f21d0f2e85
Model: fpadovani/tur-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.299895036737142,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 9383935887360000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|