
|
|
"mean_token_accuracy": 0.09518391564488411,
|
|
"num_tokens": 1677270.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.7168646335601805,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6433,
|
|
"mean_token_accuracy": 0.09483171701431274,
|
|
"num_tokens": 1686770.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.760430765151978,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.7126,
|
|
"mean_token_accuracy": 0.09171252027153969,
|
|
"num_tokens": 1697507.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.743275165557861,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.6634,
|
|
"mean_token_accuracy": 0.09470361396670342,
|
|
"num_tokens": 1708253.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.803777408599854,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.7314,
|
|
"mean_token_accuracy": 0.08744200840592384,
|
|
"num_tokens": 1717827.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.641020631790161,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5264,
|
|
"mean_token_accuracy": 0.10062878951430321,
|
|
"num_tokens": 1726678.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.729559707641601,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.6837,
|
|
"mean_token_accuracy": 0.09284055829048157,
|
|
"num_tokens": 1737518.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.701491022109986,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5668,
|
|
"mean_token_accuracy": 0.09772049933671952,
|
|
"num_tokens": 1746338.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.655733203887939,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.667,
|
|
"mean_token_accuracy": 0.09409659132361411,
|
|
"num_tokens": 1756538.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.753999948501587,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.654,
|
|
"mean_token_accuracy": 0.09215902574360371,
|
|
"num_tokens": 1766722.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.662614202499389,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.5758,
|
|
"mean_token_accuracy": 0.09804621636867523,
|
|
"num_tokens": 1777039.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.686301565170288,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.69,
|
|
"mean_token_accuracy": 0.08747479245066643,
|
|
"num_tokens": 1787621.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.739987802505493,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6941,
|
|
"mean_token_accuracy": 0.0946861956268549,
|
|
"num_tokens": 1798345.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.674608373641968,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6303,
|
|
"mean_token_accuracy": 0.10006568729877471,
|
|
"num_tokens": 1807994.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.651217222213745,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5652,
|
|
"mean_token_accuracy": 0.08964619114995002,
|
|
"num_tokens": 1817965.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.639501237869263,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.62,
|
|
"mean_token_accuracy": 0.09154486805200576,
|
|
"num_tokens": 1827094.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.7448944568634035,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5907,
|
|
"mean_token_accuracy": 0.09276118874549866,
|
|
"num_tokens": 1837754.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.587901210784912,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.5858,
|
|
"mean_token_accuracy": 0.09547252953052521,
|
|
"num_tokens": 1847500.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.606810808181763,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.6324,
|
|
"mean_token_accuracy": 0.08944343850016594,
|
|
"num_tokens": 1857663.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.784541130065918,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6947,
|
|
"mean_token_accuracy": 0.0932641200721264,
|
|
"num_tokens": 1867752.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.556209373474121,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.626,
|
|
"mean_token_accuracy": 0.09295311495661736,
|
|
"num_tokens": 1877479.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.730465078353882,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6473,
|
|
"mean_token_accuracy": 0.09373209923505783,
|
|
"num_tokens": 1887944.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.654263734817505,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5671,
|
|
"mean_token_accuracy": 0.09599127843976021,
|
|
"num_tokens": 1896991.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.621188306808472,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.5894,
|
|
"mean_token_accuracy": 0.1009646438062191,
|
|
"num_tokens": 1907216.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.716098117828369,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5806,
|
|
"mean_token_accuracy": 0.09529191181063652,
|
|
"num_tokens": 1917206.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.511505031585694,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.672,
|
|
"mean_token_accuracy": 0.09074099287390709,
|
|
"num_tokens": 1929669.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.717717981338501,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.5271,
|
|
"mean_token_accuracy": 0.09860590994358062,
|
|
"num_tokens": 1939881.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.50510540008545,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.5609,
|
|
"mean_token_accuracy": 0.09686254858970642,
|
|
"num_tokens": 1949423.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.61955680847168,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.5959,
|
|
"mean_token_accuracy": 0.09370956495404244,
|
|
"num_tokens": 1959214.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.723949670791626,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5537,
|
|
"mean_token_accuracy": 0.0956396333873272,
|
|
"num_tokens": 1968963.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.549405145645141,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.5633,
|
|
"mean_token_accuracy": 0.09498978704214096,
|
|
"num_tokens": 1979551.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.5673760890960695,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.5157,
|
|
"mean_token_accuracy": 0.09872248247265816,
|
|
"num_tokens": 1988432.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.55355863571167,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.5591,
|
|
"mean_token_accuracy": 0.09609471410512924,
|
|
"num_tokens": 1997509.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.737374544143677,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.7221,
|
|
"mean_token_accuracy": 0.09012902900576591,
|
|
"num_tokens": 2007406.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.63672366142273,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.5417,
|
|
"mean_token_accuracy": 0.09073366522789002,
|
|
"num_tokens": 2016760.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.532858657836914,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.5635,
|
|
"mean_token_accuracy": 0.09805454760789871,
|
|
"num_tokens": 2027776.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.5644487857818605,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.4998,
|
|
"mean_token_accuracy": 0.10216570869088173,
|
|
"num_tokens": 2036955.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.550212717056274,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.4273,
|
|
"mean_token_accuracy": 0.10139072239398957,
|
|
"num_tokens": 2046118.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.455883264541626,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.5015,
|
|
"mean_token_accuracy": 0.09121370837092399,
|
|
"num_tokens": 2056266.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.592077207565308,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.5511,
|
|
"mean_token_accuracy": 0.0956337384879589,
|
|
"num_tokens": 2067416.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.572665500640869,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.5287,
|
|
"mean_token_accuracy": 0.09303966537117958,
|
|
"num_tokens": 2076926.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.479141426086426,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.5214,
|
|
"mean_token_accuracy": 0.09900636374950408,
|
|
"num_tokens": 2088017.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.522082901000976,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.5462,
|
|
"mean_token_accuracy": 0.09880418479442596,
|
|
"num_tokens": 2097249.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.551411294937134,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.4761,
|
|
"mean_token_accuracy": 0.0976270966231823,
|
|
"num_tokens": 2105778.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.56266303062439,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.5119,
|
|
"mean_token_accuracy": 0.10032028555870057,
|
|
"num_tokens": 2114710.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.5173601627349855,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.4467,
|
|
"mean_token_accuracy": 0.09914555251598359,
|
|
"num_tokens": 2124002.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.5395721912384035,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.5423,
|
|
"mean_token_accuracy": 0.0994409941136837,
|
|
"num_tokens": 2134592.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.472764301300049,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.3796,
|
|
"mean_token_accuracy": 0.10381273031234742,
|
|
"num_tokens": 2143641.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.512874698638916,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.5118,
|
|
"mean_token_accuracy": 0.09514869302511215,
|
|
"num_tokens": 2154738.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.4650367259979244,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.464,
|
|
"mean_token_accuracy": 0.10286911129951477,
|
|
"num_tokens": 2164365.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.42442216873169,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.3251,
|
|
"mean_token_accuracy": 0.10485819950699807,
|
|
"num_tokens": 2173185.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.488422584533692,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.4557,
|
|
"mean_token_accuracy": 0.10024777427315712,
|
|
"num_tokens": 2184717.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.4683778285980225,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.4244,
|
|
"mean_token_accuracy": 0.10170031487941741,
|
|
"num_tokens": 2193681.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.480268287658691,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.4427,
|
|
"mean_token_accuracy": 0.09846253246068955,
|
|
"num_tokens": 2203366.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.510249376296997,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.437,
|
|
"mean_token_accuracy": 0.10007026195526122,
|
|
"num_tokens": 2213982.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.470330047607422,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.4809,
|
|
"mean_token_accuracy": 0.09837306439876556,
|
|
"num_tokens": 2222897.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.428879880905152,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.4428,
|
|
"mean_token_accuracy": 0.10468190163373947,
|
|
"num_tokens": 2232472.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.399091100692749,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.4736,
|
|
"mean_token_accuracy": 0.10416980311274529,
|
|
"num_tokens": 2242666.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.615888071060181,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.5362,
|
|
"mean_token_accuracy": 0.09456123262643815,
|
|
"num_tokens": 2254586.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.44240026473999,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.3675,
|
|
"mean_token_accuracy": 0.10122138187289238,
|
|
"num_tokens": 2264619.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.638830471038818,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.4664,
|
|
"mean_token_accuracy": 0.0914570763707161,
|
|
"num_tokens": 2274114.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.202870082855225,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.3752,
|
|
"mean_token_accuracy": 0.10422463156282902,
|
|
"num_tokens": 2283887.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.499454975128174,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.3798,
|
|
"mean_token_accuracy": 0.10416734889149666,
|
|
"num_tokens": 2293090.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.405326890945434,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.4941,
|
|
"mean_token_accuracy": 0.1007530689239502,
|
|
"num_tokens": 2302828.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.508965539932251,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.3741,
|
|
"mean_token_accuracy": 0.10420065671205521,
|
|
"num_tokens": 2311415.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.418776798248291,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.4587,
|
|
"mean_token_accuracy": 0.09595207944512367,
|
|
"num_tokens": 2321512.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.462272262573242,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.3597,
|
|
"mean_token_accuracy": 0.09774425327777862,
|
|
"num_tokens": 2331398.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.390771961212158,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.3398,
|
|
"mean_token_accuracy": 0.10234742686152458,
|
|
"num_tokens": 2341751.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.501025581359864,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.3795,
|
|
"mean_token_accuracy": 0.09952760934829712,
|
|
"num_tokens": 2352538.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.375369358062744,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.45,
|
|
"mean_token_accuracy": 0.09802018627524375,
|
|
"num_tokens": 2362433.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.532867479324341,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.4279,
|
|
"mean_token_accuracy": 0.09662150442600251,
|
|
"num_tokens": 2372431.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.313345861434937,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.4233,
|
|
"mean_token_accuracy": 0.10795046091079712,
|
|
"num_tokens": 2382483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.574924325942993,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.4059,
|
|
"mean_token_accuracy": 0.09452533945441247,
|
|
"num_tokens": 2392835.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.347304105758667,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.3737,
|
|
"mean_token_accuracy": 0.09439274296164513,
|
|
"num_tokens": 2402305.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.343445539474487,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.3078,
|
|
"mean_token_accuracy": 0.10918881967663766,
|
|
"num_tokens": 2412093.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.356309986114502,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.2729,
|
|
"mean_token_accuracy": 0.11116204932332038,
|
|
"num_tokens": 2421349.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.334961366653443,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.2729,
|
|
"mean_token_accuracy": 0.11540432274341583,
|
|
"num_tokens": 2430672.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.312632274627686,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.3496,
|
|
"mean_token_accuracy": 0.1008877657353878,
|
|
"num_tokens": 2439355.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.394206523895264,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.3439,
|
|
"mean_token_accuracy": 0.10909157991409302,
|
|
"num_tokens": 2448860.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.350288391113281,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.3731,
|
|
"mean_token_accuracy": 0.10190236046910287,
|
|
"num_tokens": 2458276.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.332216119766235,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.2885,
|
|
"mean_token_accuracy": 0.10416633412241935,
|
|
"num_tokens": 2467791.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.432009840011597,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.4218,
|
|
"mean_token_accuracy": 0.10164169669151306,
|
|
"num_tokens": 2477549.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.333640623092651,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.323,
|
|
"mean_token_accuracy": 0.09840168058872223,
|
|
"num_tokens": 2487549.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.464362382888794,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.3226,
|
|
"mean_token_accuracy": 0.10223804861307144,
|
|
"num_tokens": 2496799.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.4028078556060795,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.4079,
|
|
"mean_token_accuracy": 0.09940458238124847,
|
|
"num_tokens": 2505795.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.363927745819092,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.229,
|
|
"mean_token_accuracy": 0.10232904329895973,
|
|
"num_tokens": 2515289.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.393394041061401,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.4109,
|
|
"mean_token_accuracy": 0.09670610949397088,
|
|
"num_tokens": 2524563.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.354452133178711,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.3183,
|
|
"mean_token_accuracy": 0.10640332400798798,
|
|
"num_tokens": 2534057.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.3064008235931395,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.2834,
|
|
"mean_token_accuracy": 0.10942733064293861,
|
|
"num_tokens": 2544646.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.4173472881317135,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.3696,
|
|
"mean_token_accuracy": 0.1016182117164135,
|
|
"num_tokens": 2553843.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.349134922027588,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.4124,
|
|
"mean_token_accuracy": 0.09806189686059952,
|
|
"num_tokens": 2564061.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.351945590972901,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.2677,
|
|
"mean_token_accuracy": 0.10726078897714615,
|
|
"num_tokens": 2574758.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.341266250610351,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.3301,
|
|
"mean_token_accuracy": 0.10427657440304756,
|
|
"num_tokens": 2585213.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.415141153335571,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.3863,
|
|
"mean_token_accuracy": 0.10240926444530488,
|
|
"num_tokens": 2595511.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.322946357727051,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.3065,
|
|
"mean_token_accuracy": 0.1043054111301899,
|
|
"num_tokens": 2605930.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.352214527130127,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.1786,
|
|
"mean_token_accuracy": 0.11697915494441986,
|
|
"num_tokens": 2614224.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.341785049438476,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.4133,
|
|
"mean_token_accuracy": 0.09787786826491356,
|
|
"num_tokens": 2624879.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.313656330108643,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.2542,
|
|
"mean_token_accuracy": 0.10557752177119255,
|
|
"num_tokens": 2633836.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.303465509414673,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.3265,
|
|
"mean_token_accuracy": 0.10393745005130768,
|
|
"num_tokens": 2643754.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.485411548614502,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.3691,
|
|
"mean_token_accuracy": 0.10118599981069565,
|
|
"num_tokens": 2652708.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.293326139450073,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.3332,
|
|
"mean_token_accuracy": 0.10101174637675285,
|
|
"num_tokens": 2662353.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.395275354385376,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.2455,
|
|
"mean_token_accuracy": 0.10808999240398406,
|
|
"num_tokens": 2672376.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.28541202545166,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.343,
|
|
"mean_token_accuracy": 0.10266417935490608,
|
|
"num_tokens": 2682115.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.361982917785644,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.3249,
|
|
"mean_token_accuracy": 0.10273946896195411,
|
|
"num_tokens": 2692429.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.356666135787964,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.2624,
|
|
"mean_token_accuracy": 0.10483143851161003,
|
|
"num_tokens": 2701373.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.448349714279175,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.4456,
|
|
"mean_token_accuracy": 0.10275454893708229,
|
|
"num_tokens": 2710717.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.243832445144653,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.3053,
|
|
"mean_token_accuracy": 0.1035049244761467,
|
|
"num_tokens": 2720936.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.444944524765015,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.2552,
|
|
"mean_token_accuracy": 0.11174436882138253,
|
|
"num_tokens": 2730504.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.234856271743775,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.2567,
|
|
"mean_token_accuracy": 0.10671055763959884,
|
|
"num_tokens": 2739069.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.39029221534729,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.3385,
|
|
"mean_token_accuracy": 0.09800549671053886,
|
|
"num_tokens": 2748941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.275935411453247,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.2932,
|
|
"mean_token_accuracy": 0.11003827452659606,
|
|
"num_tokens": 2758915.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.405569314956665,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.3226,
|
|
"mean_token_accuracy": 0.10157396346330642,
|
|
"num_tokens": 2768972.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.269433259963989,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.1646,
|
|
"mean_token_accuracy": 0.11019177362322807,
|
|
"num_tokens": 2777989.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.236843538284302,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.2713,
|
|
"mean_token_accuracy": 0.10585586354136467,
|
|
"num_tokens": 2788227.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.350889062881469,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.2754,
|
|
"mean_token_accuracy": 0.10650887861847877,
|
|
"num_tokens": 2797729.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.336771488189697,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.2716,
|
|
"mean_token_accuracy": 0.1051708072423935,
|
|
"num_tokens": 2807215.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.2520225048065186,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.1883,
|
|
"mean_token_accuracy": 0.10783864781260491,
|
|
"num_tokens": 2816945.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.216451740264892,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.2712,
|
|
"mean_token_accuracy": 0.10556349977850914,
|
|
"num_tokens": 2827072.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.333676815032959,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.1848,
|
|
"mean_token_accuracy": 0.10760891959071159,
|
|
"num_tokens": 2837928.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.182110834121704,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.224,
|
|
"mean_token_accuracy": 0.11059348955750466,
|
|
"num_tokens": 2847861.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.324659442901611,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.2266,
|
|
"mean_token_accuracy": 0.10654641091823577,
|
|
"num_tokens": 2857885.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.342340612411499,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.2576,
|
|
"mean_token_accuracy": 0.10456847101449966,
|
|
"num_tokens": 2867004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.183152198791504,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 7.1181,
|
|
"mean_token_accuracy": 0.11030580475926399,
|
|
"num_tokens": 2876285.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.275135135650634,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.2797,
|
|
"mean_token_accuracy": 0.10354529283940792,
|
|
"num_tokens": 2886967.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.288818311691284,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 7.2214,
|
|
"mean_token_accuracy": 0.10634861737489701,
|
|
"num_tokens": 2897137.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.203562879562378,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.189,
|
|
"mean_token_accuracy": 0.11473996862769127,
|
|
"num_tokens": 2907658.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.289450311660767,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.1948,
|
|
"mean_token_accuracy": 0.10778787955641747,
|
|
"num_tokens": 2917801.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.242615985870361,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.2853,
|
|
"mean_token_accuracy": 0.10557879060506821,
|
|
"num_tokens": 2927188.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.2714708805084225,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.1637,
|
|
"mean_token_accuracy": 0.10618824735283852,
|
|
"num_tokens": 2936781.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.207219743728638,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.146,
|
|
"mean_token_accuracy": 0.10595403760671615,
|
|
"num_tokens": 2946426.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.163693475723266,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.1859,
|
|
"mean_token_accuracy": 0.1059610590338707,
|
|
"num_tokens": 2956246.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.299579715728759,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.1782,
|
|
"mean_token_accuracy": 0.10952525734901428,
|
|
"num_tokens": 2965930.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.17916841506958,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 7.1203,
|
|
"mean_token_accuracy": 0.11073079928755761,
|
|
"num_tokens": 2975975.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.203798532485962,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 7.1483,
|
|
"mean_token_accuracy": 0.10983792692422867,
|
|
"num_tokens": 2985343.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.188997840881347,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 7.1451,
|
|
"mean_token_accuracy": 0.1086390919983387,
|
|
"num_tokens": 2994420.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.235520648956299,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.2723,
|
|
"mean_token_accuracy": 0.10853548273444176,
|
|
"num_tokens": 3004447.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.342757797241211,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 7.1605,
|
|
"mean_token_accuracy": 0.10739956200122833,
|
|
"num_tokens": 3014596.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.138177442550659,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 7.0981,
|
|
"mean_token_accuracy": 0.10866019204258918,
|
|
"num_tokens": 3024528.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.240619468688965,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 7.2099,
|
|
"mean_token_accuracy": 0.10421332791447639,
|
|
"num_tokens": 3035233.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.229916572570801,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.2099,
|
|
"mean_token_accuracy": 0.10832755044102668,
|
|
"num_tokens": 3045890.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.2049596309661865,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 7.106,
|
|
"mean_token_accuracy": 0.11494272649288177,
|
|
"num_tokens": 3056640.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.144407796859741,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 7.1441,
|
|
"mean_token_accuracy": 0.11316709145903588,
|
|
"num_tokens": 3066938.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.216827011108398,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.2439,
|
|
"mean_token_accuracy": 0.10790825858712197,
|
|
"num_tokens": 3076791.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.263591861724853,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 7.0932,
|
|
"mean_token_accuracy": 0.10904844701290131,
|
|
"num_tokens": 3087532.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.110728025436401,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 7.2289,
|
|
"mean_token_accuracy": 0.10976007133722306,
|
|
"num_tokens": 3097465.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.32912278175354,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.1224,
|
|
"mean_token_accuracy": 0.1091330036520958,
|
|
"num_tokens": 3107162.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.141360473632813,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 7.1238,
|
|
"mean_token_accuracy": 0.10997193083167076,
|
|
"num_tokens": 3117154.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.207948064804077,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 7.1408,
|
|
"mean_token_accuracy": 0.10777789875864982,
|
|
"num_tokens": 3127635.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.305689430236816,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 7.176,
|
|
"mean_token_accuracy": 0.10682187527418137,
|
|
"num_tokens": 3137806.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.146860361099243,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 7.2055,
|
|
"mean_token_accuracy": 0.10350432991981506,
|
|
"num_tokens": 3147704.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.246462678909301,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.1665,
|
|
"mean_token_accuracy": 0.10513406619429588,
|
|
"num_tokens": 3158486.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.2225347518920895,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.1637,
|
|
"mean_token_accuracy": 0.1100760817527771,
|
|
"num_tokens": 3168518.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.136386346817017,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 7.0505,
|
|
"mean_token_accuracy": 0.11440540626645088,
|
|
"num_tokens": 3177502.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.223326826095581,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 7.1259,
|
|
"mean_token_accuracy": 0.11024409383535386,
|
|
"num_tokens": 3187408.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.209620571136474,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.1748,
|
|
"mean_token_accuracy": 0.11251615285873413,
|
|
"num_tokens": 3196812.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.105884313583374,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 7.0282,
|
|
"mean_token_accuracy": 0.11647915989160537,
|
|
"num_tokens": 3206159.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.154392719268799,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 7.0193,
|
|
"mean_token_accuracy": 0.11799696087837219,
|
|
"num_tokens": 3217329.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.113078355789185,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 7.1432,
|
|
"mean_token_accuracy": 0.1093616746366024,
|
|
"num_tokens": 3227558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.271105813980102,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.2335,
|
|
"mean_token_accuracy": 0.10456183776259423,
|
|
"num_tokens": 3237719.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.20871205329895,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.1569,
|
|
"mean_token_accuracy": 0.11061653196811676,
|
|
"num_tokens": 3246483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.111011981964111,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 7.0442,
|
|
"mean_token_accuracy": 0.11448038592934609,
|
|
"num_tokens": 3256955.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.170991039276123,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 7.1342,
|
|
"mean_token_accuracy": 0.1075492449104786,
|
|
"num_tokens": 3266799.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.175664854049683,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 7.1038,
|
|
"mean_token_accuracy": 0.10848242715001107,
|
|
"num_tokens": 3276595.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.121126556396485,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.11261371076107025,
|
|
"num_tokens": 3286047.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.220827436447143,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 7.1485,
|
|
"mean_token_accuracy": 0.10454296097159385,
|
|
"num_tokens": 3295364.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.113693380355835,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 7.0472,
|
|
"mean_token_accuracy": 0.11581237241625786,
|
|
"num_tokens": 3305319.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.098750734329224,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 7.0623,
|
|
"mean_token_accuracy": 0.11507118344306946,
|
|
"num_tokens": 3315349.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.151982069015503,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 7.1436,
|
|
"mean_token_accuracy": 0.10506928116083145,
|
|
"num_tokens": 3325603.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.133093595504761,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 7.0563,
|
|
"mean_token_accuracy": 0.11085285693407058,
|
|
"num_tokens": 3334693.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.1613341808319095,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 7.0656,
|
|
"mean_token_accuracy": 0.10509323179721833,
|
|
"num_tokens": 3345259.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.052835845947266,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 7.0619,
|
|
"mean_token_accuracy": 0.108848088234663,
|
|
"num_tokens": 3354072.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.273435640335083,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 7.0622,
|
|
"mean_token_accuracy": 0.10689497664570809,
|
|
"num_tokens": 3364881.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.050932312011719,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 7.0324,
|
|
"mean_token_accuracy": 0.1095457673072815,
|
|
"num_tokens": 3374030.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.092038965225219,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 7.0593,
|
|
"mean_token_accuracy": 0.10611691325902939,
|
|
"num_tokens": 3384009.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.284945869445801,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 7.1744,
|
|
"mean_token_accuracy": 0.10681680515408516,
|
|
"num_tokens": 3393660.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.17227029800415,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 7.1897,
|
|
"mean_token_accuracy": 0.1081137239933014,
|
|
"num_tokens": 3404364.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.234745454788208,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 7.0754,
|
|
"mean_token_accuracy": 0.10843142941594124,
|
|
"num_tokens": 3412990.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.947238445281982,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 7.0372,
|
|
"mean_token_accuracy": 0.11110711246728897,
|
|
"num_tokens": 3422339.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.149367761611939,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 7.0285,
|
|
"mean_token_accuracy": 0.11542280092835426,
|
|
"num_tokens": 3433093.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.15626335144043,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 7.1192,
|
|
"mean_token_accuracy": 0.10659995451569557,
|
|
"num_tokens": 3443464.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.114335584640503,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 7.0495,
|
|
"mean_token_accuracy": 0.10678325593471527,
|
|
"num_tokens": 3453380.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.190001773834228,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 7.1148,
|
|
"mean_token_accuracy": 0.11223250329494476,
|
|
"num_tokens": 3463583.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.0208066463470455,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 7.0105,
|
|
"mean_token_accuracy": 0.11592019125819206,
|
|
"num_tokens": 3473640.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.113274097442627,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 7.0769,
|
|
"mean_token_accuracy": 0.11162511184811592,
|
|
"num_tokens": 3483827.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.152011203765869,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 7.0245,
|
|
"mean_token_accuracy": 0.11725858971476555,
|
|
"num_tokens": 3493763.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.105683755874634,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 7.1331,
|
|
"mean_token_accuracy": 0.10835669562220573,
|
|
"num_tokens": 3503119.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.186274528503418,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 7.0585,
|
|
"mean_token_accuracy": 0.10770363509654998,
|
|
"num_tokens": 3513235.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.211988544464111,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.1643,
|
|
"mean_token_accuracy": 0.10430835708975791,
|
|
"num_tokens": 3523633.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.082215309143066,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 7.0093,
|
|
"mean_token_accuracy": 0.11031374111771583,
|
|
"num_tokens": 3532888.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.140625905990601,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 7.0527,
|
|
"mean_token_accuracy": 0.11224330216646194,
|
|
"num_tokens": 3541942.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.046121978759766,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 7.0113,
|
|
"mean_token_accuracy": 0.10969708785414696,
|
|
"num_tokens": 3551544.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.076622200012207,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.11504804566502572,
|
|
"num_tokens": 3561024.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.142001152038574,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 6.9931,
|
|
"mean_token_accuracy": 0.11953055635094642,
|
|
"num_tokens": 3570962.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.922073125839233,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 6.9879,
|
|
"mean_token_accuracy": 0.11443007588386536,
|
|
"num_tokens": 3580669.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.153632020950317,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 7.0082,
|
|
"mean_token_accuracy": 0.11323033571243286,
|
|
"num_tokens": 3590627.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.0444121837615965,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 7.0866,
|
|
"mean_token_accuracy": 0.10459914803504944,
|
|
"num_tokens": 3599872.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.135852479934693,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 7.0671,
|
|
"mean_token_accuracy": 0.11241727098822593,
|
|
"num_tokens": 3609809.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.2499583721160885,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 7.0773,
|
|
"mean_token_accuracy": 0.11519879400730133,
|
|
"num_tokens": 3619385.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.968499565124512,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.9203,
|
|
"mean_token_accuracy": 0.12208465933799743,
|
|
"num_tokens": 3628867.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.032136726379394,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.9271,
|
|
"mean_token_accuracy": 0.11781778261065483,
|
|
"num_tokens": 3637528.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.131372499465942,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 7.0523,
|
|
"mean_token_accuracy": 0.10981304794549943,
|
|
"num_tokens": 3648011.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.092602205276489,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 7.0339,
|
|
"mean_token_accuracy": 0.11578032821416855,
|
|
"num_tokens": 3657648.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.072668981552124,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 7.0437,
|
|
"mean_token_accuracy": 0.11318779215216637,
|
|
"num_tokens": 3666965.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.153492784500122,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 7.0735,
|
|
"mean_token_accuracy": 0.10511444881558418,
|
|
"num_tokens": 3676609.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.012405109405518,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.9304,
|
|
"mean_token_accuracy": 0.11578108370304108,
|
|
"num_tokens": 3685884.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.043309020996094,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 7.0879,
|
|
"mean_token_accuracy": 0.11302101239562035,
|
|
"num_tokens": 3695436.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.1143311023712155,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.9076,
|
|
"mean_token_accuracy": 0.12109773308038711,
|
|
"num_tokens": 3704806.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.979010534286499,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 6.9918,
|
|
"mean_token_accuracy": 0.11695808097720146,
|
|
"num_tokens": 3713927.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.1983567237854,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 7.0666,
|
|
"mean_token_accuracy": 0.10940969362854958,
|
|
"num_tokens": 3723685.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.993364381790161,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 7.0327,
|
|
"mean_token_accuracy": 0.11247843354940415,
|
|
"num_tokens": 3733918.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.085520219802857,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 6.9868,
|
|
"mean_token_accuracy": 0.11154783442616463,
|
|
"num_tokens": 3744466.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.1121289253234865,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.9372,
|
|
"mean_token_accuracy": 0.11101839020848274,
|
|
"num_tokens": 3754082.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.008188533782959,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.9694,
|
|
"mean_token_accuracy": 0.11511853858828544,
|
|
"num_tokens": 3763111.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.1465226173400875,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 7.0187,
|
|
"mean_token_accuracy": 0.10961114466190339,
|
|
"num_tokens": 3772555.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.155064296722412,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 7.0649,
|
|
"mean_token_accuracy": 0.1120420217514038,
|
|
"num_tokens": 3783073.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.897677850723267,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 7.0001,
|
|
"mean_token_accuracy": 0.1147444948554039,
|
|
"num_tokens": 3792277.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.110321664810181,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.9678,
|
|
"mean_token_accuracy": 0.11609976217150689,
|
|
"num_tokens": 3801098.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.104807186126709,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 6.9855,
|
|
"mean_token_accuracy": 0.11322086304426193,
|
|
"num_tokens": 3810614.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.023803997039795,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.9879,
|
|
"mean_token_accuracy": 0.11285669654607773,
|
|
"num_tokens": 3818989.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.011999940872192,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 7.0185,
|
|
"mean_token_accuracy": 0.11454365253448487,
|
|
"num_tokens": 3829319.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.093687629699707,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 7.052,
|
|
"mean_token_accuracy": 0.10922376289963723,
|
|
"num_tokens": 3839545.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.0437132835388185,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.982,
|
|
"mean_token_accuracy": 0.11502454653382302,
|
|
"num_tokens": 3849029.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.036665391921997,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 7.0307,
|
|
"mean_token_accuracy": 0.11234677508473397,
|
|
"num_tokens": 3859463.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.178880786895752,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 7.0665,
|
|
"mean_token_accuracy": 0.1138896718621254,
|
|
"num_tokens": 3869695.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.052155542373657,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 7.0182,
|
|
"mean_token_accuracy": 0.11386001110076904,
|
|
"num_tokens": 3879608.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.002656650543213,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.9328,
|
|
"mean_token_accuracy": 0.11322358548641205,
|
|
"num_tokens": 3888709.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.9356893539428714,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.8784,
|
|
"mean_token_accuracy": 0.11385609433054925,
|
|
"num_tokens": 3898392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.109602928161621,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 7.0962,
|
|
"mean_token_accuracy": 0.10173079818487167,
|
|
"num_tokens": 3909508.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.016517782211304,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.9499,
|
|
"mean_token_accuracy": 0.11535055190324783,
|
|
"num_tokens": 3918155.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.097119283676148,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 6.9733,
|
|
"mean_token_accuracy": 0.11269012987613677,
|
|
"num_tokens": 3928478.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.00243239402771,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 7.0207,
|
|
"mean_token_accuracy": 0.12159764543175697,
|
|
"num_tokens": 3938126.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.912168693542481,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.8656,
|
|
"mean_token_accuracy": 0.11626059859991074,
|
|
"num_tokens": 3948176.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.11488447189331,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.9832,
|
|
"mean_token_accuracy": 0.11340783983469009,
|
|
"num_tokens": 3958983.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.037908840179443,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.9383,
|
|
"mean_token_accuracy": 0.11477451324462891,
|
|
"num_tokens": 3968766.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.995463895797729,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.9589,
|
|
"mean_token_accuracy": 0.11554277166724206,
|
|
"num_tokens": 3979487.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.027395153045655,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.9399,
|
|
"mean_token_accuracy": 0.11524380594491959,
|
|
"num_tokens": 3988450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.013701009750366,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.9426,
|
|
"mean_token_accuracy": 0.11618846654891968,
|
|
"num_tokens": 3997492.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.018197727203369,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.9379,
|
|
"mean_token_accuracy": 0.11913173943758011,
|
|
"num_tokens": 4007298.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.063361120223999,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.9694,
|
|
"mean_token_accuracy": 0.11549432277679443,
|
|
"num_tokens": 4017727.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.956744623184204,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.9688,
|
|
"mean_token_accuracy": 0.11394633799791336,
|
|
"num_tokens": 4027618.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.018502855300904,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.1113269604742527,
|
|
"num_tokens": 4038831.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.088349199295044,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.9536,
|
|
"mean_token_accuracy": 0.11713754236698151,
|
|
"num_tokens": 4048736.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.927730417251587,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.8668,
|
|
"mean_token_accuracy": 0.11648354679346085,
|
|
"num_tokens": 4057633.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.0192708492279055,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.1224412478506565,
|
|
"num_tokens": 4067883.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.048581552505493,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.8595,
|
|
"mean_token_accuracy": 0.12078917920589446,
|
|
"num_tokens": 4078147.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.922640562057495,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.8328,
|
|
"mean_token_accuracy": 0.12206020206212997,
|
|
"num_tokens": 4087130.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.915320634841919,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.9515,
|
|
"mean_token_accuracy": 0.12251704409718514,
|
|
"num_tokens": 4096840.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.133029270172119,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.9766,
|
|
"mean_token_accuracy": 0.11555029898881912,
|
|
"num_tokens": 4105842.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.949610185623169,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.11520621851086617,
|
|
"num_tokens": 4114865.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.083245754241943,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 7.0161,
|
|
"mean_token_accuracy": 0.10906583741307259,
|
|
"num_tokens": 4124954.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.9515073776245115,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.12042388617992401,
|
|
"num_tokens": 4134091.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.048494529724121,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.9573,
|
|
"mean_token_accuracy": 0.11529561281204223,
|
|
"num_tokens": 4143566.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.024812936782837,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.9208,
|
|
"mean_token_accuracy": 0.11166013404726982,
|
|
"num_tokens": 4153053.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.9540647029876705,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.896,
|
|
"mean_token_accuracy": 0.12232667654752731,
|
|
"num_tokens": 4162925.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.9011767387390135,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.1230908177793026,
|
|
"num_tokens": 4172077.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.9595249652862545,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.9244,
|
|
"mean_token_accuracy": 0.11470091789960861,
|
|
"num_tokens": 4182134.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.040814352035523,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.9441,
|
|
"mean_token_accuracy": 0.11132864132523537,
|
|
"num_tokens": 4191963.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.906561183929443,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.8927,
|
|
"mean_token_accuracy": 0.11642092615365982,
|
|
"num_tokens": 4202180.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.05922155380249,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.924,
|
|
"mean_token_accuracy": 0.11686432883143424,
|
|
"num_tokens": 4211874.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.941175365447998,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.11368393003940583,
|
|
"num_tokens": 4221610.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.828761768341065,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.831,
|
|
"mean_token_accuracy": 0.12876630201935768,
|
|
"num_tokens": 4230610.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.962120294570923,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.9461,
|
|
"mean_token_accuracy": 0.11206507235765457,
|
|
"num_tokens": 4241389.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.020627546310425,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.8901,
|
|
"mean_token_accuracy": 0.11771368458867074,
|
|
"num_tokens": 4250617.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.930497503280639,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.8774,
|
|
"mean_token_accuracy": 0.12080463096499443,
|
|
"num_tokens": 4260000.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.881647682189941,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.8233,
|
|
"mean_token_accuracy": 0.11715791299939156,
|
|
"num_tokens": 4269751.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.977957820892334,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.8898,
|
|
"mean_token_accuracy": 0.11791151389479637,
|
|
"num_tokens": 4279210.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.000884628295898,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.84,
|
|
"mean_token_accuracy": 0.1202585093677044,
|
|
"num_tokens": 4288573.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.901773357391358,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.8756,
|
|
"mean_token_accuracy": 0.11356504261493683,
|
|
"num_tokens": 4298438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.925487279891968,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.7819,
|
|
"mean_token_accuracy": 0.12836189493536948,
|
|
"num_tokens": 4307174.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.067652225494385,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.9745,
|
|
"mean_token_accuracy": 0.1136770062148571,
|
|
"num_tokens": 4317220.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.984744215011597,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.12194864749908448,
|
|
"num_tokens": 4326496.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.905305337905884,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.11901782974600791,
|
|
"num_tokens": 4335705.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.03793044090271,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.9112,
|
|
"mean_token_accuracy": 0.1200287975370884,
|
|
"num_tokens": 4344711.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.928197145462036,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.9239,
|
|
"mean_token_accuracy": 0.11762578636407853,
|
|
"num_tokens": 4355448.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.843606281280517,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.7873,
|
|
"mean_token_accuracy": 0.12028947919607162,
|
|
"num_tokens": 4365104.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.9312232494354244,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.12458315268158912,
|
|
"num_tokens": 4375219.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.943724775314331,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.9059,
|
|
"mean_token_accuracy": 0.11273334845900536,
|
|
"num_tokens": 4385294.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.021584129333496,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.8766,
|
|
"mean_token_accuracy": 0.11276980042457581,
|
|
"num_tokens": 4394305.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.873253679275512,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.7415,
|
|
"mean_token_accuracy": 0.12254593893885612,
|
|
"num_tokens": 4403732.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.929276704788208,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.9641,
|
|
"mean_token_accuracy": 0.11173295974731445,
|
|
"num_tokens": 4413730.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.033787107467651,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.9852,
|
|
"mean_token_accuracy": 0.11005716025829315,
|
|
"num_tokens": 4423051.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.026523208618164,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.9691,
|
|
"mean_token_accuracy": 0.11586882919073105,
|
|
"num_tokens": 4433363.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.950811290740967,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.9189,
|
|
"mean_token_accuracy": 0.11593685448169708,
|
|
"num_tokens": 4442984.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.989126873016358,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.865,
|
|
"mean_token_accuracy": 0.11428796350955964,
|
|
"num_tokens": 4452364.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.007836103439331,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.8918,
|
|
"mean_token_accuracy": 0.11280409172177315,
|
|
"num_tokens": 4461904.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.916662788391113,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.838,
|
|
"mean_token_accuracy": 0.11601078361272812,
|
|
"num_tokens": 4470633.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.945051670074463,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.8637,
|
|
"mean_token_accuracy": 0.11577488556504249,
|
|
"num_tokens": 4480673.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.933673238754272,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.11377951726317406,
|
|
"num_tokens": 4489923.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.885636615753174,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.8218,
|
|
"mean_token_accuracy": 0.11800332292914391,
|
|
"num_tokens": 4501007.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.897295141220093,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.8368,
|
|
"mean_token_accuracy": 0.11717171370983123,
|
|
"num_tokens": 4510460.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.949653673171997,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.11965522542595863,
|
|
"num_tokens": 4521026.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.94604001045227,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.12275644540786743,
|
|
"num_tokens": 4530818.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.833601999282837,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.129067625105381,
|
|
"num_tokens": 4539512.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.991441965103149,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.9527,
|
|
"mean_token_accuracy": 0.10756491348147393,
|
|
"num_tokens": 4549030.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.9421521663665775,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.8029,
|
|
"mean_token_accuracy": 0.12596326917409897,
|
|
"num_tokens": 4559347.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.901503849029541,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.8526,
|
|
"mean_token_accuracy": 0.11550995856523513,
|
|
"num_tokens": 4568721.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.883442735671997,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.8582,
|
|
"mean_token_accuracy": 0.11971477419137955,
|
|
"num_tokens": 4578265.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.883966016769409,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.8159,
|
|
"mean_token_accuracy": 0.12598463222384454,
|
|
"num_tokens": 4588694.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.959873485565185,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.819,
|
|
"mean_token_accuracy": 0.1255710557103157,
|
|
"num_tokens": 4597754.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.884046936035157,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.8304,
|
|
"mean_token_accuracy": 0.12266772165894509,
|
|
"num_tokens": 4606874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.87273941040039,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.7216,
|
|
"mean_token_accuracy": 0.12119160741567611,
|
|
"num_tokens": 4615588.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.8096753597259525,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.8858,
|
|
"mean_token_accuracy": 0.12267793342471123,
|
|
"num_tokens": 4625919.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.987924003601075,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.8238,
|
|
"mean_token_accuracy": 0.1198611631989479,
|
|
"num_tokens": 4635539.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.882870531082153,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.8214,
|
|
"mean_token_accuracy": 0.11646069437265397,
|
|
"num_tokens": 4645833.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.859278011322021,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.9272,
|
|
"mean_token_accuracy": 0.12224952504038811,
|
|
"num_tokens": 4655166.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.9933693408966064,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.8107,
|
|
"mean_token_accuracy": 0.1250378169119358,
|
|
"num_tokens": 4664884.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.858077096939087,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.9125,
|
|
"mean_token_accuracy": 0.11868099793791771,
|
|
"num_tokens": 4675172.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.997228765487671,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.1240590751171112,
|
|
"num_tokens": 4684588.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.890038633346558,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.9168,
|
|
"mean_token_accuracy": 0.12128965482115746,
|
|
"num_tokens": 4694434.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.885320329666138,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.8599,
|
|
"mean_token_accuracy": 0.11919219568371772,
|
|
"num_tokens": 4705080.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.015338325500489,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.9445,
|
|
"mean_token_accuracy": 0.115231192111969,
|
|
"num_tokens": 4714466.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.8764424324035645,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.8364,
|
|
"mean_token_accuracy": 0.1243220515549183,
|
|
"num_tokens": 4724047.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.968001174926758,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.8619,
|
|
"mean_token_accuracy": 0.11686329171061516,
|
|
"num_tokens": 4733153.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.93342227935791,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.7318,
|
|
"mean_token_accuracy": 0.1258167415857315,
|
|
"num_tokens": 4743239.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.811439895629883,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.7928,
|
|
"mean_token_accuracy": 0.11975357532501221,
|
|
"num_tokens": 4753128.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.061700773239136,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 7.041,
|
|
"mean_token_accuracy": 0.10650341138243676,
|
|
"num_tokens": 4764056.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.925562858581543,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.8635,
|
|
"mean_token_accuracy": 0.1168606698513031,
|
|
"num_tokens": 4773354.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.838783550262451,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.7888,
|
|
"mean_token_accuracy": 0.11904187425971031,
|
|
"num_tokens": 4783367.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.842602968215942,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.6707,
|
|
"mean_token_accuracy": 0.13226605579257011,
|
|
"num_tokens": 4793028.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.91138973236084,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.8631,
|
|
"mean_token_accuracy": 0.11812737509608269,
|
|
"num_tokens": 4804032.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.952124071121216,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.8866,
|
|
"mean_token_accuracy": 0.12024495378136635,
|
|
"num_tokens": 4813294.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.905491209030151,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.7871,
|
|
"mean_token_accuracy": 0.12213733345270157,
|
|
"num_tokens": 4823461.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.783637142181396,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.8421,
|
|
"mean_token_accuracy": 0.12206422239542007,
|
|
"num_tokens": 4832464.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.889177703857422,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.8056,
|
|
"mean_token_accuracy": 0.11893631145358086,
|
|
"num_tokens": 4842697.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.928496265411377,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.8574,
|
|
"mean_token_accuracy": 0.120989241451025,
|
|
"num_tokens": 4853129.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.909238862991333,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.903,
|
|
"mean_token_accuracy": 0.11157827898859977,
|
|
"num_tokens": 4864048.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.845878267288208,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.8355,
|
|
"mean_token_accuracy": 0.1195888414978981,
|
|
"num_tokens": 4874368.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.974607992172241,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.12127717137336731,
|
|
"num_tokens": 4884813.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.844524717330932,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.882,
|
|
"mean_token_accuracy": 0.11751366555690765,
|
|
"num_tokens": 4895594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.964616298675537,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.774,
|
|
"mean_token_accuracy": 0.12162590026855469,
|
|
"num_tokens": 4904922.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.8929506778717045,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.11948562785983086,
|
|
"num_tokens": 4915009.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.884179592132568,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.914,
|
|
"mean_token_accuracy": 0.1151105597615242,
|
|
"num_tokens": 4924916.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.864490032196045,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.8192,
|
|
"mean_token_accuracy": 0.11743849441409111,
|
|
"num_tokens": 4935127.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.89161958694458,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.8121,
|
|
"mean_token_accuracy": 0.12027946040034294,
|
|
"num_tokens": 4944749.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.839969301223755,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.13174954876303674,
|
|
"num_tokens": 4953868.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.85071587562561,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.781,
|
|
"mean_token_accuracy": 0.1238086350262165,
|
|
"num_tokens": 4963282.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.700375747680664,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.6188,
|
|
"mean_token_accuracy": 0.13516242504119874,
|
|
"num_tokens": 4973099.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.858307123184204,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.8016,
|
|
"mean_token_accuracy": 0.11923333331942558,
|
|
"num_tokens": 4983771.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.813778829574585,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.13007574677467346,
|
|
"num_tokens": 4993648.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.8086004734039305,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.8059,
|
|
"mean_token_accuracy": 0.12374277338385582,
|
|
"num_tokens": 5002821.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9158666133880615,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.8179,
|
|
"mean_token_accuracy": 0.11914320066571235,
|
|
"num_tokens": 5012655.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.749571657180786,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.11989297941327096,
|
|
"num_tokens": 5023649.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.877628374099731,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.7411,
|
|
"mean_token_accuracy": 0.1278075806796551,
|
|
"num_tokens": 5031945.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.862940835952759,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.815,
|
|
"mean_token_accuracy": 0.11514976248145103,
|
|
"num_tokens": 5042036.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.813757658004761,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.7905,
|
|
"mean_token_accuracy": 0.12084953859448433,
|
|
"num_tokens": 5050986.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.886504650115967,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.7903,
|
|
"mean_token_accuracy": 0.1246580310165882,
|
|
"num_tokens": 5061408.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.785292768478394,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.12291771844029427,
|
|
"num_tokens": 5071646.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.817554712295532,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.8184,
|
|
"mean_token_accuracy": 0.12439500764012337,
|
|
"num_tokens": 5083185.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.925652647018433,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.7735,
|
|
"mean_token_accuracy": 0.12057823091745376,
|
|
"num_tokens": 5092993.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.828229284286499,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.8237,
|
|
"mean_token_accuracy": 0.11826542019844055,
|
|
"num_tokens": 5102709.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.896103000640869,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.7654,
|
|
"mean_token_accuracy": 0.11819369643926621,
|
|
"num_tokens": 5112858.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.856741428375244,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.6749,
|
|
"mean_token_accuracy": 0.1281345531344414,
|
|
"num_tokens": 5123573.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.764648580551148,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.8517,
|
|
"mean_token_accuracy": 0.11786950081586837,
|
|
"num_tokens": 5132908.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.912869548797607,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.7485,
|
|
"mean_token_accuracy": 0.1265025995671749,
|
|
"num_tokens": 5142331.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.9357281684875485,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.8393,
|
|
"mean_token_accuracy": 0.11436363682150841,
|
|
"num_tokens": 5152517.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.8380382537841795,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.7778,
|
|
"mean_token_accuracy": 0.12275150492787361,
|
|
"num_tokens": 5162418.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.820027017593384,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.7797,
|
|
"mean_token_accuracy": 0.11911472529172898,
|
|
"num_tokens": 5171948.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.898890399932862,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.12626254335045814,
|
|
"num_tokens": 5180963.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.807502412796021,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.8283,
|
|
"mean_token_accuracy": 0.12082352638244628,
|
|
"num_tokens": 5192305.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.86788969039917,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.7126,
|
|
"mean_token_accuracy": 0.12578068524599076,
|
|
"num_tokens": 5201503.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.793289661407471,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.6664,
|
|
"mean_token_accuracy": 0.12352387979626656,
|
|
"num_tokens": 5210206.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.692011928558349,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.1274379923939705,
|
|
"num_tokens": 5220256.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.840415620803833,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.7336,
|
|
"mean_token_accuracy": 0.1253110870718956,
|
|
"num_tokens": 5229128.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.794884872436524,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.6659,
|
|
"mean_token_accuracy": 0.12167781367897987,
|
|
"num_tokens": 5239468.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.794555521011352,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.768,
|
|
"mean_token_accuracy": 0.12150566056370735,
|
|
"num_tokens": 5247957.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.927483987808228,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.7862,
|
|
"mean_token_accuracy": 0.1188110314309597,
|
|
"num_tokens": 5257960.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.722643184661865,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.6354,
|
|
"mean_token_accuracy": 0.1271999478340149,
|
|
"num_tokens": 5266696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.765709590911865,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.13072306290268898,
|
|
"num_tokens": 5275619.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.817221784591675,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.1238712303340435,
|
|
"num_tokens": 5284884.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.799127197265625,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.6684,
|
|
"mean_token_accuracy": 0.1343806691467762,
|
|
"num_tokens": 5293909.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.712032699584961,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.1175712764263153,
|
|
"num_tokens": 5303142.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.842455434799194,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.11897132322192192,
|
|
"num_tokens": 5313055.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.790426254272461,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.7946,
|
|
"mean_token_accuracy": 0.11414426565170288,
|
|
"num_tokens": 5323773.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.721665477752685,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.13403543531894685,
|
|
"num_tokens": 5334613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.777459335327149,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.664,
|
|
"mean_token_accuracy": 0.12990061491727828,
|
|
"num_tokens": 5344151.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.7387457370758055,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.12913709804415702,
|
|
"num_tokens": 5352425.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.82868595123291,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.8319,
|
|
"mean_token_accuracy": 0.11914294064044953,
|
|
"num_tokens": 5361811.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.832614994049072,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.11754570752382279,
|
|
"num_tokens": 5371463.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.818097829818726,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.6401,
|
|
"mean_token_accuracy": 0.1298965960741043,
|
|
"num_tokens": 5381464.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.674585819244385,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.7192,
|
|
"mean_token_accuracy": 0.1203085571527481,
|
|
"num_tokens": 5391012.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.939772033691407,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.8237,
|
|
"mean_token_accuracy": 0.12208779081702233,
|
|
"num_tokens": 5401198.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.8920979499816895,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.12084006369113923,
|
|
"num_tokens": 5410592.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.6667835235595705,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.12609246745705605,
|
|
"num_tokens": 5420878.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.835362100601197,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.7409,
|
|
"mean_token_accuracy": 0.12492544427514077,
|
|
"num_tokens": 5431199.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.808431673049927,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.68,
|
|
"mean_token_accuracy": 0.1254745155572891,
|
|
"num_tokens": 5441661.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.681165075302124,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.6732,
|
|
"mean_token_accuracy": 0.12912385687232017,
|
|
"num_tokens": 5451863.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.828213024139404,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.7308,
|
|
"mean_token_accuracy": 0.12578752413392066,
|
|
"num_tokens": 5461600.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.906319808959961,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.11796140745282173,
|
|
"num_tokens": 5470097.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.886836528778076,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.8941,
|
|
"mean_token_accuracy": 0.11296176090836525,
|
|
"num_tokens": 5480906.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.949836778640747,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.11996870562434196,
|
|
"num_tokens": 5489732.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.6947015762329105,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.5782,
|
|
"mean_token_accuracy": 0.13047064021229743,
|
|
"num_tokens": 5498422.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.7099450588226315,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.7244,
|
|
"mean_token_accuracy": 0.12029694393277168,
|
|
"num_tokens": 5507958.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.8781578540802,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.7506,
|
|
"mean_token_accuracy": 0.1246604599058628,
|
|
"num_tokens": 5516752.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.751307106018066,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.7763,
|
|
"mean_token_accuracy": 0.12477909997105599,
|
|
"num_tokens": 5527211.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.780982398986817,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.12461251020431519,
|
|
"num_tokens": 5536925.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.845695829391479,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.8396,
|
|
"mean_token_accuracy": 0.1158826120197773,
|
|
"num_tokens": 5546800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.741491508483887,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.6801,
|
|
"mean_token_accuracy": 0.1240173600614071,
|
|
"num_tokens": 5557266.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.809528160095215,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.12244971096515656,
|
|
"num_tokens": 5566169.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.791384696960449,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.12420285567641258,
|
|
"num_tokens": 5575566.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.755648517608643,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.6381,
|
|
"mean_token_accuracy": 0.12499300390481949,
|
|
"num_tokens": 5584804.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.7822061538696286,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.1191313810646534,
|
|
"num_tokens": 5594361.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.848558330535889,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.12073459699749947,
|
|
"num_tokens": 5605682.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.7933878898620605,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.768,
|
|
"mean_token_accuracy": 0.118593979626894,
|
|
"num_tokens": 5617251.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.756092596054077,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.12677795737981795,
|
|
"num_tokens": 5627140.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.708715581893921,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.5964,
|
|
"mean_token_accuracy": 0.12997669354081154,
|
|
"num_tokens": 5635486.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.793992185592652,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.7669,
|
|
"mean_token_accuracy": 0.11563235074281693,
|
|
"num_tokens": 5645621.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.9069499492645265,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.8248,
|
|
"mean_token_accuracy": 0.11520569920539855,
|
|
"num_tokens": 5655626.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.817208242416382,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.12128069922327996,
|
|
"num_tokens": 5664547.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.791419172286988,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.747,
|
|
"mean_token_accuracy": 0.12001895159482956,
|
|
"num_tokens": 5674861.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.762214231491089,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.6782,
|
|
"mean_token_accuracy": 0.11858229264616967,
|
|
"num_tokens": 5684143.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.764250040054321,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.6529,
|
|
"mean_token_accuracy": 0.12445368096232415,
|
|
"num_tokens": 5693837.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.869545316696167,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.11787635460495949,
|
|
"num_tokens": 5704827.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.8025154113769535,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.7719,
|
|
"mean_token_accuracy": 0.12075797915458679,
|
|
"num_tokens": 5714419.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.739893627166748,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.12215565443038941,
|
|
"num_tokens": 5724983.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.787188720703125,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.6291,
|
|
"mean_token_accuracy": 0.12742045596241952,
|
|
"num_tokens": 5734471.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.803781652450562,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.7518,
|
|
"mean_token_accuracy": 0.12121198177337647,
|
|
"num_tokens": 5744801.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.755331993103027,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.11747701466083527,
|
|
"num_tokens": 5754267.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.691815185546875,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.6434,
|
|
"mean_token_accuracy": 0.1278532288968563,
|
|
"num_tokens": 5764466.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.797782039642334,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.12012682259082794,
|
|
"num_tokens": 5775158.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.804054927825928,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.1323493793606758,
|
|
"num_tokens": 5783320.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.675914669036866,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.7086,
|
|
"mean_token_accuracy": 0.12223785743117332,
|
|
"num_tokens": 5792980.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.874987697601318,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.7467,
|
|
"mean_token_accuracy": 0.12244661524891853,
|
|
"num_tokens": 5802338.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.739057731628418,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.6364,
|
|
"mean_token_accuracy": 0.12737288773059846,
|
|
"num_tokens": 5811388.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.72182264328003,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.12516121342778205,
|
|
"num_tokens": 5821108.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.731955909729004,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.7281,
|
|
"mean_token_accuracy": 0.1192234419286251,
|
|
"num_tokens": 5831389.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.72219705581665,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.5871,
|
|
"mean_token_accuracy": 0.13089271262288094,
|
|
"num_tokens": 5840392.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.748080110549926,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.6116,
|
|
"mean_token_accuracy": 0.12855779454112054,
|
|
"num_tokens": 5850032.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.770363426208496,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.6699,
|
|
"mean_token_accuracy": 0.12747157365083694,
|
|
"num_tokens": 5859204.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.715180587768555,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.12443819269537926,
|
|
"num_tokens": 5868582.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.790849494934082,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.6241,
|
|
"mean_token_accuracy": 0.1298421509563923,
|
|
"num_tokens": 5879601.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.615208382644594,
|
|
"eval_loss": 6.721776008605957,
|
|
"eval_mean_token_accuracy": 0.1284465000584829,
|
|
"eval_num_tokens": 5879601.0,
|
|
"eval_runtime": 23.8533,
|
|
"eval_samples_per_second": 1301.497,
|
|
"eval_steps_per_second": 162.703,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.722339534759522,
|
|
"epoch": 0.30039486179837055,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995454644392967,
|
|
"loss": 6.6878,
|
|
"mean_token_accuracy": 0.11981307566165925,
|
|
"num_tokens": 5890255.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.71357798576355,
|
|
"epoch": 0.30089468685959914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995431942370087,
|
|
"loss": 6.7052,
|
|
"mean_token_accuracy": 0.1337470643222332,
|
|
"num_tokens": 5899965.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.788109397888183,
|
|
"epoch": 0.3013945119208277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995409183852718,
|
|
"loss": 6.5939,
|
|
"mean_token_accuracy": 0.1301611252129078,
|
|
"num_tokens": 5910082.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.672738313674927,
|
|
"epoch": 0.30189433698205626,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995386368841432,
|
|
"loss": 6.7355,
|
|
"mean_token_accuracy": 0.12291843146085739,
|
|
"num_tokens": 5920267.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.816665887832642,
|
|
"epoch": 0.30239416204328484,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995363497336802,
|
|
"loss": 6.7141,
|
|
"mean_token_accuracy": 0.12424932271242142,
|
|
"num_tokens": 5929275.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.827727603912353,
|
|
"epoch": 0.30289398710451343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995340569339405,
|
|
"loss": 6.7413,
|
|
"mean_token_accuracy": 0.11787217631936073,
|
|
"num_tokens": 5939305.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.836606121063232,
|
|
"epoch": 0.303393812165742,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004995317584849817,
|
|
"loss": 6.8025,
|
|
"mean_token_accuracy": 0.11330446675419807,
|
|
"num_tokens": 5950816.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.678486394882202,
|
|
"epoch": 0.30389363722697055,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995294543868615,
|
|
"loss": 6.5774,
|
|
"mean_token_accuracy": 0.13259122967720033,
|
|
"num_tokens": 5959824.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.767902612686157,
|
|
"epoch": 0.30439346228819913,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995271446396382,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.12707387283444405,
|
|
"num_tokens": 5968752.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.74622220993042,
|
|
"epoch": 0.3048932873494277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995248292433697,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.12331249415874482,
|
|
"num_tokens": 5979085.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.713514804840088,
|
|
"epoch": 0.30539311241065625,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995225081981142,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.12420432046055793,
|
|
"num_tokens": 5990378.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.778734540939331,
|
|
"epoch": 0.30589293747188484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995201815039301,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.13564710617065429,
|
|
"num_tokens": 5999524.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.687535905838013,
|
|
"epoch": 0.3063927625331134,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995178491608762,
|
|
"loss": 6.6806,
|
|
"mean_token_accuracy": 0.12482227534055709,
|
|
"num_tokens": 6009928.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.640461874008179,
|
|
"epoch": 0.30689258759434196,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995155111690107,
|
|
"loss": 6.5585,
|
|
"mean_token_accuracy": 0.1330404207110405,
|
|
"num_tokens": 6019683.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.843991374969482,
|
|
"epoch": 0.30739241265557055,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499513167528393,
|
|
"loss": 6.6812,
|
|
"mean_token_accuracy": 0.1237489826977253,
|
|
"num_tokens": 6030506.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.77349967956543,
|
|
"epoch": 0.30789223771679913,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995108182390815,
|
|
"loss": 6.6639,
|
|
"mean_token_accuracy": 0.1260622389614582,
|
|
"num_tokens": 6039720.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.598236227035523,
|
|
"epoch": 0.30839206277802766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995084633011359,
|
|
"loss": 6.5091,
|
|
"mean_token_accuracy": 0.13624039590358733,
|
|
"num_tokens": 6049336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.623972368240357,
|
|
"epoch": 0.30889188783925625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499506102714615,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.12994642406702042,
|
|
"num_tokens": 6059420.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.739403963088989,
|
|
"epoch": 0.30939171290048484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995037364795782,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.1298194333910942,
|
|
"num_tokens": 6069035.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.70915584564209,
|
|
"epoch": 0.3098915379617134,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995013645960853,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.123585245013237,
|
|
"num_tokens": 6077863.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.67954273223877,
|
|
"epoch": 0.31039136302294196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994989870641958,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.12600963637232782,
|
|
"num_tokens": 6088929.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.679830694198609,
|
|
"epoch": 0.31089118808417054,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994966038839695,
|
|
"loss": 6.6119,
|
|
"mean_token_accuracy": 0.13017525151371956,
|
|
"num_tokens": 6098673.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.706893873214722,
|
|
"epoch": 0.31139101314539913,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994942150554666,
|
|
"loss": 6.4884,
|
|
"mean_token_accuracy": 0.1320834055542946,
|
|
"num_tokens": 6107289.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.5927753925323485,
|
|
"epoch": 0.31189083820662766,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994918205787468,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.13047196641564368,
|
|
"num_tokens": 6117811.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.712067270278931,
|
|
"epoch": 0.31239066326785625,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994894204538706,
|
|
"loss": 6.6538,
|
|
"mean_token_accuracy": 0.12287433221936225,
|
|
"num_tokens": 6127740.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.733972358703613,
|
|
"epoch": 0.31289048832908484,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994870146808984,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.12414981052279472,
|
|
"num_tokens": 6137253.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.68615574836731,
|
|
"epoch": 0.31339031339031337,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994846032598906,
|
|
"loss": 6.6661,
|
|
"mean_token_accuracy": 0.12876934111118316,
|
|
"num_tokens": 6147420.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.702655982971192,
|
|
"epoch": 0.31389013845154196,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994821861909082,
|
|
"loss": 6.6069,
|
|
"mean_token_accuracy": 0.1283666931092739,
|
|
"num_tokens": 6156436.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.622131776809693,
|
|
"epoch": 0.31438996351277054,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994797634740114,
|
|
"loss": 6.5698,
|
|
"mean_token_accuracy": 0.126331477612257,
|
|
"num_tokens": 6165526.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.778597736358643,
|
|
"epoch": 0.3148897885739991,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994773351092618,
|
|
"loss": 6.7677,
|
|
"mean_token_accuracy": 0.12162536010146141,
|
|
"num_tokens": 6176093.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.703013753890991,
|
|
"epoch": 0.31538961363522766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049947490109672,
|
|
"loss": 6.5791,
|
|
"mean_token_accuracy": 0.1345700092613697,
|
|
"num_tokens": 6185373.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.736076927185058,
|
|
"epoch": 0.31588943869645625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994724614364476,
|
|
"loss": 6.6927,
|
|
"mean_token_accuracy": 0.12343047335743904,
|
|
"num_tokens": 6196252.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.801714611053467,
|
|
"epoch": 0.31638926375768484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994700161285058,
|
|
"loss": 6.6215,
|
|
"mean_token_accuracy": 0.1300746403634548,
|
|
"num_tokens": 6206463.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.67550048828125,
|
|
"epoch": 0.31688908881891337,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499467565172956,
|
|
"loss": 6.6001,
|
|
"mean_token_accuracy": 0.1312672823667526,
|
|
"num_tokens": 6216676.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.689395141601563,
|
|
"epoch": 0.31738891388014195,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994651085698602,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.1254762552678585,
|
|
"num_tokens": 6227261.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.707279872894287,
|
|
"epoch": 0.31788873894137054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049946264631928,
|
|
"loss": 6.5674,
|
|
"mean_token_accuracy": 0.12468275651335717,
|
|
"num_tokens": 6237468.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.642337942123413,
|
|
"epoch": 0.3183885640025991,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994601784212774,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.136201723664999,
|
|
"num_tokens": 6247164.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.649035453796387,
|
|
"epoch": 0.31888838906382766,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994577048759144,
|
|
"loss": 6.6264,
|
|
"mean_token_accuracy": 0.13031774014234543,
|
|
"num_tokens": 6257635.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.798333024978637,
|
|
"epoch": 0.31938821412505625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994552256832533,
|
|
"loss": 6.6984,
|
|
"mean_token_accuracy": 0.1256155826151371,
|
|
"num_tokens": 6266823.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.774302530288696,
|
|
"epoch": 0.3198880391862848,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994527408433566,
|
|
"loss": 6.6072,
|
|
"mean_token_accuracy": 0.12974709048867225,
|
|
"num_tokens": 6276527.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.751862907409668,
|
|
"epoch": 0.32038786424751337,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994502503562865,
|
|
"loss": 6.6704,
|
|
"mean_token_accuracy": 0.12288417518138886,
|
|
"num_tokens": 6286499.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.685272693634033,
|
|
"epoch": 0.32088768930874195,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499447754222106,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.130257061868906,
|
|
"num_tokens": 6296550.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.667414760589599,
|
|
"epoch": 0.3213875143699705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994452524408777,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.1256569355726242,
|
|
"num_tokens": 6306951.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.833637809753418,
|
|
"epoch": 0.32188733943119907,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994427450126646,
|
|
"loss": 6.6768,
|
|
"mean_token_accuracy": 0.11989659443497658,
|
|
"num_tokens": 6316026.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.648589992523194,
|
|
"epoch": 0.32238716449242766,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994402319375298,
|
|
"loss": 6.6104,
|
|
"mean_token_accuracy": 0.12591632306575776,
|
|
"num_tokens": 6325064.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.721154403686524,
|
|
"epoch": 0.32288698955365625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994377132155366,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.12740512788295746,
|
|
"num_tokens": 6334443.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.727579784393311,
|
|
"epoch": 0.3233868146148848,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994351888467482,
|
|
"loss": 6.643,
|
|
"mean_token_accuracy": 0.12921743839979172,
|
|
"num_tokens": 6346103.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.644028043746948,
|
|
"epoch": 0.32388663967611336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994326588312282,
|
|
"loss": 6.6215,
|
|
"mean_token_accuracy": 0.12528072744607927,
|
|
"num_tokens": 6356576.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.75742621421814,
|
|
"epoch": 0.32438646473734195,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994301231690403,
|
|
"loss": 6.6181,
|
|
"mean_token_accuracy": 0.12732079029083251,
|
|
"num_tokens": 6364796.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.732314491271973,
|
|
"epoch": 0.3248862897985705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994275818602482,
|
|
"loss": 6.6953,
|
|
"mean_token_accuracy": 0.12702387496829032,
|
|
"num_tokens": 6374951.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.662586832046509,
|
|
"epoch": 0.32538611485979907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994250349049159,
|
|
"loss": 6.5877,
|
|
"mean_token_accuracy": 0.1256158784031868,
|
|
"num_tokens": 6384230.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.721761417388916,
|
|
"epoch": 0.32588593992102766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994224823031075,
|
|
"loss": 6.5777,
|
|
"mean_token_accuracy": 0.12750042378902435,
|
|
"num_tokens": 6394070.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.610982847213745,
|
|
"epoch": 0.3263857649822562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994199240548873,
|
|
"loss": 6.5717,
|
|
"mean_token_accuracy": 0.13098210096359253,
|
|
"num_tokens": 6403968.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.757144117355347,
|
|
"epoch": 0.3268855900434848,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994173601603194,
|
|
"loss": 6.6887,
|
|
"mean_token_accuracy": 0.1251855470240116,
|
|
"num_tokens": 6413254.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.648221397399903,
|
|
"epoch": 0.32738541510471336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994147906194684,
|
|
"loss": 6.5344,
|
|
"mean_token_accuracy": 0.1325840137898922,
|
|
"num_tokens": 6421266.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.694507598876953,
|
|
"epoch": 0.3278852401659419,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994122154323992,
|
|
"loss": 6.6342,
|
|
"mean_token_accuracy": 0.1262752406299114,
|
|
"num_tokens": 6429596.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.775129127502441,
|
|
"epoch": 0.3283850652271705,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994096345991763,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.12423462271690369,
|
|
"num_tokens": 6440825.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.608078670501709,
|
|
"epoch": 0.32888489028839907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994070481198649,
|
|
"loss": 6.5928,
|
|
"mean_token_accuracy": 0.12965668961405755,
|
|
"num_tokens": 6450576.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.702484655380249,
|
|
"epoch": 0.32938471534962765,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994044559945296,
|
|
"loss": 6.5951,
|
|
"mean_token_accuracy": 0.13519497066736222,
|
|
"num_tokens": 6459673.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.664275407791138,
|
|
"epoch": 0.3298845404108562,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994018582232361,
|
|
"loss": 6.5782,
|
|
"mean_token_accuracy": 0.12735630720853805,
|
|
"num_tokens": 6469353.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.654953193664551,
|
|
"epoch": 0.3303843654720848,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993992548060497,
|
|
"loss": 6.5833,
|
|
"mean_token_accuracy": 0.1305153839290142,
|
|
"num_tokens": 6479610.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.682379102706909,
|
|
"epoch": 0.33088419053331336,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993966457430357,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.131649050116539,
|
|
"num_tokens": 6488866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.717644453048706,
|
|
"epoch": 0.3313840155945419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993940310342598,
|
|
"loss": 6.518,
|
|
"mean_token_accuracy": 0.13404856026172637,
|
|
"num_tokens": 6498396.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.6136088371276855,
|
|
"epoch": 0.3318838406557705,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993914106797879,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.1354752868413925,
|
|
"num_tokens": 6508347.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.722569513320923,
|
|
"epoch": 0.33238366571699907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993887846796858,
|
|
"loss": 6.6592,
|
|
"mean_token_accuracy": 0.12250009402632714,
|
|
"num_tokens": 6518369.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.662774610519409,
|
|
"epoch": 0.3328834907782276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993861530340196,
|
|
"loss": 6.6214,
|
|
"mean_token_accuracy": 0.13503153324127198,
|
|
"num_tokens": 6527477.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.718849229812622,
|
|
"epoch": 0.3333833158394562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993835157428555,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.13233767300844193,
|
|
"num_tokens": 6536271.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.716184806823731,
|
|
"epoch": 0.33388314090068477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993808728062599,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.13095614314079285,
|
|
"num_tokens": 6546295.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.672792673110962,
|
|
"epoch": 0.3343829659619133,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993782242242994,
|
|
"loss": 6.5532,
|
|
"mean_token_accuracy": 0.13651400059461594,
|
|
"num_tokens": 6557338.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.640097570419312,
|
|
"epoch": 0.3348827910231419,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993755699970404,
|
|
"loss": 6.57,
|
|
"mean_token_accuracy": 0.13229951858520508,
|
|
"num_tokens": 6567916.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.671002817153931,
|
|
"epoch": 0.3353826160843705,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993729101245498,
|
|
"loss": 6.6875,
|
|
"mean_token_accuracy": 0.12816037237644196,
|
|
"num_tokens": 6577821.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.742249488830566,
|
|
"epoch": 0.33588244114559906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993702446068945,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.1282327353954315,
|
|
"num_tokens": 6587674.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.683386659622192,
|
|
"epoch": 0.3363822662068276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993675734441416,
|
|
"loss": 6.6515,
|
|
"mean_token_accuracy": 0.13280568197369574,
|
|
"num_tokens": 6597292.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.594243669509888,
|
|
"epoch": 0.3368820912680562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993648966363583,
|
|
"loss": 6.5701,
|
|
"mean_token_accuracy": 0.13267690166831017,
|
|
"num_tokens": 6608698.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.730088233947754,
|
|
"epoch": 0.33738191632928477,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499362214183612,
|
|
"loss": 6.5643,
|
|
"mean_token_accuracy": 0.12787219882011414,
|
|
"num_tokens": 6617914.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.590554046630859,
|
|
"epoch": 0.3378817413905133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049935952608597,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.13169657364487647,
|
|
"num_tokens": 6627457.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.691078758239746,
|
|
"epoch": 0.3383815664517419,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993568323435002,
|
|
"loss": 6.5613,
|
|
"mean_token_accuracy": 0.13399697616696357,
|
|
"num_tokens": 6636511.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.647966480255127,
|
|
"epoch": 0.3388813915129705,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993541329562702,
|
|
"loss": 6.5478,
|
|
"mean_token_accuracy": 0.12832800596952437,
|
|
"num_tokens": 6647028.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.6662462711334225,
|
|
"epoch": 0.339381216574199,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993514279243477,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.1287503607571125,
|
|
"num_tokens": 6656407.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.704301548004151,
|
|
"epoch": 0.3398810416354276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993487172478012,
|
|
"loss": 6.5443,
|
|
"mean_token_accuracy": 0.13133591488003732,
|
|
"num_tokens": 6665554.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.704265069961548,
|
|
"epoch": 0.3403808666966562,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993460009266988,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.12598370388150215,
|
|
"num_tokens": 6675730.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.577371120452881,
|
|
"epoch": 0.3408806917578847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993432789611086,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.13635042160749436,
|
|
"num_tokens": 6685871.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.715635204315186,
|
|
"epoch": 0.3413805168191133,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993405513510992,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.1186644345521927,
|
|
"num_tokens": 6697503.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.721425724029541,
|
|
"epoch": 0.3418803418803419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993378180967394,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.13019852563738823,
|
|
"num_tokens": 6708022.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.631089878082276,
|
|
"epoch": 0.3423801669415705,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993350791980978,
|
|
"loss": 6.6171,
|
|
"mean_token_accuracy": 0.13050465658307076,
|
|
"num_tokens": 6717510.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.6999125480651855,
|
|
"epoch": 0.342879992002799,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993323346552433,
|
|
"loss": 6.6302,
|
|
"mean_token_accuracy": 0.1296307161450386,
|
|
"num_tokens": 6726538.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.747427368164063,
|
|
"epoch": 0.3433798170640276,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993295844682449,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.13428208231925964,
|
|
"num_tokens": 6736750.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.616900205612183,
|
|
"epoch": 0.3438796421252562,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499326828637172,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.1279594212770462,
|
|
"num_tokens": 6746366.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.578363037109375,
|
|
"epoch": 0.3443794671864847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993240671620938,
|
|
"loss": 6.5935,
|
|
"mean_token_accuracy": 0.12818874344229697,
|
|
"num_tokens": 6755887.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.709596347808838,
|
|
"epoch": 0.3448792922477133,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993213000430797,
|
|
"loss": 6.5994,
|
|
"mean_token_accuracy": 0.13560046702623368,
|
|
"num_tokens": 6764434.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.743025636672973,
|
|
"epoch": 0.3453791173089419,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993185272801995,
|
|
"loss": 6.7018,
|
|
"mean_token_accuracy": 0.11916685327887536,
|
|
"num_tokens": 6774237.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.760094881057739,
|
|
"epoch": 0.3458789423701704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993157488735228,
|
|
"loss": 6.5579,
|
|
"mean_token_accuracy": 0.12662035152316092,
|
|
"num_tokens": 6784537.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.629041051864624,
|
|
"epoch": 0.346378767431399,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993129648231197,
|
|
"loss": 6.5326,
|
|
"mean_token_accuracy": 0.13424717038869857,
|
|
"num_tokens": 6794223.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.571995496749878,
|
|
"epoch": 0.3468785924926276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049931017512906,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.1289962500333786,
|
|
"num_tokens": 6803680.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.819319772720337,
|
|
"epoch": 0.3473784175538562,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993073797914141,
|
|
"loss": 6.5711,
|
|
"mean_token_accuracy": 0.1251891352236271,
|
|
"num_tokens": 6812853.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.609120512008667,
|
|
"epoch": 0.3478782426150847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993045788102522,
|
|
"loss": 6.6439,
|
|
"mean_token_accuracy": 0.12747282832860946,
|
|
"num_tokens": 6822104.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.676856327056885,
|
|
"epoch": 0.3483780676763133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993017721856449,
|
|
"loss": 6.609,
|
|
"mean_token_accuracy": 0.12209485694766045,
|
|
"num_tokens": 6832683.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.785378742218017,
|
|
"epoch": 0.3488778927375419,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992989599176626,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.12543685734272003,
|
|
"num_tokens": 6843191.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.6238781929016115,
|
|
"epoch": 0.3493777177987704,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992961420063763,
|
|
"loss": 6.5765,
|
|
"mean_token_accuracy": 0.128035569190979,
|
|
"num_tokens": 6852205.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.5474427223205565,
|
|
"epoch": 0.349877542859999,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992933184518567,
|
|
"loss": 6.4989,
|
|
"mean_token_accuracy": 0.1326678402721882,
|
|
"num_tokens": 6863052.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.698447322845459,
|
|
"epoch": 0.3503773679212276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992904892541749,
|
|
"loss": 6.5544,
|
|
"mean_token_accuracy": 0.13316056430339812,
|
|
"num_tokens": 6872717.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.612038040161133,
|
|
"epoch": 0.3508771929824561,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992876544134022,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.14064068496227264,
|
|
"num_tokens": 6881351.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.6335334300994875,
|
|
"epoch": 0.3513770180436847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992848139296098,
|
|
"loss": 6.5409,
|
|
"mean_token_accuracy": 0.1337484709918499,
|
|
"num_tokens": 6891353.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.704902029037475,
|
|
"epoch": 0.3518768431049133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992819678028692,
|
|
"loss": 6.632,
|
|
"mean_token_accuracy": 0.1213303491473198,
|
|
"num_tokens": 6902352.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.70453896522522,
|
|
"epoch": 0.3523766681661418,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499279116033252,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.12167268171906472,
|
|
"num_tokens": 6911950.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.6038049221038815,
|
|
"epoch": 0.3528764932273704,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992762586208299,
|
|
"loss": 6.5089,
|
|
"mean_token_accuracy": 0.13899552896618844,
|
|
"num_tokens": 6921949.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.612030172348023,
|
|
"epoch": 0.353376318288599,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992733955656749,
|
|
"loss": 6.5462,
|
|
"mean_token_accuracy": 0.12957046926021576,
|
|
"num_tokens": 6932561.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.609406471252441,
|
|
"epoch": 0.3538761433498276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992705268678589,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.13685213252902031,
|
|
"num_tokens": 6941663.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.713863706588745,
|
|
"epoch": 0.3543759684110561,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992676525274542,
|
|
"loss": 6.5588,
|
|
"mean_token_accuracy": 0.12517699003219604,
|
|
"num_tokens": 6952373.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.566033792495728,
|
|
"epoch": 0.3548757934722847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992647725445331,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.13661421239376068,
|
|
"num_tokens": 6961337.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.611299800872803,
|
|
"epoch": 0.3553756185335133,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499261886919168,
|
|
"loss": 6.5146,
|
|
"mean_token_accuracy": 0.13746540248394012,
|
|
"num_tokens": 6971649.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.637835550308227,
|
|
"epoch": 0.3558754435947418,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992589956514316,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.13472158834338188,
|
|
"num_tokens": 6982261.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.612603998184204,
|
|
"epoch": 0.3563752686559704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992560987413965,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.13068577498197556,
|
|
"num_tokens": 6991324.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.5739234447479244,
|
|
"epoch": 0.356875093717199,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992531961891356,
|
|
"loss": 6.5021,
|
|
"mean_token_accuracy": 0.1353994868695736,
|
|
"num_tokens": 7001396.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.6809157371521,
|
|
"epoch": 0.35737491877842753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992502879947222,
|
|
"loss": 6.5211,
|
|
"mean_token_accuracy": 0.13213353380560874,
|
|
"num_tokens": 7010354.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.7170140743255615,
|
|
"epoch": 0.3578747438396561,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992473741582291,
|
|
"loss": 6.6138,
|
|
"mean_token_accuracy": 0.1270657241344452,
|
|
"num_tokens": 7019835.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.604812335968018,
|
|
"epoch": 0.3583745689008847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992444546797298,
|
|
"loss": 6.4893,
|
|
"mean_token_accuracy": 0.13503527417778968,
|
|
"num_tokens": 7030515.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.482302570343018,
|
|
"epoch": 0.35887439396211324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992415295592977,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.1355128839612007,
|
|
"num_tokens": 7041248.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.6671782493591305,
|
|
"epoch": 0.3593742190233418,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004992385987970064,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.12790912985801697,
|
|
"num_tokens": 7050578.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.6769624710083,
|
|
"epoch": 0.3598740440845704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992356623929297,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.12897216081619262,
|
|
"num_tokens": 7060270.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.673832035064697,
|
|
"epoch": 0.360373869145799,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992327203471414,
|
|
"loss": 6.61,
|
|
"mean_token_accuracy": 0.1256176747381687,
|
|
"num_tokens": 7070259.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.6119787216186525,
|
|
"epoch": 0.36087369420702753,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992297726597156,
|
|
"loss": 6.5286,
|
|
"mean_token_accuracy": 0.13310132548213005,
|
|
"num_tokens": 7078784.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.685658502578735,
|
|
"epoch": 0.3613735192682561,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992268193307264,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.12648143023252487,
|
|
"num_tokens": 7088632.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.586120223999023,
|
|
"epoch": 0.3618733443294847,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992238603602481,
|
|
"loss": 6.5741,
|
|
"mean_token_accuracy": 0.13020266816020012,
|
|
"num_tokens": 7097703.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.632631015777588,
|
|
"epoch": 0.36237316939071323,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992208957483552,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.13478429317474366,
|
|
"num_tokens": 7107183.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.700596857070923,
|
|
"epoch": 0.3628729944519418,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992179254951223,
|
|
"loss": 6.6018,
|
|
"mean_token_accuracy": 0.12561058178544043,
|
|
"num_tokens": 7118220.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.612575483322144,
|
|
"epoch": 0.3633728195131704,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499214949600624,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.1306740276515484,
|
|
"num_tokens": 7128322.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.569721794128418,
|
|
"epoch": 0.36387264457439894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992119680649355,
|
|
"loss": 6.5336,
|
|
"mean_token_accuracy": 0.1307792566716671,
|
|
"num_tokens": 7137284.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.63422269821167,
|
|
"epoch": 0.3643724696356275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992089808881313,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.13586053177714347,
|
|
"num_tokens": 7146598.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.760889482498169,
|
|
"epoch": 0.3648722946968561,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992059880702869,
|
|
"loss": 6.6247,
|
|
"mean_token_accuracy": 0.13818052485585214,
|
|
"num_tokens": 7156816.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.649261569976806,
|
|
"epoch": 0.36537211975808465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992029896114775,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.12462318763136863,
|
|
"num_tokens": 7166855.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.510309648513794,
|
|
"epoch": 0.36587194481931323,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991999855117787,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.13755838945508003,
|
|
"num_tokens": 7176477.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.62469482421875,
|
|
"epoch": 0.3663717698805418,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991969757712659,
|
|
"loss": 6.494,
|
|
"mean_token_accuracy": 0.1370445244014263,
|
|
"num_tokens": 7186173.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.57085165977478,
|
|
"epoch": 0.3668715949417704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991939603900149,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.13398399949073792,
|
|
"num_tokens": 7195403.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.644307947158813,
|
|
"epoch": 0.36737142000299894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991909393681015,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.13114903271198272,
|
|
"num_tokens": 7204179.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.545143175125122,
|
|
"epoch": 0.3678712450642275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991879127056017,
|
|
"loss": 6.5021,
|
|
"mean_token_accuracy": 0.13197836726903917,
|
|
"num_tokens": 7214159.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.579304599761963,
|
|
"epoch": 0.3683710701254561,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991848804025918,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.1352105386555195,
|
|
"num_tokens": 7224410.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.567760944366455,
|
|
"epoch": 0.36887089518668464,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499181842459148,
|
|
"loss": 6.5287,
|
|
"mean_token_accuracy": 0.1385655641555786,
|
|
"num_tokens": 7233740.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.60739917755127,
|
|
"epoch": 0.36937072024791323,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991787988753467,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.13437757566571235,
|
|
"num_tokens": 7242834.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.596049737930298,
|
|
"epoch": 0.3698705453091418,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991757496512645,
|
|
"loss": 6.4689,
|
|
"mean_token_accuracy": 0.14437328651547432,
|
|
"num_tokens": 7252098.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.69606122970581,
|
|
"epoch": 0.37037037037037035,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991726947869782,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.12470240518450737,
|
|
"num_tokens": 7261396.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.645996379852295,
|
|
"epoch": 0.37087019543159894,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991696342825645,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.12552324086427688,
|
|
"num_tokens": 7271138.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.613135957717896,
|
|
"epoch": 0.3713700204928275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991665681381005,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.13709988445043564,
|
|
"num_tokens": 7280164.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.61772780418396,
|
|
"epoch": 0.37186984555405606,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991634963536633,
|
|
"loss": 6.5355,
|
|
"mean_token_accuracy": 0.12880035787820815,
|
|
"num_tokens": 7288830.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.611929702758789,
|
|
"epoch": 0.37236967061528464,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991604189293303,
|
|
"loss": 6.5986,
|
|
"mean_token_accuracy": 0.12981483489274978,
|
|
"num_tokens": 7298955.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.655997228622437,
|
|
"epoch": 0.37286949567651323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991573358651787,
|
|
"loss": 6.4864,
|
|
"mean_token_accuracy": 0.1318989910185337,
|
|
"num_tokens": 7309829.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.608906221389771,
|
|
"epoch": 0.3733693207377418,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991542471612864,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.1318919137120247,
|
|
"num_tokens": 7319654.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.657841587066651,
|
|
"epoch": 0.37386914579897035,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991511528177307,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.1277618497610092,
|
|
"num_tokens": 7330415.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.699305057525635,
|
|
"epoch": 0.37436897086019894,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991480528345898,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.13054054901003836,
|
|
"num_tokens": 7339511.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.668748903274536,
|
|
"epoch": 0.3748687959214275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991449472119416,
|
|
"loss": 6.5632,
|
|
"mean_token_accuracy": 0.12433832362294198,
|
|
"num_tokens": 7348488.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.558110761642456,
|
|
"epoch": 0.37536862098265605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991418359498642,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.13206134289503096,
|
|
"num_tokens": 7357804.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.666992425918579,
|
|
"epoch": 0.37586844604388464,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991387190484358,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.1281794637441635,
|
|
"num_tokens": 7367644.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.595050287246704,
|
|
"epoch": 0.37636827110511323,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000499135596507735,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.13311903551220894,
|
|
"num_tokens": 7377357.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.59745774269104,
|
|
"epoch": 0.37686809616634176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991324683278402,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.1272532433271408,
|
|
"num_tokens": 7387306.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.632649183273315,
|
|
"epoch": 0.37736792122757035,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991293345088301,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.13223535642027856,
|
|
"num_tokens": 7397472.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.616477346420288,
|
|
"epoch": 0.37786774628879893,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991261950507837,
|
|
"loss": 6.5722,
|
|
"mean_token_accuracy": 0.1321080319583416,
|
|
"num_tokens": 7408786.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.612939405441284,
|
|
"epoch": 0.37836757135002747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049912304995378,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.12643783465027808,
|
|
"num_tokens": 7417857.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.605091714859009,
|
|
"epoch": 0.37886739641125605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991198992178979,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.1272548370063305,
|
|
"num_tokens": 7427007.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.648046636581421,
|
|
"epoch": 0.37936722147248464,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991167428432168,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.13773693814873694,
|
|
"num_tokens": 7437090.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.557371425628662,
|
|
"epoch": 0.3798670465337132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991135808298162,
|
|
"loss": 6.4864,
|
|
"mean_token_accuracy": 0.1327134557068348,
|
|
"num_tokens": 7446249.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.659952926635742,
|
|
"epoch": 0.38036687159494176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991104131777755,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.1275357760488987,
|
|
"num_tokens": 7455838.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.599836826324463,
|
|
"epoch": 0.38086669665617034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991072398871746,
|
|
"loss": 6.5768,
|
|
"mean_token_accuracy": 0.12697244733572005,
|
|
"num_tokens": 7466057.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.653259801864624,
|
|
"epoch": 0.38136652171739893,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991040609580932,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.13301845714449884,
|
|
"num_tokens": 7475174.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.621293783187866,
|
|
"epoch": 0.38186634677862746,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991008763906112,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.1384720526635647,
|
|
"num_tokens": 7484635.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.563889026641846,
|
|
"epoch": 0.38236617183985605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990976861848087,
|
|
"loss": 6.5357,
|
|
"mean_token_accuracy": 0.13021118119359015,
|
|
"num_tokens": 7496428.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.613593816757202,
|
|
"epoch": 0.38286599690108464,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990944903407663,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.1307319588959217,
|
|
"num_tokens": 7506581.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.635296249389649,
|
|
"epoch": 0.38336582196231317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990912888585641,
|
|
"loss": 6.4424,
|
|
"mean_token_accuracy": 0.1384415827691555,
|
|
"num_tokens": 7515809.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.487102079391479,
|
|
"epoch": 0.38386564702354176,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990880817382828,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.13676456585526467,
|
|
"num_tokens": 7525800.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.626596069335937,
|
|
"epoch": 0.38436547208477034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499084868980003,
|
|
"loss": 6.5738,
|
|
"mean_token_accuracy": 0.13002618104219438,
|
|
"num_tokens": 7536903.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.612464952468872,
|
|
"epoch": 0.3848652971459989,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990816505838054,
|
|
"loss": 6.5298,
|
|
"mean_token_accuracy": 0.1257986307144165,
|
|
"num_tokens": 7546004.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.652705144882202,
|
|
"epoch": 0.38536512220722746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990784265497713,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.1285960353910923,
|
|
"num_tokens": 7555971.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.683477163314819,
|
|
"epoch": 0.38586494726845605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990751968779817,
|
|
"loss": 6.5536,
|
|
"mean_token_accuracy": 0.13212867379188536,
|
|
"num_tokens": 7564569.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.594289970397949,
|
|
"epoch": 0.38636477232968464,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990719615685176,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.1284814417362213,
|
|
"num_tokens": 7574134.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.67630033493042,
|
|
"epoch": 0.38686459739091317,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990687206214608,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.13904297202825547,
|
|
"num_tokens": 7583631.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.487108564376831,
|
|
"epoch": 0.38736442245214175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990654740368925,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.13795554339885713,
|
|
"num_tokens": 7593281.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.448543834686279,
|
|
"epoch": 0.38786424751337034,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990622218148947,
|
|
"loss": 6.5306,
|
|
"mean_token_accuracy": 0.13075224310159683,
|
|
"num_tokens": 7603735.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.709584045410156,
|
|
"epoch": 0.3883640725745989,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990589639555489,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.1292933240532875,
|
|
"num_tokens": 7613126.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.645783376693726,
|
|
"epoch": 0.38886389763582746,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990557004589373,
|
|
"loss": 6.5278,
|
|
"mean_token_accuracy": 0.12787676602602005,
|
|
"num_tokens": 7623191.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.572176170349121,
|
|
"epoch": 0.38936372269705605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990524313251419,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.13649313077330588,
|
|
"num_tokens": 7634118.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.572763109207154,
|
|
"epoch": 0.3898635477582846,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990491565542449,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.1431651771068573,
|
|
"num_tokens": 7643228.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.490762662887573,
|
|
"epoch": 0.39036337281951317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990458761463289,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.1269106924533844,
|
|
"num_tokens": 7652578.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.612861061096192,
|
|
"epoch": 0.39086319788074175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990425901014763,
|
|
"loss": 6.4509,
|
|
"mean_token_accuracy": 0.13192059248685836,
|
|
"num_tokens": 7661617.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.5336158752441404,
|
|
"epoch": 0.3913630229419703,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990392984197697,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.1394348494708538,
|
|
"num_tokens": 7670864.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.572642993927002,
|
|
"epoch": 0.39186284800319887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990360011012921,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.12711714655160905,
|
|
"num_tokens": 7681528.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.668974161148071,
|
|
"epoch": 0.39236267306442746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990326981461264,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.13255584686994554,
|
|
"num_tokens": 7690398.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.461314916610718,
|
|
"epoch": 0.39286249812565605,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990293895543555,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.13599226996302605,
|
|
"num_tokens": 7699843.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.546249485015869,
|
|
"epoch": 0.3933623231868846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499026075326063,
|
|
"loss": 6.5107,
|
|
"mean_token_accuracy": 0.1358805276453495,
|
|
"num_tokens": 7710181.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.648956441879273,
|
|
"epoch": 0.39386214824811316,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499022755461332,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.13313849717378617,
|
|
"num_tokens": 7719148.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.438974761962891,
|
|
"epoch": 0.39436197330934175,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499019429960246,
|
|
"loss": 6.3295,
|
|
"mean_token_accuracy": 0.14517943039536477,
|
|
"num_tokens": 7728551.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.55150351524353,
|
|
"epoch": 0.3948617983705703,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990160988228888,
|
|
"loss": 6.5259,
|
|
"mean_token_accuracy": 0.12912257239222527,
|
|
"num_tokens": 7739083.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.653018426895142,
|
|
"epoch": 0.39536162343179887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990127620493444,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.13356704488396645,
|
|
"num_tokens": 7749684.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.540141296386719,
|
|
"epoch": 0.39586144849302746,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990094196396964,
|
|
"loss": 6.3969,
|
|
"mean_token_accuracy": 0.13822795003652572,
|
|
"num_tokens": 7759281.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.52960433959961,
|
|
"epoch": 0.396361273554256,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499006071594029,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.13620271161198616,
|
|
"num_tokens": 7768612.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.552225589752197,
|
|
"epoch": 0.3968610986154846,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990027179124266,
|
|
"loss": 6.424,
|
|
"mean_token_accuracy": 0.13467555791139602,
|
|
"num_tokens": 7778333.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.65633454322815,
|
|
"epoch": 0.39736092367671316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989993585949733,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.12997083067893983,
|
|
"num_tokens": 7787547.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.531152963638306,
|
|
"epoch": 0.3978607487379417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989959936417541,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.13278501704335213,
|
|
"num_tokens": 7798407.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.558915996551514,
|
|
"epoch": 0.3983605737991703,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498992623052853,
|
|
"loss": 6.4154,
|
|
"mean_token_accuracy": 0.14237021654844284,
|
|
"num_tokens": 7807879.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.485930013656616,
|
|
"epoch": 0.39886039886039887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989892468283553,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.13894546329975127,
|
|
"num_tokens": 7817210.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.660465812683105,
|
|
"epoch": 0.39936022392162746,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989858649683457,
|
|
"loss": 6.6211,
|
|
"mean_token_accuracy": 0.12636715099215506,
|
|
"num_tokens": 7827845.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.727644062042236,
|
|
"epoch": 0.399860048982856,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989824774729094,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.13661194518208503,
|
|
"num_tokens": 7836994.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.53096227645874,
|
|
"epoch": 0.4003598740440846,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989790843421317,
|
|
"loss": 6.5293,
|
|
"mean_token_accuracy": 0.13115536719560622,
|
|
"num_tokens": 7846733.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.515123510360718,
|
|
"epoch": 0.40085969910531316,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004989756855760979,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.13563456535339355,
|
|
"num_tokens": 7856393.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.645159435272217,
|
|
"epoch": 0.4013595241665417,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989722811748934,
|
|
"loss": 6.5328,
|
|
"mean_token_accuracy": 0.13331457674503328,
|
|
"num_tokens": 7866394.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.595888614654541,
|
|
"epoch": 0.4018593492277703,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989688711386039,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.1277965322136879,
|
|
"num_tokens": 7877084.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.656990814208984,
|
|
"epoch": 0.40235917428899887,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989654554673152,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.1284612499177456,
|
|
"num_tokens": 7887289.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.553845167160034,
|
|
"epoch": 0.4028589993502274,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989620341611133,
|
|
"loss": 6.4928,
|
|
"mean_token_accuracy": 0.1331907719373703,
|
|
"num_tokens": 7897315.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.681213474273681,
|
|
"epoch": 0.403358824411456,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989586072200843,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.12706032618880272,
|
|
"num_tokens": 7905913.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.57252607345581,
|
|
"epoch": 0.40385864947268457,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989551746443143,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.1398092433810234,
|
|
"num_tokens": 7914879.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.54695086479187,
|
|
"epoch": 0.4043584745339131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989517364338899,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.13144304752349853,
|
|
"num_tokens": 7925163.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.656905651092529,
|
|
"epoch": 0.4048582995951417,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989482925888974,
|
|
"loss": 6.4442,
|
|
"mean_token_accuracy": 0.13604791313409806,
|
|
"num_tokens": 7934380.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.5723072528839115,
|
|
"epoch": 0.4053581246563703,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989448431094233,
|
|
"loss": 6.505,
|
|
"mean_token_accuracy": 0.12940779998898505,
|
|
"num_tokens": 7944600.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.492002820968628,
|
|
"epoch": 0.40585794971759886,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989413879955548,
|
|
"loss": 6.4116,
|
|
"mean_token_accuracy": 0.1383023105561733,
|
|
"num_tokens": 7953545.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.512488126754761,
|
|
"epoch": 0.4063577747788274,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989379272473785,
|
|
"loss": 6.4916,
|
|
"mean_token_accuracy": 0.13396764397621155,
|
|
"num_tokens": 7962931.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.619950819015503,
|
|
"epoch": 0.406857599840056,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004989344608649815,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.13626711219549179,
|
|
"num_tokens": 7973090.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.57343430519104,
|
|
"epoch": 0.40735742490128457,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989309888484511,
|
|
"loss": 6.5865,
|
|
"mean_token_accuracy": 0.12389916554093361,
|
|
"num_tokens": 7982208.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.533903121948242,
|
|
"epoch": 0.4078572499625131,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989275111978748,
|
|
"loss": 6.5283,
|
|
"mean_token_accuracy": 0.1353437304496765,
|
|
"num_tokens": 7993389.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.577138662338257,
|
|
"epoch": 0.4083570750237417,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989240279133398,
|
|
"loss": 6.4166,
|
|
"mean_token_accuracy": 0.13624165430665017,
|
|
"num_tokens": 8002749.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.607124853134155,
|
|
"epoch": 0.4088569000849703,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989205389949339,
|
|
"loss": 6.4177,
|
|
"mean_token_accuracy": 0.13583638072013854,
|
|
"num_tokens": 8011552.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.465263938903808,
|
|
"epoch": 0.4093567251461988,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989170444427448,
|
|
"loss": 6.4401,
|
|
"mean_token_accuracy": 0.13448849990963935,
|
|
"num_tokens": 8020622.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.486138868331909,
|
|
"epoch": 0.4098565502074274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989135442568606,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.13940291702747346,
|
|
"num_tokens": 8030356.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.590310192108154,
|
|
"epoch": 0.410356375268656,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989100384373693,
|
|
"loss": 6.4842,
|
|
"mean_token_accuracy": 0.12944861948490144,
|
|
"num_tokens": 8039903.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.558611154556274,
|
|
"epoch": 0.4108562003298845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989065269843588,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.1317477710545063,
|
|
"num_tokens": 8050488.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.529536294937134,
|
|
"epoch": 0.4113560253911131,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498903009897918,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.13413968533277512,
|
|
"num_tokens": 8060179.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.548681688308716,
|
|
"epoch": 0.4118558504523417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988994871781349,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.13198244497179984,
|
|
"num_tokens": 8070915.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.566651725769043,
|
|
"epoch": 0.4123556755135703,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988959588250983,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.13837631642818451,
|
|
"num_tokens": 8080203.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.558019542694092,
|
|
"epoch": 0.4128555005747988,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498892424838897,
|
|
"loss": 6.4488,
|
|
"mean_token_accuracy": 0.13629123866558074,
|
|
"num_tokens": 8090552.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.532246923446655,
|
|
"epoch": 0.4133553256360274,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988888852196199,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.13859262466430664,
|
|
"num_tokens": 8099947.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.519168424606323,
|
|
"epoch": 0.413855150697256,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988853399673562,
|
|
"loss": 6.5004,
|
|
"mean_token_accuracy": 0.12965430393815042,
|
|
"num_tokens": 8110502.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.593302869796753,
|
|
"epoch": 0.4143549757584845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988817890821948,
|
|
"loss": 6.5276,
|
|
"mean_token_accuracy": 0.12973300293087958,
|
|
"num_tokens": 8118762.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.579014635086059,
|
|
"epoch": 0.4148548008197131,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988782325642252,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.12978375628590583,
|
|
"num_tokens": 8129072.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.577251672744751,
|
|
"epoch": 0.4153546258809417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498874670413537,
|
|
"loss": 6.4643,
|
|
"mean_token_accuracy": 0.12749237492680549,
|
|
"num_tokens": 8138504.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.687809801101684,
|
|
"epoch": 0.4158544509421702,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988711026302197,
|
|
"loss": 6.5391,
|
|
"mean_token_accuracy": 0.1325111597776413,
|
|
"num_tokens": 8148534.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.560407733917236,
|
|
"epoch": 0.4163542760033988,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988675292143629,
|
|
"loss": 6.5791,
|
|
"mean_token_accuracy": 0.12417998611927032,
|
|
"num_tokens": 8160272.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.616597700119018,
|
|
"epoch": 0.4168541010646274,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988639501660568,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.13744847923517228,
|
|
"num_tokens": 8170053.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.641278076171875,
|
|
"epoch": 0.4173539261258559,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988603654853913,
|
|
"loss": 6.4686,
|
|
"mean_token_accuracy": 0.1311160683631897,
|
|
"num_tokens": 8179425.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.508156824111938,
|
|
"epoch": 0.4178537511870845,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988567751724565,
|
|
"loss": 6.4887,
|
|
"mean_token_accuracy": 0.13093385472893715,
|
|
"num_tokens": 8189846.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.579239797592163,
|
|
"epoch": 0.4183535762483131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498853179227343,
|
|
"loss": 6.5015,
|
|
"mean_token_accuracy": 0.13485166803002357,
|
|
"num_tokens": 8198596.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.628087949752808,
|
|
"epoch": 0.4188534013095417,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498849577650141,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.13375448137521745,
|
|
"num_tokens": 8206849.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.547364807128906,
|
|
"epoch": 0.4193532263707702,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988459704409413,
|
|
"loss": 6.4421,
|
|
"mean_token_accuracy": 0.13590684682130813,
|
|
"num_tokens": 8216260.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.561947917938232,
|
|
"epoch": 0.4198530514319988,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988423575998345,
|
|
"loss": 6.4716,
|
|
"mean_token_accuracy": 0.13637885823845863,
|
|
"num_tokens": 8224650.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.416500473022461,
|
|
"epoch": 0.4203528764932274,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004988387391269117,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.1439281329512596,
|
|
"num_tokens": 8235276.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.57451548576355,
|
|
"epoch": 0.4208527015544559,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988351150222638,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.13464779406785965,
|
|
"num_tokens": 8244687.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.576171207427978,
|
|
"epoch": 0.4213525266156845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988314852859819,
|
|
"loss": 6.5495,
|
|
"mean_token_accuracy": 0.1311263471841812,
|
|
"num_tokens": 8255091.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.430039262771606,
|
|
"epoch": 0.4218523516769131,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004988278499181575,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.14942151606082915,
|
|
"num_tokens": 8265172.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.5439403533935545,
|
|
"epoch": 0.4223521767381416,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498824208918882,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.13363671451807022,
|
|
"num_tokens": 8275625.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.441909456253052,
|
|
"epoch": 0.4228520017993702,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498820562288247,
|
|
"loss": 6.4127,
|
|
"mean_token_accuracy": 0.1346836991608143,
|
|
"num_tokens": 8284343.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.592450761795044,
|
|
"epoch": 0.4233518268605988,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988169100263442,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.12972462475299834,
|
|
"num_tokens": 8293430.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.562317848205566,
|
|
"epoch": 0.4238516519218274,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988132521332656,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12977709472179413,
|
|
"num_tokens": 8302925.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.502162170410156,
|
|
"epoch": 0.4243514769830559,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988095886091031,
|
|
"loss": 6.4335,
|
|
"mean_token_accuracy": 0.1341563068330288,
|
|
"num_tokens": 8312134.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.54831829071045,
|
|
"epoch": 0.4248513020442845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988059194539489,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.1345089428126812,
|
|
"num_tokens": 8320942.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.595415735244751,
|
|
"epoch": 0.4253511271055131,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988022446678954,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.13361355662345886,
|
|
"num_tokens": 8331898.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.467858219146729,
|
|
"epoch": 0.4258509521667416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987985642510352,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.1376283772289753,
|
|
"num_tokens": 8341728.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.537617444992065,
|
|
"epoch": 0.4263507772279702,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987948782034605,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.13970415219664573,
|
|
"num_tokens": 8351611.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.519968032836914,
|
|
"epoch": 0.4268506022891988,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987911865252644,
|
|
"loss": 6.4076,
|
|
"mean_token_accuracy": 0.1417715758085251,
|
|
"num_tokens": 8360528.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.440678501129151,
|
|
"epoch": 0.42735042735042733,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987874892165395,
|
|
"loss": 6.4679,
|
|
"mean_token_accuracy": 0.1354478821158409,
|
|
"num_tokens": 8369898.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.54773736000061,
|
|
"epoch": 0.4278502524116559,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498783786277379,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.1384521782398224,
|
|
"num_tokens": 8379928.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.575797080993652,
|
|
"epoch": 0.4283500774728845,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987800777078759,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.1369698688387871,
|
|
"num_tokens": 8389208.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.507793331146241,
|
|
"epoch": 0.42884990253411304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987763635081238,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.13886258453130723,
|
|
"num_tokens": 8398364.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.527761459350586,
|
|
"epoch": 0.4293497275953416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498772643678216,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.13071525171399118,
|
|
"num_tokens": 8408756.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.588776969909668,
|
|
"epoch": 0.4298495526565702,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987689182182459,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.1393563099205494,
|
|
"num_tokens": 8418318.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.485627889633179,
|
|
"epoch": 0.4303493777177988,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987651871283075,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.129922616481781,
|
|
"num_tokens": 8427709.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.570569610595703,
|
|
"epoch": 0.43084920277902733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987614504084946,
|
|
"loss": 6.4601,
|
|
"mean_token_accuracy": 0.12916277721524239,
|
|
"num_tokens": 8437848.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.584947824478149,
|
|
"epoch": 0.4313490278402559,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987577080589012,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.1359340153634548,
|
|
"num_tokens": 8447466.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.501195859909058,
|
|
"epoch": 0.4318488529014845,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987539600796213,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.14214334413409233,
|
|
"num_tokens": 8456651.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.558067512512207,
|
|
"epoch": 0.43234867796271303,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987502064707494,
|
|
"loss": 6.4643,
|
|
"mean_token_accuracy": 0.1354033648967743,
|
|
"num_tokens": 8466421.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.496439695358276,
|
|
"epoch": 0.4328485030239416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987464472323799,
|
|
"loss": 6.4057,
|
|
"mean_token_accuracy": 0.13391259014606477,
|
|
"num_tokens": 8476419.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.551824522018433,
|
|
"epoch": 0.4333483280851702,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987426823646074,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.13297546803951263,
|
|
"num_tokens": 8486652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.498467206954956,
|
|
"epoch": 0.43384815314639874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987389118675266,
|
|
"loss": 6.3827,
|
|
"mean_token_accuracy": 0.13717494830489158,
|
|
"num_tokens": 8495965.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.535243654251099,
|
|
"epoch": 0.4343479782076273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987351357412322,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.1338575914502144,
|
|
"num_tokens": 8506018.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.497014379501342,
|
|
"epoch": 0.4348478032688559,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987313539858196,
|
|
"loss": 6.4454,
|
|
"mean_token_accuracy": 0.13558314517140388,
|
|
"num_tokens": 8516178.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.585453891754151,
|
|
"epoch": 0.43534762833008445,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987275666013836,
|
|
"loss": 6.4918,
|
|
"mean_token_accuracy": 0.13078081533312796,
|
|
"num_tokens": 8525548.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.610603332519531,
|
|
"epoch": 0.43584745339131303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987237735880195,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.1313353419303894,
|
|
"num_tokens": 8535941.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.449689245223999,
|
|
"epoch": 0.4363472784525416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987199749458229,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.1431761458516121,
|
|
"num_tokens": 8545381.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.507636165618896,
|
|
"epoch": 0.4368471035137702,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987161706748893,
|
|
"loss": 6.4532,
|
|
"mean_token_accuracy": 0.13456403464078903,
|
|
"num_tokens": 8555827.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.456200647354126,
|
|
"epoch": 0.43734692857499874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987123607753144,
|
|
"loss": 6.3278,
|
|
"mean_token_accuracy": 0.14644061625003815,
|
|
"num_tokens": 8565508.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.585708093643189,
|
|
"epoch": 0.4378467536362273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498708545247194,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.12930210530757905,
|
|
"num_tokens": 8576273.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.59512243270874,
|
|
"epoch": 0.4383465786974559,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987047240906243,
|
|
"loss": 6.4783,
|
|
"mean_token_accuracy": 0.13295421227812768,
|
|
"num_tokens": 8585488.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.563721609115601,
|
|
"epoch": 0.43884640375868444,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987008973057012,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.1319626584649086,
|
|
"num_tokens": 8595299.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.517096900939942,
|
|
"epoch": 0.43934622881991303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986970648925211,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.13585217520594597,
|
|
"num_tokens": 8604910.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.542190885543823,
|
|
"epoch": 0.4398460538811416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986932268511804,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.1373402938246727,
|
|
"num_tokens": 8614966.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.479302310943604,
|
|
"epoch": 0.44034587894237015,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004986893831817758,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.1341715231537819,
|
|
"num_tokens": 8624539.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.482782411575317,
|
|
"epoch": 0.44084570400359874,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986855338844038,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.14404137432575226,
|
|
"num_tokens": 8633775.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.537249374389648,
|
|
"epoch": 0.4413455290648273,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986816789591613,
|
|
"loss": 6.4477,
|
|
"mean_token_accuracy": 0.13106013759970664,
|
|
"num_tokens": 8643798.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.402342319488525,
|
|
"epoch": 0.44184535412605586,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986778184061453,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.14136381298303605,
|
|
"num_tokens": 8653695.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.498728609085083,
|
|
"epoch": 0.44234517918728444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986739522254529,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.133646971732378,
|
|
"num_tokens": 8663521.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.602633380889893,
|
|
"epoch": 0.44284500424851303,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986700804171816,
|
|
"loss": 6.5281,
|
|
"mean_token_accuracy": 0.13027760684490203,
|
|
"num_tokens": 8673108.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.553408813476563,
|
|
"epoch": 0.4433448293097416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986662029814285,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.13585576713085173,
|
|
"num_tokens": 8682917.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.493464040756225,
|
|
"epoch": 0.44384465437097015,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986623199182913,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.12620678618550302,
|
|
"num_tokens": 8692436.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.477138090133667,
|
|
"epoch": 0.44434447943219874,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986584312278678,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.13831330388784407,
|
|
"num_tokens": 8702627.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.529372692108154,
|
|
"epoch": 0.4448443044934273,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986545369102556,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.12833660021424292,
|
|
"num_tokens": 8711697.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.534554958343506,
|
|
"epoch": 0.44534412955465585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986506369655528,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.12715906277298927,
|
|
"num_tokens": 8721449.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.482955360412598,
|
|
"epoch": 0.44584395461588444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986467313938575,
|
|
"loss": 6.4338,
|
|
"mean_token_accuracy": 0.13206081166863443,
|
|
"num_tokens": 8731829.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.509197664260864,
|
|
"epoch": 0.44634377967711303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498642820195268,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.15030839443206787,
|
|
"num_tokens": 8741768.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.541743755340576,
|
|
"epoch": 0.44684360473834156,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986389033698827,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.12767333239316941,
|
|
"num_tokens": 8751473.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.594388389587403,
|
|
"epoch": 0.44734342979957015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986349809178002,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.12825369611382484,
|
|
"num_tokens": 8761229.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.460408163070679,
|
|
"epoch": 0.44784325486079873,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986310528391192,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.13727328032255173,
|
|
"num_tokens": 8770670.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.5151279926300045,
|
|
"epoch": 0.44834307992202727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986271191339383,
|
|
"loss": 6.424,
|
|
"mean_token_accuracy": 0.13391717299818992,
|
|
"num_tokens": 8780816.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.590042543411255,
|
|
"epoch": 0.44884290498325585,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986231798023566,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.13050450384616852,
|
|
"num_tokens": 8790304.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.51934061050415,
|
|
"epoch": 0.44934273004448444,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986192348444734,
|
|
"loss": 6.4289,
|
|
"mean_token_accuracy": 0.13259972184896468,
|
|
"num_tokens": 8799188.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.5724410057067875,
|
|
"epoch": 0.449842555105713,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986152842603877,
|
|
"loss": 6.4841,
|
|
"mean_token_accuracy": 0.1367173857986927,
|
|
"num_tokens": 8810194.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.550623226165771,
|
|
"epoch": 0.45034238016694156,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986113280501989,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.13392266556620597,
|
|
"num_tokens": 8820394.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.518058443069458,
|
|
"epoch": 0.45084220522817015,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986073662140068,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.1375273697078228,
|
|
"num_tokens": 8831308.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.5074177265167235,
|
|
"epoch": 0.45134203028939873,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986033987519109,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.13824616745114326,
|
|
"num_tokens": 8841461.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.522912502288818,
|
|
"epoch": 0.45184185535062726,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985994256640108,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.13351252377033235,
|
|
"num_tokens": 8850356.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.560211801528931,
|
|
"epoch": 0.45234168041185585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985954469504069,
|
|
"loss": 6.4882,
|
|
"mean_token_accuracy": 0.12924721613526344,
|
|
"num_tokens": 8859863.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.542526531219482,
|
|
"epoch": 0.45284150547308444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985914626111991,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.1316630944609642,
|
|
"num_tokens": 8869887.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.534689950942993,
|
|
"epoch": 0.45334133053431297,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985874726464875,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.1328124076128006,
|
|
"num_tokens": 8879950.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.506281328201294,
|
|
"epoch": 0.45384115559554156,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985834770563727,
|
|
"loss": 6.2745,
|
|
"mean_token_accuracy": 0.14639786183834075,
|
|
"num_tokens": 8888304.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.448099851608276,
|
|
"epoch": 0.45434098065677014,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985794758409552,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.1479883685708046,
|
|
"num_tokens": 8898642.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.4671882629394535,
|
|
"epoch": 0.4548408057179987,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985754690003354,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.12737697884440422,
|
|
"num_tokens": 8909202.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.428459501266479,
|
|
"epoch": 0.45534063077922726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985714565346145,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.14508851915597915,
|
|
"num_tokens": 8918844.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.563408041000367,
|
|
"epoch": 0.45584045584045585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985674384438933,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.13017046675086022,
|
|
"num_tokens": 8928706.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.520368385314941,
|
|
"epoch": 0.45634028090168444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985634147282729,
|
|
"loss": 6.3717,
|
|
"mean_token_accuracy": 0.13715771734714508,
|
|
"num_tokens": 8939293.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.4421862125396725,
|
|
"epoch": 0.45684010596291297,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985593853878544,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.13338134214282035,
|
|
"num_tokens": 8947922.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.471314525604248,
|
|
"epoch": 0.45733993102414155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985553504227394,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.14011099338531494,
|
|
"num_tokens": 8957745.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.5710876941680905,
|
|
"epoch": 0.45783975608537014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985513098330293,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.128147342056036,
|
|
"num_tokens": 8968331.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.486983776092529,
|
|
"epoch": 0.4583395811465987,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985472636188257,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.1420034348964691,
|
|
"num_tokens": 8977752.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.475470018386841,
|
|
"epoch": 0.45883940620782726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985432117802305,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.13253813087940217,
|
|
"num_tokens": 8986701.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.4574915885925295,
|
|
"epoch": 0.45933923126905585,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985391543173456,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.1383625775575638,
|
|
"num_tokens": 8996192.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.53081111907959,
|
|
"epoch": 0.4598390563302844,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498535091230273,
|
|
"loss": 6.3961,
|
|
"mean_token_accuracy": 0.13408192694187165,
|
|
"num_tokens": 9007059.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.431706523895263,
|
|
"epoch": 0.46033888139151297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985310225191152,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.13652804791927337,
|
|
"num_tokens": 9016923.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.507685661315918,
|
|
"epoch": 0.46083870645274155,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985269481839744,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.13447274193167685,
|
|
"num_tokens": 9026034.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.65610179901123,
|
|
"epoch": 0.4613385315139701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985228682249529,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.13391346409916877,
|
|
"num_tokens": 9036773.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.514581489562988,
|
|
"epoch": 0.46183835657519867,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985187826421538,
|
|
"loss": 6.4226,
|
|
"mean_token_accuracy": 0.13582958281040192,
|
|
"num_tokens": 9047825.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.560742998123169,
|
|
"epoch": 0.46233818163642726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985146914356795,
|
|
"loss": 6.5195,
|
|
"mean_token_accuracy": 0.1312625989317894,
|
|
"num_tokens": 9056295.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.4778799533844,
|
|
"epoch": 0.46283800669765585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498510594605633,
|
|
"loss": 6.4434,
|
|
"mean_token_accuracy": 0.1328299857676029,
|
|
"num_tokens": 9067245.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.512774324417114,
|
|
"epoch": 0.4633378317588844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985064921521177,
|
|
"loss": 6.4092,
|
|
"mean_token_accuracy": 0.13674387484788894,
|
|
"num_tokens": 9077528.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.516362190246582,
|
|
"epoch": 0.46383765682011296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985023840752364,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.1389579489827156,
|
|
"num_tokens": 9086015.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.543647289276123,
|
|
"epoch": 0.46433748188134155,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984982703750926,
|
|
"loss": 6.416,
|
|
"mean_token_accuracy": 0.13164832666516305,
|
|
"num_tokens": 9095963.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.420813703536988,
|
|
"epoch": 0.4648373069425701,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984941510517899,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.1416421115398407,
|
|
"num_tokens": 9105819.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.399018716812134,
|
|
"epoch": 0.46533713200379867,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984900261054319,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.14381264969706536,
|
|
"num_tokens": 9114574.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.508393812179565,
|
|
"epoch": 0.46583695706502726,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984858955361224,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.12810177654027938,
|
|
"num_tokens": 9125490.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.613577079772949,
|
|
"epoch": 0.4663367821262558,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984817593439651,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.13605340495705603,
|
|
"num_tokens": 9134886.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.437576580047607,
|
|
"epoch": 0.4668366071874844,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984776175290643,
|
|
"loss": 6.3636,
|
|
"mean_token_accuracy": 0.1394120089709759,
|
|
"num_tokens": 9143598.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.389187288284302,
|
|
"epoch": 0.46733643224871296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984734700915242,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.12344528511166572,
|
|
"num_tokens": 9153051.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.58816876411438,
|
|
"epoch": 0.4678362573099415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498469317031449,
|
|
"loss": 6.3858,
|
|
"mean_token_accuracy": 0.13521411269903183,
|
|
"num_tokens": 9162472.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.503498077392578,
|
|
"epoch": 0.4683360823711701,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984651583489434,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.13402297496795654,
|
|
"num_tokens": 9171453.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.438160753250122,
|
|
"epoch": 0.46883590743239867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984609940441119,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.13773744702339172,
|
|
"num_tokens": 9181104.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.49449200630188,
|
|
"epoch": 0.46933573249362726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984568241170593,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.14121029451489447,
|
|
"num_tokens": 9190403.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.460302019119263,
|
|
"epoch": 0.4698355575548558,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984526485678905,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.14223534017801284,
|
|
"num_tokens": 9199132.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.528104639053344,
|
|
"epoch": 0.4703353826160844,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984484673967105,
|
|
"loss": 6.4731,
|
|
"mean_token_accuracy": 0.12893762961030006,
|
|
"num_tokens": 9208274.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.529750728607178,
|
|
"epoch": 0.47083520767731296,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984442806036246,
|
|
"loss": 6.4343,
|
|
"mean_token_accuracy": 0.1426217757165432,
|
|
"num_tokens": 9218513.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.514943647384643,
|
|
"epoch": 0.4713350327385415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984400881887381,
|
|
"loss": 6.4473,
|
|
"mean_token_accuracy": 0.12802284434437752,
|
|
"num_tokens": 9229197.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.48367395401001,
|
|
"epoch": 0.4718348577997701,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984358901521565,
|
|
"loss": 6.31,
|
|
"mean_token_accuracy": 0.1381663367152214,
|
|
"num_tokens": 9239465.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.483723926544189,
|
|
"epoch": 0.47233468286099867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984316864939853,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.1365165390074253,
|
|
"num_tokens": 9250112.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.5218719959259035,
|
|
"epoch": 0.4728345079222272,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984274772143304,
|
|
"loss": 6.4217,
|
|
"mean_token_accuracy": 0.13553764224052428,
|
|
"num_tokens": 9259406.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.527883625030517,
|
|
"epoch": 0.4733343329834558,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984232623132977,
|
|
"loss": 6.3466,
|
|
"mean_token_accuracy": 0.1345366470515728,
|
|
"num_tokens": 9269462.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.471977996826172,
|
|
"epoch": 0.4738341580446844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984190417909932,
|
|
"loss": 6.4256,
|
|
"mean_token_accuracy": 0.13124653920531273,
|
|
"num_tokens": 9280291.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.5116735935211185,
|
|
"epoch": 0.4743339831059129,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984148156475231,
|
|
"loss": 6.3778,
|
|
"mean_token_accuracy": 0.12980158179998397,
|
|
"num_tokens": 9289680.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.504691743850708,
|
|
"epoch": 0.4748338081671415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984105838829937,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.13800340965390206,
|
|
"num_tokens": 9301043.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.359691429138183,
|
|
"epoch": 0.4753336332283701,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984063464975116,
|
|
"loss": 6.4217,
|
|
"mean_token_accuracy": 0.1337859511375427,
|
|
"num_tokens": 9311851.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.592877006530761,
|
|
"epoch": 0.47583345828959867,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984021034911833,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.13857403621077538,
|
|
"num_tokens": 9320886.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.487786293029785,
|
|
"epoch": 0.4763332833508272,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983978548641154,
|
|
"loss": 6.4401,
|
|
"mean_token_accuracy": 0.1338131070137024,
|
|
"num_tokens": 9330518.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.443555736541748,
|
|
"epoch": 0.4768331084120558,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983936006164151,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.13514435514807702,
|
|
"num_tokens": 9339703.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.66024603843689,
|
|
"epoch": 0.47733293347328437,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983893407481892,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.1282417118549347,
|
|
"num_tokens": 9349931.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.463759994506836,
|
|
"epoch": 0.4778327585345129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983850752595451,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.13968004956841468,
|
|
"num_tokens": 9358984.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.527974271774292,
|
|
"epoch": 0.4783325835957415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983808041505898,
|
|
"loss": 6.3281,
|
|
"mean_token_accuracy": 0.13808016926050187,
|
|
"num_tokens": 9368081.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.543414449691772,
|
|
"epoch": 0.4788324086569701,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983765274214311,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.12913113012909888,
|
|
"num_tokens": 9377346.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.38665771484375,
|
|
"epoch": 0.4793322337181986,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983722450721764,
|
|
"loss": 6.4229,
|
|
"mean_token_accuracy": 0.13916267231106758,
|
|
"num_tokens": 9387493.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.544322204589844,
|
|
"epoch": 0.4798320587794272,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983679571029336,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.13306548595428466,
|
|
"num_tokens": 9397154.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.542267990112305,
|
|
"epoch": 0.4803318838406558,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983636635138103,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.13155010417103769,
|
|
"num_tokens": 9406705.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.495486164093018,
|
|
"epoch": 0.4808317089018843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983593643049148,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.14006763696670532,
|
|
"num_tokens": 9416850.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.415793943405151,
|
|
"epoch": 0.4813315339631129,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983550594763552,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.13997766971588135,
|
|
"num_tokens": 9425841.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.418641853332519,
|
|
"epoch": 0.4818313590243415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983507490282397,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.1414778672158718,
|
|
"num_tokens": 9436748.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.478595304489136,
|
|
"epoch": 0.4823311840855701,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983464329606768,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.1369209259748459,
|
|
"num_tokens": 9446043.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.4545375347137455,
|
|
"epoch": 0.4828310091467986,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983421112737752,
|
|
"loss": 6.4416,
|
|
"mean_token_accuracy": 0.132239031791687,
|
|
"num_tokens": 9455480.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.503011035919189,
|
|
"epoch": 0.4833308342080272,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983377839676435,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.13139901012182237,
|
|
"num_tokens": 9464412.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.522000694274903,
|
|
"epoch": 0.4838306592692558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983334510423906,
|
|
"loss": 6.3695,
|
|
"mean_token_accuracy": 0.13747578635811805,
|
|
"num_tokens": 9475639.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.4971763610839846,
|
|
"epoch": 0.4843304843304843,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983291124981257,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.1367343321442604,
|
|
"num_tokens": 9484721.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.388935947418213,
|
|
"epoch": 0.4848303093917129,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983247683349576,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.14191571101546288,
|
|
"num_tokens": 9494594.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.374627542495728,
|
|
"epoch": 0.4853301344529415,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983204185529959,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.14378543868660926,
|
|
"num_tokens": 9503707.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.455869340896607,
|
|
"epoch": 0.48582995951417,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983160631523499,
|
|
"loss": 6.2809,
|
|
"mean_token_accuracy": 0.13805698603391647,
|
|
"num_tokens": 9512473.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.418364858627319,
|
|
"epoch": 0.4863297845753986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983117021331293,
|
|
"loss": 6.4083,
|
|
"mean_token_accuracy": 0.13700531646609307,
|
|
"num_tokens": 9523253.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.521939849853515,
|
|
"epoch": 0.4868296096366272,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983073354954436,
|
|
"loss": 6.3777,
|
|
"mean_token_accuracy": 0.13949814885854722,
|
|
"num_tokens": 9531938.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.59939751625061,
|
|
"epoch": 0.4873294346978557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983029632394029,
|
|
"loss": 6.3754,
|
|
"mean_token_accuracy": 0.13508883193135263,
|
|
"num_tokens": 9541542.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.371125173568726,
|
|
"epoch": 0.4878292597590843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498298585365117,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.14197706952691078,
|
|
"num_tokens": 9551521.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.467463541030884,
|
|
"epoch": 0.4883290848203129,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982942018726963,
|
|
"loss": 6.443,
|
|
"mean_token_accuracy": 0.141734978556633,
|
|
"num_tokens": 9561605.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.471908760070801,
|
|
"epoch": 0.4888289098815415,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982898127622508,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.13869891613721846,
|
|
"num_tokens": 9571591.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.385383081436157,
|
|
"epoch": 0.48932873494277,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982854180338911,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.1401084266602993,
|
|
"num_tokens": 9580994.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.559015560150146,
|
|
"epoch": 0.4898285600039986,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982810176877279,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.1354878470301628,
|
|
"num_tokens": 9589268.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.46404128074646,
|
|
"epoch": 0.4903283850652272,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982766117238716,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.13586771190166474,
|
|
"num_tokens": 9599461.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.503689765930176,
|
|
"epoch": 0.4908282101264557,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982722001424331,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.134616681933403,
|
|
"num_tokens": 9609629.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.419895076751709,
|
|
"epoch": 0.4913280351876843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982677829435236,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.1450149841606617,
|
|
"num_tokens": 9619618.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.437411975860596,
|
|
"epoch": 0.4918278602489129,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982633601272543,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.13925076201558112,
|
|
"num_tokens": 9629042.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.463222169876099,
|
|
"epoch": 0.4923276853101414,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982589316937361,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.14059789702296258,
|
|
"num_tokens": 9638596.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.488814878463745,
|
|
"epoch": 0.49282751037137,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982544976430808,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.13408228531479835,
|
|
"num_tokens": 9648505.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.38788857460022,
|
|
"epoch": 0.4933273354325986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982500579753995,
|
|
"loss": 6.3899,
|
|
"mean_token_accuracy": 0.1382318913936615,
|
|
"num_tokens": 9658113.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.476542186737061,
|
|
"epoch": 0.49382716049382713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982456126908044,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.13840780779719353,
|
|
"num_tokens": 9668075.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.5929343700408936,
|
|
"epoch": 0.4943269855550557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004982411617894071,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.13169767037034036,
|
|
"num_tokens": 9678139.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.444349527359009,
|
|
"epoch": 0.4948268106162843,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982367052713196,
|
|
"loss": 6.4219,
|
|
"mean_token_accuracy": 0.12752186879515648,
|
|
"num_tokens": 9687328.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.430422306060791,
|
|
"epoch": 0.4953266356775129,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982322431366541,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.1412187784910202,
|
|
"num_tokens": 9697536.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.502705144882202,
|
|
"epoch": 0.4958264607387414,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982277753855227,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.1386316880583763,
|
|
"num_tokens": 9706804.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.534018230438233,
|
|
"epoch": 0.49632628579997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498223302018038,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.14683042243123054,
|
|
"num_tokens": 9716868.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.403007745742798,
|
|
"epoch": 0.4968261108611986,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982188230343124,
|
|
"loss": 6.4068,
|
|
"mean_token_accuracy": 0.13918600156903266,
|
|
"num_tokens": 9728790.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.54256911277771,
|
|
"epoch": 0.49732593592242713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982143384344587,
|
|
"loss": 6.4124,
|
|
"mean_token_accuracy": 0.13571546748280525,
|
|
"num_tokens": 9739118.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.522776079177857,
|
|
"epoch": 0.4978257609836557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982098482185897,
|
|
"loss": 6.38,
|
|
"mean_token_accuracy": 0.1403428755700588,
|
|
"num_tokens": 9749347.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.51669135093689,
|
|
"epoch": 0.4983255860448843,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982053523868182,
|
|
"loss": 6.4333,
|
|
"mean_token_accuracy": 0.13202799037098883,
|
|
"num_tokens": 9759432.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.41639199256897,
|
|
"epoch": 0.49882541110611284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982008509392576,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13148636296391486,
|
|
"num_tokens": 9768666.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.398564863204956,
|
|
"epoch": 0.4993252361673414,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498196343876021,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.14879042357206346,
|
|
"num_tokens": 9778699.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.455457496643066,
|
|
"epoch": 0.49982506122857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981918311972219,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.13913736939430238,
|
|
"num_tokens": 9788156.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.448054504394531,
|
|
"epoch": 0.5003248862897985,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981873129029737,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.14729730635881425,
|
|
"num_tokens": 9797293.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.3916370391845705,
|
|
"epoch": 0.5008247113510271,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049818278899339,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.14214758723974227,
|
|
"num_tokens": 9806962.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.443386697769165,
|
|
"epoch": 0.5013245364122557,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498178259468585,
|
|
"loss": 6.4267,
|
|
"mean_token_accuracy": 0.13721726089715958,
|
|
"num_tokens": 9816689.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.508077478408813,
|
|
"epoch": 0.5018243614734843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981737243286722,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.1371029019355774,
|
|
"num_tokens": 9826321.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.540329885482788,
|
|
"epoch": 0.5023241865347129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981691835737661,
|
|
"loss": 6.4547,
|
|
"mean_token_accuracy": 0.12951614782214166,
|
|
"num_tokens": 9836054.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.554930019378662,
|
|
"epoch": 0.5028240115959414,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981646372039807,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.13512118458747863,
|
|
"num_tokens": 9846516.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.424113798141479,
|
|
"epoch": 0.50332383665717,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981600852194305,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.14665252566337586,
|
|
"num_tokens": 9856599.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.4051251888275145,
|
|
"epoch": 0.5038236617183985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049815552762023,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.1417568065226078,
|
|
"num_tokens": 9866922.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.43504490852356,
|
|
"epoch": 0.5043234867796271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981509644064937,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.13958919197320938,
|
|
"num_tokens": 9876174.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.415535640716553,
|
|
"epoch": 0.5048233118408557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004981463955783367,
|
|
"loss": 6.277,
|
|
"mean_token_accuracy": 0.14316560924053193,
|
|
"num_tokens": 9886208.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.410051488876343,
|
|
"epoch": 0.5053231369020843,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981418211358736,
|
|
"loss": 6.3386,
|
|
"mean_token_accuracy": 0.1408532105386257,
|
|
"num_tokens": 9896522.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.4151115894317625,
|
|
"epoch": 0.5058229619633129,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981372410792199,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.14682593569159508,
|
|
"num_tokens": 9905753.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.4666502475738525,
|
|
"epoch": 0.5063227870245414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981326554084906,
|
|
"loss": 6.4301,
|
|
"mean_token_accuracy": 0.13811509534716607,
|
|
"num_tokens": 9916566.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.468195056915283,
|
|
"epoch": 0.50682261208577,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981280641238011,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.1303804561495781,
|
|
"num_tokens": 9926126.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.513017320632935,
|
|
"epoch": 0.5073224371469985,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981234672252669,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.13405416831374167,
|
|
"num_tokens": 9937666.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.552185869216919,
|
|
"epoch": 0.5078222622082271,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981188647130037,
|
|
"loss": 6.4457,
|
|
"mean_token_accuracy": 0.13834275752305986,
|
|
"num_tokens": 9947107.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.480519962310791,
|
|
"epoch": 0.5083220872694557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981142565871272,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.1375648148357868,
|
|
"num_tokens": 9956484.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.3329003810882565,
|
|
"epoch": 0.5088219123306843,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981096428477535,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.13904502466320992,
|
|
"num_tokens": 9966731.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.461158180236817,
|
|
"epoch": 0.5093217373919128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981050234949986,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.141248919069767,
|
|
"num_tokens": 9976491.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.507654333114624,
|
|
"epoch": 0.5098215624531414,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004981003985289786,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.1455710768699646,
|
|
"num_tokens": 9985248.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.403945112228394,
|
|
"epoch": 0.51032138751437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980957679498101,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.14013429135084152,
|
|
"num_tokens": 9995578.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.518911504745484,
|
|
"epoch": 0.5108212125755985,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980911317576095,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.131076168268919,
|
|
"num_tokens": 10006078.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.529238319396972,
|
|
"epoch": 0.5113210376368271,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980864899524933,
|
|
"loss": 6.4132,
|
|
"mean_token_accuracy": 0.12879174426198006,
|
|
"num_tokens": 10015943.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.472807931900024,
|
|
"epoch": 0.5118208626980557,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980818425345786,
|
|
"loss": 6.4037,
|
|
"mean_token_accuracy": 0.13248924538493156,
|
|
"num_tokens": 10025738.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.562513828277588,
|
|
"epoch": 0.5123206877592843,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498077189503982,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.13115599527955055,
|
|
"num_tokens": 10035032.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.44153413772583,
|
|
"epoch": 0.5128205128205128,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980725308608208,
|
|
"loss": 6.3326,
|
|
"mean_token_accuracy": 0.14097934886813163,
|
|
"num_tokens": 10044201.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.356708717346192,
|
|
"epoch": 0.5133203378817414,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004980678666052121,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.1402401879429817,
|
|
"num_tokens": 10054163.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.438456249237061,
|
|
"epoch": 0.51382016294297,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980631967372733,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.14144863486289977,
|
|
"num_tokens": 10065225.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.506520509719849,
|
|
"epoch": 0.5143199880041985,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980585212571218,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.13947251960635185,
|
|
"num_tokens": 10074776.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.506457757949829,
|
|
"epoch": 0.5148198130654271,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980538401648753,
|
|
"loss": 6.4989,
|
|
"mean_token_accuracy": 0.1341721385717392,
|
|
"num_tokens": 10085917.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.491835975646973,
|
|
"epoch": 0.5153196381266557,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980491534606517,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.14042604863643646,
|
|
"num_tokens": 10094727.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.414020919799805,
|
|
"epoch": 0.5158194631878842,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980444611445686,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.14486273229122162,
|
|
"num_tokens": 10104839.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.405583190917969,
|
|
"epoch": 0.5163192882491128,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980397632167444,
|
|
"loss": 6.283,
|
|
"mean_token_accuracy": 0.14061587750911714,
|
|
"num_tokens": 10114501.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.421072101593017,
|
|
"epoch": 0.5168191133103414,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980350596772971,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.1360914647579193,
|
|
"num_tokens": 10124597.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.322241735458374,
|
|
"epoch": 0.51731893837157,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004980303505263451,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.1398468352854252,
|
|
"num_tokens": 10135695.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.337439060211182,
|
|
"epoch": 0.5178187634327985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980256357640069,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.1377136953175068,
|
|
"num_tokens": 10146107.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.509029197692871,
|
|
"epoch": 0.5183185884940271,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980209153904011,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.14012961685657502,
|
|
"num_tokens": 10155983.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.484198379516601,
|
|
"epoch": 0.5188184135552557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980161894056464,
|
|
"loss": 6.3634,
|
|
"mean_token_accuracy": 0.13489748686552047,
|
|
"num_tokens": 10166183.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.425005865097046,
|
|
"epoch": 0.5193182386164842,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004980114578098618,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.14645392522215844,
|
|
"num_tokens": 10175524.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.425123023986816,
|
|
"epoch": 0.5198180636777128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980067206031663,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.1262257769703865,
|
|
"num_tokens": 10186235.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.554209804534912,
|
|
"epoch": 0.5203178887389414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980019777856791,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.13365318030118942,
|
|
"num_tokens": 10196166.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.4457080364227295,
|
|
"epoch": 0.52081771380017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979972293575195,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.1418666884303093,
|
|
"num_tokens": 10205691.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.373795413970948,
|
|
"epoch": 0.5213175388613985,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979924753188069,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.14232254922389984,
|
|
"num_tokens": 10216224.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.42751636505127,
|
|
"epoch": 0.5218173639226271,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979877156696612,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.13963486701250077,
|
|
"num_tokens": 10226468.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.572753286361694,
|
|
"epoch": 0.5223171889838556,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004979829504102018,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.13437848538160324,
|
|
"num_tokens": 10235932.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.501198482513428,
|
|
"epoch": 0.5228170140450842,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004979781795405488,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.13081177026033403,
|
|
"num_tokens": 10246052.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.514893627166748,
|
|
"epoch": 0.5233168391063128,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979734030608222,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.13877685070037843,
|
|
"num_tokens": 10255056.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.41351842880249,
|
|
"epoch": 0.5238166641675414,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979686209711422,
|
|
"loss": 6.3236,
|
|
"mean_token_accuracy": 0.14136184826493264,
|
|
"num_tokens": 10265403.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.4000389099121096,
|
|
"epoch": 0.5243164892287699,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497963833271629,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.14661918953061104,
|
|
"num_tokens": 10275148.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.497857189178466,
|
|
"epoch": 0.5248163142899985,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979590399624031,
|
|
"loss": 6.3258,
|
|
"mean_token_accuracy": 0.1367676131427288,
|
|
"num_tokens": 10285083.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.351488733291626,
|
|
"epoch": 0.5253161393512271,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979542410435852,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.1327349342405796,
|
|
"num_tokens": 10294466.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.473018169403076,
|
|
"epoch": 0.5258159644124556,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979494365152959,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.13443218246102334,
|
|
"num_tokens": 10304333.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.546953201293945,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979446263776562,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.13749662265181542,
|
|
"num_tokens": 10314880.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.468399381637573,
|
|
"epoch": 0.5268156145349128,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497939810630787,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.13549398854374886,
|
|
"num_tokens": 10324060.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.399018430709839,
|
|
"epoch": 0.5273154395961414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979349892748096,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.13540468364953995,
|
|
"num_tokens": 10335248.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.429918575286865,
|
|
"epoch": 0.5278152646573699,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979301623098452,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.14516004547476768,
|
|
"num_tokens": 10343974.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.467012786865235,
|
|
"epoch": 0.5283150897185985,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979253297360153,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.132409206032753,
|
|
"num_tokens": 10354037.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.463950347900391,
|
|
"epoch": 0.528814914779827,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979204915534415,
|
|
"loss": 6.3708,
|
|
"mean_token_accuracy": 0.1383878469467163,
|
|
"num_tokens": 10364714.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.403480291366577,
|
|
"epoch": 0.5293147398410556,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004979156477622454,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.13828956931829453,
|
|
"num_tokens": 10373972.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.431853246688843,
|
|
"epoch": 0.5298145649022842,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979107983625491,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.14456052631139754,
|
|
"num_tokens": 10382882.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.368200063705444,
|
|
"epoch": 0.5303143899635128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979059433544744,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.14171645417809486,
|
|
"num_tokens": 10392257.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.441417694091797,
|
|
"epoch": 0.5308142150247414,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979010827381435,
|
|
"loss": 6.3507,
|
|
"mean_token_accuracy": 0.13942453265190125,
|
|
"num_tokens": 10401055.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.545503997802735,
|
|
"epoch": 0.5313140400859699,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978962165136787,
|
|
"loss": 6.4602,
|
|
"mean_token_accuracy": 0.12886520549654962,
|
|
"num_tokens": 10411443.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.514301300048828,
|
|
"epoch": 0.5318138651471985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004978913446812025,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.13929549753665924,
|
|
"num_tokens": 10422142.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.498802709579468,
|
|
"epoch": 0.532313690208427,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978864672408374,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.1346695177257061,
|
|
"num_tokens": 10432454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.387129497528076,
|
|
"epoch": 0.5328135152696556,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978815841927061,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.14032170325517654,
|
|
"num_tokens": 10443625.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.516609001159668,
|
|
"epoch": 0.5333133403308842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978766955369315,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.14243654310703277,
|
|
"num_tokens": 10454055.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.39882082939148,
|
|
"epoch": 0.5338131653921128,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004978718012736367,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.1444314181804657,
|
|
"num_tokens": 10462683.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.375852918624878,
|
|
"epoch": 0.5343129904533414,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978669014029446,
|
|
"loss": 6.2677,
|
|
"mean_token_accuracy": 0.14716348573565483,
|
|
"num_tokens": 10471699.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.343105220794678,
|
|
"epoch": 0.5348128155145699,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978619959249787,
|
|
"loss": 6.1928,
|
|
"mean_token_accuracy": 0.14977386742830276,
|
|
"num_tokens": 10480790.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.384857606887818,
|
|
"epoch": 0.5353126405757984,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978570848398623,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.1346427671611309,
|
|
"num_tokens": 10490202.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.409596252441406,
|
|
"epoch": 0.535812465637027,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497852168147719,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.135125882178545,
|
|
"num_tokens": 10499690.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.506616926193237,
|
|
"epoch": 0.5363122906982556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004978472458486724,
|
|
"loss": 6.3409,
|
|
"mean_token_accuracy": 0.13681497648358346,
|
|
"num_tokens": 10510120.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.451282787322998,
|
|
"epoch": 0.5368121157594842,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978423179428466,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.1353305995464325,
|
|
"num_tokens": 10520521.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.345026111602783,
|
|
"epoch": 0.5373119408207128,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004978373844303653,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.146633118391037,
|
|
"num_tokens": 10530233.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.39206018447876,
|
|
"epoch": 0.5378117658819414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978324453113528,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.1419048637151718,
|
|
"num_tokens": 10539683.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.433778715133667,
|
|
"epoch": 0.5383115909431699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978275005859333,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.14073469638824462,
|
|
"num_tokens": 10549483.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.4962962627410885,
|
|
"epoch": 0.5388114160043984,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978225502542313,
|
|
"loss": 6.4297,
|
|
"mean_token_accuracy": 0.1314571052789688,
|
|
"num_tokens": 10560464.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.474843263626099,
|
|
"epoch": 0.539311241065627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978175943163712,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.13529158234596253,
|
|
"num_tokens": 10568660.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.471502637863159,
|
|
"epoch": 0.5398110661268556,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978126327724777,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.1399627573788166,
|
|
"num_tokens": 10577304.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.408673906326294,
|
|
"epoch": 0.5403108911880842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978076656226758,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.14970972910523414,
|
|
"num_tokens": 10587591.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.422517013549805,
|
|
"epoch": 0.5408107162493128,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004978026928670902,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.13947502374649048,
|
|
"num_tokens": 10598591.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.347539710998535,
|
|
"epoch": 0.5413105413105413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977977145058463,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.13943241089582442,
|
|
"num_tokens": 10608842.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.373945426940918,
|
|
"epoch": 0.5418103663717699,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977927305390693,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.1439303234219551,
|
|
"num_tokens": 10618812.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.496698093414307,
|
|
"epoch": 0.5423101914329984,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977877409668845,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.13219047337770462,
|
|
"num_tokens": 10629244.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.5158854007720945,
|
|
"epoch": 0.542810016494227,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977827457894174,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.13357137739658356,
|
|
"num_tokens": 10638931.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.399742889404297,
|
|
"epoch": 0.5433098415554556,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977777450067937,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.14259956628084183,
|
|
"num_tokens": 10648754.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.37289662361145,
|
|
"epoch": 0.5438096666166842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977727386191393,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.14566398561000823,
|
|
"num_tokens": 10657716.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.3968058109283445,
|
|
"epoch": 0.5443094916779128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977677266265802,
|
|
"loss": 6.2695,
|
|
"mean_token_accuracy": 0.14065478518605232,
|
|
"num_tokens": 10667621.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.349292135238647,
|
|
"epoch": 0.5448093167391413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004977627090292424,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13979329094290732,
|
|
"num_tokens": 10676640.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.358928394317627,
|
|
"epoch": 0.5453091418003698,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977576858272521,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.13097573891282083,
|
|
"num_tokens": 10687034.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.441195011138916,
|
|
"epoch": 0.5458089668615984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977526570207358,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.1447528585791588,
|
|
"num_tokens": 10696234.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.350192499160767,
|
|
"epoch": 0.546308791922827,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977476226098199,
|
|
"loss": 6.2766,
|
|
"mean_token_accuracy": 0.14773816764354705,
|
|
"num_tokens": 10705733.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.444482421875,
|
|
"epoch": 0.5468086169840556,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977425825946312,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.14336602985858918,
|
|
"num_tokens": 10714628.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.5299904346466064,
|
|
"epoch": 0.5473084420452842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977375369752964,
|
|
"loss": 6.4323,
|
|
"mean_token_accuracy": 0.12882368937134742,
|
|
"num_tokens": 10726120.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.414555168151855,
|
|
"epoch": 0.5478082671065128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977324857519425,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.13879045769572257,
|
|
"num_tokens": 10735976.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.464913558959961,
|
|
"epoch": 0.5483080921677413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977274289246967,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.13373840898275374,
|
|
"num_tokens": 10745730.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.473123788833618,
|
|
"epoch": 0.5488079172289698,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977223664936859,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.1395411156117916,
|
|
"num_tokens": 10755435.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.343825244903565,
|
|
"epoch": 0.5493077422901984,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977172984590378,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.14526784494519235,
|
|
"num_tokens": 10765483.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.333004331588745,
|
|
"epoch": 0.549807567351427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977122248208798,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.1436666414141655,
|
|
"num_tokens": 10775034.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.344209480285644,
|
|
"epoch": 0.5503073924126556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977071455793394,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.13889251425862312,
|
|
"num_tokens": 10784799.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.418334102630615,
|
|
"epoch": 0.5508072174738842,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977020607345445,
|
|
"loss": 6.3333,
|
|
"mean_token_accuracy": 0.1300968937575817,
|
|
"num_tokens": 10794907.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.361036586761474,
|
|
"epoch": 0.5513070425351128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004976969702866231,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.1447628490626812,
|
|
"num_tokens": 10804374.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.394205904006958,
|
|
"epoch": 0.5518068675963412,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976918742357033,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.14091094583272934,
|
|
"num_tokens": 10814245.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.374346590042114,
|
|
"epoch": 0.5523066926575698,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976867725819133,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.14092635586857796,
|
|
"num_tokens": 10824667.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.367292499542236,
|
|
"epoch": 0.5528065177187984,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976816653253813,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.14192148000001908,
|
|
"num_tokens": 10834890.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.393146085739136,
|
|
"epoch": 0.553306342780027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976765524662359,
|
|
"loss": 6.2179,
|
|
"mean_token_accuracy": 0.14673539698123933,
|
|
"num_tokens": 10844751.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.462450361251831,
|
|
"epoch": 0.5538061678412556,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976714340046058,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.14202267900109292,
|
|
"num_tokens": 10854113.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.349339580535888,
|
|
"epoch": 0.5543059929024842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004976663099406196,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.14216559752821922,
|
|
"num_tokens": 10863468.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.440054082870484,
|
|
"epoch": 0.5548058179637128,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004976611802744066,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.14115004390478134,
|
|
"num_tokens": 10873381.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.44648699760437,
|
|
"epoch": 0.5553056430249412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976560450060954,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.14238317012786866,
|
|
"num_tokens": 10883457.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.284746313095093,
|
|
"epoch": 0.5558054680861698,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976509041358154,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.14156111627817153,
|
|
"num_tokens": 10892822.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.328335857391357,
|
|
"epoch": 0.5563052931473984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497645757663696,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.1516851395368576,
|
|
"num_tokens": 10901935.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.307885026931762,
|
|
"epoch": 0.556805118208627,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976406055898665,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.13936870023608208,
|
|
"num_tokens": 10911863.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.404980182647705,
|
|
"epoch": 0.5573049432698556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976354479144568,
|
|
"loss": 6.2631,
|
|
"mean_token_accuracy": 0.14423334300518037,
|
|
"num_tokens": 10921196.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.397053003311157,
|
|
"epoch": 0.5578047683310842,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976302846375965,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.14099265187978743,
|
|
"num_tokens": 10931374.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.453075885772705,
|
|
"epoch": 0.5583045933923126,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976251157594155,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.13292488008737563,
|
|
"num_tokens": 10941002.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.4787900924682615,
|
|
"epoch": 0.5588044184535412,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976199412800437,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.1385272614657879,
|
|
"num_tokens": 10950602.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.421299600601197,
|
|
"epoch": 0.5593042435147698,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976147611996118,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.14085360541939734,
|
|
"num_tokens": 10960363.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.42499852180481,
|
|
"epoch": 0.5598040685759984,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004976095755182496,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.1343800149857998,
|
|
"num_tokens": 10970179.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.388416910171509,
|
|
"epoch": 0.560303893637227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976043842360877,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.1408168628811836,
|
|
"num_tokens": 10980446.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.361445617675781,
|
|
"epoch": 0.5608037186984556,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497599187353257,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.13696268126368522,
|
|
"num_tokens": 10990883.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.464084434509277,
|
|
"epoch": 0.5613035437596842,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975939848698879,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.14719685465097426,
|
|
"num_tokens": 11000956.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.375065851211548,
|
|
"epoch": 0.5618033688209126,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975887767861113,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.14079812467098235,
|
|
"num_tokens": 11010873.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.432920503616333,
|
|
"epoch": 0.5623031938821412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975835631020585,
|
|
"loss": 6.2392,
|
|
"mean_token_accuracy": 0.14312080442905425,
|
|
"num_tokens": 11020192.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.3562421798706055,
|
|
"epoch": 0.5628030189433698,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975783438178605,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.13569467142224312,
|
|
"num_tokens": 11030466.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.361410617828369,
|
|
"epoch": 0.5633028440045984,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975731189336487,
|
|
"loss": 6.2416,
|
|
"mean_token_accuracy": 0.14767612665891647,
|
|
"num_tokens": 11040309.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.403742837905884,
|
|
"epoch": 0.563802669065827,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975678884495544,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.13869719654321672,
|
|
"num_tokens": 11049560.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.479496192932129,
|
|
"epoch": 0.5643024941270556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004975626523657093,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.13150647208094596,
|
|
"num_tokens": 11059352.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.46918420791626,
|
|
"epoch": 0.564802319188284,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975574106822451,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.1438026748597622,
|
|
"num_tokens": 11069159.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.422984552383423,
|
|
"epoch": 0.5653021442495126,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004975521633992938,
|
|
"loss": 6.3772,
|
|
"mean_token_accuracy": 0.13444813266396521,
|
|
"num_tokens": 11078960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.363971948623657,
|
|
"epoch": 0.5658019693107412,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975469105169873,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.1523880749940872,
|
|
"num_tokens": 11089408.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.4301598072052,
|
|
"epoch": 0.5663017943719698,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975416520354579,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.13310238793492318,
|
|
"num_tokens": 11099485.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.457961130142212,
|
|
"epoch": 0.5668016194331984,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975363879548377,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.14362878128886222,
|
|
"num_tokens": 11109568.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.543348550796509,
|
|
"epoch": 0.567301444494427,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975311182752592,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.12970269322395325,
|
|
"num_tokens": 11119433.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.518721628189087,
|
|
"epoch": 0.5678012695556556,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004975258429968551,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.13601181283593178,
|
|
"num_tokens": 11130060.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.4756677627563475,
|
|
"epoch": 0.568301094616884,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975205621197581,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.13375984281301498,
|
|
"num_tokens": 11140417.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.5089599609375,
|
|
"epoch": 0.5688009196781126,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975152756441009,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.1424649626016617,
|
|
"num_tokens": 11150830.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.41643648147583,
|
|
"epoch": 0.5693007447393412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004975099835700166,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.14934798330068588,
|
|
"num_tokens": 11161057.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.330704832077027,
|
|
"epoch": 0.5698005698005698,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975046858976386,
|
|
"loss": 6.252,
|
|
"mean_token_accuracy": 0.14019235074520112,
|
|
"num_tokens": 11170182.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.366567659378052,
|
|
"epoch": 0.5703003948617984,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974993826270997,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14439581632614135,
|
|
"num_tokens": 11179962.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.347713899612427,
|
|
"epoch": 0.570800219923027,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004974940737585337,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.1533850759267807,
|
|
"num_tokens": 11189341.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.198566246032715,
|
|
"epoch": 0.5713000449842555,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497488759292074,
|
|
"loss": 6.3078,
|
|
"mean_token_accuracy": 0.14763169661164283,
|
|
"num_tokens": 11199264.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.301087284088135,
|
|
"epoch": 0.571799870045484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974834392278545,
|
|
"loss": 6.2995,
|
|
"mean_token_accuracy": 0.14792427718639373,
|
|
"num_tokens": 11209257.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.50325756072998,
|
|
"epoch": 0.5722996951067126,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974781135660088,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.1401437282562256,
|
|
"num_tokens": 11218294.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.329670333862305,
|
|
"epoch": 0.5727995201679412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974727823066709,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.14815108031034468,
|
|
"num_tokens": 11227684.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.42995138168335,
|
|
"epoch": 0.5732993452291698,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974674454499753,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.131838421523571,
|
|
"num_tokens": 11237195.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.459194278717041,
|
|
"epoch": 0.5737991702903984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974621029960559,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.1389889284968376,
|
|
"num_tokens": 11246871.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.434127759933472,
|
|
"epoch": 0.574298995351627,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974567549450472,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.1382865436375141,
|
|
"num_tokens": 11256298.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.52130823135376,
|
|
"epoch": 0.5747988204128555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974514012970839,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.1376474231481552,
|
|
"num_tokens": 11265857.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.310161113739014,
|
|
"epoch": 0.575298645474084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974460420523005,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.15020117908716202,
|
|
"num_tokens": 11275406.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.391592979431152,
|
|
"epoch": 0.5757984705353126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004974406772108319,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.14891301542520524,
|
|
"num_tokens": 11283910.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.411246824264526,
|
|
"epoch": 0.5762982955965412,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974353067728132,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.13905480802059172,
|
|
"num_tokens": 11293808.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.410305786132812,
|
|
"epoch": 0.5767981206577698,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004974299307383794,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.14077953696250917,
|
|
"num_tokens": 11302519.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.4257300853729244,
|
|
"epoch": 0.5772979457189984,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974245491076656,
|
|
"loss": 6.3865,
|
|
"mean_token_accuracy": 0.131597201526165,
|
|
"num_tokens": 11312609.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.4404510974884035,
|
|
"epoch": 0.5777977707802269,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004974191618808075,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.14218593165278434,
|
|
"num_tokens": 11322471.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.474221086502075,
|
|
"epoch": 0.5782975958414555,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974137690579405,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.14048926532268524,
|
|
"num_tokens": 11333332.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.422118186950684,
|
|
"epoch": 0.578797420902684,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974083706392004,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.1382746011018753,
|
|
"num_tokens": 11342952.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.428772211074829,
|
|
"epoch": 0.5792972459639126,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974029666247228,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.13532100170850753,
|
|
"num_tokens": 11353509.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.558149433135986,
|
|
"epoch": 0.5797970710251412,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973975570146438,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.13695346638560296,
|
|
"num_tokens": 11363065.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.312878847122192,
|
|
"epoch": 0.5802968960863698,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004973921418090997,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.14104935005307198,
|
|
"num_tokens": 11373720.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.303160190582275,
|
|
"epoch": 0.5807967211475984,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973867210082263,
|
|
"loss": 6.2445,
|
|
"mean_token_accuracy": 0.1410558134317398,
|
|
"num_tokens": 11384432.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.469102764129639,
|
|
"epoch": 0.5812965462088269,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004973812946121603,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.13949493914842606,
|
|
"num_tokens": 11394100.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.391165828704834,
|
|
"epoch": 0.5817963712700555,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973758626210382,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.13762608021497727,
|
|
"num_tokens": 11403359.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.431511735916137,
|
|
"epoch": 0.582296196331284,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973704250349965,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.13376598954200744,
|
|
"num_tokens": 11412921.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.368031454086304,
|
|
"epoch": 0.5827960213925126,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004973649818541722,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.1414501264691353,
|
|
"num_tokens": 11422459.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.334111738204956,
|
|
"epoch": 0.5832958464537412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973595330787022,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.1441892385482788,
|
|
"num_tokens": 11431517.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.4042764663696286,
|
|
"epoch": 0.5837956715149698,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973540787087235,
|
|
"loss": 6.2785,
|
|
"mean_token_accuracy": 0.1401561513543129,
|
|
"num_tokens": 11440662.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.305119132995605,
|
|
"epoch": 0.5842954965761983,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973486187443734,
|
|
"loss": 6.1169,
|
|
"mean_token_accuracy": 0.152145853638649,
|
|
"num_tokens": 11449762.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.258690071105957,
|
|
"epoch": 0.5847953216374269,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973431531857893,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.15245335996150972,
|
|
"num_tokens": 11459963.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.378319978713989,
|
|
"epoch": 0.5852951466986555,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973376820331087,
|
|
"loss": 6.3085,
|
|
"mean_token_accuracy": 0.1369134873151779,
|
|
"num_tokens": 11469063.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.395351839065552,
|
|
"epoch": 0.585794971759884,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973322052864692,
|
|
"loss": 6.1971,
|
|
"mean_token_accuracy": 0.1487408384680748,
|
|
"num_tokens": 11477651.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.449237442016601,
|
|
"epoch": 0.5862947968211126,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973267229460087,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.13495168089866638,
|
|
"num_tokens": 11487248.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.412726211547851,
|
|
"epoch": 0.5867946218823412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497321235011865,
|
|
"loss": 6.3799,
|
|
"mean_token_accuracy": 0.13810717761516572,
|
|
"num_tokens": 11497066.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.479768466949463,
|
|
"epoch": 0.5872944469435698,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973157414841763,
|
|
"loss": 6.3386,
|
|
"mean_token_accuracy": 0.13051055520772933,
|
|
"num_tokens": 11508490.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.466969633102417,
|
|
"epoch": 0.5877942720047983,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973102423630806,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.1406203828752041,
|
|
"num_tokens": 11518851.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.424728870391846,
|
|
"epoch": 0.5882940970660269,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973047376487166,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.14128684774041175,
|
|
"num_tokens": 11529102.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.388212013244629,
|
|
"epoch": 0.5887939221272555,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972992273412224,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.1358910955488682,
|
|
"num_tokens": 11540563.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.391242265701294,
|
|
"epoch": 0.589293747188484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004972937114407369,
|
|
"loss": 6.2476,
|
|
"mean_token_accuracy": 0.14669288769364358,
|
|
"num_tokens": 11549955.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.376825428009033,
|
|
"epoch": 0.5897935722497126,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497288189947399,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.14328095093369483,
|
|
"num_tokens": 11558932.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.270180940628052,
|
|
"epoch": 0.5902933973109412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004972826628613472,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.14396324902772903,
|
|
"num_tokens": 11568901.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.410828733444214,
|
|
"epoch": 0.5907932223721697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972771301827209,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.14194692373275758,
|
|
"num_tokens": 11579738.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.410345602035522,
|
|
"epoch": 0.5912930474333983,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004972715919116592,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.14249148815870286,
|
|
"num_tokens": 11590293.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.413597536087036,
|
|
"epoch": 0.5917928724946269,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972660480483015,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.13725078403949736,
|
|
"num_tokens": 11599745.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.4196656227111815,
|
|
"epoch": 0.5922926975558555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972604985927871,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13385162949562074,
|
|
"num_tokens": 11609958.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.465918827056885,
|
|
"epoch": 0.592792522617084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972549435452558,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.13586054369807243,
|
|
"num_tokens": 11619941.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.357407808303833,
|
|
"epoch": 0.5932923476783126,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972493829058474,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.14977660328149794,
|
|
"num_tokens": 11630287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.351117706298828,
|
|
"epoch": 0.5937921727395412,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004972438166747016,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.14242334812879562,
|
|
"num_tokens": 11639806.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.377180862426758,
|
|
"epoch": 0.5942919978007697,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972382448519586,
|
|
"loss": 6.333,
|
|
"mean_token_accuracy": 0.1424495354294777,
|
|
"num_tokens": 11650132.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.390507555007934,
|
|
"epoch": 0.5947918228619983,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004972326674377586,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.14251381009817124,
|
|
"num_tokens": 11659670.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.415858125686645,
|
|
"epoch": 0.5952916479232269,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972270844322418,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.14169998168945314,
|
|
"num_tokens": 11669998.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.416223192214966,
|
|
"epoch": 0.5957914729844555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972214958355488,
|
|
"loss": 6.306,
|
|
"mean_token_accuracy": 0.13907138854265214,
|
|
"num_tokens": 11679052.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.397159767150879,
|
|
"epoch": 0.596291298045684,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972159016478201,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.14112116992473603,
|
|
"num_tokens": 11687957.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.3890931606292725,
|
|
"epoch": 0.5967911231069126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972103018691965,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.14139744713902475,
|
|
"num_tokens": 11696922.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.377246761322022,
|
|
"epoch": 0.5972909481681411,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004972046964998189,
|
|
"loss": 6.2039,
|
|
"mean_token_accuracy": 0.14591391384601593,
|
|
"num_tokens": 11706600.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.311473655700683,
|
|
"epoch": 0.5977907732293697,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004971990855398283,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.1409190982580185,
|
|
"num_tokens": 11715933.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.391643905639649,
|
|
"epoch": 0.5982905982905983,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004971934689893658,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.14715758115053176,
|
|
"num_tokens": 11724807.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.410089302062988,
|
|
"epoch": 0.5987904233518269,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004971878468485729,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.14309779852628707,
|
|
"num_tokens": 11734985.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.356278133392334,
|
|
"epoch": 0.5992902484130554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497182219117591,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.13901931121945382,
|
|
"num_tokens": 11743418.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.3269764423370365,
|
|
"epoch": 0.599790073474284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004971765857965615,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.13885150700807572,
|
|
"num_tokens": 11752953.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.599790073474284,
|
|
"eval_entropy": 6.200126294468027,
|
|
"eval_loss": 6.319167137145996,
|
|
"eval_mean_token_accuracy": 0.14492665400250562,
|
|
"eval_num_tokens": 11752953.0,
|
|
"eval_runtime": 23.6915,
|
|
"eval_samples_per_second": 1310.384,
|
|
"eval_steps_per_second": 163.814,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"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": 1.8661672894464e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|