7409bf690e
Model: fpadovani/eng-latn-100mb-after-ppt-shuff-dyck-disjoint-tok-ckpt500_seed3407_seed3407 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": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.25639886856079,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 11.7409,
|
|
"mean_token_accuracy": 0.0026910859567578884,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.252698040008545,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 11.7094,
|
|
"mean_token_accuracy": 0.0012989068985916675,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.256062889099121,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 11.6893,
|
|
"mean_token_accuracy": 0.002295289159519598,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.28339958190918,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 11.5471,
|
|
"mean_token_accuracy": 0.003405291523085907,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.283167362213135,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.3861,
|
|
"mean_token_accuracy": 0.006172553007490933,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.233351135253907,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 11.2207,
|
|
"mean_token_accuracy": 0.022563868667930365,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.17716064453125,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.9781,
|
|
"mean_token_accuracy": 0.02911745272576809,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.325019550323486,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.6651,
|
|
"mean_token_accuracy": 0.030208175629377367,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.383963871002198,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.5824,
|
|
"mean_token_accuracy": 0.02886309754103422,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.449808597564697,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.4605,
|
|
"mean_token_accuracy": 0.038186770118772986,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.461854267120362,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3849,
|
|
"mean_token_accuracy": 0.040889688022434714,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.472981071472168,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.295,
|
|
"mean_token_accuracy": 0.037749376334249976,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.491286468505859,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.2382,
|
|
"mean_token_accuracy": 0.03989502489566803,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.506498050689697,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 10.1488,
|
|
"mean_token_accuracy": 0.03764319252222777,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.518252658843995,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 10.0531,
|
|
"mean_token_accuracy": 0.038073062710464,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.528139972686768,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.9445,
|
|
"mean_token_accuracy": 0.039117959514260295,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.524243068695068,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.8407,
|
|
"mean_token_accuracy": 0.044676617905497554,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.510469150543212,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.7592,
|
|
"mean_token_accuracy": 0.038761510699987414,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.509880542755127,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.6288,
|
|
"mean_token_accuracy": 0.042973919026553634,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.515023994445801,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.5036,
|
|
"mean_token_accuracy": 0.039228996820747854,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.511959838867188,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.3655,
|
|
"mean_token_accuracy": 0.041880004480481146,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.486880874633789,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.2756,
|
|
"mean_token_accuracy": 0.03760720025748014,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.462724304199218,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.084,
|
|
"mean_token_accuracy": 0.038566050492227076,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.42501459121704,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8662,
|
|
"mean_token_accuracy": 0.041522559337317945,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.37605791091919,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7259,
|
|
"mean_token_accuracy": 0.035992196202278136,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.301450824737548,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5828,
|
|
"mean_token_accuracy": 0.03876302167773247,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.22424955368042,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.4842,
|
|
"mean_token_accuracy": 0.03725951910018921,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.137630462646484,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3182,
|
|
"mean_token_accuracy": 0.04086887463927269,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.952799987792968,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.1687,
|
|
"mean_token_accuracy": 0.04170650318264961,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.707593727111817,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.9867,
|
|
"mean_token_accuracy": 0.04252769723534584,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.44668788909912,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.8717,
|
|
"mean_token_accuracy": 0.03686592467129231,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.195470142364503,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.7169,
|
|
"mean_token_accuracy": 0.0400078721344471,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.776480579376221,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6303,
|
|
"mean_token_accuracy": 0.04083114080131054,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.479571533203124,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6035,
|
|
"mean_token_accuracy": 0.039075618609786034,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.282562637329102,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5491,
|
|
"mean_token_accuracy": 0.03750791251659393,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.006285572052002,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5439,
|
|
"mean_token_accuracy": 0.038402245566248897,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.9631373405456545,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.493,
|
|
"mean_token_accuracy": 0.0437284167855978,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.781239318847656,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4957,
|
|
"mean_token_accuracy": 0.04678881764411926,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.785053539276123,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5136,
|
|
"mean_token_accuracy": 0.04727039746940136,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.740858125686645,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5696,
|
|
"mean_token_accuracy": 0.04193144179880619,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.758722639083862,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4302,
|
|
"mean_token_accuracy": 0.045322371646761894,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.715395164489746,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4423,
|
|
"mean_token_accuracy": 0.058253410086035726,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.59510555267334,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5059,
|
|
"mean_token_accuracy": 0.058244950324296954,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.6779868602752686,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.458,
|
|
"mean_token_accuracy": 0.06584881767630577,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.6262555599212645,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3474,
|
|
"mean_token_accuracy": 0.06667502745985984,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.683849191665649,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5293,
|
|
"mean_token_accuracy": 0.0678394366055727,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.675125026702881,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.3906,
|
|
"mean_token_accuracy": 0.07262160144746303,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.534460210800171,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.3269,
|
|
"mean_token_accuracy": 0.0788414567708969,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.556740760803223,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4559,
|
|
"mean_token_accuracy": 0.07313848771154881,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.651741409301758,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.4231,
|
|
"mean_token_accuracy": 0.06984101124107837,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.559566640853882,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4417,
|
|
"mean_token_accuracy": 0.07528160624206066,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.60768313407898,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3847,
|
|
"mean_token_accuracy": 0.07447496987879276,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.602000761032104,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.3083,
|
|
"mean_token_accuracy": 0.07689321786165237,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.546748113632202,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3863,
|
|
"mean_token_accuracy": 0.0756129652261734,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.626759958267212,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3776,
|
|
"mean_token_accuracy": 0.07868644669651985,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.603859090805054,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.3381,
|
|
"mean_token_accuracy": 0.0748847633600235,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.569405174255371,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2915,
|
|
"mean_token_accuracy": 0.08101793453097343,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.554937267303467,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.2766,
|
|
"mean_token_accuracy": 0.08518879413604737,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.543597173690796,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2827,
|
|
"mean_token_accuracy": 0.0838129960000515,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.536286020278931,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.2208,
|
|
"mean_token_accuracy": 0.08279290944337844,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.500700044631958,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.2719,
|
|
"mean_token_accuracy": 0.08277729079127312,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.403319644927978,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0849,
|
|
"mean_token_accuracy": 0.08483515977859497,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.422772455215454,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.173,
|
|
"mean_token_accuracy": 0.08649655506014824,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.5332183837890625,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1756,
|
|
"mean_token_accuracy": 0.08641982153058052,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.479076910018921,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.2977,
|
|
"mean_token_accuracy": 0.08264525830745698,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.496834087371826,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2999,
|
|
"mean_token_accuracy": 0.08251902386546135,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.395641613006592,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.0579,
|
|
"mean_token_accuracy": 0.08676571622490883,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.39327449798584,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.1187,
|
|
"mean_token_accuracy": 0.0880549892783165,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.318950414657593,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0332,
|
|
"mean_token_accuracy": 0.08635925874114037,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.353262042999267,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0952,
|
|
"mean_token_accuracy": 0.09182592332363129,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.3257616519927975,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.136,
|
|
"mean_token_accuracy": 0.08920007646083832,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.399164628982544,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1632,
|
|
"mean_token_accuracy": 0.08764473721385002,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.224786233901978,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0352,
|
|
"mean_token_accuracy": 0.09125346541404725,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.286064577102661,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0431,
|
|
"mean_token_accuracy": 0.09055957570672035,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.305629539489746,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.09202495589852333,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.371310424804688,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.1098,
|
|
"mean_token_accuracy": 0.08957164734601974,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.336284589767456,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.063,
|
|
"mean_token_accuracy": 0.09114922881126404,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.226832294464112,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9601,
|
|
"mean_token_accuracy": 0.0964093454182148,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.222394752502441,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0239,
|
|
"mean_token_accuracy": 0.10131923705339432,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.244077253341675,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9904,
|
|
"mean_token_accuracy": 0.09794511124491692,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.264095592498779,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0037,
|
|
"mean_token_accuracy": 0.09216101467609406,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.212151622772216,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9559,
|
|
"mean_token_accuracy": 0.10168264731764794,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.21423306465149,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9665,
|
|
"mean_token_accuracy": 0.09732877537608146,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.138846921920776,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9948,
|
|
"mean_token_accuracy": 0.09952060505747795,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.175388956069947,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8805,
|
|
"mean_token_accuracy": 0.10059212520718575,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.089182806015015,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9372,
|
|
"mean_token_accuracy": 0.09849796593189239,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.184536552429199,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.889,
|
|
"mean_token_accuracy": 0.10151714682579041,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.127185440063476,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.10072232410311699,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.1458930492401125,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.1004769742488861,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.197234964370727,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0244,
|
|
"mean_token_accuracy": 0.10357746407389641,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.973642158508301,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8315,
|
|
"mean_token_accuracy": 0.1050386182963848,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.1875935077667235,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9257,
|
|
"mean_token_accuracy": 0.09776141494512558,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.147069692611694,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.9539,
|
|
"mean_token_accuracy": 0.09493176713585853,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.040191555023194,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8166,
|
|
"mean_token_accuracy": 0.10042703226208687,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.027799129486084,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8431,
|
|
"mean_token_accuracy": 0.1014677569270134,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.141836309432984,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9903,
|
|
"mean_token_accuracy": 0.10095212161540985,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.945070791244507,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8419,
|
|
"mean_token_accuracy": 0.10394882559776306,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.250262975692749,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.9611,
|
|
"mean_token_accuracy": 0.10339747741818428,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.982399654388428,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8471,
|
|
"mean_token_accuracy": 0.0988765001296997,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.01871132850647,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9121,
|
|
"mean_token_accuracy": 0.1074085734784603,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.023473834991455,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.10938784778118134,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.023718929290771,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8839,
|
|
"mean_token_accuracy": 0.11009863540530204,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.948973846435547,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.10685163512825965,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.0727332592010494,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8908,
|
|
"mean_token_accuracy": 0.10683172717690467,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.95055775642395,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.10525572448968887,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.000631856918335,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7251,
|
|
"mean_token_accuracy": 0.10736186131834984,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.959245443344116,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7478,
|
|
"mean_token_accuracy": 0.10534990206360817,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.902206563949585,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9124,
|
|
"mean_token_accuracy": 0.10460811406373978,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.9541998386383055,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7425,
|
|
"mean_token_accuracy": 0.11181432232260705,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.080395078659057,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.8042,
|
|
"mean_token_accuracy": 0.10288820937275886,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.755504512786866,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.11182279288768768,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.958348941802979,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.1030250370502472,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.0104207515716555,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7471,
|
|
"mean_token_accuracy": 0.1139664702117443,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.860793161392212,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.8584,
|
|
"mean_token_accuracy": 0.11190064251422882,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.909835290908814,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.747,
|
|
"mean_token_accuracy": 0.11047227904200554,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.996085596084595,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7767,
|
|
"mean_token_accuracy": 0.11513174846768379,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.839344120025634,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7449,
|
|
"mean_token_accuracy": 0.11083959862589836,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.863824939727783,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.727,
|
|
"mean_token_accuracy": 0.11484655365347862,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.9280845642089846,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8363,
|
|
"mean_token_accuracy": 0.11602571532130242,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.001092004776001,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9057,
|
|
"mean_token_accuracy": 0.10357883349061012,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.722957897186279,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5765,
|
|
"mean_token_accuracy": 0.11965182796120644,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.931371068954467,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7924,
|
|
"mean_token_accuracy": 0.11453562378883361,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.858430242538452,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8079,
|
|
"mean_token_accuracy": 0.1133706197142601,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.822653102874756,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.11548932567238808,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.799988889694214,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.7658,
|
|
"mean_token_accuracy": 0.11335846111178398,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.776160717010498,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6291,
|
|
"mean_token_accuracy": 0.12655726373195647,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.81230092048645,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.677,
|
|
"mean_token_accuracy": 0.120645322650671,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.884833669662475,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.11574307680130005,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.699341487884522,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6679,
|
|
"mean_token_accuracy": 0.12265671268105507,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.890548658370972,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.1140442967414856,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.8591334342956545,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7635,
|
|
"mean_token_accuracy": 0.11165911853313445,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.80465030670166,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.11683566421270371,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.709757089614868,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5363,
|
|
"mean_token_accuracy": 0.121712426841259,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.838316631317139,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8144,
|
|
"mean_token_accuracy": 0.1120360791683197,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.873385381698609,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.7205,
|
|
"mean_token_accuracy": 0.11793086603283882,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.792718982696533,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.12022969275712966,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.644273567199707,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6175,
|
|
"mean_token_accuracy": 0.12695625126361848,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.711900901794434,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6209,
|
|
"mean_token_accuracy": 0.1197846882045269,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.7214684009552,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.6278,
|
|
"mean_token_accuracy": 0.11783769056200981,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.796803903579712,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7268,
|
|
"mean_token_accuracy": 0.1210656888782978,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.696943473815918,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.5718,
|
|
"mean_token_accuracy": 0.1262438789010048,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.750957107543945,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5652,
|
|
"mean_token_accuracy": 0.12253414019942284,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.546931219100952,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5747,
|
|
"mean_token_accuracy": 0.12381779551506042,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.817351818084717,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.7402,
|
|
"mean_token_accuracy": 0.11719322726130485,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.713132858276367,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.11970261111855507,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.730032444000244,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.12532211914658548,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.764851093292236,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5684,
|
|
"mean_token_accuracy": 0.1264908105134964,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.644136762619018,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.12845728248357774,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.66550931930542,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.6157,
|
|
"mean_token_accuracy": 0.1237633615732193,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.739824438095093,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6554,
|
|
"mean_token_accuracy": 0.12233619689941407,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.677445888519287,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.13024282306432725,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.733970499038696,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6821,
|
|
"mean_token_accuracy": 0.12274667993187904,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.672050523757934,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.12385557517409325,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.624249505996704,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.11638602316379547,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.845441389083862,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.12483799159526825,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.763451385498047,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.7368,
|
|
"mean_token_accuracy": 0.1217820793390274,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.595237827301025,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4325,
|
|
"mean_token_accuracy": 0.13330992460250854,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.58812689781189,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.12191837057471275,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.780652809143066,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6634,
|
|
"mean_token_accuracy": 0.123942082375288,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.602289724349975,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5703,
|
|
"mean_token_accuracy": 0.12607999593019487,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.695853853225708,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5673,
|
|
"mean_token_accuracy": 0.12844647020101546,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.667530870437622,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6049,
|
|
"mean_token_accuracy": 0.12256239578127862,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.709681272506714,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.12430930361151696,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.590344858169556,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5098,
|
|
"mean_token_accuracy": 0.12951224520802498,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.738299226760864,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.11758637428283691,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.652737951278686,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6038,
|
|
"mean_token_accuracy": 0.12358284816145897,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.627905178070068,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.598,
|
|
"mean_token_accuracy": 0.12505071982741356,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.549618434906006,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4806,
|
|
"mean_token_accuracy": 0.13302377462387086,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.733680200576782,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.6641,
|
|
"mean_token_accuracy": 0.12029701620340347,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.674782085418701,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5505,
|
|
"mean_token_accuracy": 0.13130439519882203,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.632183504104614,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6123,
|
|
"mean_token_accuracy": 0.11986933276057243,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.6506672382354735,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.128663220256567,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.659067535400391,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.6133,
|
|
"mean_token_accuracy": 0.12502505853772164,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.522532606124878,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.465,
|
|
"mean_token_accuracy": 0.1305969774723053,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.521027231216431,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5332,
|
|
"mean_token_accuracy": 0.12862171232700348,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.733491516113281,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6259,
|
|
"mean_token_accuracy": 0.12553723603487016,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.552764797210694,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4797,
|
|
"mean_token_accuracy": 0.12476090043783188,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.5761137962341305,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.13477788046002387,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.574522161483765,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.12630576267838478,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.519236660003662,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.13307079225778579,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.607462596893311,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5494,
|
|
"mean_token_accuracy": 0.13406692892313005,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.4195150375366214,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.13798633739352226,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.49401707649231,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.13152770772576333,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.484944677352905,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4981,
|
|
"mean_token_accuracy": 0.12505212873220445,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.572954750061035,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5125,
|
|
"mean_token_accuracy": 0.12695388346910477,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.553452968597412,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.12948471456766128,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.6269059658050535,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5882,
|
|
"mean_token_accuracy": 0.12736724987626075,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.718510961532592,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6336,
|
|
"mean_token_accuracy": 0.12538549676537514,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.5074928283691404,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.13048772215843202,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.615377426147461,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.1323799431324005,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.48550271987915,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4768,
|
|
"mean_token_accuracy": 0.13284032344818114,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.5667078495025635,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5651,
|
|
"mean_token_accuracy": 0.12846669927239418,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.492109537124634,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.13522292152047158,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.475024604797364,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.12998763769865035,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.565961837768555,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4639,
|
|
"mean_token_accuracy": 0.12638997063040733,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.398307752609253,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4561,
|
|
"mean_token_accuracy": 0.13463474065065384,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.4558258056640625,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4511,
|
|
"mean_token_accuracy": 0.12646445855498314,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.489946889877319,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.13445554673671722,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.453236436843872,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4207,
|
|
"mean_token_accuracy": 0.13301730901002884,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.585108804702759,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.1316801317036152,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.456496858596802,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.5247,
|
|
"mean_token_accuracy": 0.12453527525067329,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.560186100006104,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.491,
|
|
"mean_token_accuracy": 0.1362232081592083,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.490068674087524,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.1341004975140095,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.507891464233398,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.12934465631842612,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.524950933456421,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.127571739256382,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.621273231506348,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.5086,
|
|
"mean_token_accuracy": 0.1368153616786003,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.402975273132324,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.4343,
|
|
"mean_token_accuracy": 0.1310793451964855,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.539117860794067,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.131030685454607,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.555915832519531,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.4067,
|
|
"mean_token_accuracy": 0.14168997928500177,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.3779439449310305,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.13549636751413346,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.440852689743042,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.13899283483624458,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.419764804840088,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.1340063691139221,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.476871919631958,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.1311580441892147,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.585131025314331,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.4729,
|
|
"mean_token_accuracy": 0.13767909109592438,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.413916444778442,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.13483774214982985,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.425882148742676,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.13548125475645065,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.4980425357818605,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.5464,
|
|
"mean_token_accuracy": 0.1351483039557934,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.573987579345703,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.13326464518904685,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.402809953689575,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.4139,
|
|
"mean_token_accuracy": 0.13775320574641228,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.311347532272339,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.14299433752894403,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.469817876815796,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.14109985455870627,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.417138671875,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.13988902568817138,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.481253623962402,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.13518037721514703,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.59227557182312,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.4646,
|
|
"mean_token_accuracy": 0.1327376738190651,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.266043615341187,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.13951586112380027,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.528832149505615,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.3984,
|
|
"mean_token_accuracy": 0.13773541748523713,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.33425726890564,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.1425212301313877,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.518994569778442,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.3819,
|
|
"mean_token_accuracy": 0.13330503478646277,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.3555159091949465,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.1448584720492363,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3979815483093265,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.13572428226470948,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.344897937774658,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.14001458808779715,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.554988098144531,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.3852,
|
|
"mean_token_accuracy": 0.13615019991993904,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.3376793384552,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.3748,
|
|
"mean_token_accuracy": 0.13186048045754434,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.344990921020508,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.1399838626384735,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.420182085037231,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.13971240893006326,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.348382759094238,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.3225,
|
|
"mean_token_accuracy": 0.13963563665747641,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.378366088867187,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.4077,
|
|
"mean_token_accuracy": 0.13064486235380174,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.471061944961548,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.142090106010437,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.4110862731933596,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.14113106280565263,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.469895267486573,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.1292402721941471,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.354708957672119,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.14201848655939103,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.4176633834838865,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.13264842703938484,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.377297592163086,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.13756700977683067,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.4666331768035885,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.14598208293318748,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.428584241867066,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.4134,
|
|
"mean_token_accuracy": 0.1348503641784191,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.266319847106933,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.1396687351167202,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.460708808898926,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.13702112659811974,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.414711141586304,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.4365,
|
|
"mean_token_accuracy": 0.13701202794909478,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.432314443588257,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.13881635367870332,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.358312511444092,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.14529771953821183,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.419577169418335,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.2782,
|
|
"mean_token_accuracy": 0.14040456488728523,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.296146583557129,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.14076389670372008,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.348859882354736,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.1368976838886738,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.348705673217774,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.13619414418935777,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.347746229171753,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.2028,
|
|
"mean_token_accuracy": 0.14546942338347435,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.289702272415161,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.2401,
|
|
"mean_token_accuracy": 0.14375891238451005,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.35533881187439,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.2663,
|
|
"mean_token_accuracy": 0.14633105844259262,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.233186101913452,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.14503639936447144,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.362540769577026,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.13664028346538543,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.306020212173462,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.2357,
|
|
"mean_token_accuracy": 0.13921404853463173,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.284024572372436,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.14088367968797683,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.376524925231934,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.3348,
|
|
"mean_token_accuracy": 0.13199515640735626,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.2676990032196045,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.1430131196975708,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.3416272640228275,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.13728150352835655,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.376453304290772,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.13831673040986062,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.417525577545166,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.13861921206116676,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.407558107376099,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.13716086149215698,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.188078784942627,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.13945341408252715,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.482673597335816,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.353,
|
|
"mean_token_accuracy": 0.14002300277352334,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.254575872421265,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.14595276713371277,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.553881549835205,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.13388766795396806,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.27535490989685,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.2853,
|
|
"mean_token_accuracy": 0.13878872245550156,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.293557262420654,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.14105164185166358,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.372267818450927,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.1421847365796566,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.353737211227417,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.3003,
|
|
"mean_token_accuracy": 0.1419496037065983,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.360533714294434,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.1449585184454918,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.235655450820923,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.13456685617566108,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.440259408950806,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.13899147212505342,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.34439787864685,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.14071865901350974,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.224101924896241,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.14295614287257194,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.388071966171265,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.13431284055113793,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.397411298751831,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.143301859498024,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.158065271377564,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.2684,
|
|
"mean_token_accuracy": 0.13974310755729674,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.432788991928101,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.14211769849061967,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.21512804031372,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.2877,
|
|
"mean_token_accuracy": 0.14602836072444916,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.338991689682007,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.13677069991827012,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.18875823020935,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.13699881434440614,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.351223182678223,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.14297635555267335,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.344785833358765,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.13555386140942574,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.229445600509644,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.14848765432834626,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.131477737426758,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.14189836829900743,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.446213865280152,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.1473018154501915,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.181229066848755,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.15136088579893112,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.132031583786011,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.1496811881661415,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.244436836242675,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.1549,
|
|
"mean_token_accuracy": 0.14772350192070008,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.332507038116455,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.3432,
|
|
"mean_token_accuracy": 0.14269206747412683,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.224244928359985,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.1542764872312546,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.275435161590576,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.14152566939592362,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.349188041687012,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.13980446606874466,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.26988787651062,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.15189649015665055,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.249851369857788,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.14386393129825592,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.336975526809693,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.1504651814699173,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.2502185821533205,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.1409212589263916,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.462999057769776,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.288,
|
|
"mean_token_accuracy": 0.1381421558558941,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.246134901046753,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.13986739218235017,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.3834983825683596,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.1448330372571945,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.145442771911621,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.14555919021368027,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.297583770751953,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.1472916215658188,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.213202953338623,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.1482724741101265,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.228994274139405,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.1479077994823456,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.121140384674073,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.14061250612139703,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.5244382381439205,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.3998,
|
|
"mean_token_accuracy": 0.14157005473971368,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.189446020126343,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.15490597486495972,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.284439182281494,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.13803954273462296,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.291994380950928,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.14772795587778093,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.30311017036438,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.14605900645256042,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.187708377838135,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.1448603853583336,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.21040096282959,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.14277410134673119,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.308737564086914,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.1415993995964527,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.151534795761108,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.14444077014923096,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.327757406234741,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.15372487977147103,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.3059488296508786,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.14689953327178956,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.120879793167115,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.152867791056633,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.267522573471069,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.14639166221022606,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.195144271850586,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.1583167091012001,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.165605783462524,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.1476339131593704,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.1696093559265135,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.1420426405966282,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.245587396621704,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.1402585081756115,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.302711725234985,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.14278458282351494,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.166055631637573,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.1390815943479538,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.152737283706665,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.15113601088523865,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.079391670227051,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14676920920610428,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.2547712326049805,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.14625280648469924,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.255711317062378,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.1443650782108307,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.278718280792236,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.14049319103360175,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.170718765258789,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 6.0598,
|
|
"mean_token_accuracy": 0.15319431126117705,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.1924333572387695,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.1471312403678894,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.224253702163696,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.14361522495746612,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.230266857147217,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.1505300983786583,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.259658145904541,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.14401278346776963,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.167710828781128,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14654720053076745,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.081889629364014,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.15570705085992814,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.077426338195801,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.15049063116312028,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.112188291549683,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.148158148676157,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.089222717285156,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.1548941805958748,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.0848329067230225,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14957866221666336,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.147818183898925,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.1490088775753975,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.188397979736328,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 6.1385,
|
|
"mean_token_accuracy": 0.15051164627075195,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.246903657913208,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.15150685235857964,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.131383800506592,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 6.105,
|
|
"mean_token_accuracy": 0.14395989701151848,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.214809513092041,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.1482173793017864,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.142779541015625,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.14746149256825447,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.216650819778442,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14692942351102828,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.062715196609497,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.15319886654615403,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.210793972015381,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.15144960433244706,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.174288940429688,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.14908579289913176,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.225276279449463,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.1512651652097702,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.183860206604004,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.15166645050048827,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.145701837539673,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.14939896166324615,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.029658460617066,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.1588248908519745,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.135398435592651,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.14331067353487015,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.15322699546814,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.1573499321937561,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.208154487609863,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.1487251937389374,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.128590059280396,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.1585391640663147,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.332269668579102,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.2477,
|
|
"mean_token_accuracy": 0.1459768995642662,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.105072927474976,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.14765892326831817,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.109910249710083,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.15023878514766692,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.175615119934082,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.157446925342083,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.236642742156983,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.14365296810865402,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.346523237228394,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.14365033358335494,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.223315095901489,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14539413154125214,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.098178768157959,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.1485121563076973,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.124366617202758,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.1491617165505886,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.119881010055542,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.15643363893032075,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.118890285491943,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.1560173213481903,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.123640012741089,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.15241918265819548,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.308550214767456,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.15168551802635194,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.042774629592896,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.14869935661554337,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.086363315582275,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.15354848504066468,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.137011957168579,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.15438924431800843,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.263278245925903,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.14329903498291968,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.198366451263428,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 6.161,
|
|
"mean_token_accuracy": 0.14747311770915986,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.277743291854859,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.14608076959848404,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.069996547698975,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.15598759353160857,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.026457405090332,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.15107496082782745,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.290648698806763,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.15128218084573747,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.10584077835083,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.14796533063054085,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.090063381195068,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.15715189576148986,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.042044544219971,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.15147724151611328,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.2164843559265135,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.1436479665338993,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.175703525543213,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 6.0064,
|
|
"mean_token_accuracy": 0.1556989625096321,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.869294500350952,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15484603345394135,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.039911985397339,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.1563266322016716,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.159225559234619,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.1488205224275589,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.015854930877685,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 6.0076,
|
|
"mean_token_accuracy": 0.14695556685328484,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.244098138809204,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.14658438861370088,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.135475778579712,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.15329247564077378,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.063277769088745,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.14928158596158028,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.266687870025635,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.15549051016569138,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.027319240570068,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.15551431477069855,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.019188499450683,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.15041673630476,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.231358623504638,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.15111713707447053,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.196571016311646,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.1539139837026596,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.084535074234009,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.15315846651792525,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.096588039398194,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.15145348012447357,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.213549852371216,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.145511694252491,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.154675054550171,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.15400808304548264,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.01413254737854,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.1529553934931755,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.154169607162475,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.15515930503606795,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.079659175872803,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.16131191849708557,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.063276243209839,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.1526772379875183,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.107676076889038,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.1490740567445755,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.250979852676392,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.14502785950899125,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.109724712371826,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.15285840034484863,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.003591156005859,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.15680260062217713,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.083307552337646,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.1513105571269989,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.155953454971313,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.14754048883914947,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.174464988708496,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.1461272232234478,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.1856427669525145,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.15473159700632094,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.077418518066406,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15717330425977707,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.082688808441162,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 6.0996,
|
|
"mean_token_accuracy": 0.15195055305957794,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.22024130821228,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.1504859909415245,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.151685571670532,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.14684750735759736,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.061194324493409,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.1638572856783867,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.022126531600952,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15314062237739562,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.996016979217529,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.1606994539499283,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.060186147689819,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.15231975466012954,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.0076862335205075,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.1594335064291954,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.193838834762573,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.14647017419338226,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.1166502952575685,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.9985,
|
|
"mean_token_accuracy": 0.1459207035601139,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.083969259262085,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.15580957233905793,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.976114320755005,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.16323217898607253,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.061397123336792,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.14964161813259125,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.107447004318237,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.15928057283163072,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.872031927108765,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.15852829664945603,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.157621288299561,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.16119896918535231,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.080954504013062,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.14659972339868546,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.237659978866577,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.16113914996385575,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.919554424285889,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.15738066136837006,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.218607234954834,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14981306791305543,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.19651517868042,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.14576388597488404,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.0613480567932125,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.15590714514255524,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.968810176849365,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.1578755110502243,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.131110334396363,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.14955551028251649,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.9506998538970945,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.16224861592054368,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.0852518558502195,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.15131033658981324,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.060042428970337,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1576952561736107,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.013088703155518,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.15376421064138412,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.1519105434417725,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.15947780162096023,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.026669692993164,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.15224288105964662,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.166677522659302,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.15358851104974747,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.102503728866577,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.1501933827996254,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.090739488601685,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.15912422835826873,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.151770973205567,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.14825651198625564,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.138964891433716,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.15490673780441283,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.038366365432739,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.15771733224391937,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.103801107406616,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.15576983839273453,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.129735326766967,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.15617480129003525,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.987654972076416,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.15116089582443237,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.157898807525635,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.15195467919111252,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.094862699508667,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.1550524652004242,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.958035707473755,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.1468196243047714,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.126406049728393,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.15484741032123567,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.043291521072388,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.15324235707521439,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.055290842056275,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.16078570783138274,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.993036842346191,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 6.0215,
|
|
"mean_token_accuracy": 0.1626984179019928,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.009312629699707,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.15396428406238555,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.020443344116211,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15726363211870192,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.102507829666138,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15023885518312455,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.035394668579102,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.15539337694644928,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.038948059082031,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.15632582753896712,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.083648633956909,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.15450441390275954,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.8433245658874515,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.15305204540491105,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.025034093856812,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.15324413478374482,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.916028690338135,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.15359498262405397,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.049281930923462,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.1482474312186241,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.043624353408814,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.15914819538593292,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.079010963439941,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.1458563432097435,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.132135200500488,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.16378798931837082,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.050425243377686,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.15482408478856086,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.0575597286224365,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.1507862962782383,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.040148830413818,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.15217866897583007,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.045368623733521,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.15985994040966034,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.910307359695435,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.15814046263694764,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.159975671768189,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.14930515587329865,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.926601505279541,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.9607,
|
|
"mean_token_accuracy": 0.16299881041049957,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.892569589614868,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.15828869342803956,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.01947603225708,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.16353946775197983,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.1192179203033445,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.1688,
|
|
"mean_token_accuracy": 0.15179817527532577,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.088233995437622,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15265644788742067,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.960464429855347,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.8577,
|
|
"mean_token_accuracy": 0.15811959505081177,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.074854564666748,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.15298570096492767,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.961808776855468,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.15553341507911683,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.985595941543579,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.16250037103891374,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.943635702133179,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.15700624138116837,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.043688678741455,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.1516438513994217,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.1347261428833,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.15147426277399062,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.014614534378052,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15230564698576926,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.008048486709595,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.15721939951181413,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.101916837692261,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.15063416808843613,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.013814878463745,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.15371579229831694,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.024594354629516,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.14784704446792601,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.051389265060425,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.15591129958629607,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.990168857574463,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.15703389495611192,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.092303705215454,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.15879166424274443,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.900774335861206,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.1561056926846504,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.969459009170532,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.15508987456560136,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.097274971008301,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.1543091729283333,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.94429612159729,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.15240908712148665,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.034660053253174,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.15858010351657867,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.085075855255127,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.15524982064962387,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.04909462928772,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.1601421758532524,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.977365207672119,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.15049331039190292,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.137782859802246,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.15206752270460128,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.952969312667847,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.1582716077566147,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.9377197265625,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.167465503513813,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.0136088848114015,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.1571892872452736,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.062278985977173,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.15861130356788636,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.848001956939697,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.1530233860015869,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.030651712417603,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.9058,
|
|
"mean_token_accuracy": 0.16201242804527283,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.013105869293213,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1577301412820816,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.03218035697937,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.15995176434516906,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.098472261428833,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.14447705671191216,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.97599425315857,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.15990931689739227,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.9088949203491214,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.15515819191932678,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.012001180648804,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.14992934688925744,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.072331762313842,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.1609386384487152,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.996478271484375,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.16165445894002914,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.978861856460571,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.150858586281538,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.955687618255615,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.1639521986246109,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.951510906219482,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.15955302566289903,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.063926649093628,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.15360975861549378,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.02715482711792,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.1463753491640091,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.025208616256714,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.1480000451207161,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.800934886932373,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.16546161770820617,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.921378183364868,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.1579037681221962,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.919540977478027,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.15591801702976227,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.953354835510254,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15558021366596222,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.10141167640686,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.1546380952000618,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.984244871139526,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.15790919214487076,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.809388446807861,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1557815633714199,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.070313596725464,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.15179309844970704,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.969070339202881,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.15632378160953522,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.966453695297242,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.16056556701660157,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.998284339904785,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.1577038884162903,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.920602607727051,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.15675391405820846,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.051038122177124,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.1568444013595581,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.945160531997681,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.15690646022558213,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.832088613510132,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.1716798350214958,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.002315855026245,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.15082325488328935,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.019475936889648,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.14947013407945633,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.9253801822662355,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.1644776478409767,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.855195665359497,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.16404712200164795,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.913083553314209,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15659398585557938,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.013282346725464,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15299334228038788,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.030122756958008,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.1562565177679062,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.946122312545777,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.15526296347379684,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.001246643066406,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.15969813764095306,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.9897809505462645,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.15685173273086547,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.88944444656372,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.16546466201543808,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.891298627853393,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.16037205457687378,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.019705200195313,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.16337641030550004,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.061544942855835,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.15389910191297532,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.868814754486084,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.157982175052166,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.909223985671997,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.1622636839747429,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.955548286437988,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.1647718846797943,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.898680114746094,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.1575847841799259,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.998651695251465,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.15362707823514937,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.001203966140747,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.8944,
|
|
"mean_token_accuracy": 0.16161568313837052,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.875576114654541,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.16204904466867448,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.017832040786743,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.15353279262781144,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.99152102470398,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.15284417122602462,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.00714955329895,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.15483998730778695,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.8733357906341555,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.16367374062538148,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.974071979522705,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.15994496941566466,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.964216232299805,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.16927893757820128,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.935434436798095,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.1512233465909958,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.02995548248291,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.1587122306227684,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.9784949779510494,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.15752865448594094,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.020418548583985,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.1578624352812767,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.879127836227417,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.16676969081163406,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.935239315032959,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.16207789927721022,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.898339509963989,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.16786165684461593,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.955675268173218,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.16191720515489577,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.991767835617066,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.9314,
|
|
"mean_token_accuracy": 0.1532451778650284,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.945623350143433,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.1646365851163864,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.8691150665283205,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.16271614283323288,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.8914587020874025,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.1637248530983925,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.8711829662323,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.15968684256076812,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.02776026725769,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.16189566254615784,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.9975940704345705,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.823,
|
|
"mean_token_accuracy": 0.16222766041755676,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.858269691467285,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.15825014412403107,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.004867458343506,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.987,
|
|
"mean_token_accuracy": 0.15539744198322297,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.02716212272644,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.8425,
|
|
"mean_token_accuracy": 0.160085965692997,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.868495655059815,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.1606067419052124,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.955172061920166,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.17116498202085495,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.75142731666565,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.16292239129543304,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.8972403049469,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1556589461863041,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.964262771606445,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.1654741033911705,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.850085067749023,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.16476777344942092,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.856326704514774,
|
|
"eval_loss": 5.906490325927734,
|
|
"eval_mean_token_accuracy": 0.1660596932999661,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 60.6974,
|
|
"eval_samples_per_second": 510.944,
|
|
"eval_steps_per_second": 63.874,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0448431460352e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|