54134 lines
1.5 MiB
54134 lines
1.5 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.8892931671036437,
|
|
"eval_steps": 3000,
|
|
"global_step": 27000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691989517211914,
|
|
"epoch": 0.0005350741077639254,
|
|
"grad_norm": 10.75,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8201,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10038.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.69193468093872,
|
|
"epoch": 0.0010701482155278507,
|
|
"grad_norm": 11.9375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.789,
|
|
"mean_token_accuracy": 0.00010810811072587967,
|
|
"num_tokens": 21916.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.690756225585938,
|
|
"epoch": 0.0016052223232917758,
|
|
"grad_norm": 8.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5855,
|
|
"mean_token_accuracy": 0.029181174421682953,
|
|
"num_tokens": 33434.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.660381984710693,
|
|
"epoch": 0.0021402964310557014,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.3113,
|
|
"mean_token_accuracy": 0.04592931531369686,
|
|
"num_tokens": 44216.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.51073760986328,
|
|
"epoch": 0.0026753705388196263,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.1036,
|
|
"mean_token_accuracy": 0.04351861346513033,
|
|
"num_tokens": 54874.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.5190824508667,
|
|
"epoch": 0.0032104446465835517,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.9872,
|
|
"mean_token_accuracy": 0.041112912446260454,
|
|
"num_tokens": 65085.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.547387790679931,
|
|
"epoch": 0.003745518754347477,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.904,
|
|
"mean_token_accuracy": 0.04395376648753881,
|
|
"num_tokens": 75601.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.474061203002929,
|
|
"epoch": 0.004280592862111403,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.8879,
|
|
"mean_token_accuracy": 0.04307105913758278,
|
|
"num_tokens": 86193.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.531705379486084,
|
|
"epoch": 0.004815666969875327,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.8417,
|
|
"mean_token_accuracy": 0.043867765367031096,
|
|
"num_tokens": 96957.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.478270435333252,
|
|
"epoch": 0.005350741077639253,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.8114,
|
|
"mean_token_accuracy": 0.046108495071530343,
|
|
"num_tokens": 108408.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.473760986328125,
|
|
"epoch": 0.005885815185403178,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.7686,
|
|
"mean_token_accuracy": 0.05027508921921253,
|
|
"num_tokens": 119273.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.462549209594727,
|
|
"epoch": 0.006420889293167103,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.6954,
|
|
"mean_token_accuracy": 0.05541543699800968,
|
|
"num_tokens": 130817.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.302016353607177,
|
|
"epoch": 0.006955963400931029,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.6448,
|
|
"mean_token_accuracy": 0.05586838573217392,
|
|
"num_tokens": 142599.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.404022407531738,
|
|
"epoch": 0.007491037508694954,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.5697,
|
|
"mean_token_accuracy": 0.05663685463368893,
|
|
"num_tokens": 153617.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.37060546875,
|
|
"epoch": 0.00802611161645888,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.5239,
|
|
"mean_token_accuracy": 0.05575243458151817,
|
|
"num_tokens": 165280.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.341149616241456,
|
|
"epoch": 0.008561185724222806,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.4643,
|
|
"mean_token_accuracy": 0.055300182476639745,
|
|
"num_tokens": 176896.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.367101669311523,
|
|
"epoch": 0.00909625983198673,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.4019,
|
|
"mean_token_accuracy": 0.05629164129495621,
|
|
"num_tokens": 188000.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.27455005645752,
|
|
"epoch": 0.009631333939750655,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.3493,
|
|
"mean_token_accuracy": 0.057158011198043826,
|
|
"num_tokens": 199360.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.319551277160645,
|
|
"epoch": 0.01016640804751458,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.2957,
|
|
"mean_token_accuracy": 0.052791529521346095,
|
|
"num_tokens": 210214.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.196423625946045,
|
|
"epoch": 0.010701482155278505,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.1506,
|
|
"mean_token_accuracy": 0.06025413721799851,
|
|
"num_tokens": 220567.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.14912462234497,
|
|
"epoch": 0.011236556263042432,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.057,
|
|
"mean_token_accuracy": 0.06051998771727085,
|
|
"num_tokens": 230585.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.099914455413819,
|
|
"epoch": 0.011771630370806356,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.9907,
|
|
"mean_token_accuracy": 0.06339392885565757,
|
|
"num_tokens": 241996.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.083064746856689,
|
|
"epoch": 0.012306704478570282,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9558,
|
|
"mean_token_accuracy": 0.05828723199665546,
|
|
"num_tokens": 253348.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.981218147277833,
|
|
"epoch": 0.012841778586334207,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8376,
|
|
"mean_token_accuracy": 0.05671278983354568,
|
|
"num_tokens": 264239.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.828715324401855,
|
|
"epoch": 0.013376852694098133,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7502,
|
|
"mean_token_accuracy": 0.056628919392824176,
|
|
"num_tokens": 274522.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.77067985534668,
|
|
"epoch": 0.013911926801862057,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6474,
|
|
"mean_token_accuracy": 0.06091504544019699,
|
|
"num_tokens": 284492.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.592880916595458,
|
|
"epoch": 0.014447000909625984,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6035,
|
|
"mean_token_accuracy": 0.05946716032922268,
|
|
"num_tokens": 294796.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.45958080291748,
|
|
"epoch": 0.014982075017389908,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.574,
|
|
"mean_token_accuracy": 0.05749143101274967,
|
|
"num_tokens": 305252.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.359578514099121,
|
|
"epoch": 0.015517149125153834,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.4804,
|
|
"mean_token_accuracy": 0.056437050178647044,
|
|
"num_tokens": 315505.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.158096408843994,
|
|
"epoch": 0.01605222323291776,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.4819,
|
|
"mean_token_accuracy": 0.05990221984684467,
|
|
"num_tokens": 326997.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.094014644622803,
|
|
"epoch": 0.016587297340681685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.4165,
|
|
"mean_token_accuracy": 0.05523004196584225,
|
|
"num_tokens": 338089.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.880174732208252,
|
|
"epoch": 0.01712237144844561,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.4077,
|
|
"mean_token_accuracy": 0.05682347491383553,
|
|
"num_tokens": 348536.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.93060073852539,
|
|
"epoch": 0.017657445556209534,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.4181,
|
|
"mean_token_accuracy": 0.058796605467796324,
|
|
"num_tokens": 359776.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.809493732452392,
|
|
"epoch": 0.01819251966397346,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.3472,
|
|
"mean_token_accuracy": 0.06165213547646999,
|
|
"num_tokens": 370810.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.747115898132325,
|
|
"epoch": 0.018727593771737387,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.3511,
|
|
"mean_token_accuracy": 0.05888295993208885,
|
|
"num_tokens": 381788.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.742884063720703,
|
|
"epoch": 0.01926266787950131,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.3376,
|
|
"mean_token_accuracy": 0.0602983683347702,
|
|
"num_tokens": 391984.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.610486602783203,
|
|
"epoch": 0.019797741987265235,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.3311,
|
|
"mean_token_accuracy": 0.058925900235772134,
|
|
"num_tokens": 403430.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.670144844055176,
|
|
"epoch": 0.02033281609502916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.318,
|
|
"mean_token_accuracy": 0.05627542734146118,
|
|
"num_tokens": 414467.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.56268243789673,
|
|
"epoch": 0.020867890202793088,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.2838,
|
|
"mean_token_accuracy": 0.06462269835174084,
|
|
"num_tokens": 425752.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.562543296813965,
|
|
"epoch": 0.02140296431055701,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.2618,
|
|
"mean_token_accuracy": 0.06471644267439843,
|
|
"num_tokens": 435908.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.58950891494751,
|
|
"epoch": 0.021938038418320937,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.3051,
|
|
"mean_token_accuracy": 0.05973440445959568,
|
|
"num_tokens": 446424.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.575794887542724,
|
|
"epoch": 0.022473112526084863,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.2691,
|
|
"mean_token_accuracy": 0.0648487914353609,
|
|
"num_tokens": 456854.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.506811428070069,
|
|
"epoch": 0.02300818663384879,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.2861,
|
|
"mean_token_accuracy": 0.06673729792237282,
|
|
"num_tokens": 467899.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.497941493988037,
|
|
"epoch": 0.023543260741612712,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.2297,
|
|
"mean_token_accuracy": 0.06340378113090991,
|
|
"num_tokens": 478683.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.574148082733155,
|
|
"epoch": 0.02407833484937664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.2648,
|
|
"mean_token_accuracy": 0.06170066706836223,
|
|
"num_tokens": 488745.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.4907470703125,
|
|
"epoch": 0.024613408957140565,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.3431,
|
|
"mean_token_accuracy": 0.059930100291967395,
|
|
"num_tokens": 499448.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.599916458129883,
|
|
"epoch": 0.02514848306490449,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.27,
|
|
"mean_token_accuracy": 0.0650645636022091,
|
|
"num_tokens": 510148.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.483675956726074,
|
|
"epoch": 0.025683557172668414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.1965,
|
|
"mean_token_accuracy": 0.06112907975912094,
|
|
"num_tokens": 522093.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.460341262817384,
|
|
"epoch": 0.02621863128043234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.2277,
|
|
"mean_token_accuracy": 0.06530554480850696,
|
|
"num_tokens": 532598.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.49462070465088,
|
|
"epoch": 0.026753705388196266,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.1956,
|
|
"mean_token_accuracy": 0.06578520573675632,
|
|
"num_tokens": 542652.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.460633659362793,
|
|
"epoch": 0.027288779495960192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.2328,
|
|
"mean_token_accuracy": 0.06693280301988125,
|
|
"num_tokens": 552526.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.399180793762207,
|
|
"epoch": 0.027823853603724115,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.2517,
|
|
"mean_token_accuracy": 0.06344069167971611,
|
|
"num_tokens": 563143.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.48379201889038,
|
|
"epoch": 0.02835892771148804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.2149,
|
|
"mean_token_accuracy": 0.06581672765314579,
|
|
"num_tokens": 573814.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.457896327972412,
|
|
"epoch": 0.028894001819251967,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.1733,
|
|
"mean_token_accuracy": 0.07218663729727268,
|
|
"num_tokens": 585367.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.507985496520996,
|
|
"epoch": 0.02942907592701589,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.2318,
|
|
"mean_token_accuracy": 0.06521918512880802,
|
|
"num_tokens": 595902.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.41034107208252,
|
|
"epoch": 0.029964150034779816,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.138,
|
|
"mean_token_accuracy": 0.0642226304858923,
|
|
"num_tokens": 607178.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.431483745574951,
|
|
"epoch": 0.030499224142543743,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.1309,
|
|
"mean_token_accuracy": 0.06817701198160649,
|
|
"num_tokens": 618604.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.404507827758788,
|
|
"epoch": 0.03103429825030767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.2,
|
|
"mean_token_accuracy": 0.0719299040734768,
|
|
"num_tokens": 628111.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.490602397918702,
|
|
"epoch": 0.03156937235807159,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.2289,
|
|
"mean_token_accuracy": 0.06933129876852036,
|
|
"num_tokens": 639358.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.35900354385376,
|
|
"epoch": 0.03210444646583552,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.0903,
|
|
"mean_token_accuracy": 0.07086234539747238,
|
|
"num_tokens": 649504.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.400328350067138,
|
|
"epoch": 0.032639520573599444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.1111,
|
|
"mean_token_accuracy": 0.0681851863861084,
|
|
"num_tokens": 659924.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.422282886505126,
|
|
"epoch": 0.03317459468136337,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.15,
|
|
"mean_token_accuracy": 0.06455899253487588,
|
|
"num_tokens": 671120.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.319589424133301,
|
|
"epoch": 0.033709668789127296,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.1985,
|
|
"mean_token_accuracy": 0.06430512070655822,
|
|
"num_tokens": 681956.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.48956241607666,
|
|
"epoch": 0.03424474289689122,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.182,
|
|
"mean_token_accuracy": 0.06503869034349918,
|
|
"num_tokens": 693226.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.33993911743164,
|
|
"epoch": 0.03477981700465514,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.1812,
|
|
"mean_token_accuracy": 0.07134119421243668,
|
|
"num_tokens": 704691.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.362220954895019,
|
|
"epoch": 0.03531489111241907,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.1304,
|
|
"mean_token_accuracy": 0.062357674539089206,
|
|
"num_tokens": 716000.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.332426834106446,
|
|
"epoch": 0.035849965220182994,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.0529,
|
|
"mean_token_accuracy": 0.06962560564279556,
|
|
"num_tokens": 726723.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.32654685974121,
|
|
"epoch": 0.03638503932794692,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.0646,
|
|
"mean_token_accuracy": 0.07072275690734386,
|
|
"num_tokens": 736740.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.333600425720215,
|
|
"epoch": 0.03692011343571085,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.1131,
|
|
"mean_token_accuracy": 0.068069913610816,
|
|
"num_tokens": 747567.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.398985290527344,
|
|
"epoch": 0.03745518754347477,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.0626,
|
|
"mean_token_accuracy": 0.06914932392537594,
|
|
"num_tokens": 757937.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.163579368591309,
|
|
"epoch": 0.0379902616512387,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.0955,
|
|
"mean_token_accuracy": 0.07165054567158222,
|
|
"num_tokens": 768003.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.49596710205078,
|
|
"epoch": 0.03852533575900262,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.1288,
|
|
"mean_token_accuracy": 0.06314317509531975,
|
|
"num_tokens": 779098.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.285042762756348,
|
|
"epoch": 0.039060409866766545,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.099,
|
|
"mean_token_accuracy": 0.06513171158730983,
|
|
"num_tokens": 790002.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.28923921585083,
|
|
"epoch": 0.03959548397453047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.0887,
|
|
"mean_token_accuracy": 0.06843880005180836,
|
|
"num_tokens": 800444.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.375462627410888,
|
|
"epoch": 0.0401305580822944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.0323,
|
|
"mean_token_accuracy": 0.0713271751999855,
|
|
"num_tokens": 810912.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.272585010528564,
|
|
"epoch": 0.04066563219005832,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.1198,
|
|
"mean_token_accuracy": 0.0620170421898365,
|
|
"num_tokens": 822809.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.293894195556641,
|
|
"epoch": 0.04120070629782225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.0433,
|
|
"mean_token_accuracy": 0.07052243873476982,
|
|
"num_tokens": 833362.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.276584053039551,
|
|
"epoch": 0.041735780405586176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.0465,
|
|
"mean_token_accuracy": 0.07357921116054059,
|
|
"num_tokens": 844239.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.217984676361084,
|
|
"epoch": 0.0422708545133501,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.0493,
|
|
"mean_token_accuracy": 0.06498224660754204,
|
|
"num_tokens": 855178.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.19730110168457,
|
|
"epoch": 0.04280592862111402,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.0369,
|
|
"mean_token_accuracy": 0.07206248976290226,
|
|
"num_tokens": 866120.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.337959480285644,
|
|
"epoch": 0.04334100272887795,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.0361,
|
|
"mean_token_accuracy": 0.07243039160966873,
|
|
"num_tokens": 876569.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.284227752685547,
|
|
"epoch": 0.043876076836641874,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.0951,
|
|
"mean_token_accuracy": 0.06462065242230892,
|
|
"num_tokens": 887580.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.235477828979493,
|
|
"epoch": 0.0444111509444058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.0165,
|
|
"mean_token_accuracy": 0.0666106827557087,
|
|
"num_tokens": 897922.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.222909069061279,
|
|
"epoch": 0.044946225052169726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.9827,
|
|
"mean_token_accuracy": 0.07159848175942898,
|
|
"num_tokens": 908522.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.27180290222168,
|
|
"epoch": 0.04548129915993365,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.9946,
|
|
"mean_token_accuracy": 0.06654324233531952,
|
|
"num_tokens": 918253.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.194285202026368,
|
|
"epoch": 0.04601637326769758,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.0034,
|
|
"mean_token_accuracy": 0.07207662984728813,
|
|
"num_tokens": 929150.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.239371013641357,
|
|
"epoch": 0.0465514473754615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.0511,
|
|
"mean_token_accuracy": 0.07106035277247429,
|
|
"num_tokens": 941041.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.180944156646728,
|
|
"epoch": 0.047086521483225424,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.9757,
|
|
"mean_token_accuracy": 0.07760139927268028,
|
|
"num_tokens": 952714.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.150847339630127,
|
|
"epoch": 0.04762159559098935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.0514,
|
|
"mean_token_accuracy": 0.06907343231141568,
|
|
"num_tokens": 964330.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.246770858764648,
|
|
"epoch": 0.04815666969875328,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.9805,
|
|
"mean_token_accuracy": 0.06862297914922237,
|
|
"num_tokens": 975257.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.260761165618897,
|
|
"epoch": 0.0486917438065172,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.9876,
|
|
"mean_token_accuracy": 0.07001541927456856,
|
|
"num_tokens": 986335.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.069970512390137,
|
|
"epoch": 0.04922681791428113,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.8883,
|
|
"mean_token_accuracy": 0.07471956759691238,
|
|
"num_tokens": 997521.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.172566795349121,
|
|
"epoch": 0.049761892022045055,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.941,
|
|
"mean_token_accuracy": 0.0669164728373289,
|
|
"num_tokens": 1008383.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.124609184265136,
|
|
"epoch": 0.05029696612980898,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.998,
|
|
"mean_token_accuracy": 0.06806416064500809,
|
|
"num_tokens": 1020552.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.196929836273194,
|
|
"epoch": 0.0508320402375729,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.9718,
|
|
"mean_token_accuracy": 0.07053619101643563,
|
|
"num_tokens": 1031127.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.022743558883667,
|
|
"epoch": 0.05136711434533683,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8837,
|
|
"mean_token_accuracy": 0.07386223524808884,
|
|
"num_tokens": 1043209.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.2311222076416,
|
|
"epoch": 0.05190218845310075,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.0182,
|
|
"mean_token_accuracy": 0.06782832555472851,
|
|
"num_tokens": 1054032.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.030213356018066,
|
|
"epoch": 0.05243726256086468,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.8628,
|
|
"mean_token_accuracy": 0.07288614809513091,
|
|
"num_tokens": 1064565.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.178169107437133,
|
|
"epoch": 0.052972336668628606,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.9975,
|
|
"mean_token_accuracy": 0.0721826508641243,
|
|
"num_tokens": 1076352.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.112149047851563,
|
|
"epoch": 0.05350741077639253,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.9381,
|
|
"mean_token_accuracy": 0.07542271986603737,
|
|
"num_tokens": 1087697.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.137825202941894,
|
|
"epoch": 0.05404248488415646,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.876,
|
|
"mean_token_accuracy": 0.07182962782680988,
|
|
"num_tokens": 1098056.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.017078876495361,
|
|
"epoch": 0.054577558991920384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.8477,
|
|
"mean_token_accuracy": 0.07691125422716141,
|
|
"num_tokens": 1109219.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.091530561447144,
|
|
"epoch": 0.055112633099684304,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.9312,
|
|
"mean_token_accuracy": 0.0700716007500887,
|
|
"num_tokens": 1120248.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.096777963638306,
|
|
"epoch": 0.05564770720744823,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.9366,
|
|
"mean_token_accuracy": 0.07186660170555115,
|
|
"num_tokens": 1131278.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.089863491058349,
|
|
"epoch": 0.056182781315212156,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.9537,
|
|
"mean_token_accuracy": 0.06224438659846783,
|
|
"num_tokens": 1143147.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.162030553817749,
|
|
"epoch": 0.05671785542297608,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.84,
|
|
"mean_token_accuracy": 0.0739860113710165,
|
|
"num_tokens": 1154316.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.977855777740478,
|
|
"epoch": 0.05725292953074001,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.8967,
|
|
"mean_token_accuracy": 0.06953345276415349,
|
|
"num_tokens": 1164696.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.048009157180786,
|
|
"epoch": 0.057788003638503935,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.8769,
|
|
"mean_token_accuracy": 0.07776758968830108,
|
|
"num_tokens": 1176129.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.093161487579346,
|
|
"epoch": 0.05832307774626786,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.8881,
|
|
"mean_token_accuracy": 0.07334664314985276,
|
|
"num_tokens": 1186499.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.04116907119751,
|
|
"epoch": 0.05885815185403178,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.8557,
|
|
"mean_token_accuracy": 0.07062512040138244,
|
|
"num_tokens": 1196841.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.01404366493225,
|
|
"epoch": 0.059393225961795706,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8108,
|
|
"mean_token_accuracy": 0.07467551231384277,
|
|
"num_tokens": 1207647.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.952892255783081,
|
|
"epoch": 0.05992830006955963,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.801,
|
|
"mean_token_accuracy": 0.07650438733398915,
|
|
"num_tokens": 1217072.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.061871433258057,
|
|
"epoch": 0.06046337417732356,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9129,
|
|
"mean_token_accuracy": 0.0698221705853939,
|
|
"num_tokens": 1228564.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.987078428268433,
|
|
"epoch": 0.060998448285087485,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8458,
|
|
"mean_token_accuracy": 0.07497354932129383,
|
|
"num_tokens": 1238755.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.964116954803467,
|
|
"epoch": 0.06153352239285141,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.8004,
|
|
"mean_token_accuracy": 0.0752273216843605,
|
|
"num_tokens": 1248968.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.962353372573853,
|
|
"epoch": 0.06206859650061534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.7714,
|
|
"mean_token_accuracy": 0.07172017395496369,
|
|
"num_tokens": 1259256.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.952462911605835,
|
|
"epoch": 0.06260367060837926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.8067,
|
|
"mean_token_accuracy": 0.07487296611070633,
|
|
"num_tokens": 1270469.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.963806390762329,
|
|
"epoch": 0.06313874471614318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.7694,
|
|
"mean_token_accuracy": 0.07279012463986874,
|
|
"num_tokens": 1280558.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.986854600906372,
|
|
"epoch": 0.06367381882390712,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.8307,
|
|
"mean_token_accuracy": 0.0718784749507904,
|
|
"num_tokens": 1291372.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.02498688697815,
|
|
"epoch": 0.06420889293167104,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.9061,
|
|
"mean_token_accuracy": 0.0674042422324419,
|
|
"num_tokens": 1302521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.8433699131011965,
|
|
"epoch": 0.06474396703943497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.7274,
|
|
"mean_token_accuracy": 0.07444682195782662,
|
|
"num_tokens": 1313632.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.005569124221802,
|
|
"epoch": 0.06527904114719889,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.8118,
|
|
"mean_token_accuracy": 0.07571293860673904,
|
|
"num_tokens": 1325247.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.937390947341919,
|
|
"epoch": 0.06581411525496281,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.8015,
|
|
"mean_token_accuracy": 0.075490290671587,
|
|
"num_tokens": 1336026.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.93022665977478,
|
|
"epoch": 0.06634918936272674,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.7122,
|
|
"mean_token_accuracy": 0.0769732192158699,
|
|
"num_tokens": 1346920.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.828203010559082,
|
|
"epoch": 0.06688426347049066,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.8585,
|
|
"mean_token_accuracy": 0.0724661260843277,
|
|
"num_tokens": 1359752.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.050937986373901,
|
|
"epoch": 0.06741933757825459,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.8615,
|
|
"mean_token_accuracy": 0.07357175201177597,
|
|
"num_tokens": 1370874.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.897751331329346,
|
|
"epoch": 0.06795441168601851,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.7624,
|
|
"mean_token_accuracy": 0.07756051793694496,
|
|
"num_tokens": 1382316.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.840310096740723,
|
|
"epoch": 0.06848948579378245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.7878,
|
|
"mean_token_accuracy": 0.07577594220638276,
|
|
"num_tokens": 1394656.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.928963756561279,
|
|
"epoch": 0.06902455990154636,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.7522,
|
|
"mean_token_accuracy": 0.07719769552350045,
|
|
"num_tokens": 1405061.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.838529491424561,
|
|
"epoch": 0.06955963400931028,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.7183,
|
|
"mean_token_accuracy": 0.08189134374260902,
|
|
"num_tokens": 1415573.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.810403823852539,
|
|
"epoch": 0.07009470811707422,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.7436,
|
|
"mean_token_accuracy": 0.07435674965381622,
|
|
"num_tokens": 1426103.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.886046600341797,
|
|
"epoch": 0.07062978222483814,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.7599,
|
|
"mean_token_accuracy": 0.07234186008572578,
|
|
"num_tokens": 1437256.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.909786796569824,
|
|
"epoch": 0.07116485633260207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.7241,
|
|
"mean_token_accuracy": 0.0786049198359251,
|
|
"num_tokens": 1446975.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.831602573394775,
|
|
"epoch": 0.07169993044036599,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.7425,
|
|
"mean_token_accuracy": 0.07444198578596115,
|
|
"num_tokens": 1457751.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.829366731643677,
|
|
"epoch": 0.07223500454812992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.7049,
|
|
"mean_token_accuracy": 0.0754860796034336,
|
|
"num_tokens": 1468186.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.825147390365601,
|
|
"epoch": 0.07277007865589384,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.7508,
|
|
"mean_token_accuracy": 0.07570655383169651,
|
|
"num_tokens": 1479780.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.8603636741638185,
|
|
"epoch": 0.07330515276365776,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6712,
|
|
"mean_token_accuracy": 0.0832133986055851,
|
|
"num_tokens": 1490565.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.892835903167724,
|
|
"epoch": 0.0738402268714217,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.7227,
|
|
"mean_token_accuracy": 0.07809135504066944,
|
|
"num_tokens": 1501552.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.798111057281494,
|
|
"epoch": 0.07437530097918561,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.7035,
|
|
"mean_token_accuracy": 0.07376831583678722,
|
|
"num_tokens": 1513311.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.795570516586304,
|
|
"epoch": 0.07491037508694955,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.7428,
|
|
"mean_token_accuracy": 0.08057990670204163,
|
|
"num_tokens": 1524142.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.8165356636047365,
|
|
"epoch": 0.07544544919471347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.7188,
|
|
"mean_token_accuracy": 0.07599906846880913,
|
|
"num_tokens": 1535571.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.865922546386718,
|
|
"epoch": 0.0759805233024774,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.7225,
|
|
"mean_token_accuracy": 0.07798022851347923,
|
|
"num_tokens": 1546528.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.727042579650879,
|
|
"epoch": 0.07651559741024132,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.7386,
|
|
"mean_token_accuracy": 0.07202219888567925,
|
|
"num_tokens": 1557264.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.867890882492065,
|
|
"epoch": 0.07705067151800524,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.6785,
|
|
"mean_token_accuracy": 0.08276100754737854,
|
|
"num_tokens": 1566773.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.699678039550781,
|
|
"epoch": 0.07758574562576917,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.6459,
|
|
"mean_token_accuracy": 0.08662735894322396,
|
|
"num_tokens": 1578173.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.779191970825195,
|
|
"epoch": 0.07812081973353309,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.6221,
|
|
"mean_token_accuracy": 0.08249625936150551,
|
|
"num_tokens": 1588537.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.7231770038604735,
|
|
"epoch": 0.07865589384129702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.6355,
|
|
"mean_token_accuracy": 0.08746174871921539,
|
|
"num_tokens": 1599159.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.7618378639221195,
|
|
"epoch": 0.07919096794906094,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.6989,
|
|
"mean_token_accuracy": 0.07925031632184983,
|
|
"num_tokens": 1610378.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.720492362976074,
|
|
"epoch": 0.07972604205682488,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.705,
|
|
"mean_token_accuracy": 0.07612368240952491,
|
|
"num_tokens": 1621215.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.786748743057251,
|
|
"epoch": 0.0802611161645888,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6622,
|
|
"mean_token_accuracy": 0.0790612380951643,
|
|
"num_tokens": 1631170.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.78691840171814,
|
|
"epoch": 0.08079619027235273,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.6574,
|
|
"mean_token_accuracy": 0.07428538724780083,
|
|
"num_tokens": 1641897.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.766008996963501,
|
|
"epoch": 0.08133126438011665,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.7353,
|
|
"mean_token_accuracy": 0.07569916620850563,
|
|
"num_tokens": 1653592.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.616559743881226,
|
|
"epoch": 0.08186633848788057,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.6528,
|
|
"mean_token_accuracy": 0.07474047541618348,
|
|
"num_tokens": 1665760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.830330228805542,
|
|
"epoch": 0.0824014125956445,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.6454,
|
|
"mean_token_accuracy": 0.08570240736007691,
|
|
"num_tokens": 1676211.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.737586927413941,
|
|
"epoch": 0.08293648670340842,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.6666,
|
|
"mean_token_accuracy": 0.0797475405037403,
|
|
"num_tokens": 1686405.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.75378794670105,
|
|
"epoch": 0.08347156081117235,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.6699,
|
|
"mean_token_accuracy": 0.07950277514755726,
|
|
"num_tokens": 1697340.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.726286888122559,
|
|
"epoch": 0.08400663491893627,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.5787,
|
|
"mean_token_accuracy": 0.0861763522028923,
|
|
"num_tokens": 1707250.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.63549427986145,
|
|
"epoch": 0.0845417090267002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.5653,
|
|
"mean_token_accuracy": 0.0784637302160263,
|
|
"num_tokens": 1718333.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.709765481948852,
|
|
"epoch": 0.08507678313446412,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.6627,
|
|
"mean_token_accuracy": 0.07198781482875347,
|
|
"num_tokens": 1730520.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.7255151748657225,
|
|
"epoch": 0.08561185724222804,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.7149,
|
|
"mean_token_accuracy": 0.07679420076310635,
|
|
"num_tokens": 1741898.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.718593311309815,
|
|
"epoch": 0.08614693134999198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.6508,
|
|
"mean_token_accuracy": 0.08017718270421029,
|
|
"num_tokens": 1751671.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.577520227432251,
|
|
"epoch": 0.0866820054577559,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.6669,
|
|
"mean_token_accuracy": 0.08265335634350776,
|
|
"num_tokens": 1762076.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.796188259124756,
|
|
"epoch": 0.08721707956551983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.642,
|
|
"mean_token_accuracy": 0.07752098590135574,
|
|
"num_tokens": 1772666.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.724516534805298,
|
|
"epoch": 0.08775215367328375,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.6572,
|
|
"mean_token_accuracy": 0.08227546997368336,
|
|
"num_tokens": 1783621.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.700971364974976,
|
|
"epoch": 0.08828722778104768,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.7147,
|
|
"mean_token_accuracy": 0.07807004414498805,
|
|
"num_tokens": 1794654.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.651264762878418,
|
|
"epoch": 0.0888223018888116,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.6008,
|
|
"mean_token_accuracy": 0.0848226711153984,
|
|
"num_tokens": 1805853.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.536796283721924,
|
|
"epoch": 0.08935737599657552,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.5896,
|
|
"mean_token_accuracy": 0.0828265130519867,
|
|
"num_tokens": 1817006.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.733750724792481,
|
|
"epoch": 0.08989245010433945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.583,
|
|
"mean_token_accuracy": 0.07734453342854977,
|
|
"num_tokens": 1827166.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.7373639106750485,
|
|
"epoch": 0.09042752421210337,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6809,
|
|
"mean_token_accuracy": 0.07751412987709046,
|
|
"num_tokens": 1837182.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.567351484298706,
|
|
"epoch": 0.0909625983198673,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.6388,
|
|
"mean_token_accuracy": 0.07895995602011681,
|
|
"num_tokens": 1849034.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.595164203643799,
|
|
"epoch": 0.09149767242763122,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5075,
|
|
"mean_token_accuracy": 0.08833360373973846,
|
|
"num_tokens": 1859033.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.610419750213623,
|
|
"epoch": 0.09203274653539516,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6121,
|
|
"mean_token_accuracy": 0.08088177517056465,
|
|
"num_tokens": 1870274.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.5731220722198485,
|
|
"epoch": 0.09256782064315908,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.5611,
|
|
"mean_token_accuracy": 0.08315053284168243,
|
|
"num_tokens": 1881306.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.561473751068116,
|
|
"epoch": 0.093102894750923,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.5356,
|
|
"mean_token_accuracy": 0.08015808910131454,
|
|
"num_tokens": 1892464.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.661314296722412,
|
|
"epoch": 0.09363796885868693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6219,
|
|
"mean_token_accuracy": 0.07585933655500413,
|
|
"num_tokens": 1903743.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.607653522491455,
|
|
"epoch": 0.09417304296645085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5902,
|
|
"mean_token_accuracy": 0.08468717783689499,
|
|
"num_tokens": 1915253.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.622669744491577,
|
|
"epoch": 0.09470811707421478,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5473,
|
|
"mean_token_accuracy": 0.08187699615955353,
|
|
"num_tokens": 1926113.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.57468581199646,
|
|
"epoch": 0.0952431911819787,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.6456,
|
|
"mean_token_accuracy": 0.08173620626330376,
|
|
"num_tokens": 1937718.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.625470066070557,
|
|
"epoch": 0.09577826528974263,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6334,
|
|
"mean_token_accuracy": 0.0791581004858017,
|
|
"num_tokens": 1948307.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.575066232681275,
|
|
"epoch": 0.09631333939750655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.4358,
|
|
"mean_token_accuracy": 0.09009880647063255,
|
|
"num_tokens": 1957861.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.480437755584717,
|
|
"epoch": 0.09684841350527049,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4911,
|
|
"mean_token_accuracy": 0.08970233350992203,
|
|
"num_tokens": 1967984.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.55365891456604,
|
|
"epoch": 0.0973834876130344,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.4885,
|
|
"mean_token_accuracy": 0.08413884043693542,
|
|
"num_tokens": 1978608.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.550483322143554,
|
|
"epoch": 0.09791856172079832,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.547,
|
|
"mean_token_accuracy": 0.08248279690742492,
|
|
"num_tokens": 1989355.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.514042758941651,
|
|
"epoch": 0.09845363582856226,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.5303,
|
|
"mean_token_accuracy": 0.08344742506742478,
|
|
"num_tokens": 1999754.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.540969705581665,
|
|
"epoch": 0.09898870993632618,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5232,
|
|
"mean_token_accuracy": 0.0832397285848856,
|
|
"num_tokens": 2010877.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.635095930099487,
|
|
"epoch": 0.09952378404409011,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.6286,
|
|
"mean_token_accuracy": 0.08003128916025162,
|
|
"num_tokens": 2022301.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.549521160125733,
|
|
"epoch": 0.10005885815185403,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5119,
|
|
"mean_token_accuracy": 0.08251530304551125,
|
|
"num_tokens": 2033537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.477602958679199,
|
|
"epoch": 0.10059393225961796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.4502,
|
|
"mean_token_accuracy": 0.0781034879386425,
|
|
"num_tokens": 2044360.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.583854675292969,
|
|
"epoch": 0.10112900636738188,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.5601,
|
|
"mean_token_accuracy": 0.08421726487576961,
|
|
"num_tokens": 2055000.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.492854499816895,
|
|
"epoch": 0.1016640804751458,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.5467,
|
|
"mean_token_accuracy": 0.08681007251143455,
|
|
"num_tokens": 2064807.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.5536168098449705,
|
|
"epoch": 0.10219915458290973,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.5102,
|
|
"mean_token_accuracy": 0.08256960362195968,
|
|
"num_tokens": 2075618.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.505359792709351,
|
|
"epoch": 0.10273422869067365,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.5116,
|
|
"mean_token_accuracy": 0.08244576305150986,
|
|
"num_tokens": 2086226.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.541278457641601,
|
|
"epoch": 0.10326930279843759,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5116,
|
|
"mean_token_accuracy": 0.08005514740943909,
|
|
"num_tokens": 2097222.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.481921100616455,
|
|
"epoch": 0.1038043769062015,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.541,
|
|
"mean_token_accuracy": 0.08661947920918464,
|
|
"num_tokens": 2108919.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.46715989112854,
|
|
"epoch": 0.10433945101396544,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.4939,
|
|
"mean_token_accuracy": 0.08317564725875855,
|
|
"num_tokens": 2120215.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.5228071212768555,
|
|
"epoch": 0.10487452512172936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.5188,
|
|
"mean_token_accuracy": 0.0818349651992321,
|
|
"num_tokens": 2131503.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.487857866287231,
|
|
"epoch": 0.10540959922949328,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.4588,
|
|
"mean_token_accuracy": 0.08936587274074555,
|
|
"num_tokens": 2141551.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.4559633255004885,
|
|
"epoch": 0.10594467333725721,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.4615,
|
|
"mean_token_accuracy": 0.08929954171180725,
|
|
"num_tokens": 2151821.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.451591444015503,
|
|
"epoch": 0.10647974744502113,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.5065,
|
|
"mean_token_accuracy": 0.08539062738418579,
|
|
"num_tokens": 2162474.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.53413724899292,
|
|
"epoch": 0.10701482155278506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5602,
|
|
"mean_token_accuracy": 0.08457510098814965,
|
|
"num_tokens": 2173985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.5422203063964846,
|
|
"epoch": 0.10754989566054898,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999999979210101,
|
|
"loss": 7.5944,
|
|
"mean_token_accuracy": 0.07782966643571854,
|
|
"num_tokens": 2186432.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.4759071350097654,
|
|
"epoch": 0.10808496976831292,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999999894751138,
|
|
"loss": 7.4463,
|
|
"mean_token_accuracy": 0.0834141232073307,
|
|
"num_tokens": 2197085.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.424153137207031,
|
|
"epoch": 0.10862004387607684,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999999745323744,
|
|
"loss": 7.4486,
|
|
"mean_token_accuracy": 0.08975227214396,
|
|
"num_tokens": 2207162.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.464861583709717,
|
|
"epoch": 0.10915511798384077,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999530927923,
|
|
"loss": 7.5469,
|
|
"mean_token_accuracy": 0.07938519641757011,
|
|
"num_tokens": 2218714.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.515410757064819,
|
|
"epoch": 0.10969019209160469,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999251563682,
|
|
"loss": 7.4879,
|
|
"mean_token_accuracy": 0.08599804565310479,
|
|
"num_tokens": 2229711.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.45625114440918,
|
|
"epoch": 0.11022526619936861,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999998907231029,
|
|
"loss": 7.4912,
|
|
"mean_token_accuracy": 0.08116911202669144,
|
|
"num_tokens": 2239885.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.481421899795532,
|
|
"epoch": 0.11076034030713254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999998497929974,
|
|
"loss": 7.4923,
|
|
"mean_token_accuracy": 0.08827452957630158,
|
|
"num_tokens": 2250221.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.4760716438293455,
|
|
"epoch": 0.11129541441489646,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999998023660527,
|
|
"loss": 7.5526,
|
|
"mean_token_accuracy": 0.07815601006150245,
|
|
"num_tokens": 2261059.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.454020214080811,
|
|
"epoch": 0.11183048852266039,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999997484422705,
|
|
"loss": 7.4273,
|
|
"mean_token_accuracy": 0.08656688034534454,
|
|
"num_tokens": 2271174.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.404057025909424,
|
|
"epoch": 0.11236556263042431,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999996880216521,
|
|
"loss": 7.5037,
|
|
"mean_token_accuracy": 0.08764296993613244,
|
|
"num_tokens": 2282431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.506435585021973,
|
|
"epoch": 0.11290063673818825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996211041994,
|
|
"loss": 7.4922,
|
|
"mean_token_accuracy": 0.08441931083798408,
|
|
"num_tokens": 2292891.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.472446441650391,
|
|
"epoch": 0.11343571084595216,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999995476899141,
|
|
"loss": 7.5049,
|
|
"mean_token_accuracy": 0.08200813457369804,
|
|
"num_tokens": 2303764.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.319696569442749,
|
|
"epoch": 0.11397078495371608,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999994677787987,
|
|
"loss": 7.4002,
|
|
"mean_token_accuracy": 0.09418007209897042,
|
|
"num_tokens": 2314172.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.449784660339356,
|
|
"epoch": 0.11450585906148002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999993813708551,
|
|
"loss": 7.3939,
|
|
"mean_token_accuracy": 0.08950763419270516,
|
|
"num_tokens": 2324848.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.320974636077881,
|
|
"epoch": 0.11504093316924394,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499999288466086,
|
|
"loss": 7.4332,
|
|
"mean_token_accuracy": 0.08251803517341613,
|
|
"num_tokens": 2336601.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.46982364654541,
|
|
"epoch": 0.11557600727700787,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999991890644941,
|
|
"loss": 7.4167,
|
|
"mean_token_accuracy": 0.0846226740628481,
|
|
"num_tokens": 2347281.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.453939628601074,
|
|
"epoch": 0.11611108138477179,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999990831660822,
|
|
"loss": 7.4224,
|
|
"mean_token_accuracy": 0.0908889777958393,
|
|
"num_tokens": 2358199.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.446761226654052,
|
|
"epoch": 0.11664615549253572,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999989707708534,
|
|
"loss": 7.4877,
|
|
"mean_token_accuracy": 0.08379835970699787,
|
|
"num_tokens": 2369092.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.3978382587432865,
|
|
"epoch": 0.11718122960029964,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999988518788111,
|
|
"loss": 7.458,
|
|
"mean_token_accuracy": 0.08341244608163834,
|
|
"num_tokens": 2378849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.428147649765014,
|
|
"epoch": 0.11771630370806356,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999987264899583,
|
|
"loss": 7.4385,
|
|
"mean_token_accuracy": 0.09159169495105743,
|
|
"num_tokens": 2389587.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.492716360092163,
|
|
"epoch": 0.1182513778158275,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499998594604299,
|
|
"loss": 7.434,
|
|
"mean_token_accuracy": 0.08649549037218093,
|
|
"num_tokens": 2400442.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.284411334991455,
|
|
"epoch": 0.11878645192359141,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499998456221837,
|
|
"loss": 7.4154,
|
|
"mean_token_accuracy": 0.08677608072757721,
|
|
"num_tokens": 2410771.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.476975584030152,
|
|
"epoch": 0.11932152603135535,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999983113425762,
|
|
"loss": 7.4299,
|
|
"mean_token_accuracy": 0.09064068272709846,
|
|
"num_tokens": 2421112.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.400354480743408,
|
|
"epoch": 0.11985660013911927,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999981599665207,
|
|
"loss": 7.4163,
|
|
"mean_token_accuracy": 0.08564619868993759,
|
|
"num_tokens": 2431891.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.315796279907227,
|
|
"epoch": 0.1203916742468832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999980020936748,
|
|
"loss": 7.3479,
|
|
"mean_token_accuracy": 0.08722568973898888,
|
|
"num_tokens": 2442987.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.354978418350219,
|
|
"epoch": 0.12092674835464712,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999978377240434,
|
|
"loss": 7.4002,
|
|
"mean_token_accuracy": 0.08564592450857163,
|
|
"num_tokens": 2452703.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.375062036514282,
|
|
"epoch": 0.12146182246241104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499997666857631,
|
|
"loss": 7.4598,
|
|
"mean_token_accuracy": 0.08786297589540482,
|
|
"num_tokens": 2462975.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.394401025772095,
|
|
"epoch": 0.12199689657017497,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999974894944426,
|
|
"loss": 7.4003,
|
|
"mean_token_accuracy": 0.08598766103386879,
|
|
"num_tokens": 2473853.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.384897661209107,
|
|
"epoch": 0.12253197067793889,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999973056344832,
|
|
"loss": 7.3822,
|
|
"mean_token_accuracy": 0.08470982015132904,
|
|
"num_tokens": 2485633.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.337519359588623,
|
|
"epoch": 0.12306704478570282,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999971152777583,
|
|
"loss": 7.3414,
|
|
"mean_token_accuracy": 0.08668373227119446,
|
|
"num_tokens": 2496922.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.443722057342529,
|
|
"epoch": 0.12360211889346674,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999969184242733,
|
|
"loss": 7.4147,
|
|
"mean_token_accuracy": 0.0896741084754467,
|
|
"num_tokens": 2507890.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.319026279449463,
|
|
"epoch": 0.12413719300123068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499996715074034,
|
|
"loss": 7.4076,
|
|
"mean_token_accuracy": 0.09130077436566353,
|
|
"num_tokens": 2519749.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.3418297290802,
|
|
"epoch": 0.1246722671089946,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999965052270461,
|
|
"loss": 7.4121,
|
|
"mean_token_accuracy": 0.09187431186437607,
|
|
"num_tokens": 2530666.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.364394998550415,
|
|
"epoch": 0.12520734121675853,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999962888833157,
|
|
"loss": 7.4155,
|
|
"mean_token_accuracy": 0.08915347754955291,
|
|
"num_tokens": 2541594.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.363469171524048,
|
|
"epoch": 0.12574241532452243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999960660428491,
|
|
"loss": 7.3946,
|
|
"mean_token_accuracy": 0.0930194191634655,
|
|
"num_tokens": 2552330.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.449467992782592,
|
|
"epoch": 0.12627748943228637,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999958367056526,
|
|
"loss": 7.4494,
|
|
"mean_token_accuracy": 0.08116971924901009,
|
|
"num_tokens": 2564601.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.422946262359619,
|
|
"epoch": 0.1268125635400503,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499995600871733,
|
|
"loss": 7.4242,
|
|
"mean_token_accuracy": 0.08717223256826401,
|
|
"num_tokens": 2575539.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.284857511520386,
|
|
"epoch": 0.12734763764781423,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999953585410971,
|
|
"loss": 7.3588,
|
|
"mean_token_accuracy": 0.08616523109376431,
|
|
"num_tokens": 2586635.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.405594778060913,
|
|
"epoch": 0.12788271175557814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999951097137518,
|
|
"loss": 7.388,
|
|
"mean_token_accuracy": 0.08991223797202111,
|
|
"num_tokens": 2596814.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.325789880752564,
|
|
"epoch": 0.12841778586334207,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999948543897044,
|
|
"loss": 7.4089,
|
|
"mean_token_accuracy": 0.08616380542516708,
|
|
"num_tokens": 2608087.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.498183393478394,
|
|
"epoch": 0.128952859971106,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999945925689621,
|
|
"loss": 7.41,
|
|
"mean_token_accuracy": 0.08784973174333573,
|
|
"num_tokens": 2619377.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.285972166061401,
|
|
"epoch": 0.12948793407886994,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999943242515325,
|
|
"loss": 7.314,
|
|
"mean_token_accuracy": 0.08880106881260871,
|
|
"num_tokens": 2629089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.320152521133423,
|
|
"epoch": 0.13002300818663384,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999940494374236,
|
|
"loss": 7.3835,
|
|
"mean_token_accuracy": 0.08867338374257087,
|
|
"num_tokens": 2639743.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.45218596458435,
|
|
"epoch": 0.13055808229439778,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499993768126643,
|
|
"loss": 7.4254,
|
|
"mean_token_accuracy": 0.082533248513937,
|
|
"num_tokens": 2650631.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.268480491638184,
|
|
"epoch": 0.1310931564021617,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499993480319199,
|
|
"loss": 7.3811,
|
|
"mean_token_accuracy": 0.0892926201224327,
|
|
"num_tokens": 2660197.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.394870710372925,
|
|
"epoch": 0.13162823050992561,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999931860150999,
|
|
"loss": 7.3556,
|
|
"mean_token_accuracy": 0.08826216235756874,
|
|
"num_tokens": 2670162.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.390807247161865,
|
|
"epoch": 0.13216330461768955,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999928852143541,
|
|
"loss": 7.3554,
|
|
"mean_token_accuracy": 0.08857011944055557,
|
|
"num_tokens": 2681233.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.200170421600342,
|
|
"epoch": 0.13269837872545348,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999925779169703,
|
|
"loss": 7.3187,
|
|
"mean_token_accuracy": 0.09283828288316727,
|
|
"num_tokens": 2692145.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.413662004470825,
|
|
"epoch": 0.13323345283321741,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999922641229575,
|
|
"loss": 7.3447,
|
|
"mean_token_accuracy": 0.09158495515584945,
|
|
"num_tokens": 2703192.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.324686527252197,
|
|
"epoch": 0.13376852694098132,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999919438323248,
|
|
"loss": 7.3597,
|
|
"mean_token_accuracy": 0.08890319019556045,
|
|
"num_tokens": 2714804.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.333380794525146,
|
|
"epoch": 0.13430360104874525,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999916170450812,
|
|
"loss": 7.3259,
|
|
"mean_token_accuracy": 0.09193522408604622,
|
|
"num_tokens": 2724340.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.259483861923218,
|
|
"epoch": 0.13483867515650919,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999912837612364,
|
|
"loss": 7.3341,
|
|
"mean_token_accuracy": 0.09227988123893738,
|
|
"num_tokens": 2735767.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.455391693115234,
|
|
"epoch": 0.1353737492642731,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999909439807997,
|
|
"loss": 7.3851,
|
|
"mean_token_accuracy": 0.08482631966471672,
|
|
"num_tokens": 2747658.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.264850521087647,
|
|
"epoch": 0.13590882337203702,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999905977037813,
|
|
"loss": 7.2465,
|
|
"mean_token_accuracy": 0.09336961582303047,
|
|
"num_tokens": 2757901.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.284139823913574,
|
|
"epoch": 0.13644389747980096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999902449301909,
|
|
"loss": 7.2989,
|
|
"mean_token_accuracy": 0.0874991238117218,
|
|
"num_tokens": 2768945.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.24199595451355,
|
|
"epoch": 0.1369789715875649,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999898856600387,
|
|
"loss": 7.271,
|
|
"mean_token_accuracy": 0.103138717263937,
|
|
"num_tokens": 2780276.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.350469398498535,
|
|
"epoch": 0.1375140456953288,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999895198933354,
|
|
"loss": 7.3416,
|
|
"mean_token_accuracy": 0.09537098631262779,
|
|
"num_tokens": 2791183.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.342680644989014,
|
|
"epoch": 0.13804911980309273,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999891476300911,
|
|
"loss": 7.2607,
|
|
"mean_token_accuracy": 0.08925738111138344,
|
|
"num_tokens": 2801928.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.263091659545898,
|
|
"epoch": 0.13858419391085666,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499988768870317,
|
|
"loss": 7.3525,
|
|
"mean_token_accuracy": 0.08583549410104752,
|
|
"num_tokens": 2813415.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.329908657073974,
|
|
"epoch": 0.13911926801862057,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999883836140236,
|
|
"loss": 7.3533,
|
|
"mean_token_accuracy": 0.08882890194654465,
|
|
"num_tokens": 2825288.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.312420797348023,
|
|
"epoch": 0.1396543421263845,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999879918612224,
|
|
"loss": 7.3068,
|
|
"mean_token_accuracy": 0.09304987639188766,
|
|
"num_tokens": 2836298.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.313601350784301,
|
|
"epoch": 0.14018941623414843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999875936119245,
|
|
"loss": 7.2898,
|
|
"mean_token_accuracy": 0.0945392332971096,
|
|
"num_tokens": 2846367.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.240101766586304,
|
|
"epoch": 0.14072449034191237,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999871888661415,
|
|
"loss": 7.3047,
|
|
"mean_token_accuracy": 0.08923600688576698,
|
|
"num_tokens": 2856832.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.309039974212647,
|
|
"epoch": 0.14125956444967627,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499986777623885,
|
|
"loss": 7.3245,
|
|
"mean_token_accuracy": 0.08692366257309914,
|
|
"num_tokens": 2867954.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.439533376693726,
|
|
"epoch": 0.1417946385574402,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999863598851669,
|
|
"loss": 7.3611,
|
|
"mean_token_accuracy": 0.09297569468617439,
|
|
"num_tokens": 2878714.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.053972816467285,
|
|
"epoch": 0.14232971266520414,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999859356499992,
|
|
"loss": 7.298,
|
|
"mean_token_accuracy": 0.10052636489272118,
|
|
"num_tokens": 2890697.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.382122421264649,
|
|
"epoch": 0.14286478677296804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999855049183943,
|
|
"loss": 7.3219,
|
|
"mean_token_accuracy": 0.08626203685998916,
|
|
"num_tokens": 2901468.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.25765290260315,
|
|
"epoch": 0.14339986088073198,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999850676903646,
|
|
"loss": 7.2671,
|
|
"mean_token_accuracy": 0.09408968985080719,
|
|
"num_tokens": 2913466.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.231286239624024,
|
|
"epoch": 0.1439349349884959,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999846239659226,
|
|
"loss": 7.2505,
|
|
"mean_token_accuracy": 0.09706522151827812,
|
|
"num_tokens": 2923638.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.269954109191895,
|
|
"epoch": 0.14447000909625984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999841737450812,
|
|
"loss": 7.3357,
|
|
"mean_token_accuracy": 0.09442631006240845,
|
|
"num_tokens": 2934790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.268723440170288,
|
|
"epoch": 0.14500508320402375,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999837170278535,
|
|
"loss": 7.2757,
|
|
"mean_token_accuracy": 0.08723422512412071,
|
|
"num_tokens": 2946320.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.3566694259643555,
|
|
"epoch": 0.14554015731178768,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999832538142526,
|
|
"loss": 7.2369,
|
|
"mean_token_accuracy": 0.09091865047812461,
|
|
"num_tokens": 2957077.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.177463865280151,
|
|
"epoch": 0.14607523141955162,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999827841042917,
|
|
"loss": 7.2678,
|
|
"mean_token_accuracy": 0.08816000148653984,
|
|
"num_tokens": 2967286.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.2939177513122555,
|
|
"epoch": 0.14661030552731552,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999823078979846,
|
|
"loss": 7.3057,
|
|
"mean_token_accuracy": 0.09016561508178711,
|
|
"num_tokens": 2979516.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.379639339447022,
|
|
"epoch": 0.14714537963507945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999818251953449,
|
|
"loss": 7.419,
|
|
"mean_token_accuracy": 0.08294185698032379,
|
|
"num_tokens": 2991594.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.246149206161499,
|
|
"epoch": 0.1476804537428434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999813359963867,
|
|
"loss": 7.2972,
|
|
"mean_token_accuracy": 0.08775367885828018,
|
|
"num_tokens": 3002487.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.372300243377685,
|
|
"epoch": 0.14821552785060732,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999808403011241,
|
|
"loss": 7.3157,
|
|
"mean_token_accuracy": 0.09396110102534294,
|
|
"num_tokens": 3013197.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.142706060409546,
|
|
"epoch": 0.14875060195837123,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999803381095712,
|
|
"loss": 7.3451,
|
|
"mean_token_accuracy": 0.09063652530312538,
|
|
"num_tokens": 3024512.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.415092658996582,
|
|
"epoch": 0.14928567606613516,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999798294217428,
|
|
"loss": 7.3046,
|
|
"mean_token_accuracy": 0.08789012357592582,
|
|
"num_tokens": 3035621.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.229216432571411,
|
|
"epoch": 0.1498207501738991,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999793142376533,
|
|
"loss": 7.2876,
|
|
"mean_token_accuracy": 0.09253833740949631,
|
|
"num_tokens": 3046492.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.263148021697998,
|
|
"epoch": 0.150355824281663,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999787925573177,
|
|
"loss": 7.3086,
|
|
"mean_token_accuracy": 0.09204896241426468,
|
|
"num_tokens": 3057715.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.3932922840118405,
|
|
"epoch": 0.15089089838942693,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999782643807513,
|
|
"loss": 7.2654,
|
|
"mean_token_accuracy": 0.09031828343868256,
|
|
"num_tokens": 3068344.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.193799686431885,
|
|
"epoch": 0.15142597249719086,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999777297079689,
|
|
"loss": 7.2547,
|
|
"mean_token_accuracy": 0.09031877219676972,
|
|
"num_tokens": 3079576.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.342895412445069,
|
|
"epoch": 0.1519610466049548,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999771885389863,
|
|
"loss": 7.2153,
|
|
"mean_token_accuracy": 0.09486196860671044,
|
|
"num_tokens": 3090201.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.1453712463378904,
|
|
"epoch": 0.1524961207127187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999766408738189,
|
|
"loss": 7.1936,
|
|
"mean_token_accuracy": 0.10047192424535752,
|
|
"num_tokens": 3099824.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.24136872291565,
|
|
"epoch": 0.15303119482048264,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999760867124827,
|
|
"loss": 7.2738,
|
|
"mean_token_accuracy": 0.09082015976309776,
|
|
"num_tokens": 3109948.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.299263906478882,
|
|
"epoch": 0.15356626892824657,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999755260549937,
|
|
"loss": 7.2626,
|
|
"mean_token_accuracy": 0.0974075585603714,
|
|
"num_tokens": 3121492.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.21744818687439,
|
|
"epoch": 0.15410134303601047,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004999749589013677,
|
|
"loss": 7.0545,
|
|
"mean_token_accuracy": 0.10996845588088036,
|
|
"num_tokens": 3131990.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.1235129833221436,
|
|
"epoch": 0.1546364171437744,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999743852516217,
|
|
"loss": 7.2409,
|
|
"mean_token_accuracy": 0.0921150028705597,
|
|
"num_tokens": 3142567.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.32010293006897,
|
|
"epoch": 0.15517149125153834,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999738051057717,
|
|
"loss": 7.2522,
|
|
"mean_token_accuracy": 0.09435679912567138,
|
|
"num_tokens": 3153083.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.188344669342041,
|
|
"epoch": 0.15570656535930227,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999732184638347,
|
|
"loss": 7.2555,
|
|
"mean_token_accuracy": 0.09004457890987397,
|
|
"num_tokens": 3163985.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.262719058990479,
|
|
"epoch": 0.15624163946706618,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999726253258278,
|
|
"loss": 7.2392,
|
|
"mean_token_accuracy": 0.09183276668190957,
|
|
"num_tokens": 3175259.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.254732751846314,
|
|
"epoch": 0.1567767135748301,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999720256917678,
|
|
"loss": 7.206,
|
|
"mean_token_accuracy": 0.0977108657360077,
|
|
"num_tokens": 3185487.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.127510118484497,
|
|
"epoch": 0.15731178768259405,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999714195616723,
|
|
"loss": 7.1831,
|
|
"mean_token_accuracy": 0.09826227650046349,
|
|
"num_tokens": 3196200.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.333015441894531,
|
|
"epoch": 0.15784686179035795,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999708069355586,
|
|
"loss": 7.3054,
|
|
"mean_token_accuracy": 0.0843054249882698,
|
|
"num_tokens": 3207675.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.17571177482605,
|
|
"epoch": 0.15838193589812188,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999701878134445,
|
|
"loss": 7.1815,
|
|
"mean_token_accuracy": 0.09501941055059433,
|
|
"num_tokens": 3218117.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.304254627227783,
|
|
"epoch": 0.15891701000588582,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999695621953477,
|
|
"loss": 7.2505,
|
|
"mean_token_accuracy": 0.10208047479391098,
|
|
"num_tokens": 3229208.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.173984098434448,
|
|
"epoch": 0.15945208411364975,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999689300812866,
|
|
"loss": 7.1584,
|
|
"mean_token_accuracy": 0.101242895424366,
|
|
"num_tokens": 3239586.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.24401364326477,
|
|
"epoch": 0.15998715822141366,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999682914712791,
|
|
"loss": 7.2254,
|
|
"mean_token_accuracy": 0.09680869728326798,
|
|
"num_tokens": 3250103.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.228427124023438,
|
|
"epoch": 0.1605222323291776,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999676463653439,
|
|
"loss": 7.2027,
|
|
"mean_token_accuracy": 0.10232653468847275,
|
|
"num_tokens": 3261844.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.227877807617188,
|
|
"epoch": 0.16105730643694152,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999669947634996,
|
|
"loss": 7.1639,
|
|
"mean_token_accuracy": 0.09760255515575408,
|
|
"num_tokens": 3272073.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.178577184677124,
|
|
"epoch": 0.16159238054470546,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999663366657647,
|
|
"loss": 7.1667,
|
|
"mean_token_accuracy": 0.09620498046278954,
|
|
"num_tokens": 3281725.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.214940547943115,
|
|
"epoch": 0.16212745465246936,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999656720721586,
|
|
"loss": 7.3059,
|
|
"mean_token_accuracy": 0.094396660476923,
|
|
"num_tokens": 3292708.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.296448183059693,
|
|
"epoch": 0.1626625287602333,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999650009827004,
|
|
"loss": 7.2773,
|
|
"mean_token_accuracy": 0.09127842709422111,
|
|
"num_tokens": 3303548.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.19203143119812,
|
|
"epoch": 0.16319760286799723,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999643233974092,
|
|
"loss": 7.1486,
|
|
"mean_token_accuracy": 0.09975013583898544,
|
|
"num_tokens": 3314261.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.1947274684906,
|
|
"epoch": 0.16373267697576113,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999636393163049,
|
|
"loss": 7.1714,
|
|
"mean_token_accuracy": 0.09445247575640678,
|
|
"num_tokens": 3324833.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.053837537765503,
|
|
"epoch": 0.16426775108352507,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999629487394071,
|
|
"loss": 7.0568,
|
|
"mean_token_accuracy": 0.10237468853592872,
|
|
"num_tokens": 3334790.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.266930866241455,
|
|
"epoch": 0.164802825191289,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999622516667358,
|
|
"loss": 7.205,
|
|
"mean_token_accuracy": 0.09691800698637962,
|
|
"num_tokens": 3345115.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.133483982086181,
|
|
"epoch": 0.16533789929905293,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499961548098311,
|
|
"loss": 7.089,
|
|
"mean_token_accuracy": 0.10441275909543038,
|
|
"num_tokens": 3356187.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.117019701004028,
|
|
"epoch": 0.16587297340681684,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999608380341533,
|
|
"loss": 7.1282,
|
|
"mean_token_accuracy": 0.09887576475739479,
|
|
"num_tokens": 3367218.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.160897636413575,
|
|
"epoch": 0.16640804751458077,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999601214742829,
|
|
"loss": 7.27,
|
|
"mean_token_accuracy": 0.08936030119657516,
|
|
"num_tokens": 3377557.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.371627759933472,
|
|
"epoch": 0.1669431216223447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999593984187206,
|
|
"loss": 7.2482,
|
|
"mean_token_accuracy": 0.09751093834638595,
|
|
"num_tokens": 3387402.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.0916835308074955,
|
|
"epoch": 0.1674781957301086,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999586688674872,
|
|
"loss": 7.1346,
|
|
"mean_token_accuracy": 0.09648581743240356,
|
|
"num_tokens": 3397924.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.216659879684448,
|
|
"epoch": 0.16801326983787254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499957932820604,
|
|
"loss": 7.2118,
|
|
"mean_token_accuracy": 0.08759412840008736,
|
|
"num_tokens": 3408622.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.262946891784668,
|
|
"epoch": 0.16854834394563648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499957190278092,
|
|
"loss": 7.1622,
|
|
"mean_token_accuracy": 0.09248490408062934,
|
|
"num_tokens": 3419692.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.098281383514404,
|
|
"epoch": 0.1690834180534004,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999564412399728,
|
|
"loss": 7.2154,
|
|
"mean_token_accuracy": 0.09459864124655723,
|
|
"num_tokens": 3430986.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.176830434799195,
|
|
"epoch": 0.1696184921611643,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499955685706268,
|
|
"loss": 7.1354,
|
|
"mean_token_accuracy": 0.09504674524068832,
|
|
"num_tokens": 3442211.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.03007402420044,
|
|
"epoch": 0.17015356626892825,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999549236769993,
|
|
"loss": 7.1229,
|
|
"mean_token_accuracy": 0.10297105386853218,
|
|
"num_tokens": 3453585.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.225273466110229,
|
|
"epoch": 0.17068864037669218,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999541551521888,
|
|
"loss": 7.1695,
|
|
"mean_token_accuracy": 0.0996770367026329,
|
|
"num_tokens": 3464156.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.249066162109375,
|
|
"epoch": 0.17122371448445609,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999533801318587,
|
|
"loss": 7.2238,
|
|
"mean_token_accuracy": 0.08952004536986351,
|
|
"num_tokens": 3474853.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.262774181365967,
|
|
"epoch": 0.17175878859222002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999525986160313,
|
|
"loss": 7.194,
|
|
"mean_token_accuracy": 0.10073793306946754,
|
|
"num_tokens": 3486841.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.140778827667236,
|
|
"epoch": 0.17229386269998395,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999518106047293,
|
|
"loss": 7.2169,
|
|
"mean_token_accuracy": 0.09210691601037979,
|
|
"num_tokens": 3498735.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.175544404983521,
|
|
"epoch": 0.17282893680774788,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999510160979754,
|
|
"loss": 7.2352,
|
|
"mean_token_accuracy": 0.10104434639215469,
|
|
"num_tokens": 3508829.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.1884317874908445,
|
|
"epoch": 0.1733640109155118,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999502150957925,
|
|
"loss": 7.141,
|
|
"mean_token_accuracy": 0.09438429847359657,
|
|
"num_tokens": 3519465.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.188577127456665,
|
|
"epoch": 0.17389908502327572,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999494075982037,
|
|
"loss": 7.1086,
|
|
"mean_token_accuracy": 0.10255491808056831,
|
|
"num_tokens": 3530401.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.12376561164856,
|
|
"epoch": 0.17443415913103966,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999485936052324,
|
|
"loss": 7.1856,
|
|
"mean_token_accuracy": 0.09849482700228691,
|
|
"num_tokens": 3541136.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.288824605941772,
|
|
"epoch": 0.17496923323880356,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499947773116902,
|
|
"loss": 7.1753,
|
|
"mean_token_accuracy": 0.09568259268999099,
|
|
"num_tokens": 3552525.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.090163278579712,
|
|
"epoch": 0.1755043073465675,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999469461332365,
|
|
"loss": 7.1414,
|
|
"mean_token_accuracy": 0.09975111782550812,
|
|
"num_tokens": 3563028.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.199271249771118,
|
|
"epoch": 0.17603938145433143,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999461126542592,
|
|
"loss": 7.0912,
|
|
"mean_token_accuracy": 0.10047454982995987,
|
|
"num_tokens": 3573354.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.979637813568115,
|
|
"epoch": 0.17657445556209536,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999452726799947,
|
|
"loss": 7.0802,
|
|
"mean_token_accuracy": 0.09618928134441376,
|
|
"num_tokens": 3585576.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.297661590576172,
|
|
"epoch": 0.17710952966985927,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999444262104671,
|
|
"loss": 7.2058,
|
|
"mean_token_accuracy": 0.08774002119898797,
|
|
"num_tokens": 3596478.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.110372161865234,
|
|
"epoch": 0.1776446037776232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999435732457007,
|
|
"loss": 7.153,
|
|
"mean_token_accuracy": 0.09257297441363335,
|
|
"num_tokens": 3608014.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.221296691894532,
|
|
"epoch": 0.17817967788538713,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999427137857203,
|
|
"loss": 7.2102,
|
|
"mean_token_accuracy": 0.09210594072937965,
|
|
"num_tokens": 3620120.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.107110977172852,
|
|
"epoch": 0.17871475199315104,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999418478305506,
|
|
"loss": 7.1096,
|
|
"mean_token_accuracy": 0.09546202942728996,
|
|
"num_tokens": 3632578.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.156751394271851,
|
|
"epoch": 0.17924982610091497,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999409753802167,
|
|
"loss": 7.131,
|
|
"mean_token_accuracy": 0.10362366437911988,
|
|
"num_tokens": 3643245.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.167398452758789,
|
|
"epoch": 0.1797849002086789,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999400964347437,
|
|
"loss": 7.1251,
|
|
"mean_token_accuracy": 0.09799086153507233,
|
|
"num_tokens": 3655832.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.151060581207275,
|
|
"epoch": 0.18031997431644284,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999392109941571,
|
|
"loss": 7.1001,
|
|
"mean_token_accuracy": 0.09830698594450951,
|
|
"num_tokens": 3666566.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.172510385513306,
|
|
"epoch": 0.18085504842420674,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999383190584822,
|
|
"loss": 7.1298,
|
|
"mean_token_accuracy": 0.10040193051099777,
|
|
"num_tokens": 3677572.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.112444877624512,
|
|
"epoch": 0.18139012253197068,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999374206277451,
|
|
"loss": 7.0549,
|
|
"mean_token_accuracy": 0.09736391827464104,
|
|
"num_tokens": 3687116.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.057082557678223,
|
|
"epoch": 0.1819251966397346,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999365157019717,
|
|
"loss": 7.1658,
|
|
"mean_token_accuracy": 0.09722192957997322,
|
|
"num_tokens": 3697961.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.233665180206299,
|
|
"epoch": 0.18246027074749852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999356042811878,
|
|
"loss": 7.0802,
|
|
"mean_token_accuracy": 0.10210576206445694,
|
|
"num_tokens": 3708834.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.087706089019775,
|
|
"epoch": 0.18299534485526245,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049993468636542,
|
|
"loss": 7.1472,
|
|
"mean_token_accuracy": 0.09556594043970108,
|
|
"num_tokens": 3719835.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.116140556335449,
|
|
"epoch": 0.18353041896302638,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999337619546948,
|
|
"loss": 7.0339,
|
|
"mean_token_accuracy": 0.10466360598802567,
|
|
"num_tokens": 3730408.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.085261631011963,
|
|
"epoch": 0.18406549307079031,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999328310490387,
|
|
"loss": 7.1275,
|
|
"mean_token_accuracy": 0.09871943295001984,
|
|
"num_tokens": 3741257.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.190493202209472,
|
|
"epoch": 0.18460056717855422,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999318936484789,
|
|
"loss": 7.1175,
|
|
"mean_token_accuracy": 0.10177163109183311,
|
|
"num_tokens": 3752615.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.106344223022461,
|
|
"epoch": 0.18513564128631815,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999309497530422,
|
|
"loss": 7.1395,
|
|
"mean_token_accuracy": 0.09094236344099045,
|
|
"num_tokens": 3763656.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.083023738861084,
|
|
"epoch": 0.1856707153940821,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999299993627558,
|
|
"loss": 7.1148,
|
|
"mean_token_accuracy": 0.10153383314609528,
|
|
"num_tokens": 3775257.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.0514672756195065,
|
|
"epoch": 0.186205789501846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999290424776475,
|
|
"loss": 7.0758,
|
|
"mean_token_accuracy": 0.1056319996714592,
|
|
"num_tokens": 3786094.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.330498886108399,
|
|
"epoch": 0.18674086360960993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999280790977445,
|
|
"loss": 7.1657,
|
|
"mean_token_accuracy": 0.09170655235648155,
|
|
"num_tokens": 3796672.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.131537580490113,
|
|
"epoch": 0.18727593771737386,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499927109223075,
|
|
"loss": 7.1508,
|
|
"mean_token_accuracy": 0.09670756980776787,
|
|
"num_tokens": 3807910.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.103532934188843,
|
|
"epoch": 0.1878110118251378,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999261328536667,
|
|
"loss": 7.1028,
|
|
"mean_token_accuracy": 0.1024494618177414,
|
|
"num_tokens": 3820792.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.02842001914978,
|
|
"epoch": 0.1883460859329017,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999251499895479,
|
|
"loss": 7.0234,
|
|
"mean_token_accuracy": 0.1013932503759861,
|
|
"num_tokens": 3831126.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.213843870162964,
|
|
"epoch": 0.18888116004066563,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999241606307471,
|
|
"loss": 7.1353,
|
|
"mean_token_accuracy": 0.10057510435581207,
|
|
"num_tokens": 3841923.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.119020175933838,
|
|
"epoch": 0.18941623414842956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999231647772927,
|
|
"loss": 7.0491,
|
|
"mean_token_accuracy": 0.10542590543627739,
|
|
"num_tokens": 3852504.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.992453765869141,
|
|
"epoch": 0.1899513082561935,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999221624292136,
|
|
"loss": 7.0559,
|
|
"mean_token_accuracy": 0.10485710874199868,
|
|
"num_tokens": 3862761.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.134696340560913,
|
|
"epoch": 0.1904863823639574,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999211535865385,
|
|
"loss": 7.0556,
|
|
"mean_token_accuracy": 0.09678238332271576,
|
|
"num_tokens": 3873662.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.063473129272461,
|
|
"epoch": 0.19102145647172133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999201382492969,
|
|
"loss": 7.0088,
|
|
"mean_token_accuracy": 0.10047155022621154,
|
|
"num_tokens": 3884835.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.110291051864624,
|
|
"epoch": 0.19155653057948527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999191164175178,
|
|
"loss": 7.154,
|
|
"mean_token_accuracy": 0.09878607764840126,
|
|
"num_tokens": 3895073.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.209331798553467,
|
|
"epoch": 0.19209160468724917,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999180880912309,
|
|
"loss": 7.1115,
|
|
"mean_token_accuracy": 0.09884128645062447,
|
|
"num_tokens": 3905440.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.072672271728516,
|
|
"epoch": 0.1926266787950131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999170532704657,
|
|
"loss": 7.1145,
|
|
"mean_token_accuracy": 0.0968818336725235,
|
|
"num_tokens": 3917135.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.13597002029419,
|
|
"epoch": 0.19316175290277704,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999160119552523,
|
|
"loss": 7.117,
|
|
"mean_token_accuracy": 0.10278327167034149,
|
|
"num_tokens": 3928247.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.091355848312378,
|
|
"epoch": 0.19369682701054097,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999149641456206,
|
|
"loss": 7.1009,
|
|
"mean_token_accuracy": 0.09872358813881874,
|
|
"num_tokens": 3938609.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.21585783958435,
|
|
"epoch": 0.19423190111830488,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499913909841601,
|
|
"loss": 7.0861,
|
|
"mean_token_accuracy": 0.10127425193786621,
|
|
"num_tokens": 3949221.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.009944200515747,
|
|
"epoch": 0.1947669752260688,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999128490432238,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.09548230320215226,
|
|
"num_tokens": 3959475.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.083078098297119,
|
|
"epoch": 0.19530204933383274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999117817505196,
|
|
"loss": 7.0515,
|
|
"mean_token_accuracy": 0.1084510900080204,
|
|
"num_tokens": 3969638.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.053667259216309,
|
|
"epoch": 0.19583712344159665,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999107079635194,
|
|
"loss": 7.1079,
|
|
"mean_token_accuracy": 0.10137292668223381,
|
|
"num_tokens": 3980543.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.355273485183716,
|
|
"epoch": 0.19637219754936058,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499909627682254,
|
|
"loss": 7.162,
|
|
"mean_token_accuracy": 0.08682658635079861,
|
|
"num_tokens": 3993518.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.068727111816406,
|
|
"epoch": 0.19690727165712452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999085409067549,
|
|
"loss": 7.1487,
|
|
"mean_token_accuracy": 0.09789205938577653,
|
|
"num_tokens": 4002940.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.013206481933594,
|
|
"epoch": 0.19744234576488845,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999074476370531,
|
|
"loss": 7.0792,
|
|
"mean_token_accuracy": 0.09683184549212456,
|
|
"num_tokens": 4013982.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.100980806350708,
|
|
"epoch": 0.19797741987265235,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999063478731805,
|
|
"loss": 7.0638,
|
|
"mean_token_accuracy": 0.10558338239789009,
|
|
"num_tokens": 4025607.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.0951310157775875,
|
|
"epoch": 0.1985124939804163,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999052416151687,
|
|
"loss": 7.1104,
|
|
"mean_token_accuracy": 0.10141080170869828,
|
|
"num_tokens": 4037467.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.149590158462525,
|
|
"epoch": 0.19904756808818022,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999041288630496,
|
|
"loss": 7.1127,
|
|
"mean_token_accuracy": 0.10126180425286294,
|
|
"num_tokens": 4049146.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.181366395950318,
|
|
"epoch": 0.19958264219594413,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999030096168553,
|
|
"loss": 7.1485,
|
|
"mean_token_accuracy": 0.09781184569001197,
|
|
"num_tokens": 4060500.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.157667875289917,
|
|
"epoch": 0.20011771630370806,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999018838766182,
|
|
"loss": 7.0987,
|
|
"mean_token_accuracy": 0.0985781691968441,
|
|
"num_tokens": 4070553.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.14162769317627,
|
|
"epoch": 0.200652790411472,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499900751642371,
|
|
"loss": 7.0343,
|
|
"mean_token_accuracy": 0.11338024884462357,
|
|
"num_tokens": 4079653.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.015338134765625,
|
|
"epoch": 0.20118786451923593,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998996129141461,
|
|
"loss": 7.123,
|
|
"mean_token_accuracy": 0.09923376441001892,
|
|
"num_tokens": 4089912.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.212585592269898,
|
|
"epoch": 0.20172293862699983,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998984676919764,
|
|
"loss": 7.0772,
|
|
"mean_token_accuracy": 0.09714810699224471,
|
|
"num_tokens": 4100577.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.073903751373291,
|
|
"epoch": 0.20225801273476376,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998973159758952,
|
|
"loss": 7.1033,
|
|
"mean_token_accuracy": 0.09901956990361213,
|
|
"num_tokens": 4111752.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.06131501197815,
|
|
"epoch": 0.2027930868425277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998961577659355,
|
|
"loss": 7.0616,
|
|
"mean_token_accuracy": 0.10182834565639495,
|
|
"num_tokens": 4122616.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.192514705657959,
|
|
"epoch": 0.2033281609502916,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998949930621309,
|
|
"loss": 7.1547,
|
|
"mean_token_accuracy": 0.10196215733885765,
|
|
"num_tokens": 4134275.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.112344741821289,
|
|
"epoch": 0.20386323505805554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998938218645149,
|
|
"loss": 7.0506,
|
|
"mean_token_accuracy": 0.10170819535851479,
|
|
"num_tokens": 4146412.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.029837560653687,
|
|
"epoch": 0.20439830916581947,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998926441731215,
|
|
"loss": 7.0512,
|
|
"mean_token_accuracy": 0.1002343863248825,
|
|
"num_tokens": 4157592.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.06212477684021,
|
|
"epoch": 0.2049333832735834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998914599879845,
|
|
"loss": 7.0269,
|
|
"mean_token_accuracy": 0.09835589304566383,
|
|
"num_tokens": 4168637.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.0664630889892575,
|
|
"epoch": 0.2054684573813473,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998902693091382,
|
|
"loss": 7.0736,
|
|
"mean_token_accuracy": 0.09925776198506356,
|
|
"num_tokens": 4179951.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.0451087474823,
|
|
"epoch": 0.20600353148911124,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998890721366171,
|
|
"loss": 6.9616,
|
|
"mean_token_accuracy": 0.10666931569576263,
|
|
"num_tokens": 4189895.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.097507953643799,
|
|
"epoch": 0.20653860559687517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998878684704556,
|
|
"loss": 7.0214,
|
|
"mean_token_accuracy": 0.10524726510047913,
|
|
"num_tokens": 4199796.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.036600160598755,
|
|
"epoch": 0.20707367970463908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998866583106884,
|
|
"loss": 7.0461,
|
|
"mean_token_accuracy": 0.09883956611156464,
|
|
"num_tokens": 4210428.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.218980216979981,
|
|
"epoch": 0.207608753812403,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998854416573506,
|
|
"loss": 7.1246,
|
|
"mean_token_accuracy": 0.10078881680965424,
|
|
"num_tokens": 4221515.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.1100975513458256,
|
|
"epoch": 0.20814382792016695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998842185104772,
|
|
"loss": 7.1387,
|
|
"mean_token_accuracy": 0.09548087790608406,
|
|
"num_tokens": 4232580.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.041958284378052,
|
|
"epoch": 0.20867890202793088,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998829888701036,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.10664152652025223,
|
|
"num_tokens": 4242871.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.147633504867554,
|
|
"epoch": 0.20921397613569478,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998817527362654,
|
|
"loss": 7.0773,
|
|
"mean_token_accuracy": 0.09752313494682312,
|
|
"num_tokens": 4253419.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.032255792617798,
|
|
"epoch": 0.20974905024345872,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998805101089982,
|
|
"loss": 7.0528,
|
|
"mean_token_accuracy": 0.10345240533351899,
|
|
"num_tokens": 4264327.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.170184564590454,
|
|
"epoch": 0.21028412435122265,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998792609883378,
|
|
"loss": 7.0428,
|
|
"mean_token_accuracy": 0.10343464836478233,
|
|
"num_tokens": 4274568.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.056762933731079,
|
|
"epoch": 0.21081919845898656,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998780053743203,
|
|
"loss": 7.0324,
|
|
"mean_token_accuracy": 0.10682544857263565,
|
|
"num_tokens": 4284895.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.12225079536438,
|
|
"epoch": 0.2113542725667505,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998767432669822,
|
|
"loss": 7.0637,
|
|
"mean_token_accuracy": 0.0994573712348938,
|
|
"num_tokens": 4297258.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.026572132110596,
|
|
"epoch": 0.21188934667451442,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998754746663595,
|
|
"loss": 6.9842,
|
|
"mean_token_accuracy": 0.10585973560810089,
|
|
"num_tokens": 4308307.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.050811910629273,
|
|
"epoch": 0.21242442078227836,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998741995724892,
|
|
"loss": 7.0491,
|
|
"mean_token_accuracy": 0.10263351649045944,
|
|
"num_tokens": 4318801.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.070459413528442,
|
|
"epoch": 0.21295949489004226,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998729179854079,
|
|
"loss": 7.0252,
|
|
"mean_token_accuracy": 0.10016985535621643,
|
|
"num_tokens": 4329531.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.054882478713989,
|
|
"epoch": 0.2134945689978062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998716299051527,
|
|
"loss": 7.0253,
|
|
"mean_token_accuracy": 0.10470812693238259,
|
|
"num_tokens": 4341203.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.026881456375122,
|
|
"epoch": 0.21402964310557013,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998703353317609,
|
|
"loss": 7.0788,
|
|
"mean_token_accuracy": 0.0973646655678749,
|
|
"num_tokens": 4352426.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.11639552116394,
|
|
"epoch": 0.21456471721333403,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998690342652697,
|
|
"loss": 7.0103,
|
|
"mean_token_accuracy": 0.10563170909881592,
|
|
"num_tokens": 4363413.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.054438829421997,
|
|
"epoch": 0.21509979132109797,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998677267057166,
|
|
"loss": 6.951,
|
|
"mean_token_accuracy": 0.10644056648015976,
|
|
"num_tokens": 4373470.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.9533806324005125,
|
|
"epoch": 0.2156348654288619,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998664126531397,
|
|
"loss": 7.0164,
|
|
"mean_token_accuracy": 0.10371329113841057,
|
|
"num_tokens": 4384438.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.1470112800598145,
|
|
"epoch": 0.21616993953662583,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998650921075766,
|
|
"loss": 6.9978,
|
|
"mean_token_accuracy": 0.10406329333782197,
|
|
"num_tokens": 4395100.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.9813416481018065,
|
|
"epoch": 0.21670501364438974,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998637650690656,
|
|
"loss": 7.1179,
|
|
"mean_token_accuracy": 0.09519804865121842,
|
|
"num_tokens": 4407131.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.10913496017456,
|
|
"epoch": 0.21724008775215367,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499862431537645,
|
|
"loss": 6.9569,
|
|
"mean_token_accuracy": 0.10057392492890357,
|
|
"num_tokens": 4417701.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.981591272354126,
|
|
"epoch": 0.2177751618599176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998610915133533,
|
|
"loss": 7.0173,
|
|
"mean_token_accuracy": 0.10014636293053628,
|
|
"num_tokens": 4429309.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.007551097869873,
|
|
"epoch": 0.21831023596768154,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998597449962292,
|
|
"loss": 7.0663,
|
|
"mean_token_accuracy": 0.10122283399105073,
|
|
"num_tokens": 4440850.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.092380857467651,
|
|
"epoch": 0.21884531007544544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998583919863115,
|
|
"loss": 7.0501,
|
|
"mean_token_accuracy": 0.09975898936390877,
|
|
"num_tokens": 4451995.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.99484076499939,
|
|
"epoch": 0.21938038418320938,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998570324836393,
|
|
"loss": 6.959,
|
|
"mean_token_accuracy": 0.10816834419965744,
|
|
"num_tokens": 4461916.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.084143257141113,
|
|
"epoch": 0.2199154582909733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499855666488252,
|
|
"loss": 7.0571,
|
|
"mean_token_accuracy": 0.10147327557206154,
|
|
"num_tokens": 4471603.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.105906391143799,
|
|
"epoch": 0.22045053239873721,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998542940001889,
|
|
"loss": 7.083,
|
|
"mean_token_accuracy": 0.10265670791268348,
|
|
"num_tokens": 4483166.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.020576333999633,
|
|
"epoch": 0.22098560650650115,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998529150194895,
|
|
"loss": 7.0022,
|
|
"mean_token_accuracy": 0.09936799854040146,
|
|
"num_tokens": 4493824.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.097088718414307,
|
|
"epoch": 0.22152068061426508,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998515295461939,
|
|
"loss": 6.9225,
|
|
"mean_token_accuracy": 0.1188635177910328,
|
|
"num_tokens": 4505674.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.968977689743042,
|
|
"epoch": 0.22205575472202901,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499850137580342,
|
|
"loss": 7.0049,
|
|
"mean_token_accuracy": 0.10718596279621125,
|
|
"num_tokens": 4516516.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.039025449752808,
|
|
"epoch": 0.22259082882979292,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998487391219739,
|
|
"loss": 6.9963,
|
|
"mean_token_accuracy": 0.09949744194746017,
|
|
"num_tokens": 4527811.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.0311308860778805,
|
|
"epoch": 0.22312590293755685,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998473341711301,
|
|
"loss": 6.9388,
|
|
"mean_token_accuracy": 0.09995686337351799,
|
|
"num_tokens": 4538988.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.018882703781128,
|
|
"epoch": 0.22366097704532079,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998459227278512,
|
|
"loss": 6.9733,
|
|
"mean_token_accuracy": 0.1059156596660614,
|
|
"num_tokens": 4550049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.072498369216919,
|
|
"epoch": 0.2241960511530847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998445047921777,
|
|
"loss": 7.0719,
|
|
"mean_token_accuracy": 0.10480737760663032,
|
|
"num_tokens": 4559784.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.031924390792847,
|
|
"epoch": 0.22473112526084862,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998430803641509,
|
|
"loss": 6.9337,
|
|
"mean_token_accuracy": 0.10361162722110748,
|
|
"num_tokens": 4569982.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.939174699783325,
|
|
"epoch": 0.22526619936861256,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998416494438118,
|
|
"loss": 6.9534,
|
|
"mean_token_accuracy": 0.10496753230690956,
|
|
"num_tokens": 4581117.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.033869123458862,
|
|
"epoch": 0.2258012734763765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998402120312014,
|
|
"loss": 7.0198,
|
|
"mean_token_accuracy": 0.10706626474857331,
|
|
"num_tokens": 4592012.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.034424209594727,
|
|
"epoch": 0.2263363475841404,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998387681263616,
|
|
"loss": 7.0581,
|
|
"mean_token_accuracy": 0.10076023638248444,
|
|
"num_tokens": 4602591.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.038776493072509,
|
|
"epoch": 0.22687142169190433,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499837317729334,
|
|
"loss": 6.985,
|
|
"mean_token_accuracy": 0.10343138575553894,
|
|
"num_tokens": 4613418.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.944168281555176,
|
|
"epoch": 0.22740649579966826,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998358608401603,
|
|
"loss": 6.9051,
|
|
"mean_token_accuracy": 0.11338085606694222,
|
|
"num_tokens": 4625156.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.1117607116699215,
|
|
"epoch": 0.22794156990743217,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499834397458883,
|
|
"loss": 6.937,
|
|
"mean_token_accuracy": 0.10821644887328148,
|
|
"num_tokens": 4634523.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.958322238922119,
|
|
"epoch": 0.2284766440151961,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998329275855438,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.11250298544764518,
|
|
"num_tokens": 4646292.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.985101842880249,
|
|
"epoch": 0.22901171812296003,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998314512201855,
|
|
"loss": 6.9099,
|
|
"mean_token_accuracy": 0.10238043665885925,
|
|
"num_tokens": 4656417.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.924033832550049,
|
|
"epoch": 0.22954679223072397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998299683628507,
|
|
"loss": 6.9282,
|
|
"mean_token_accuracy": 0.10534189045429229,
|
|
"num_tokens": 4666933.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.059316158294678,
|
|
"epoch": 0.23008186633848787,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998284790135821,
|
|
"loss": 7.1084,
|
|
"mean_token_accuracy": 0.09782184064388275,
|
|
"num_tokens": 4678482.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.053033971786499,
|
|
"epoch": 0.2306169404462518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998269831724228,
|
|
"loss": 6.9481,
|
|
"mean_token_accuracy": 0.1064787782728672,
|
|
"num_tokens": 4688454.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.9519795894622805,
|
|
"epoch": 0.23115201455401574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998254808394159,
|
|
"loss": 6.9839,
|
|
"mean_token_accuracy": 0.1061179980635643,
|
|
"num_tokens": 4699545.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.083680486679077,
|
|
"epoch": 0.23168708866177964,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998239720146048,
|
|
"loss": 6.9986,
|
|
"mean_token_accuracy": 0.10272667407989503,
|
|
"num_tokens": 4711149.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.961511278152466,
|
|
"epoch": 0.23222216276954358,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998224566980332,
|
|
"loss": 6.9935,
|
|
"mean_token_accuracy": 0.10200226753950119,
|
|
"num_tokens": 4722651.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.031105852127075,
|
|
"epoch": 0.2327572368773075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998209348897447,
|
|
"loss": 6.9926,
|
|
"mean_token_accuracy": 0.09458313658833503,
|
|
"num_tokens": 4733883.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.135159015655518,
|
|
"epoch": 0.23329231098507144,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998194065897833,
|
|
"loss": 6.955,
|
|
"mean_token_accuracy": 0.10691621899604797,
|
|
"num_tokens": 4744517.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.9776819229125975,
|
|
"epoch": 0.23382738509283535,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499817871798193,
|
|
"loss": 6.9804,
|
|
"mean_token_accuracy": 0.11214952319860458,
|
|
"num_tokens": 4755481.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.972070980072021,
|
|
"epoch": 0.23436245920059928,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998163305150185,
|
|
"loss": 6.9039,
|
|
"mean_token_accuracy": 0.11068079173564911,
|
|
"num_tokens": 4765535.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.973287200927734,
|
|
"epoch": 0.23489753330836322,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998147827403038,
|
|
"loss": 7.0273,
|
|
"mean_token_accuracy": 0.10471541583538055,
|
|
"num_tokens": 4777045.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.077732086181641,
|
|
"epoch": 0.23543260741612712,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499813228474094,
|
|
"loss": 6.9064,
|
|
"mean_token_accuracy": 0.10825864002108573,
|
|
"num_tokens": 4787958.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.917084503173828,
|
|
"epoch": 0.23596768152389105,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998116677164338,
|
|
"loss": 6.9445,
|
|
"mean_token_accuracy": 0.10730226412415504,
|
|
"num_tokens": 4798502.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.931448936462402,
|
|
"epoch": 0.236502755631655,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998101004673682,
|
|
"loss": 6.9413,
|
|
"mean_token_accuracy": 0.11088823229074478,
|
|
"num_tokens": 4809179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.135161733627319,
|
|
"epoch": 0.23703782973941892,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998085267269426,
|
|
"loss": 7.0215,
|
|
"mean_token_accuracy": 0.09467339664697647,
|
|
"num_tokens": 4819803.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.004361200332641,
|
|
"epoch": 0.23757290384718283,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998069464952025,
|
|
"loss": 6.9916,
|
|
"mean_token_accuracy": 0.10000614672899247,
|
|
"num_tokens": 4831226.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 7.049906778335571,
|
|
"epoch": 0.23810797795494676,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998053597721932,
|
|
"loss": 7.0124,
|
|
"mean_token_accuracy": 0.10538152158260346,
|
|
"num_tokens": 4842168.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 7.019608783721924,
|
|
"epoch": 0.2386430520627107,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998037665579608,
|
|
"loss": 6.9621,
|
|
"mean_token_accuracy": 0.10858180820941925,
|
|
"num_tokens": 4852655.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.915230321884155,
|
|
"epoch": 0.2391781261704746,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998021668525513,
|
|
"loss": 6.8626,
|
|
"mean_token_accuracy": 0.10984659045934678,
|
|
"num_tokens": 4862164.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.046167945861816,
|
|
"epoch": 0.23971320027823853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998005606560107,
|
|
"loss": 6.9964,
|
|
"mean_token_accuracy": 0.10990610420703888,
|
|
"num_tokens": 4874233.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.992388391494751,
|
|
"epoch": 0.24024827438600246,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997989479683856,
|
|
"loss": 6.9876,
|
|
"mean_token_accuracy": 0.1066631942987442,
|
|
"num_tokens": 4885948.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.963246202468872,
|
|
"epoch": 0.2407833484937664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997973287897224,
|
|
"loss": 6.9667,
|
|
"mean_token_accuracy": 0.10817388147115707,
|
|
"num_tokens": 4897128.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.980781888961792,
|
|
"epoch": 0.2413184226015303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997957031200681,
|
|
"loss": 6.939,
|
|
"mean_token_accuracy": 0.11121672838926315,
|
|
"num_tokens": 4907699.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.887354183197021,
|
|
"epoch": 0.24185349670929424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997940709594692,
|
|
"loss": 6.8796,
|
|
"mean_token_accuracy": 0.10674800127744674,
|
|
"num_tokens": 4918772.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.091795778274536,
|
|
"epoch": 0.24238857081705817,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997924323079733,
|
|
"loss": 6.9368,
|
|
"mean_token_accuracy": 0.10729291215538979,
|
|
"num_tokens": 4930046.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.9101183891296385,
|
|
"epoch": 0.24292364492482207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997907871656273,
|
|
"loss": 6.9568,
|
|
"mean_token_accuracy": 0.10801581889390946,
|
|
"num_tokens": 4940609.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.002806997299194,
|
|
"epoch": 0.243458719032586,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997891355324791,
|
|
"loss": 6.9658,
|
|
"mean_token_accuracy": 0.10598139539361,
|
|
"num_tokens": 4951339.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.983994722366333,
|
|
"epoch": 0.24399379314034994,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997874774085761,
|
|
"loss": 6.878,
|
|
"mean_token_accuracy": 0.10262224972248077,
|
|
"num_tokens": 4961083.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.895718050003052,
|
|
"epoch": 0.24452886724811387,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997858127939662,
|
|
"loss": 6.8908,
|
|
"mean_token_accuracy": 0.10761211439967155,
|
|
"num_tokens": 4971399.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.041612005233764,
|
|
"epoch": 0.24506394135587778,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997841416886976,
|
|
"loss": 6.9715,
|
|
"mean_token_accuracy": 0.1061974436044693,
|
|
"num_tokens": 4982429.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 7.0298323154449465,
|
|
"epoch": 0.2455990154636417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997824640928186,
|
|
"loss": 7.0184,
|
|
"mean_token_accuracy": 0.10754595324397087,
|
|
"num_tokens": 4993706.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.988226366043091,
|
|
"epoch": 0.24613408957140565,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997807800063774,
|
|
"loss": 6.9127,
|
|
"mean_token_accuracy": 0.10858980864286423,
|
|
"num_tokens": 5005411.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.023472309112549,
|
|
"epoch": 0.24666916367916958,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499779089429423,
|
|
"loss": 7.0413,
|
|
"mean_token_accuracy": 0.10208934471011162,
|
|
"num_tokens": 5016011.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.013689231872559,
|
|
"epoch": 0.24720423778693348,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997773923620037,
|
|
"loss": 6.9954,
|
|
"mean_token_accuracy": 0.10329191759228706,
|
|
"num_tokens": 5027841.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 7.100406980514526,
|
|
"epoch": 0.24773931189469742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997756888041689,
|
|
"loss": 6.9853,
|
|
"mean_token_accuracy": 0.09798330888152122,
|
|
"num_tokens": 5038640.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.95166802406311,
|
|
"epoch": 0.24827438600246135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997739787559677,
|
|
"loss": 6.9356,
|
|
"mean_token_accuracy": 0.10357877835631371,
|
|
"num_tokens": 5050423.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.978884506225586,
|
|
"epoch": 0.24880946011022526,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997722622174494,
|
|
"loss": 6.954,
|
|
"mean_token_accuracy": 0.10356095060706139,
|
|
"num_tokens": 5060654.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.934212970733642,
|
|
"epoch": 0.2493445342179892,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997705391886636,
|
|
"loss": 6.8582,
|
|
"mean_token_accuracy": 0.11322998628020287,
|
|
"num_tokens": 5070165.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.913174200057983,
|
|
"epoch": 0.24987960832575312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997688096696601,
|
|
"loss": 6.8995,
|
|
"mean_token_accuracy": 0.10103722065687179,
|
|
"num_tokens": 5080937.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.911728572845459,
|
|
"epoch": 0.25041468243351706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997670736604888,
|
|
"loss": 6.8744,
|
|
"mean_token_accuracy": 0.11288927420973778,
|
|
"num_tokens": 5090955.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 7.074804210662842,
|
|
"epoch": 0.250949756541281,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997653311611998,
|
|
"loss": 7.0112,
|
|
"mean_token_accuracy": 0.09920887500047684,
|
|
"num_tokens": 5102201.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.0164875984191895,
|
|
"epoch": 0.25148483064904487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997635821718435,
|
|
"loss": 6.9312,
|
|
"mean_token_accuracy": 0.11026841551065444,
|
|
"num_tokens": 5112235.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.8925614833831785,
|
|
"epoch": 0.2520199047568088,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004997618266924704,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.10299434512853622,
|
|
"num_tokens": 5122360.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 7.002241230010986,
|
|
"epoch": 0.25255497886457273,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499760064723131,
|
|
"loss": 6.9801,
|
|
"mean_token_accuracy": 0.1024145670235157,
|
|
"num_tokens": 5133084.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.938703870773315,
|
|
"epoch": 0.25309005297233667,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997582962638764,
|
|
"loss": 6.9133,
|
|
"mean_token_accuracy": 0.09837969020009041,
|
|
"num_tokens": 5144495.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.031873512268066,
|
|
"epoch": 0.2536251270801006,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997565213147575,
|
|
"loss": 6.9238,
|
|
"mean_token_accuracy": 0.10646962001919746,
|
|
"num_tokens": 5154824.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.939056253433227,
|
|
"epoch": 0.25416020118786453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997547398758257,
|
|
"loss": 6.9111,
|
|
"mean_token_accuracy": 0.10193499475717545,
|
|
"num_tokens": 5165061.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.981441783905029,
|
|
"epoch": 0.25469527529562846,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997529519471323,
|
|
"loss": 6.8679,
|
|
"mean_token_accuracy": 0.11417916044592857,
|
|
"num_tokens": 5174964.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.884857940673828,
|
|
"epoch": 0.25523034940339234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997511575287291,
|
|
"loss": 6.9267,
|
|
"mean_token_accuracy": 0.10812475010752678,
|
|
"num_tokens": 5185458.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.991512250900269,
|
|
"epoch": 0.2557654235111563,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997493566206677,
|
|
"loss": 6.9025,
|
|
"mean_token_accuracy": 0.10954718366265297,
|
|
"num_tokens": 5196193.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.966927862167358,
|
|
"epoch": 0.2563004976189202,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997475492230003,
|
|
"loss": 7.0198,
|
|
"mean_token_accuracy": 0.09881971776485443,
|
|
"num_tokens": 5208541.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.989241456985473,
|
|
"epoch": 0.25683557172668414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499745735335779,
|
|
"loss": 6.8501,
|
|
"mean_token_accuracy": 0.10620964914560319,
|
|
"num_tokens": 5218567.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.943647241592407,
|
|
"epoch": 0.2573706458344481,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997439149590561,
|
|
"loss": 6.9666,
|
|
"mean_token_accuracy": 0.10247603580355644,
|
|
"num_tokens": 5228293.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.982013940811157,
|
|
"epoch": 0.257905719942212,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997420880928843,
|
|
"loss": 6.913,
|
|
"mean_token_accuracy": 0.10574470162391662,
|
|
"num_tokens": 5238880.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.9576988697052,
|
|
"epoch": 0.25844079404997594,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997402547373162,
|
|
"loss": 6.9947,
|
|
"mean_token_accuracy": 0.10212295204401016,
|
|
"num_tokens": 5250104.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.100748538970947,
|
|
"epoch": 0.2589758681577399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997384148924049,
|
|
"loss": 7.0243,
|
|
"mean_token_accuracy": 0.10289878994226456,
|
|
"num_tokens": 5260355.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.962227201461792,
|
|
"epoch": 0.25951094226550375,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997365685582035,
|
|
"loss": 6.9296,
|
|
"mean_token_accuracy": 0.10283196046948433,
|
|
"num_tokens": 5272117.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.9883177280426025,
|
|
"epoch": 0.2600460163732677,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997347157347651,
|
|
"loss": 7.0307,
|
|
"mean_token_accuracy": 0.10037739872932434,
|
|
"num_tokens": 5284583.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 7.049625587463379,
|
|
"epoch": 0.2605810904810316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997328564221435,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.12059795558452606,
|
|
"num_tokens": 5295846.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.871410655975342,
|
|
"epoch": 0.26111616458879555,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997309906203922,
|
|
"loss": 6.9662,
|
|
"mean_token_accuracy": 0.10526571422815323,
|
|
"num_tokens": 5307802.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.033421468734741,
|
|
"epoch": 0.2616512386965595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997291183295652,
|
|
"loss": 6.8913,
|
|
"mean_token_accuracy": 0.10737156346440316,
|
|
"num_tokens": 5318263.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.998748159408569,
|
|
"epoch": 0.2621863128043234,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997272395497164,
|
|
"loss": 6.9388,
|
|
"mean_token_accuracy": 0.10455406904220581,
|
|
"num_tokens": 5328555.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.912611675262451,
|
|
"epoch": 0.26272138691208735,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997253542809002,
|
|
"loss": 6.9152,
|
|
"mean_token_accuracy": 0.10682450905442238,
|
|
"num_tokens": 5339954.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.079062366485596,
|
|
"epoch": 0.26325646101985123,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997234625231709,
|
|
"loss": 6.9637,
|
|
"mean_token_accuracy": 0.10808332860469819,
|
|
"num_tokens": 5350919.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.93997278213501,
|
|
"epoch": 0.26379153512761516,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997215642765832,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.10664721727371215,
|
|
"num_tokens": 5361844.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.987752532958984,
|
|
"epoch": 0.2643266092353791,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499719659541192,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.10334968268871307,
|
|
"num_tokens": 5372026.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.954167985916138,
|
|
"epoch": 0.26486168334314303,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997177483170521,
|
|
"loss": 6.9927,
|
|
"mean_token_accuracy": 0.10936494544148445,
|
|
"num_tokens": 5382965.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 7.007135391235352,
|
|
"epoch": 0.26539675745090696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997158306042188,
|
|
"loss": 6.9458,
|
|
"mean_token_accuracy": 0.10711643844842911,
|
|
"num_tokens": 5393738.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.897781848907471,
|
|
"epoch": 0.2659318315586709,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997139064027476,
|
|
"loss": 6.8237,
|
|
"mean_token_accuracy": 0.1119477018713951,
|
|
"num_tokens": 5404059.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.912676382064819,
|
|
"epoch": 0.26646690566643483,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997119757126938,
|
|
"loss": 6.855,
|
|
"mean_token_accuracy": 0.10871710032224655,
|
|
"num_tokens": 5414152.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 7.022440433502197,
|
|
"epoch": 0.2670019797741987,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997100385341133,
|
|
"loss": 7.0235,
|
|
"mean_token_accuracy": 0.10726772770285606,
|
|
"num_tokens": 5425227.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 7.004488468170166,
|
|
"epoch": 0.26753705388196264,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997080948670621,
|
|
"loss": 6.8663,
|
|
"mean_token_accuracy": 0.11122208759188652,
|
|
"num_tokens": 5435716.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.936031723022461,
|
|
"epoch": 0.26807212798972657,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997061447115962,
|
|
"loss": 6.9347,
|
|
"mean_token_accuracy": 0.10375397354364395,
|
|
"num_tokens": 5446519.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.975105237960816,
|
|
"epoch": 0.2686072020974905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997041880677719,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.10548185482621193,
|
|
"num_tokens": 5457496.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.880755996704101,
|
|
"epoch": 0.26914227620525444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997022249356457,
|
|
"loss": 6.823,
|
|
"mean_token_accuracy": 0.11008255481719971,
|
|
"num_tokens": 5469059.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.923517560958862,
|
|
"epoch": 0.26967735031301837,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997002553152745,
|
|
"loss": 6.9138,
|
|
"mean_token_accuracy": 0.10938023030757904,
|
|
"num_tokens": 5480324.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.9742035388946535,
|
|
"epoch": 0.2702124244207823,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996982792067148,
|
|
"loss": 6.9339,
|
|
"mean_token_accuracy": 0.09864719212055206,
|
|
"num_tokens": 5491513.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.8970160484313965,
|
|
"epoch": 0.2707474985285462,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499696296610024,
|
|
"loss": 6.8394,
|
|
"mean_token_accuracy": 0.1051232136785984,
|
|
"num_tokens": 5502414.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.9252660274505615,
|
|
"epoch": 0.2712825726363101,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996943075252592,
|
|
"loss": 6.9715,
|
|
"mean_token_accuracy": 0.1062911570072174,
|
|
"num_tokens": 5512962.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.977799654006958,
|
|
"epoch": 0.27181764674407405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996923119524777,
|
|
"loss": 6.8355,
|
|
"mean_token_accuracy": 0.10766077339649201,
|
|
"num_tokens": 5524648.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.855292940139771,
|
|
"epoch": 0.272352720851838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996903098917375,
|
|
"loss": 6.9214,
|
|
"mean_token_accuracy": 0.0998130515217781,
|
|
"num_tokens": 5536158.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.939780187606812,
|
|
"epoch": 0.2728877949596019,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499688301343096,
|
|
"loss": 6.8405,
|
|
"mean_token_accuracy": 0.10747457072138786,
|
|
"num_tokens": 5547374.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 7.020946025848389,
|
|
"epoch": 0.27342286906736585,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996862863066114,
|
|
"loss": 6.9137,
|
|
"mean_token_accuracy": 0.10850636437535285,
|
|
"num_tokens": 5559212.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.907329320907593,
|
|
"epoch": 0.2739579431751298,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996842647823419,
|
|
"loss": 6.8823,
|
|
"mean_token_accuracy": 0.10653341263532638,
|
|
"num_tokens": 5569302.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.910869598388672,
|
|
"epoch": 0.27449301728289366,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996822367703458,
|
|
"loss": 6.8905,
|
|
"mean_token_accuracy": 0.10348111093044281,
|
|
"num_tokens": 5581688.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.955097198486328,
|
|
"epoch": 0.2750280913906576,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996802022706817,
|
|
"loss": 6.8211,
|
|
"mean_token_accuracy": 0.10833865478634834,
|
|
"num_tokens": 5591376.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.861729669570923,
|
|
"epoch": 0.2755631654984215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996781612834083,
|
|
"loss": 6.8798,
|
|
"mean_token_accuracy": 0.10732169449329376,
|
|
"num_tokens": 5601510.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 7.005447006225586,
|
|
"epoch": 0.27609823960618546,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996761138085846,
|
|
"loss": 6.9316,
|
|
"mean_token_accuracy": 0.1021797627210617,
|
|
"num_tokens": 5611436.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.92574257850647,
|
|
"epoch": 0.2766333137139494,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996740598462697,
|
|
"loss": 6.9341,
|
|
"mean_token_accuracy": 0.10267650112509727,
|
|
"num_tokens": 5620470.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.860880899429321,
|
|
"epoch": 0.2771683878217133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996719993965229,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.10769467577338218,
|
|
"num_tokens": 5630740.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.8753687858581545,
|
|
"epoch": 0.27770346192947726,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996699324594036,
|
|
"loss": 6.8303,
|
|
"mean_token_accuracy": 0.11734023317694664,
|
|
"num_tokens": 5641138.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.985844898223877,
|
|
"epoch": 0.27823853603724114,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996678590349717,
|
|
"loss": 6.974,
|
|
"mean_token_accuracy": 0.1085183672606945,
|
|
"num_tokens": 5652474.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.9662446022033695,
|
|
"epoch": 0.27877361014500507,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996657791232868,
|
|
"loss": 6.8709,
|
|
"mean_token_accuracy": 0.11153203919529915,
|
|
"num_tokens": 5663178.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.891348218917846,
|
|
"epoch": 0.279308684252769,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996636927244092,
|
|
"loss": 6.8963,
|
|
"mean_token_accuracy": 0.10582477301359176,
|
|
"num_tokens": 5673565.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 7.040777587890625,
|
|
"epoch": 0.27984375836053293,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499661599838399,
|
|
"loss": 6.9389,
|
|
"mean_token_accuracy": 0.10204790085554123,
|
|
"num_tokens": 5684651.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.929867219924927,
|
|
"epoch": 0.28037883246829687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996595004653167,
|
|
"loss": 6.8204,
|
|
"mean_token_accuracy": 0.10971119105815888,
|
|
"num_tokens": 5696081.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.925084161758423,
|
|
"epoch": 0.2809139065760608,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996573946052229,
|
|
"loss": 6.855,
|
|
"mean_token_accuracy": 0.10883698239922523,
|
|
"num_tokens": 5706830.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.910267782211304,
|
|
"epoch": 0.28144898068382473,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996552822581783,
|
|
"loss": 6.8815,
|
|
"mean_token_accuracy": 0.11361035332083702,
|
|
"num_tokens": 5717261.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.91580810546875,
|
|
"epoch": 0.2819840547915886,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499653163424244,
|
|
"loss": 6.8481,
|
|
"mean_token_accuracy": 0.10841184929013252,
|
|
"num_tokens": 5727280.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.938942956924438,
|
|
"epoch": 0.28251912889935255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996510381034814,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.10522805228829384,
|
|
"num_tokens": 5737485.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.926429605484008,
|
|
"epoch": 0.2830542030071165,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996489062959515,
|
|
"loss": 6.8735,
|
|
"mean_token_accuracy": 0.10467999801039696,
|
|
"num_tokens": 5747683.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.867719650268555,
|
|
"epoch": 0.2835892771148804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996467680017159,
|
|
"loss": 6.9325,
|
|
"mean_token_accuracy": 0.10280923023819924,
|
|
"num_tokens": 5758148.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.917259216308594,
|
|
"epoch": 0.28412435122264434,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996446232208365,
|
|
"loss": 6.8627,
|
|
"mean_token_accuracy": 0.11170612499117852,
|
|
"num_tokens": 5769109.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.9372947216033936,
|
|
"epoch": 0.2846594253304083,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996424719533753,
|
|
"loss": 6.8939,
|
|
"mean_token_accuracy": 0.1052110217511654,
|
|
"num_tokens": 5780344.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.913125228881836,
|
|
"epoch": 0.2851944994381722,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996403141993941,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.11824454516172409,
|
|
"num_tokens": 5790167.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.92453293800354,
|
|
"epoch": 0.2857295735459361,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996381499589555,
|
|
"loss": 6.8624,
|
|
"mean_token_accuracy": 0.10613423809409142,
|
|
"num_tokens": 5800076.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.944131517410279,
|
|
"epoch": 0.2862646476537,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996359792321219,
|
|
"loss": 6.8113,
|
|
"mean_token_accuracy": 0.11141969487071038,
|
|
"num_tokens": 5810547.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.8161341667175295,
|
|
"epoch": 0.28679972176146395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499633802018956,
|
|
"loss": 6.8478,
|
|
"mean_token_accuracy": 0.1100471280515194,
|
|
"num_tokens": 5821210.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.917617702484131,
|
|
"epoch": 0.2873347958692279,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996316183195204,
|
|
"loss": 6.8869,
|
|
"mean_token_accuracy": 0.10786092206835747,
|
|
"num_tokens": 5832361.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.962878274917602,
|
|
"epoch": 0.2878698699769918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996294281338786,
|
|
"loss": 6.8717,
|
|
"mean_token_accuracy": 0.10681624412536621,
|
|
"num_tokens": 5843242.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.976676988601684,
|
|
"epoch": 0.28840494408475575,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996272314620936,
|
|
"loss": 6.9215,
|
|
"mean_token_accuracy": 0.10194345191121101,
|
|
"num_tokens": 5855163.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.837163925170898,
|
|
"epoch": 0.2889400181925197,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996250283042288,
|
|
"loss": 6.8839,
|
|
"mean_token_accuracy": 0.11228486746549607,
|
|
"num_tokens": 5866908.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.974035596847534,
|
|
"epoch": 0.28947509230028357,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499622818660348,
|
|
"loss": 6.9045,
|
|
"mean_token_accuracy": 0.10939288139343262,
|
|
"num_tokens": 5877342.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.942460250854492,
|
|
"epoch": 0.2900101664080475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996206025305147,
|
|
"loss": 6.8573,
|
|
"mean_token_accuracy": 0.10582418739795685,
|
|
"num_tokens": 5887960.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.87635645866394,
|
|
"epoch": 0.29054524051581143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996183799147932,
|
|
"loss": 6.8397,
|
|
"mean_token_accuracy": 0.1095063179731369,
|
|
"num_tokens": 5899887.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.917806816101074,
|
|
"epoch": 0.29108031462357536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996161508132475,
|
|
"loss": 6.8583,
|
|
"mean_token_accuracy": 0.10231703668832778,
|
|
"num_tokens": 5911022.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 7.016377210617065,
|
|
"epoch": 0.2916153887313393,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499613915225942,
|
|
"loss": 6.9222,
|
|
"mean_token_accuracy": 0.11102863773703575,
|
|
"num_tokens": 5922780.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.881858253479004,
|
|
"epoch": 0.29215046283910323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996116731529412,
|
|
"loss": 6.9251,
|
|
"mean_token_accuracy": 0.10592872574925423,
|
|
"num_tokens": 5934112.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.8940752983093265,
|
|
"epoch": 0.29268553694686716,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049960942459431,
|
|
"loss": 6.8866,
|
|
"mean_token_accuracy": 0.1067856416106224,
|
|
"num_tokens": 5944386.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.870763492584229,
|
|
"epoch": 0.29322061105463104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996071695501132,
|
|
"loss": 6.813,
|
|
"mean_token_accuracy": 0.10948670953512192,
|
|
"num_tokens": 5955552.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.921037864685059,
|
|
"epoch": 0.293755685162395,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996049080204159,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.1098986655473709,
|
|
"num_tokens": 5966790.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.925626182556153,
|
|
"epoch": 0.2942907592701589,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996026400052835,
|
|
"loss": 6.8214,
|
|
"mean_token_accuracy": 0.10917853116989136,
|
|
"num_tokens": 5977704.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.853207015991211,
|
|
"epoch": 0.29482583337792284,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996003655047814,
|
|
"loss": 6.8364,
|
|
"mean_token_accuracy": 0.11162171512842178,
|
|
"num_tokens": 5989221.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.919997644424439,
|
|
"epoch": 0.2953609074856868,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995980845189753,
|
|
"loss": 6.871,
|
|
"mean_token_accuracy": 0.10931915193796157,
|
|
"num_tokens": 6000906.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.931192445755005,
|
|
"epoch": 0.2958959815934507,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995957970479312,
|
|
"loss": 6.8945,
|
|
"mean_token_accuracy": 0.10708941668272018,
|
|
"num_tokens": 6012039.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.8547321319580075,
|
|
"epoch": 0.29643105570121464,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995935030917148,
|
|
"loss": 6.776,
|
|
"mean_token_accuracy": 0.11066783592104912,
|
|
"num_tokens": 6024383.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.994161558151245,
|
|
"epoch": 0.2969661298089785,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995912026503926,
|
|
"loss": 6.8508,
|
|
"mean_token_accuracy": 0.10267031714320182,
|
|
"num_tokens": 6034904.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.838885879516601,
|
|
"epoch": 0.29750120391674245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499588895724031,
|
|
"loss": 6.8488,
|
|
"mean_token_accuracy": 0.10749915912747383,
|
|
"num_tokens": 6044449.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.962449741363526,
|
|
"epoch": 0.2980362780245064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995865823126968,
|
|
"loss": 6.8765,
|
|
"mean_token_accuracy": 0.10825972631573677,
|
|
"num_tokens": 6054465.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.8947694301605225,
|
|
"epoch": 0.2985713521322703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995842624164564,
|
|
"loss": 6.8962,
|
|
"mean_token_accuracy": 0.10824007838964463,
|
|
"num_tokens": 6065539.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.909287405014038,
|
|
"epoch": 0.29910642624003425,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499581936035377,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.10840294510126114,
|
|
"num_tokens": 6076135.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.903677034378052,
|
|
"epoch": 0.2996415003477982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995796031695257,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.10931005999445915,
|
|
"num_tokens": 6086604.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.90281114578247,
|
|
"epoch": 0.3001765744555621,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049957726381897,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.10950748696923256,
|
|
"num_tokens": 6095672.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.90290675163269,
|
|
"epoch": 0.300711648563326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995749179837773,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.11466853022575378,
|
|
"num_tokens": 6105652.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.826155042648315,
|
|
"epoch": 0.30124672267108993,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995725656640155,
|
|
"loss": 6.7856,
|
|
"mean_token_accuracy": 0.11099454537034034,
|
|
"num_tokens": 6116930.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.844819593429565,
|
|
"epoch": 0.30178179677885386,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995702068597524,
|
|
"loss": 6.7894,
|
|
"mean_token_accuracy": 0.11423054486513137,
|
|
"num_tokens": 6126659.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.890478515625,
|
|
"epoch": 0.3023168708866178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995678415710561,
|
|
"loss": 6.8288,
|
|
"mean_token_accuracy": 0.11060848459601402,
|
|
"num_tokens": 6137227.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.962517929077149,
|
|
"epoch": 0.3028519449943817,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499565469797995,
|
|
"loss": 6.8821,
|
|
"mean_token_accuracy": 0.10931277051568031,
|
|
"num_tokens": 6147800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.822924327850342,
|
|
"epoch": 0.30338701910214566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995630915406374,
|
|
"loss": 6.7326,
|
|
"mean_token_accuracy": 0.12161283493041992,
|
|
"num_tokens": 6157671.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.918770694732666,
|
|
"epoch": 0.3039220932099096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995607067990521,
|
|
"loss": 6.8698,
|
|
"mean_token_accuracy": 0.10645673274993897,
|
|
"num_tokens": 6168651.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.873465251922608,
|
|
"epoch": 0.30445716731767347,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499558315573308,
|
|
"loss": 6.8487,
|
|
"mean_token_accuracy": 0.1086043007671833,
|
|
"num_tokens": 6179925.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.818239831924439,
|
|
"epoch": 0.3049922414254374,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995559178634741,
|
|
"loss": 6.8438,
|
|
"mean_token_accuracy": 0.10887812077999115,
|
|
"num_tokens": 6190541.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 7.041949510574341,
|
|
"epoch": 0.30552731553320134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995535136696196,
|
|
"loss": 6.8866,
|
|
"mean_token_accuracy": 0.09955592602491378,
|
|
"num_tokens": 6201491.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.8139080047607425,
|
|
"epoch": 0.30606238964096527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499551102991814,
|
|
"loss": 6.6991,
|
|
"mean_token_accuracy": 0.11249880269169807,
|
|
"num_tokens": 6212443.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.817849111557007,
|
|
"epoch": 0.3065974637487292,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995486858301268,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.1030767761170864,
|
|
"num_tokens": 6222623.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.925403165817261,
|
|
"epoch": 0.30713253785649314,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995462621846279,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.10933116525411606,
|
|
"num_tokens": 6233712.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.854152202606201,
|
|
"epoch": 0.30766761196425707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995438320553871,
|
|
"loss": 6.8534,
|
|
"mean_token_accuracy": 0.10412434935569763,
|
|
"num_tokens": 6244254.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.823256492614746,
|
|
"epoch": 0.30820268607202095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995413954424748,
|
|
"loss": 6.7504,
|
|
"mean_token_accuracy": 0.116096231341362,
|
|
"num_tokens": 6254202.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.877709770202637,
|
|
"epoch": 0.3087377601797849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995389523459612,
|
|
"loss": 6.8231,
|
|
"mean_token_accuracy": 0.10538254305720329,
|
|
"num_tokens": 6264496.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.839356851577759,
|
|
"epoch": 0.3092728342875488,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499536502765917,
|
|
"loss": 6.828,
|
|
"mean_token_accuracy": 0.1125398851931095,
|
|
"num_tokens": 6275835.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.893553924560547,
|
|
"epoch": 0.30980790839531275,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995340467024128,
|
|
"loss": 6.7842,
|
|
"mean_token_accuracy": 0.10834744572639465,
|
|
"num_tokens": 6286805.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.906386661529541,
|
|
"epoch": 0.3103429825030767,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995315841555195,
|
|
"loss": 6.7916,
|
|
"mean_token_accuracy": 0.10366136953234673,
|
|
"num_tokens": 6298444.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.783759641647339,
|
|
"epoch": 0.3108780566108406,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995291151253083,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.11380124613642692,
|
|
"num_tokens": 6308259.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.846135902404785,
|
|
"epoch": 0.31141313071860455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995266396118505,
|
|
"loss": 6.8013,
|
|
"mean_token_accuracy": 0.10161566883325576,
|
|
"num_tokens": 6320058.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.900366973876953,
|
|
"epoch": 0.3119482048263684,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995241576152174,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.10676236972212791,
|
|
"num_tokens": 6331203.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.897499227523804,
|
|
"epoch": 0.31248327893413236,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499521669135481,
|
|
"loss": 6.8882,
|
|
"mean_token_accuracy": 0.10588050186634064,
|
|
"num_tokens": 6342027.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.894981956481933,
|
|
"epoch": 0.3130183530418963,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995191741727128,
|
|
"loss": 6.7873,
|
|
"mean_token_accuracy": 0.10809844583272935,
|
|
"num_tokens": 6352580.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.887385463714599,
|
|
"epoch": 0.3135534271496602,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499516672726985,
|
|
"loss": 6.8106,
|
|
"mean_token_accuracy": 0.11217835023999215,
|
|
"num_tokens": 6363997.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.83791708946228,
|
|
"epoch": 0.31408850125742416,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995141647983699,
|
|
"loss": 6.8464,
|
|
"mean_token_accuracy": 0.11019290536642075,
|
|
"num_tokens": 6375284.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.8710222244262695,
|
|
"epoch": 0.3146235753651881,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995116503869398,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.11758178621530532,
|
|
"num_tokens": 6386698.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.864429473876953,
|
|
"epoch": 0.315158649472952,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995091294927673,
|
|
"loss": 6.818,
|
|
"mean_token_accuracy": 0.10886727124452591,
|
|
"num_tokens": 6397237.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.973788785934448,
|
|
"epoch": 0.3156937235807159,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995066021159253,
|
|
"loss": 6.9364,
|
|
"mean_token_accuracy": 0.10483678579330444,
|
|
"num_tokens": 6408266.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.842577266693115,
|
|
"epoch": 0.31622879768847983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995040682564867,
|
|
"loss": 6.8199,
|
|
"mean_token_accuracy": 0.11405593305826187,
|
|
"num_tokens": 6419563.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.8359404563903805,
|
|
"epoch": 0.31676387179624377,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995015279145247,
|
|
"loss": 6.7863,
|
|
"mean_token_accuracy": 0.11180907115340233,
|
|
"num_tokens": 6430220.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.857833385467529,
|
|
"epoch": 0.3172989459040077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994989810901126,
|
|
"loss": 6.7961,
|
|
"mean_token_accuracy": 0.10685641467571258,
|
|
"num_tokens": 6440157.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.856301593780517,
|
|
"epoch": 0.31783402001177163,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994964277833239,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.11110184714198112,
|
|
"num_tokens": 6449511.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.923713493347168,
|
|
"epoch": 0.31836909411953557,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994938679942324,
|
|
"loss": 6.8365,
|
|
"mean_token_accuracy": 0.10282818749547004,
|
|
"num_tokens": 6460608.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.919619989395142,
|
|
"epoch": 0.3189041682272995,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994913017229121,
|
|
"loss": 6.8372,
|
|
"mean_token_accuracy": 0.1131968080997467,
|
|
"num_tokens": 6472737.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.817192554473877,
|
|
"epoch": 0.31943924233506343,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994887289694371,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.11385754495859146,
|
|
"num_tokens": 6482993.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.960534572601318,
|
|
"epoch": 0.3199743164428273,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994861497338814,
|
|
"loss": 6.9207,
|
|
"mean_token_accuracy": 0.11038238108158112,
|
|
"num_tokens": 6494530.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.894915056228638,
|
|
"epoch": 0.32050939055059124,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994835640163198,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.10633266866207122,
|
|
"num_tokens": 6504691.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.885722494125366,
|
|
"epoch": 0.3210444646583552,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994809718168267,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.10957603380084038,
|
|
"num_tokens": 6514924.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3210444646583552,
|
|
"eval_entropy": 6.6982880289021205,
|
|
"eval_loss": 6.9056596755981445,
|
|
"eval_mean_token_accuracy": 0.11213191206946045,
|
|
"eval_num_tokens": 6514924.0,
|
|
"eval_runtime": 22.6381,
|
|
"eval_samples_per_second": 1311.022,
|
|
"eval_steps_per_second": 163.883,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.774571943283081,
|
|
"epoch": 0.3215795387661191,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994783731354771,
|
|
"loss": 6.7524,
|
|
"mean_token_accuracy": 0.11166785731911659,
|
|
"num_tokens": 6526097.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.929418516159058,
|
|
"epoch": 0.32211461287388304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994757679723461,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.10639956593513489,
|
|
"num_tokens": 6536384.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.919300746917725,
|
|
"epoch": 0.322649686981647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994731563275088,
|
|
"loss": 6.8694,
|
|
"mean_token_accuracy": 0.1046457588672638,
|
|
"num_tokens": 6547161.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.785147857666016,
|
|
"epoch": 0.3231847610894109,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994705382010406,
|
|
"loss": 6.7936,
|
|
"mean_token_accuracy": 0.10720081478357316,
|
|
"num_tokens": 6556751.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.861992263793946,
|
|
"epoch": 0.3237198351971748,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994679135930174,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.1134506493806839,
|
|
"num_tokens": 6567655.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.987712669372558,
|
|
"epoch": 0.3242549093049387,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994652825035144,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.10770419910550118,
|
|
"num_tokens": 6579127.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.9072469711303714,
|
|
"epoch": 0.32478998341270265,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994626449326081,
|
|
"loss": 6.8376,
|
|
"mean_token_accuracy": 0.11200311556458473,
|
|
"num_tokens": 6590779.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.858027362823487,
|
|
"epoch": 0.3253250575204666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994600008803745,
|
|
"loss": 6.7456,
|
|
"mean_token_accuracy": 0.11969574466347695,
|
|
"num_tokens": 6600849.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.831806564331055,
|
|
"epoch": 0.3258601316282305,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994573503468899,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.11736322343349456,
|
|
"num_tokens": 6610633.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.787566423416138,
|
|
"epoch": 0.32639520573599445,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994546933322308,
|
|
"loss": 6.7953,
|
|
"mean_token_accuracy": 0.10811478719115257,
|
|
"num_tokens": 6621327.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.93750228881836,
|
|
"epoch": 0.3269302798437584,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499452029836474,
|
|
"loss": 6.7415,
|
|
"mean_token_accuracy": 0.11278096809983254,
|
|
"num_tokens": 6632267.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.810693454742432,
|
|
"epoch": 0.32746535395152226,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994493598596963,
|
|
"loss": 6.7705,
|
|
"mean_token_accuracy": 0.10761533975601197,
|
|
"num_tokens": 6642714.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.849345254898071,
|
|
"epoch": 0.3280004280592862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994466834019749,
|
|
"loss": 6.7758,
|
|
"mean_token_accuracy": 0.11640546843409538,
|
|
"num_tokens": 6652353.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.842514944076538,
|
|
"epoch": 0.32853550216705013,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994440004633871,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.11130421757698059,
|
|
"num_tokens": 6663133.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.801913261413574,
|
|
"epoch": 0.32907057627481406,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994413110440103,
|
|
"loss": 6.7354,
|
|
"mean_token_accuracy": 0.11714180111885071,
|
|
"num_tokens": 6673984.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.8637457370758055,
|
|
"epoch": 0.329605650382578,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994386151439222,
|
|
"loss": 6.8076,
|
|
"mean_token_accuracy": 0.1080280676484108,
|
|
"num_tokens": 6686171.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.933955192565918,
|
|
"epoch": 0.33014072449034193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994359127632006,
|
|
"loss": 6.8475,
|
|
"mean_token_accuracy": 0.10514529719948769,
|
|
"num_tokens": 6696609.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.89633002281189,
|
|
"epoch": 0.33067579859810586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994332039019235,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.11049062609672547,
|
|
"num_tokens": 6706188.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.708978939056396,
|
|
"epoch": 0.33121087270586974,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994304885601694,
|
|
"loss": 6.7667,
|
|
"mean_token_accuracy": 0.11125922203063965,
|
|
"num_tokens": 6716276.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.774325132369995,
|
|
"epoch": 0.3317459468136337,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994277667380162,
|
|
"loss": 6.737,
|
|
"mean_token_accuracy": 0.1192335270345211,
|
|
"num_tokens": 6727176.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.887723302841186,
|
|
"epoch": 0.3322810209213976,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994250384355429,
|
|
"loss": 6.8119,
|
|
"mean_token_accuracy": 0.11386096626520156,
|
|
"num_tokens": 6737768.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.840688323974609,
|
|
"epoch": 0.33281609502916154,
|
|
"grad_norm": 6.46875,
|
|
"learning_rate": 0.0004994223036528282,
|
|
"loss": 6.7618,
|
|
"mean_token_accuracy": 0.11079908534884453,
|
|
"num_tokens": 6747962.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.8406102657318115,
|
|
"epoch": 0.3333511691369255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499419562389951,
|
|
"loss": 6.7548,
|
|
"mean_token_accuracy": 0.1147709958255291,
|
|
"num_tokens": 6758400.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.851141119003296,
|
|
"epoch": 0.3338862432446894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994168146469904,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.11088330820202827,
|
|
"num_tokens": 6768855.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.863172101974487,
|
|
"epoch": 0.33442131735245334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994140604240259,
|
|
"loss": 6.7514,
|
|
"mean_token_accuracy": 0.1078583225607872,
|
|
"num_tokens": 6778656.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.882100915908813,
|
|
"epoch": 0.3349563914602172,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994112997211369,
|
|
"loss": 6.8182,
|
|
"mean_token_accuracy": 0.11499066054821014,
|
|
"num_tokens": 6789960.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.730247640609742,
|
|
"epoch": 0.33549146556798115,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994085325384031,
|
|
"loss": 6.8076,
|
|
"mean_token_accuracy": 0.10851202681660652,
|
|
"num_tokens": 6800188.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.906764650344849,
|
|
"epoch": 0.3360265396757451,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994057588759045,
|
|
"loss": 6.7393,
|
|
"mean_token_accuracy": 0.11358117088675498,
|
|
"num_tokens": 6811032.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.824139022827149,
|
|
"epoch": 0.336561613783509,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994029787337212,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.10829171538352966,
|
|
"num_tokens": 6823060.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.8112482070922855,
|
|
"epoch": 0.33709668789127295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994001921119333,
|
|
"loss": 6.8496,
|
|
"mean_token_accuracy": 0.10913093164563178,
|
|
"num_tokens": 6833559.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.894295167922974,
|
|
"epoch": 0.3376317619990369,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993973990106215,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.11234046593308449,
|
|
"num_tokens": 6843657.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.814738702774048,
|
|
"epoch": 0.3381668361068008,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993945994298662,
|
|
"loss": 6.7267,
|
|
"mean_token_accuracy": 0.10636094883084297,
|
|
"num_tokens": 6853615.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.858942174911499,
|
|
"epoch": 0.3387019102145647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993917933697484,
|
|
"loss": 6.8354,
|
|
"mean_token_accuracy": 0.10942788496613502,
|
|
"num_tokens": 6865256.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 7.015973472595215,
|
|
"epoch": 0.3392369843223286,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993889808303493,
|
|
"loss": 6.8711,
|
|
"mean_token_accuracy": 0.11036419197916984,
|
|
"num_tokens": 6875358.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.757581901550293,
|
|
"epoch": 0.33977205843009256,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993861618117498,
|
|
"loss": 6.7711,
|
|
"mean_token_accuracy": 0.1102716788649559,
|
|
"num_tokens": 6886584.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.8233020305633545,
|
|
"epoch": 0.3403071325378565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993833363140314,
|
|
"loss": 6.7109,
|
|
"mean_token_accuracy": 0.11896613985300064,
|
|
"num_tokens": 6896958.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.830180215835571,
|
|
"epoch": 0.3408422066456204,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993805043372756,
|
|
"loss": 6.775,
|
|
"mean_token_accuracy": 0.1163598895072937,
|
|
"num_tokens": 6907944.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.831008625030518,
|
|
"epoch": 0.34137728075338436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993776658815644,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.1049034409224987,
|
|
"num_tokens": 6919486.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.957132577896118,
|
|
"epoch": 0.3419123548611483,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993748209469796,
|
|
"loss": 6.8414,
|
|
"mean_token_accuracy": 0.11248302012681961,
|
|
"num_tokens": 6930650.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.833132362365722,
|
|
"epoch": 0.34244742896891217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993719695336033,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.11160960346460343,
|
|
"num_tokens": 6941519.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.775629329681396,
|
|
"epoch": 0.3429825030766761,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004993691116415179,
|
|
"loss": 6.8265,
|
|
"mean_token_accuracy": 0.10980288833379745,
|
|
"num_tokens": 6952952.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.945135641098022,
|
|
"epoch": 0.34351757718444004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499366247270806,
|
|
"loss": 6.7907,
|
|
"mean_token_accuracy": 0.11398276537656785,
|
|
"num_tokens": 6962867.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.850128173828125,
|
|
"epoch": 0.34405265129220397,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993633764215502,
|
|
"loss": 6.7128,
|
|
"mean_token_accuracy": 0.1149346224963665,
|
|
"num_tokens": 6973434.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.805971765518189,
|
|
"epoch": 0.3445877253999679,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993604990938336,
|
|
"loss": 6.7242,
|
|
"mean_token_accuracy": 0.12372536882758141,
|
|
"num_tokens": 6984161.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.831466388702393,
|
|
"epoch": 0.34512279950773184,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993576152877389,
|
|
"loss": 6.7023,
|
|
"mean_token_accuracy": 0.11155548840761184,
|
|
"num_tokens": 6994700.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.859937858581543,
|
|
"epoch": 0.34565787361549577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993547250033496,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.10222596898674965,
|
|
"num_tokens": 7006497.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.907996559143067,
|
|
"epoch": 0.34619294772325965,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993518282407493,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.11640164703130722,
|
|
"num_tokens": 7016415.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.780554246902466,
|
|
"epoch": 0.3467280218310236,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993489250000213,
|
|
"loss": 6.7293,
|
|
"mean_token_accuracy": 0.11351820677518845,
|
|
"num_tokens": 7026610.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.797022676467895,
|
|
"epoch": 0.3472630959387875,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993460152812497,
|
|
"loss": 6.7409,
|
|
"mean_token_accuracy": 0.11043249741196633,
|
|
"num_tokens": 7038236.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.871045017242432,
|
|
"epoch": 0.34779817004655145,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993430990845184,
|
|
"loss": 6.7892,
|
|
"mean_token_accuracy": 0.12099697217345237,
|
|
"num_tokens": 7049438.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.795158195495605,
|
|
"epoch": 0.3483332441543154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993401764099118,
|
|
"loss": 6.75,
|
|
"mean_token_accuracy": 0.10678878873586654,
|
|
"num_tokens": 7061001.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.869133567810058,
|
|
"epoch": 0.3488683182620793,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993372472575139,
|
|
"loss": 6.7464,
|
|
"mean_token_accuracy": 0.11511967554688454,
|
|
"num_tokens": 7071328.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.9016501903533936,
|
|
"epoch": 0.34940339236984325,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993343116274096,
|
|
"loss": 6.93,
|
|
"mean_token_accuracy": 0.10523641705513001,
|
|
"num_tokens": 7082597.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.860869073867798,
|
|
"epoch": 0.3499384664776071,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993313695196836,
|
|
"loss": 6.759,
|
|
"mean_token_accuracy": 0.116279286891222,
|
|
"num_tokens": 7093463.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.816839218139648,
|
|
"epoch": 0.35047354058537106,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993284209344208,
|
|
"loss": 6.8225,
|
|
"mean_token_accuracy": 0.11397869065403939,
|
|
"num_tokens": 7104350.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.929663181304932,
|
|
"epoch": 0.351008614693135,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993254658717065,
|
|
"loss": 6.78,
|
|
"mean_token_accuracy": 0.11524501666426659,
|
|
"num_tokens": 7114851.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.865924549102783,
|
|
"epoch": 0.3515436888008989,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993225043316257,
|
|
"loss": 6.8189,
|
|
"mean_token_accuracy": 0.10788183063268661,
|
|
"num_tokens": 7126440.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.94174747467041,
|
|
"epoch": 0.35207876290866286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993195363142643,
|
|
"loss": 6.8435,
|
|
"mean_token_accuracy": 0.10635844394564628,
|
|
"num_tokens": 7137884.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.8471081256866455,
|
|
"epoch": 0.3526138370164268,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993165618197076,
|
|
"loss": 6.8169,
|
|
"mean_token_accuracy": 0.10543133914470673,
|
|
"num_tokens": 7147930.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.814928293228149,
|
|
"epoch": 0.3531489111241907,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993135808480418,
|
|
"loss": 6.6758,
|
|
"mean_token_accuracy": 0.12192264795303345,
|
|
"num_tokens": 7159200.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.856072282791137,
|
|
"epoch": 0.3536839852319546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993105933993529,
|
|
"loss": 6.7738,
|
|
"mean_token_accuracy": 0.11219395026564598,
|
|
"num_tokens": 7169601.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.731938648223877,
|
|
"epoch": 0.35421905933971853,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993075994737271,
|
|
"loss": 6.7014,
|
|
"mean_token_accuracy": 0.12335732132196427,
|
|
"num_tokens": 7180465.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.827739572525024,
|
|
"epoch": 0.35475413344748247,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993045990712508,
|
|
"loss": 6.7214,
|
|
"mean_token_accuracy": 0.1124566912651062,
|
|
"num_tokens": 7190603.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.744693279266357,
|
|
"epoch": 0.3552892075552464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993015921920109,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.1178012415766716,
|
|
"num_tokens": 7201017.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.700474643707276,
|
|
"epoch": 0.35582428166301033,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499298578836094,
|
|
"loss": 6.6851,
|
|
"mean_token_accuracy": 0.11364478841423989,
|
|
"num_tokens": 7210908.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.913705682754516,
|
|
"epoch": 0.35635935577077427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499295559003587,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.11469347327947617,
|
|
"num_tokens": 7221306.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.857224035263061,
|
|
"epoch": 0.3568944298785382,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992925326945774,
|
|
"loss": 6.8446,
|
|
"mean_token_accuracy": 0.11008940190076828,
|
|
"num_tokens": 7233076.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.836943006515503,
|
|
"epoch": 0.3574295039863021,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992894999091524,
|
|
"loss": 6.833,
|
|
"mean_token_accuracy": 0.11023118868470191,
|
|
"num_tokens": 7244703.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.865760707855225,
|
|
"epoch": 0.357964578094066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992864606473996,
|
|
"loss": 6.8127,
|
|
"mean_token_accuracy": 0.10562887638807297,
|
|
"num_tokens": 7255438.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.873836708068848,
|
|
"epoch": 0.35849965220182994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992834149094069,
|
|
"loss": 6.7746,
|
|
"mean_token_accuracy": 0.10823791846632957,
|
|
"num_tokens": 7265720.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.854056453704834,
|
|
"epoch": 0.3590347263095939,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992803626952619,
|
|
"loss": 6.8105,
|
|
"mean_token_accuracy": 0.10965728536248207,
|
|
"num_tokens": 7277791.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.743177652359009,
|
|
"epoch": 0.3595698004173578,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499277304005053,
|
|
"loss": 6.6904,
|
|
"mean_token_accuracy": 0.11896344646811485,
|
|
"num_tokens": 7288521.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.8449372291564945,
|
|
"epoch": 0.36010487452512174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992742388388686,
|
|
"loss": 6.8681,
|
|
"mean_token_accuracy": 0.10312251970171929,
|
|
"num_tokens": 7299298.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.848871850967408,
|
|
"epoch": 0.3606399486328857,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992711671967968,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.11500442028045654,
|
|
"num_tokens": 7310271.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.832868242263794,
|
|
"epoch": 0.36117502274064955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992680890789268,
|
|
"loss": 6.7535,
|
|
"mean_token_accuracy": 0.11115506291389465,
|
|
"num_tokens": 7321112.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.744096136093139,
|
|
"epoch": 0.3617100968484135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992650044853471,
|
|
"loss": 6.7111,
|
|
"mean_token_accuracy": 0.11423057690262794,
|
|
"num_tokens": 7331976.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.881365203857422,
|
|
"epoch": 0.3622451709561774,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499261913416147,
|
|
"loss": 6.8157,
|
|
"mean_token_accuracy": 0.11083743125200271,
|
|
"num_tokens": 7342800.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.820743465423584,
|
|
"epoch": 0.36278024506394135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992588158714157,
|
|
"loss": 6.6508,
|
|
"mean_token_accuracy": 0.11105694174766541,
|
|
"num_tokens": 7354213.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.789371490478516,
|
|
"epoch": 0.3633153191717053,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992557118512424,
|
|
"loss": 6.7069,
|
|
"mean_token_accuracy": 0.11869031190872192,
|
|
"num_tokens": 7363250.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.7624798774719235,
|
|
"epoch": 0.3638503932794692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992526013557171,
|
|
"loss": 6.7605,
|
|
"mean_token_accuracy": 0.11203641667962075,
|
|
"num_tokens": 7374185.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.752663087844849,
|
|
"epoch": 0.36438546738723315,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992494843849294,
|
|
"loss": 6.7287,
|
|
"mean_token_accuracy": 0.10924962237477302,
|
|
"num_tokens": 7384579.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.896695327758789,
|
|
"epoch": 0.36492054149499703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992463609389694,
|
|
"loss": 6.7422,
|
|
"mean_token_accuracy": 0.10970545783638955,
|
|
"num_tokens": 7395277.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.726968002319336,
|
|
"epoch": 0.36545561560276096,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992432310179272,
|
|
"loss": 6.7332,
|
|
"mean_token_accuracy": 0.1160312682390213,
|
|
"num_tokens": 7406688.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.766181993484497,
|
|
"epoch": 0.3659906897105249,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992400946218932,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.11444359049201011,
|
|
"num_tokens": 7417378.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.967504692077637,
|
|
"epoch": 0.36652576381828883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992369517509581,
|
|
"loss": 6.8179,
|
|
"mean_token_accuracy": 0.1145808644592762,
|
|
"num_tokens": 7427675.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.834393882751465,
|
|
"epoch": 0.36706083792605276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992338024052123,
|
|
"loss": 6.8405,
|
|
"mean_token_accuracy": 0.10944146141409875,
|
|
"num_tokens": 7438083.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.772138452529907,
|
|
"epoch": 0.3675959120338167,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992306465847473,
|
|
"loss": 6.6866,
|
|
"mean_token_accuracy": 0.11544951871037483,
|
|
"num_tokens": 7449051.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.803123044967651,
|
|
"epoch": 0.36813098614158063,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992274842896536,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.11575418040156364,
|
|
"num_tokens": 7459074.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.810998582839966,
|
|
"epoch": 0.3686660602493445,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992243155200229,
|
|
"loss": 6.7908,
|
|
"mean_token_accuracy": 0.11545799896121026,
|
|
"num_tokens": 7470472.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.810088348388672,
|
|
"epoch": 0.36920113435710844,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992211402759466,
|
|
"loss": 6.7589,
|
|
"mean_token_accuracy": 0.11591348797082901,
|
|
"num_tokens": 7481477.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.811910390853882,
|
|
"epoch": 0.3697362084648724,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992179585575164,
|
|
"loss": 6.7166,
|
|
"mean_token_accuracy": 0.11710453182458877,
|
|
"num_tokens": 7491906.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.801189374923706,
|
|
"epoch": 0.3702712825726363,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499214770364824,
|
|
"loss": 6.6567,
|
|
"mean_token_accuracy": 0.10969180539250374,
|
|
"num_tokens": 7502447.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.731618452072143,
|
|
"epoch": 0.37080635668040024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992115756979617,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.12150704562664032,
|
|
"num_tokens": 7513505.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.763904094696045,
|
|
"epoch": 0.3713414307881642,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992083745570218,
|
|
"loss": 6.6731,
|
|
"mean_token_accuracy": 0.11672577038407325,
|
|
"num_tokens": 7524884.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.764589834213257,
|
|
"epoch": 0.3718765048959281,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992051669420964,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.11659367606043816,
|
|
"num_tokens": 7535942.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.77218713760376,
|
|
"epoch": 0.372411579003692,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992019528532785,
|
|
"loss": 6.7354,
|
|
"mean_token_accuracy": 0.12092937007546425,
|
|
"num_tokens": 7545506.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.874322080612183,
|
|
"epoch": 0.3729466531114559,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991987322906605,
|
|
"loss": 6.801,
|
|
"mean_token_accuracy": 0.10959522724151612,
|
|
"num_tokens": 7555328.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.811362361907959,
|
|
"epoch": 0.37348172721921985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991955052543357,
|
|
"loss": 6.6899,
|
|
"mean_token_accuracy": 0.1134427696466446,
|
|
"num_tokens": 7565762.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.830954933166504,
|
|
"epoch": 0.3740168013269838,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991922717443972,
|
|
"loss": 6.7216,
|
|
"mean_token_accuracy": 0.12056689336895943,
|
|
"num_tokens": 7575884.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.742701625823974,
|
|
"epoch": 0.3745518754347477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991890317609384,
|
|
"loss": 6.7499,
|
|
"mean_token_accuracy": 0.11369063630700112,
|
|
"num_tokens": 7586100.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.859546327590943,
|
|
"epoch": 0.37508694954251165,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991857853040528,
|
|
"loss": 6.7591,
|
|
"mean_token_accuracy": 0.11486376821994781,
|
|
"num_tokens": 7597137.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.82744083404541,
|
|
"epoch": 0.3756220236502756,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991825323738341,
|
|
"loss": 6.7932,
|
|
"mean_token_accuracy": 0.11721144542098046,
|
|
"num_tokens": 7607640.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.840407514572144,
|
|
"epoch": 0.3761570977580395,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991792729703763,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.1160910353064537,
|
|
"num_tokens": 7618319.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.877895498275757,
|
|
"epoch": 0.3766921718658034,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991760070937734,
|
|
"loss": 6.7208,
|
|
"mean_token_accuracy": 0.11491079404950141,
|
|
"num_tokens": 7628350.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.842350673675537,
|
|
"epoch": 0.3772272459735673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991727347441199,
|
|
"loss": 6.7361,
|
|
"mean_token_accuracy": 0.11011843830347061,
|
|
"num_tokens": 7637857.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.858046007156372,
|
|
"epoch": 0.37776232008133126,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991694559215102,
|
|
"loss": 6.7602,
|
|
"mean_token_accuracy": 0.11095951348543168,
|
|
"num_tokens": 7648242.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.830993270874023,
|
|
"epoch": 0.3782973941890952,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499166170626039,
|
|
"loss": 6.7743,
|
|
"mean_token_accuracy": 0.10925297141075134,
|
|
"num_tokens": 7660565.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.797787475585937,
|
|
"epoch": 0.3788324682968591,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499162878857801,
|
|
"loss": 6.7711,
|
|
"mean_token_accuracy": 0.1141252376139164,
|
|
"num_tokens": 7671600.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.854355716705323,
|
|
"epoch": 0.37936754240462306,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991595806168915,
|
|
"loss": 6.7761,
|
|
"mean_token_accuracy": 0.10867656469345092,
|
|
"num_tokens": 7682453.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.801757192611694,
|
|
"epoch": 0.379902616512387,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991562759034055,
|
|
"loss": 6.7221,
|
|
"mean_token_accuracy": 0.11367509812116623,
|
|
"num_tokens": 7693490.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.828986072540284,
|
|
"epoch": 0.38043769062015087,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991529647174386,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.1118717484176159,
|
|
"num_tokens": 7703478.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.7392528533935545,
|
|
"epoch": 0.3809727647279148,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991496470590864,
|
|
"loss": 6.7761,
|
|
"mean_token_accuracy": 0.1103611208498478,
|
|
"num_tokens": 7714647.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.863647413253784,
|
|
"epoch": 0.38150783883567874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991463229284445,
|
|
"loss": 6.7173,
|
|
"mean_token_accuracy": 0.11717814281582832,
|
|
"num_tokens": 7725528.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.771598768234253,
|
|
"epoch": 0.38204291294344267,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991429923256091,
|
|
"loss": 6.7756,
|
|
"mean_token_accuracy": 0.11080185323953629,
|
|
"num_tokens": 7737708.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.878248071670532,
|
|
"epoch": 0.3825779870512066,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991396552506762,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.11186526715755463,
|
|
"num_tokens": 7749093.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.7422984600067135,
|
|
"epoch": 0.38311306115897054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991363117037423,
|
|
"loss": 6.7004,
|
|
"mean_token_accuracy": 0.11901898533105851,
|
|
"num_tokens": 7760024.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.767995119094849,
|
|
"epoch": 0.38364813526673447,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991329616849039,
|
|
"loss": 6.7284,
|
|
"mean_token_accuracy": 0.11957356333732605,
|
|
"num_tokens": 7770801.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.866620016098023,
|
|
"epoch": 0.38418320937449835,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991296051942578,
|
|
"loss": 6.7847,
|
|
"mean_token_accuracy": 0.1116973415017128,
|
|
"num_tokens": 7782257.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.763524389266967,
|
|
"epoch": 0.3847182834822623,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991262422319008,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.11752377822995186,
|
|
"num_tokens": 7793016.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.7549824714660645,
|
|
"epoch": 0.3852533575900262,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00049912287279793,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.1228921391069889,
|
|
"num_tokens": 7802207.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.812817192077636,
|
|
"epoch": 0.38578843169779015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991194968924429,
|
|
"loss": 6.7834,
|
|
"mean_token_accuracy": 0.11178419142961502,
|
|
"num_tokens": 7813487.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.858286571502686,
|
|
"epoch": 0.3863235058055541,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991161145155367,
|
|
"loss": 6.7563,
|
|
"mean_token_accuracy": 0.11035445258021355,
|
|
"num_tokens": 7824587.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.882280063629151,
|
|
"epoch": 0.386858579913318,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991127256673091,
|
|
"loss": 6.7368,
|
|
"mean_token_accuracy": 0.11012360826134682,
|
|
"num_tokens": 7836240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.753285121917725,
|
|
"epoch": 0.38739365402108195,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991093303478582,
|
|
"loss": 6.6861,
|
|
"mean_token_accuracy": 0.11604151576757431,
|
|
"num_tokens": 7847014.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.788820505142212,
|
|
"epoch": 0.3879287281288458,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991059285572818,
|
|
"loss": 6.807,
|
|
"mean_token_accuracy": 0.11351005062460899,
|
|
"num_tokens": 7857899.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.857131767272949,
|
|
"epoch": 0.38846380223660976,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991025202956781,
|
|
"loss": 6.6902,
|
|
"mean_token_accuracy": 0.11639388576149941,
|
|
"num_tokens": 7868987.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.850029611587525,
|
|
"epoch": 0.3889988763443737,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990991055631457,
|
|
"loss": 6.81,
|
|
"mean_token_accuracy": 0.11189388036727906,
|
|
"num_tokens": 7879547.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.762338304519654,
|
|
"epoch": 0.3895339504521376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990956843597832,
|
|
"loss": 6.6763,
|
|
"mean_token_accuracy": 0.1170013889670372,
|
|
"num_tokens": 7889824.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.673375177383423,
|
|
"epoch": 0.39006902455990156,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990922566856892,
|
|
"loss": 6.669,
|
|
"mean_token_accuracy": 0.11331403329968452,
|
|
"num_tokens": 7901156.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.770735454559326,
|
|
"epoch": 0.3906040986676655,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990888225409629,
|
|
"loss": 6.7076,
|
|
"mean_token_accuracy": 0.11252901628613472,
|
|
"num_tokens": 7911695.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.755655097961426,
|
|
"epoch": 0.3911391727754294,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990853819257033,
|
|
"loss": 6.7026,
|
|
"mean_token_accuracy": 0.11720905601978301,
|
|
"num_tokens": 7923559.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.84619779586792,
|
|
"epoch": 0.3916742468831933,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990819348400097,
|
|
"loss": 6.7214,
|
|
"mean_token_accuracy": 0.11208191886544228,
|
|
"num_tokens": 7935792.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.793423795700074,
|
|
"epoch": 0.39220932099095723,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990784812839818,
|
|
"loss": 6.7092,
|
|
"mean_token_accuracy": 0.1186470128595829,
|
|
"num_tokens": 7946987.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.699849939346313,
|
|
"epoch": 0.39274439509872117,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990750212577192,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.12066235840320587,
|
|
"num_tokens": 7957160.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.781460571289062,
|
|
"epoch": 0.3932794692064851,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990715547613219,
|
|
"loss": 6.7333,
|
|
"mean_token_accuracy": 0.10956480428576469,
|
|
"num_tokens": 7968833.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.873096227645874,
|
|
"epoch": 0.39381454331424903,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990680817948898,
|
|
"loss": 6.7822,
|
|
"mean_token_accuracy": 0.10927629321813584,
|
|
"num_tokens": 7980661.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.861059999465942,
|
|
"epoch": 0.39434961742201297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990646023585234,
|
|
"loss": 6.7065,
|
|
"mean_token_accuracy": 0.11303527727723121,
|
|
"num_tokens": 7992677.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.700655746459961,
|
|
"epoch": 0.3948846915297769,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990611164523231,
|
|
"loss": 6.6919,
|
|
"mean_token_accuracy": 0.1178669311106205,
|
|
"num_tokens": 8002796.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.6995728492736815,
|
|
"epoch": 0.3954197656375408,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990576240763896,
|
|
"loss": 6.7181,
|
|
"mean_token_accuracy": 0.11917829737067223,
|
|
"num_tokens": 8012779.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.79206166267395,
|
|
"epoch": 0.3959548397453047,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990541252308237,
|
|
"loss": 6.6986,
|
|
"mean_token_accuracy": 0.11830845102667809,
|
|
"num_tokens": 8023442.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.777542209625244,
|
|
"epoch": 0.39648991385306864,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990506199157263,
|
|
"loss": 6.7844,
|
|
"mean_token_accuracy": 0.11193263530731201,
|
|
"num_tokens": 8035163.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.826216363906861,
|
|
"epoch": 0.3970249879608326,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990471081311988,
|
|
"loss": 6.7221,
|
|
"mean_token_accuracy": 0.11202551424503326,
|
|
"num_tokens": 8045330.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.826126527786255,
|
|
"epoch": 0.3975600620685965,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990435898773426,
|
|
"loss": 6.7341,
|
|
"mean_token_accuracy": 0.11674164608120918,
|
|
"num_tokens": 8056154.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.795881938934326,
|
|
"epoch": 0.39809513617636044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990400651542592,
|
|
"loss": 6.6916,
|
|
"mean_token_accuracy": 0.1208396390080452,
|
|
"num_tokens": 8066101.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.82635269165039,
|
|
"epoch": 0.3986302102841244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990365339620504,
|
|
"loss": 6.778,
|
|
"mean_token_accuracy": 0.11029551848769188,
|
|
"num_tokens": 8077249.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.791606903076172,
|
|
"epoch": 0.39916528439188825,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499032996300818,
|
|
"loss": 6.7108,
|
|
"mean_token_accuracy": 0.11683286353945732,
|
|
"num_tokens": 8088532.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.7761242389678955,
|
|
"epoch": 0.3997003584996522,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990294521706645,
|
|
"loss": 6.7513,
|
|
"mean_token_accuracy": 0.11043450236320496,
|
|
"num_tokens": 8099541.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.778212356567383,
|
|
"epoch": 0.4002354326074161,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499025901571692,
|
|
"loss": 6.7925,
|
|
"mean_token_accuracy": 0.11460375785827637,
|
|
"num_tokens": 8110532.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.860037422180175,
|
|
"epoch": 0.40077050671518005,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990223445040031,
|
|
"loss": 6.7246,
|
|
"mean_token_accuracy": 0.12051974311470985,
|
|
"num_tokens": 8120991.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.796218538284302,
|
|
"epoch": 0.401305580822944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990187809677004,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.11498752385377883,
|
|
"num_tokens": 8130737.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.687275981903076,
|
|
"epoch": 0.4018406549307079,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990152109628869,
|
|
"loss": 6.6614,
|
|
"mean_token_accuracy": 0.11621819585561752,
|
|
"num_tokens": 8142315.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.747700786590576,
|
|
"epoch": 0.40237572903847185,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990116344896657,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.10932756140828133,
|
|
"num_tokens": 8153618.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.786961269378662,
|
|
"epoch": 0.40291080314623573,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049900805154814,
|
|
"loss": 6.6973,
|
|
"mean_token_accuracy": 0.11853857338428497,
|
|
"num_tokens": 8164304.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.784421157836914,
|
|
"epoch": 0.40344587725399966,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990044621384134,
|
|
"loss": 6.694,
|
|
"mean_token_accuracy": 0.11464422270655632,
|
|
"num_tokens": 8175289.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.834812927246094,
|
|
"epoch": 0.4039809513617636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990008662605893,
|
|
"loss": 6.7375,
|
|
"mean_token_accuracy": 0.11080463156104088,
|
|
"num_tokens": 8186274.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.850270223617554,
|
|
"epoch": 0.40451602546952753,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989972639147717,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.11826486811041832,
|
|
"num_tokens": 8196380.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.745476388931275,
|
|
"epoch": 0.40505109957729146,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989936551010646,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.11468399837613105,
|
|
"num_tokens": 8207204.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.715826034545898,
|
|
"epoch": 0.4055861736850554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989900398195722,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.11534782201051712,
|
|
"num_tokens": 8217745.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.774829626083374,
|
|
"epoch": 0.40612124779281933,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989864180703988,
|
|
"loss": 6.6424,
|
|
"mean_token_accuracy": 0.11919590383768082,
|
|
"num_tokens": 8228171.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.758113431930542,
|
|
"epoch": 0.4066563219005832,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989827898536491,
|
|
"loss": 6.6973,
|
|
"mean_token_accuracy": 0.11042807400226592,
|
|
"num_tokens": 8239220.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.832132291793823,
|
|
"epoch": 0.40719139600834714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989791551694279,
|
|
"loss": 6.7518,
|
|
"mean_token_accuracy": 0.109524205327034,
|
|
"num_tokens": 8250363.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.776221656799317,
|
|
"epoch": 0.4077264701161111,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989755140178398,
|
|
"loss": 6.7123,
|
|
"mean_token_accuracy": 0.11326616704463958,
|
|
"num_tokens": 8261207.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.741102790832519,
|
|
"epoch": 0.408261544223875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989718663989905,
|
|
"loss": 6.6174,
|
|
"mean_token_accuracy": 0.11389720663428307,
|
|
"num_tokens": 8272343.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.711847400665283,
|
|
"epoch": 0.40879661833163894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989682123129849,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.11849249228835106,
|
|
"num_tokens": 8282677.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.69567084312439,
|
|
"epoch": 0.40933169243940287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989645517599286,
|
|
"loss": 6.6745,
|
|
"mean_token_accuracy": 0.11427896246314048,
|
|
"num_tokens": 8292753.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.774503755569458,
|
|
"epoch": 0.4098667665471668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989608847399275,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.11602176800370216,
|
|
"num_tokens": 8302747.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.774828100204468,
|
|
"epoch": 0.4104018406549307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989572112530871,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.10802446901798249,
|
|
"num_tokens": 8314766.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.862928152084351,
|
|
"epoch": 0.4109369147626946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989535312995139,
|
|
"loss": 6.7682,
|
|
"mean_token_accuracy": 0.11004860624670983,
|
|
"num_tokens": 8325791.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.746032285690307,
|
|
"epoch": 0.41147198887045855,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989498448793139,
|
|
"loss": 6.6939,
|
|
"mean_token_accuracy": 0.11601744443178177,
|
|
"num_tokens": 8335809.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.742163610458374,
|
|
"epoch": 0.4120070629782225,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989461519925935,
|
|
"loss": 6.6923,
|
|
"mean_token_accuracy": 0.11100121140480042,
|
|
"num_tokens": 8347505.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.8387268543243405,
|
|
"epoch": 0.4125421370859864,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989424526394596,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.1083609253168106,
|
|
"num_tokens": 8358363.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.726605081558228,
|
|
"epoch": 0.41307721119375035,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989387468200187,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.1165882483124733,
|
|
"num_tokens": 8369076.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.849684762954712,
|
|
"epoch": 0.4136122853015143,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498935034534378,
|
|
"loss": 6.7567,
|
|
"mean_token_accuracy": 0.11488589569926262,
|
|
"num_tokens": 8380071.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.779253625869751,
|
|
"epoch": 0.41414735940927816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989313157826446,
|
|
"loss": 6.7043,
|
|
"mean_token_accuracy": 0.11365948691964149,
|
|
"num_tokens": 8390574.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.762129831314087,
|
|
"epoch": 0.4146824335170421,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498927590564926,
|
|
"loss": 6.7016,
|
|
"mean_token_accuracy": 0.11860018000006675,
|
|
"num_tokens": 8401154.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.805259132385254,
|
|
"epoch": 0.415217507624806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989238588813296,
|
|
"loss": 6.7816,
|
|
"mean_token_accuracy": 0.10864789858460426,
|
|
"num_tokens": 8412113.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.893309640884399,
|
|
"epoch": 0.41575258173256996,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989201207319634,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.11186528205871582,
|
|
"num_tokens": 8422734.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.758945322036743,
|
|
"epoch": 0.4162876558403339,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989163761169351,
|
|
"loss": 6.6912,
|
|
"mean_token_accuracy": 0.11084168404340744,
|
|
"num_tokens": 8433647.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.744187116622925,
|
|
"epoch": 0.4168227299480978,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989126250363529,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.11423909962177277,
|
|
"num_tokens": 8444726.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.83604621887207,
|
|
"epoch": 0.41735780405586176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989088674903251,
|
|
"loss": 6.7264,
|
|
"mean_token_accuracy": 0.11136697009205818,
|
|
"num_tokens": 8455351.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.788657855987549,
|
|
"epoch": 0.41789287816362564,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989051034789602,
|
|
"loss": 6.7073,
|
|
"mean_token_accuracy": 0.11919761151075363,
|
|
"num_tokens": 8466423.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.769079303741455,
|
|
"epoch": 0.41842795227138957,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498901333002367,
|
|
"loss": 6.6522,
|
|
"mean_token_accuracy": 0.11701465100049972,
|
|
"num_tokens": 8475841.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.814233303070068,
|
|
"epoch": 0.4189630263791535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988975560606541,
|
|
"loss": 6.762,
|
|
"mean_token_accuracy": 0.11229455918073654,
|
|
"num_tokens": 8487656.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.776022148132324,
|
|
"epoch": 0.41949810048691744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988937726539308,
|
|
"loss": 6.7744,
|
|
"mean_token_accuracy": 0.10670395717024803,
|
|
"num_tokens": 8497959.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.763610315322876,
|
|
"epoch": 0.42003317459468137,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988899827823062,
|
|
"loss": 6.6751,
|
|
"mean_token_accuracy": 0.11493971273303032,
|
|
"num_tokens": 8508228.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.782846927642822,
|
|
"epoch": 0.4205682487024453,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049888618644589,
|
|
"loss": 6.7229,
|
|
"mean_token_accuracy": 0.11063806042075157,
|
|
"num_tokens": 8518999.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.691450452804565,
|
|
"epoch": 0.42110332281020924,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004988823836447916,
|
|
"loss": 6.7519,
|
|
"mean_token_accuracy": 0.11179999187588692,
|
|
"num_tokens": 8529583.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.894530963897705,
|
|
"epoch": 0.4216383969179731,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988785743791207,
|
|
"loss": 6.8223,
|
|
"mean_token_accuracy": 0.10763506144285202,
|
|
"num_tokens": 8540069.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.875021266937256,
|
|
"epoch": 0.42217347102573705,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988747586489876,
|
|
"loss": 6.7009,
|
|
"mean_token_accuracy": 0.11498932242393493,
|
|
"num_tokens": 8550441.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.709805822372436,
|
|
"epoch": 0.422708545133501,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498870936454502,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.11834602132439613,
|
|
"num_tokens": 8560257.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.828940343856812,
|
|
"epoch": 0.4232436192412649,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988671077957749,
|
|
"loss": 6.7485,
|
|
"mean_token_accuracy": 0.1175241857767105,
|
|
"num_tokens": 8570991.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.891437435150147,
|
|
"epoch": 0.42377869334902885,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004988632726729164,
|
|
"loss": 6.8051,
|
|
"mean_token_accuracy": 0.10697821751236916,
|
|
"num_tokens": 8583668.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.802229166030884,
|
|
"epoch": 0.4243137674567928,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988594310860374,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.1156295083463192,
|
|
"num_tokens": 8593727.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.714612770080566,
|
|
"epoch": 0.4248488415645567,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988555830352485,
|
|
"loss": 6.7209,
|
|
"mean_token_accuracy": 0.11398242264986039,
|
|
"num_tokens": 8605470.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.7963508605957035,
|
|
"epoch": 0.4253839156723206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988517285206614,
|
|
"loss": 6.6687,
|
|
"mean_token_accuracy": 0.11099848076701165,
|
|
"num_tokens": 8617176.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.803634119033814,
|
|
"epoch": 0.4259189897800845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988478675423871,
|
|
"loss": 6.7558,
|
|
"mean_token_accuracy": 0.11225240230560303,
|
|
"num_tokens": 8627756.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.793984985351562,
|
|
"epoch": 0.42645406388784846,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988440001005369,
|
|
"loss": 6.6853,
|
|
"mean_token_accuracy": 0.11842627823352814,
|
|
"num_tokens": 8637766.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.800572538375855,
|
|
"epoch": 0.4269891379956124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988401261952227,
|
|
"loss": 6.7096,
|
|
"mean_token_accuracy": 0.11486690863966942,
|
|
"num_tokens": 8648562.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.808977746963501,
|
|
"epoch": 0.4275242121033763,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988362458265565,
|
|
"loss": 6.7412,
|
|
"mean_token_accuracy": 0.10799469202756881,
|
|
"num_tokens": 8658393.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.730482482910157,
|
|
"epoch": 0.42805928621114026,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988323589946499,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.1162540040910244,
|
|
"num_tokens": 8668365.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.777298212051392,
|
|
"epoch": 0.4285943603189042,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988284656996156,
|
|
"loss": 6.7009,
|
|
"mean_token_accuracy": 0.1099359154701233,
|
|
"num_tokens": 8679228.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.780287981033325,
|
|
"epoch": 0.42912943442666807,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988245659415656,
|
|
"loss": 6.5866,
|
|
"mean_token_accuracy": 0.12446512654423714,
|
|
"num_tokens": 8688940.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.810698747634888,
|
|
"epoch": 0.429664508534432,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988206597206129,
|
|
"loss": 6.7438,
|
|
"mean_token_accuracy": 0.10872282534837723,
|
|
"num_tokens": 8699923.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.720220708847046,
|
|
"epoch": 0.43019958264219593,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049881674703687,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.12176239043474198,
|
|
"num_tokens": 8710445.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.721858978271484,
|
|
"epoch": 0.43073465674995987,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988128278904499,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.11447286382317542,
|
|
"num_tokens": 8720686.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.834508752822876,
|
|
"epoch": 0.4312697308577238,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498808902281466,
|
|
"loss": 6.7282,
|
|
"mean_token_accuracy": 0.11510429829359055,
|
|
"num_tokens": 8732122.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.744071006774902,
|
|
"epoch": 0.43180480496548773,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988049702100315,
|
|
"loss": 6.6825,
|
|
"mean_token_accuracy": 0.1182553879916668,
|
|
"num_tokens": 8744122.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.787398195266723,
|
|
"epoch": 0.43233987907325166,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988010316762598,
|
|
"loss": 6.6911,
|
|
"mean_token_accuracy": 0.115293999761343,
|
|
"num_tokens": 8754758.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.7287671089172365,
|
|
"epoch": 0.4328749531810156,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987970866802649,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.10785665214061738,
|
|
"num_tokens": 8766577.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.773381233215332,
|
|
"epoch": 0.4334100272887795,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987931352221605,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.11141579747200012,
|
|
"num_tokens": 8777698.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.788628673553466,
|
|
"epoch": 0.4339451013965434,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987891773020606,
|
|
"loss": 6.7231,
|
|
"mean_token_accuracy": 0.11151274070143699,
|
|
"num_tokens": 8788637.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.799765920639038,
|
|
"epoch": 0.43448017550430734,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987852129200799,
|
|
"loss": 6.7009,
|
|
"mean_token_accuracy": 0.11956919953227044,
|
|
"num_tokens": 8799709.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.795716381072998,
|
|
"epoch": 0.4350152496120713,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987812420763326,
|
|
"loss": 6.6905,
|
|
"mean_token_accuracy": 0.11553208827972412,
|
|
"num_tokens": 8810469.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.7736915111541744,
|
|
"epoch": 0.4355503237198352,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987772647709333,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.1123408019542694,
|
|
"num_tokens": 8821142.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.70412278175354,
|
|
"epoch": 0.43608539782759914,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498773281003997,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.12270026281476021,
|
|
"num_tokens": 8832951.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.725498294830322,
|
|
"epoch": 0.4366204719353631,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987692907756385,
|
|
"loss": 6.7344,
|
|
"mean_token_accuracy": 0.10939609631896019,
|
|
"num_tokens": 8843579.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.6969774723052975,
|
|
"epoch": 0.43715554604312695,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987652940859733,
|
|
"loss": 6.6606,
|
|
"mean_token_accuracy": 0.10758041813969613,
|
|
"num_tokens": 8854612.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.766866064071655,
|
|
"epoch": 0.4376906201508909,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987612909351167,
|
|
"loss": 6.6101,
|
|
"mean_token_accuracy": 0.12067801505327225,
|
|
"num_tokens": 8865584.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.688352346420288,
|
|
"epoch": 0.4382256942586548,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987572813231842,
|
|
"loss": 6.66,
|
|
"mean_token_accuracy": 0.12287814989686012,
|
|
"num_tokens": 8876662.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.756010103225708,
|
|
"epoch": 0.43876076836641875,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987532652502917,
|
|
"loss": 6.6831,
|
|
"mean_token_accuracy": 0.11270663142204285,
|
|
"num_tokens": 8887249.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.713475131988526,
|
|
"epoch": 0.4392958424741827,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987492427165551,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.1301178902387619,
|
|
"num_tokens": 8898635.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.678007888793945,
|
|
"epoch": 0.4398309165819466,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987452137220906,
|
|
"loss": 6.6895,
|
|
"mean_token_accuracy": 0.11399767398834229,
|
|
"num_tokens": 8908794.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.847482490539551,
|
|
"epoch": 0.44036599068971055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987411782670144,
|
|
"loss": 6.7013,
|
|
"mean_token_accuracy": 0.10850507244467736,
|
|
"num_tokens": 8919015.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.8152250289917,
|
|
"epoch": 0.44090106479747443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987371363514431,
|
|
"loss": 6.7349,
|
|
"mean_token_accuracy": 0.10842297747731208,
|
|
"num_tokens": 8929028.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.664592504501343,
|
|
"epoch": 0.44143613890523836,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987330879754933,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.11036456525325775,
|
|
"num_tokens": 8939789.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.707959175109863,
|
|
"epoch": 0.4419712130130023,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987290331392823,
|
|
"loss": 6.6225,
|
|
"mean_token_accuracy": 0.11801224276423454,
|
|
"num_tokens": 8950657.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.828504610061645,
|
|
"epoch": 0.44250628712076623,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987249718429269,
|
|
"loss": 6.7236,
|
|
"mean_token_accuracy": 0.11803532913327217,
|
|
"num_tokens": 8960744.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.705205869674683,
|
|
"epoch": 0.44304136122853016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987209040865441,
|
|
"loss": 6.5768,
|
|
"mean_token_accuracy": 0.12112260162830353,
|
|
"num_tokens": 8972411.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.801696109771728,
|
|
"epoch": 0.4435764353362941,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987168298702519,
|
|
"loss": 6.7465,
|
|
"mean_token_accuracy": 0.11419489085674286,
|
|
"num_tokens": 8982818.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.745963048934937,
|
|
"epoch": 0.44411150944405803,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004987127491941675,
|
|
"loss": 6.6657,
|
|
"mean_token_accuracy": 0.1177960142493248,
|
|
"num_tokens": 8993227.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.669366073608399,
|
|
"epoch": 0.4446465835518219,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987086620584091,
|
|
"loss": 6.6037,
|
|
"mean_token_accuracy": 0.11799841225147248,
|
|
"num_tokens": 9003796.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.772842884063721,
|
|
"epoch": 0.44518165765958584,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987045684630944,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.12047947198152542,
|
|
"num_tokens": 9014931.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.774410676956177,
|
|
"epoch": 0.44571673176734977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987004684083417,
|
|
"loss": 6.6984,
|
|
"mean_token_accuracy": 0.1164324201643467,
|
|
"num_tokens": 9025312.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.7285847663879395,
|
|
"epoch": 0.4462518058751137,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986963618942694,
|
|
"loss": 6.6642,
|
|
"mean_token_accuracy": 0.12318786159157753,
|
|
"num_tokens": 9035563.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.795755052566529,
|
|
"epoch": 0.44678687998287764,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004986922489209961,
|
|
"loss": 6.7039,
|
|
"mean_token_accuracy": 0.1175026074051857,
|
|
"num_tokens": 9046065.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.751359653472901,
|
|
"epoch": 0.44732195409064157,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986881294886406,
|
|
"loss": 6.6057,
|
|
"mean_token_accuracy": 0.1231963075697422,
|
|
"num_tokens": 9056696.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.676720142364502,
|
|
"epoch": 0.4478570281984055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986840035973218,
|
|
"loss": 6.6808,
|
|
"mean_token_accuracy": 0.11223538517951966,
|
|
"num_tokens": 9067035.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.6606361865997314,
|
|
"epoch": 0.4483921023061694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986798712471588,
|
|
"loss": 6.6574,
|
|
"mean_token_accuracy": 0.11127996742725373,
|
|
"num_tokens": 9078253.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.8346106052398685,
|
|
"epoch": 0.4489271764139333,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986757324382709,
|
|
"loss": 6.7174,
|
|
"mean_token_accuracy": 0.10800155103206635,
|
|
"num_tokens": 9088184.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.7804230690002445,
|
|
"epoch": 0.44946225052169725,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986715871707777,
|
|
"loss": 6.7777,
|
|
"mean_token_accuracy": 0.1087512344121933,
|
|
"num_tokens": 9099321.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.843128871917725,
|
|
"epoch": 0.4499973246294612,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986674354447988,
|
|
"loss": 6.8009,
|
|
"mean_token_accuracy": 0.11305928155779839,
|
|
"num_tokens": 9111410.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.831840133666992,
|
|
"epoch": 0.4505323987372251,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986632772604543,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.11788237541913986,
|
|
"num_tokens": 9121932.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.651640558242798,
|
|
"epoch": 0.45106747284498905,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004986591126178639,
|
|
"loss": 6.7181,
|
|
"mean_token_accuracy": 0.1195308357477188,
|
|
"num_tokens": 9132686.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.678121089935303,
|
|
"epoch": 0.451602546952753,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986549415171482,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.11687054708600045,
|
|
"num_tokens": 9143582.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.877950763702392,
|
|
"epoch": 0.45213762106051686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986507639584274,
|
|
"loss": 6.7232,
|
|
"mean_token_accuracy": 0.11007717251777649,
|
|
"num_tokens": 9156173.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.7473616123199465,
|
|
"epoch": 0.4526726951682808,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986465799418223,
|
|
"loss": 6.7062,
|
|
"mean_token_accuracy": 0.11616904065012931,
|
|
"num_tokens": 9166882.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.726114082336426,
|
|
"epoch": 0.4532077692760447,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986423894674534,
|
|
"loss": 6.7034,
|
|
"mean_token_accuracy": 0.11051197499036788,
|
|
"num_tokens": 9177525.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.824288320541382,
|
|
"epoch": 0.45374284338380866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986381925354422,
|
|
"loss": 6.6713,
|
|
"mean_token_accuracy": 0.11391364932060241,
|
|
"num_tokens": 9188586.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.741261911392212,
|
|
"epoch": 0.4542779174915726,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986339891459094,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.11786932200193405,
|
|
"num_tokens": 9199920.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.590327644348145,
|
|
"epoch": 0.4548129915993365,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986297792989768,
|
|
"loss": 6.583,
|
|
"mean_token_accuracy": 0.12098821178078652,
|
|
"num_tokens": 9210923.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.832316637039185,
|
|
"epoch": 0.45534806570710046,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986255629947655,
|
|
"loss": 6.7539,
|
|
"mean_token_accuracy": 0.10964171513915062,
|
|
"num_tokens": 9221459.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.773038291931153,
|
|
"epoch": 0.45588313981486434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986213402333978,
|
|
"loss": 6.6935,
|
|
"mean_token_accuracy": 0.11024248600006104,
|
|
"num_tokens": 9231768.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.713382816314697,
|
|
"epoch": 0.45641821392262827,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986171110149951,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.11179919168353081,
|
|
"num_tokens": 9242230.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.807206058502198,
|
|
"epoch": 0.4569532880303922,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986128753396798,
|
|
"loss": 6.5794,
|
|
"mean_token_accuracy": 0.1219303086400032,
|
|
"num_tokens": 9252485.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.657087945938111,
|
|
"epoch": 0.45748836213815613,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004986086332075742,
|
|
"loss": 6.6527,
|
|
"mean_token_accuracy": 0.12027468383312226,
|
|
"num_tokens": 9263014.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.737786865234375,
|
|
"epoch": 0.45802343624592007,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986043846188006,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.12059752494096757,
|
|
"num_tokens": 9273777.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.658463954925537,
|
|
"epoch": 0.458558510353684,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498600129573482,
|
|
"loss": 6.6266,
|
|
"mean_token_accuracy": 0.11395588889718056,
|
|
"num_tokens": 9284738.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.793663120269775,
|
|
"epoch": 0.45909358446144793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498595868071741,
|
|
"loss": 6.6807,
|
|
"mean_token_accuracy": 0.11528572961688041,
|
|
"num_tokens": 9295921.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.744870233535766,
|
|
"epoch": 0.4596286585692118,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985916001137006,
|
|
"loss": 6.6609,
|
|
"mean_token_accuracy": 0.11062274277210235,
|
|
"num_tokens": 9306568.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.757999467849731,
|
|
"epoch": 0.46016373267697575,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985873256994843,
|
|
"loss": 6.6262,
|
|
"mean_token_accuracy": 0.11653959006071091,
|
|
"num_tokens": 9316468.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.737951755523682,
|
|
"epoch": 0.4606988067847397,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985830448292154,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.1143273763358593,
|
|
"num_tokens": 9328185.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.743026876449585,
|
|
"epoch": 0.4612338808925036,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985787575030175,
|
|
"loss": 6.6547,
|
|
"mean_token_accuracy": 0.11528828516602516,
|
|
"num_tokens": 9338591.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.768393468856812,
|
|
"epoch": 0.46176895500026754,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985744637210144,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.11174369007349014,
|
|
"num_tokens": 9349286.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.783293533325195,
|
|
"epoch": 0.4623040291080315,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00049857016348333,
|
|
"loss": 6.658,
|
|
"mean_token_accuracy": 0.11993650272488594,
|
|
"num_tokens": 9359752.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.78243350982666,
|
|
"epoch": 0.4628391032157954,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985658567900886,
|
|
"loss": 6.7129,
|
|
"mean_token_accuracy": 0.1122040569782257,
|
|
"num_tokens": 9371823.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.643386602401733,
|
|
"epoch": 0.4633741773235593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985615436414145,
|
|
"loss": 6.5839,
|
|
"mean_token_accuracy": 0.11392313092947007,
|
|
"num_tokens": 9383127.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.734666919708252,
|
|
"epoch": 0.4639092514313232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985572240374321,
|
|
"loss": 6.6771,
|
|
"mean_token_accuracy": 0.11793937757611275,
|
|
"num_tokens": 9394296.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.754271030426025,
|
|
"epoch": 0.46444432553908715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985528979782665,
|
|
"loss": 6.6688,
|
|
"mean_token_accuracy": 0.11072949096560478,
|
|
"num_tokens": 9405988.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.822707033157348,
|
|
"epoch": 0.4649793996468511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985485654640423,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.1139429748058319,
|
|
"num_tokens": 9417479.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.696816492080688,
|
|
"epoch": 0.465514473754615,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985442264948847,
|
|
"loss": 6.6197,
|
|
"mean_token_accuracy": 0.11986967846751213,
|
|
"num_tokens": 9428050.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.653148794174195,
|
|
"epoch": 0.46604954786237895,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985398810709189,
|
|
"loss": 6.5722,
|
|
"mean_token_accuracy": 0.12251258864998818,
|
|
"num_tokens": 9438229.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.654054975509643,
|
|
"epoch": 0.4665846219701429,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985355291922704,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.11258513107895851,
|
|
"num_tokens": 9449611.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.709498739242553,
|
|
"epoch": 0.46711969607790677,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000498531170859065,
|
|
"loss": 6.614,
|
|
"mean_token_accuracy": 0.11630048006772994,
|
|
"num_tokens": 9460234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.828418874740601,
|
|
"epoch": 0.4676547701856707,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004985268060714285,
|
|
"loss": 6.7023,
|
|
"mean_token_accuracy": 0.1152671605348587,
|
|
"num_tokens": 9472136.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.6818465232849125,
|
|
"epoch": 0.46818984429343463,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985224348294868,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.12047104090452194,
|
|
"num_tokens": 9482602.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.785189914703369,
|
|
"epoch": 0.46872491840119856,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985180571333663,
|
|
"loss": 6.6442,
|
|
"mean_token_accuracy": 0.11965756639838218,
|
|
"num_tokens": 9493782.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.763046312332153,
|
|
"epoch": 0.4692599925089625,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004985136729831932,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.11808878481388092,
|
|
"num_tokens": 9504389.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.648394393920898,
|
|
"epoch": 0.46979506661672643,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004985092823790942,
|
|
"loss": 6.7447,
|
|
"mean_token_accuracy": 0.1183752790093422,
|
|
"num_tokens": 9515166.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.747145318984986,
|
|
"epoch": 0.47033014072449036,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985048853211961,
|
|
"loss": 6.6434,
|
|
"mean_token_accuracy": 0.116434495896101,
|
|
"num_tokens": 9525566.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.7929564952850345,
|
|
"epoch": 0.47086521483225424,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498500481809626,
|
|
"loss": 6.5549,
|
|
"mean_token_accuracy": 0.1208685427904129,
|
|
"num_tokens": 9536021.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.649615907669068,
|
|
"epoch": 0.4714002889400182,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004984960718445107,
|
|
"loss": 6.6641,
|
|
"mean_token_accuracy": 0.11327528953552246,
|
|
"num_tokens": 9546827.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.756602811813354,
|
|
"epoch": 0.4719353630477821,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984916554259778,
|
|
"loss": 6.7758,
|
|
"mean_token_accuracy": 0.10899243578314781,
|
|
"num_tokens": 9558104.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.866197681427002,
|
|
"epoch": 0.47247043715554604,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984872325541547,
|
|
"loss": 6.668,
|
|
"mean_token_accuracy": 0.11704885140061379,
|
|
"num_tokens": 9568487.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.716640186309815,
|
|
"epoch": 0.47300551126331,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984828032291692,
|
|
"loss": 6.6107,
|
|
"mean_token_accuracy": 0.12084364518523216,
|
|
"num_tokens": 9579509.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.742200565338135,
|
|
"epoch": 0.4735405853710739,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004984783674511492,
|
|
"loss": 6.64,
|
|
"mean_token_accuracy": 0.1198382891714573,
|
|
"num_tokens": 9589931.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.761376428604126,
|
|
"epoch": 0.47407565947883784,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984739252202227,
|
|
"loss": 6.6733,
|
|
"mean_token_accuracy": 0.11940053328871728,
|
|
"num_tokens": 9599764.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.7573480129241945,
|
|
"epoch": 0.4746107335866017,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498469476536518,
|
|
"loss": 6.6472,
|
|
"mean_token_accuracy": 0.1184098556637764,
|
|
"num_tokens": 9611145.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.6948751449584964,
|
|
"epoch": 0.47514580769436565,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984650214001636,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.12355822175741196,
|
|
"num_tokens": 9621441.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.741222667694092,
|
|
"epoch": 0.4756808818021296,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004984605598112881,
|
|
"loss": 6.6857,
|
|
"mean_token_accuracy": 0.12146021127700805,
|
|
"num_tokens": 9631874.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.717041254043579,
|
|
"epoch": 0.4762159559098935,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984560917700204,
|
|
"loss": 6.6614,
|
|
"mean_token_accuracy": 0.11106858849525451,
|
|
"num_tokens": 9643006.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.698492193222046,
|
|
"epoch": 0.47675103001765745,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984516172764894,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.12116582468152046,
|
|
"num_tokens": 9653897.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.691738748550415,
|
|
"epoch": 0.4772861041254214,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984471363308243,
|
|
"loss": 6.6263,
|
|
"mean_token_accuracy": 0.1176533468067646,
|
|
"num_tokens": 9664460.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.711106204986573,
|
|
"epoch": 0.4778211782331853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984426489331546,
|
|
"loss": 6.6385,
|
|
"mean_token_accuracy": 0.12148366495966911,
|
|
"num_tokens": 9674534.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.8625555515289305,
|
|
"epoch": 0.4783562523409492,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984381550836097,
|
|
"loss": 6.732,
|
|
"mean_token_accuracy": 0.11358912587165833,
|
|
"num_tokens": 9684828.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.851891565322876,
|
|
"epoch": 0.47889132644871313,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004984336547823196,
|
|
"loss": 6.6838,
|
|
"mean_token_accuracy": 0.11679960638284684,
|
|
"num_tokens": 9694536.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.712016582489014,
|
|
"epoch": 0.47942640055647706,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498429148029414,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.12640432715415956,
|
|
"num_tokens": 9705715.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.654127883911133,
|
|
"epoch": 0.479961474664241,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984246348250233,
|
|
"loss": 6.6293,
|
|
"mean_token_accuracy": 0.12291777729988099,
|
|
"num_tokens": 9717505.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.698559045791626,
|
|
"epoch": 0.4804965487720049,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984201151692775,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.11582913845777512,
|
|
"num_tokens": 9727910.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.681623268127441,
|
|
"epoch": 0.48103162287976886,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984155890623074,
|
|
"loss": 6.6164,
|
|
"mean_token_accuracy": 0.12003767117857933,
|
|
"num_tokens": 9738528.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.688356590270996,
|
|
"epoch": 0.4815666969875328,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984110565042435,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.11511807218194008,
|
|
"num_tokens": 9749744.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.787782335281372,
|
|
"epoch": 0.48210177109529667,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984065174952168,
|
|
"loss": 6.6415,
|
|
"mean_token_accuracy": 0.11788514703512191,
|
|
"num_tokens": 9759968.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.7138995170593265,
|
|
"epoch": 0.4826368452030606,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004984019720353582,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.11984834149479866,
|
|
"num_tokens": 9769791.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.669849443435669,
|
|
"epoch": 0.48317191931082454,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983974201247991,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.12382967993617058,
|
|
"num_tokens": 9780369.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.718169641494751,
|
|
"epoch": 0.48370699341858847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983928617636709,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.11595848128199578,
|
|
"num_tokens": 9791125.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.822065162658691,
|
|
"epoch": 0.4842420675263524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983882969521052,
|
|
"loss": 6.6623,
|
|
"mean_token_accuracy": 0.11691764071583748,
|
|
"num_tokens": 9801697.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.784085750579834,
|
|
"epoch": 0.48477714163411634,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983837256902338,
|
|
"loss": 6.7085,
|
|
"mean_token_accuracy": 0.1206382617354393,
|
|
"num_tokens": 9812171.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.700609016418457,
|
|
"epoch": 0.48531221574188027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983791479781887,
|
|
"loss": 6.5452,
|
|
"mean_token_accuracy": 0.12644470036029815,
|
|
"num_tokens": 9821596.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.76994104385376,
|
|
"epoch": 0.48584728984964415,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983745638161021,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.10886719152331352,
|
|
"num_tokens": 9831634.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.702042055130005,
|
|
"epoch": 0.4863823639574081,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983699732041064,
|
|
"loss": 6.6297,
|
|
"mean_token_accuracy": 0.12174258530139923,
|
|
"num_tokens": 9841662.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.773559427261352,
|
|
"epoch": 0.486917438065172,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498365376142334,
|
|
"loss": 6.618,
|
|
"mean_token_accuracy": 0.11437310129404069,
|
|
"num_tokens": 9853797.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.712430953979492,
|
|
"epoch": 0.48745251217293595,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983607726309179,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.1182169571518898,
|
|
"num_tokens": 9865245.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.814268589019775,
|
|
"epoch": 0.4879875862806999,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983561626699908,
|
|
"loss": 6.7454,
|
|
"mean_token_accuracy": 0.10475116744637489,
|
|
"num_tokens": 9876207.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.760530710220337,
|
|
"epoch": 0.4885226603884638,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983515462596859,
|
|
"loss": 6.5712,
|
|
"mean_token_accuracy": 0.12076753973960877,
|
|
"num_tokens": 9887210.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.743468475341797,
|
|
"epoch": 0.48905773449622775,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983469234001365,
|
|
"loss": 6.746,
|
|
"mean_token_accuracy": 0.11424284428358078,
|
|
"num_tokens": 9899607.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.662120580673218,
|
|
"epoch": 0.4895928086039917,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498342294091476,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.1255207620561123,
|
|
"num_tokens": 9909910.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.648574686050415,
|
|
"epoch": 0.49012788271175556,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983376583338382,
|
|
"loss": 6.6563,
|
|
"mean_token_accuracy": 0.11490331664681434,
|
|
"num_tokens": 9922137.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.735975837707519,
|
|
"epoch": 0.4906629568195195,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983330161273569,
|
|
"loss": 6.6451,
|
|
"mean_token_accuracy": 0.11815119236707687,
|
|
"num_tokens": 9932514.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.717578268051147,
|
|
"epoch": 0.4911980309272834,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004983283674721662,
|
|
"loss": 6.6847,
|
|
"mean_token_accuracy": 0.11441330313682556,
|
|
"num_tokens": 9943054.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.8306371688842775,
|
|
"epoch": 0.49173310503504736,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983237123684002,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.11424371600151062,
|
|
"num_tokens": 9953791.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.725871992111206,
|
|
"epoch": 0.4922681791428113,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983190508161934,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.1176756463944912,
|
|
"num_tokens": 9964782.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.776705169677735,
|
|
"epoch": 0.4928032532505752,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004983143828156804,
|
|
"loss": 6.6759,
|
|
"mean_token_accuracy": 0.1201729841530323,
|
|
"num_tokens": 9975843.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.766890525817871,
|
|
"epoch": 0.49333832735833916,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004983097083669959,
|
|
"loss": 6.6515,
|
|
"mean_token_accuracy": 0.12076375931501389,
|
|
"num_tokens": 9987060.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.729199981689453,
|
|
"epoch": 0.49387340146610303,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983050274702751,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.11678859367966651,
|
|
"num_tokens": 9997380.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.704911518096924,
|
|
"epoch": 0.49440847557386697,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983003401256529,
|
|
"loss": 6.6666,
|
|
"mean_token_accuracy": 0.11961752027273179,
|
|
"num_tokens": 10007955.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.858521175384522,
|
|
"epoch": 0.4949435496816309,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982956463332647,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.11539428681135178,
|
|
"num_tokens": 10017645.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.7818702220916744,
|
|
"epoch": 0.49547862378939483,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004982909460932463,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.11978099420666695,
|
|
"num_tokens": 10027619.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.654353475570678,
|
|
"epoch": 0.49601369789715877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498286239405733,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.12450932785868644,
|
|
"num_tokens": 10037551.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.672497034072876,
|
|
"epoch": 0.4965487720049227,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498281526270861,
|
|
"loss": 6.5851,
|
|
"mean_token_accuracy": 0.13364579305052757,
|
|
"num_tokens": 10047771.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.803449487686157,
|
|
"epoch": 0.49708384611268663,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982768066887663,
|
|
"loss": 6.7076,
|
|
"mean_token_accuracy": 0.112837415933609,
|
|
"num_tokens": 10058771.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.723805093765259,
|
|
"epoch": 0.4976189202204505,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982720806595851,
|
|
"loss": 6.5841,
|
|
"mean_token_accuracy": 0.12232825830578804,
|
|
"num_tokens": 10070318.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.68502402305603,
|
|
"epoch": 0.49815399432821444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982673481834541,
|
|
"loss": 6.614,
|
|
"mean_token_accuracy": 0.11796658039093018,
|
|
"num_tokens": 10081810.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.6698534965515135,
|
|
"epoch": 0.4986890684359784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982626092605097,
|
|
"loss": 6.6297,
|
|
"mean_token_accuracy": 0.11533761844038963,
|
|
"num_tokens": 10091724.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.763433408737183,
|
|
"epoch": 0.4992241425437423,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982578638908888,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.11898914724588394,
|
|
"num_tokens": 10102510.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.755692815780639,
|
|
"epoch": 0.49975921665150624,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982531120747286,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.11363844275474548,
|
|
"num_tokens": 10112636.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.679724454879761,
|
|
"epoch": 0.5002942907592701,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000498248353812166,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.11922202631831169,
|
|
"num_tokens": 10123562.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.720367956161499,
|
|
"epoch": 0.5008293648670341,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982435891033387,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.11208936050534249,
|
|
"num_tokens": 10134731.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.773916530609131,
|
|
"epoch": 0.501364438974798,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498238817948384,
|
|
"loss": 6.6307,
|
|
"mean_token_accuracy": 0.11377799212932586,
|
|
"num_tokens": 10145232.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.715243864059448,
|
|
"epoch": 0.501899513082562,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982340403474398,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.11478810831904411,
|
|
"num_tokens": 10155857.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.7384484767913815,
|
|
"epoch": 0.5024345871903259,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004982292563006441,
|
|
"loss": 6.6107,
|
|
"mean_token_accuracy": 0.12016694247722626,
|
|
"num_tokens": 10166145.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.8165631771087645,
|
|
"epoch": 0.5029696612980897,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498224465808135,
|
|
"loss": 6.7341,
|
|
"mean_token_accuracy": 0.10747307166457176,
|
|
"num_tokens": 10177086.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.807919645309449,
|
|
"epoch": 0.5035047354058537,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004982196688700509,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.11652338951826095,
|
|
"num_tokens": 10187120.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.746653747558594,
|
|
"epoch": 0.5040398095136176,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982148654865302,
|
|
"loss": 6.6816,
|
|
"mean_token_accuracy": 0.1173696868121624,
|
|
"num_tokens": 10197784.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.769271898269653,
|
|
"epoch": 0.5045748836213816,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982100556577115,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.12568439543247223,
|
|
"num_tokens": 10209373.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.758709573745728,
|
|
"epoch": 0.5051099577291455,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982052393837338,
|
|
"loss": 6.669,
|
|
"mean_token_accuracy": 0.11871311962604522,
|
|
"num_tokens": 10220316.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.6824239730834964,
|
|
"epoch": 0.5056450318369095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982004166647363,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.12401916012167931,
|
|
"num_tokens": 10230478.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.623062801361084,
|
|
"epoch": 0.5061801059446733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981955875008582,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.11519326344132423,
|
|
"num_tokens": 10240641.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.744868040084839,
|
|
"epoch": 0.5067151800524372,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981907518922387,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.12281770035624504,
|
|
"num_tokens": 10250676.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.859378337860107,
|
|
"epoch": 0.5072502541602012,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004981859098390177,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.11514592617750168,
|
|
"num_tokens": 10262016.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.7457503318786625,
|
|
"epoch": 0.5077853282679651,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981810613413348,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.12012371569871902,
|
|
"num_tokens": 10271985.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.745742273330689,
|
|
"epoch": 0.5083204023757291,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981762063993302,
|
|
"loss": 6.6133,
|
|
"mean_token_accuracy": 0.12136726751923561,
|
|
"num_tokens": 10282156.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.716922092437744,
|
|
"epoch": 0.5088554764834929,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498171345013144,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.11782191470265388,
|
|
"num_tokens": 10292576.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.661800575256348,
|
|
"epoch": 0.5093905505912569,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004981664771829165,
|
|
"loss": 6.6254,
|
|
"mean_token_accuracy": 0.1142365463078022,
|
|
"num_tokens": 10303648.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.715044784545898,
|
|
"epoch": 0.5099256246990208,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981616029087884,
|
|
"loss": 6.5102,
|
|
"mean_token_accuracy": 0.12722289934754372,
|
|
"num_tokens": 10314275.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.675028467178345,
|
|
"epoch": 0.5104606988067847,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981567221909004,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.11122743040323257,
|
|
"num_tokens": 10325386.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.712424802780151,
|
|
"epoch": 0.5109957729145487,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004981518350293935,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.11537306159734725,
|
|
"num_tokens": 10335041.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.743242788314819,
|
|
"epoch": 0.5115308470223126,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004981469414244086,
|
|
"loss": 6.5693,
|
|
"mean_token_accuracy": 0.12268173769116401,
|
|
"num_tokens": 10345746.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.624886989593506,
|
|
"epoch": 0.5120659211300765,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498142041376087,
|
|
"loss": 6.6945,
|
|
"mean_token_accuracy": 0.11829338818788529,
|
|
"num_tokens": 10356995.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.7250689506530765,
|
|
"epoch": 0.5126009952378404,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981371348845705,
|
|
"loss": 6.5939,
|
|
"mean_token_accuracy": 0.1246476911008358,
|
|
"num_tokens": 10368445.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.810773944854736,
|
|
"epoch": 0.5131360693456044,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981322219500006,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.1264880530536175,
|
|
"num_tokens": 10378256.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.698590278625488,
|
|
"epoch": 0.5136711434533683,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498127302572519,
|
|
"loss": 6.6306,
|
|
"mean_token_accuracy": 0.11948861032724381,
|
|
"num_tokens": 10388698.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.626500415802002,
|
|
"epoch": 0.5142062175611322,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981223767522679,
|
|
"loss": 6.6314,
|
|
"mean_token_accuracy": 0.12543342038989067,
|
|
"num_tokens": 10399975.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.73018741607666,
|
|
"epoch": 0.5147412916688962,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981174444893896,
|
|
"loss": 6.632,
|
|
"mean_token_accuracy": 0.11657147109508514,
|
|
"num_tokens": 10410480.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.754246234893799,
|
|
"epoch": 0.51527636577666,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981125057840264,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.12315746694803238,
|
|
"num_tokens": 10421023.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.691860723495483,
|
|
"epoch": 0.515811439884424,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498107560636321,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.11937036588788033,
|
|
"num_tokens": 10431152.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.669547367095947,
|
|
"epoch": 0.5163465139921879,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004981026090464161,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.11537841185927392,
|
|
"num_tokens": 10441986.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.76296591758728,
|
|
"epoch": 0.5168815880999519,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004980976510144548,
|
|
"loss": 6.6294,
|
|
"mean_token_accuracy": 0.11330693066120148,
|
|
"num_tokens": 10452932.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.730077743530273,
|
|
"epoch": 0.5174166622077158,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004980926865405801,
|
|
"loss": 6.7059,
|
|
"mean_token_accuracy": 0.1165323257446289,
|
|
"num_tokens": 10463411.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.755215454101562,
|
|
"epoch": 0.5179517363154797,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980877156249354,
|
|
"loss": 6.5955,
|
|
"mean_token_accuracy": 0.12119976133108139,
|
|
"num_tokens": 10474820.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.693712377548218,
|
|
"epoch": 0.5184868104232436,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980827382676643,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.12424970418214798,
|
|
"num_tokens": 10485701.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.697637557983398,
|
|
"epoch": 0.5190218845310075,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980777544689105,
|
|
"loss": 6.5925,
|
|
"mean_token_accuracy": 0.12146328687667847,
|
|
"num_tokens": 10495825.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.6988880157470705,
|
|
"epoch": 0.5195569586387715,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004980727642288178,
|
|
"loss": 6.5759,
|
|
"mean_token_accuracy": 0.12025154009461403,
|
|
"num_tokens": 10505847.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.712225770950317,
|
|
"epoch": 0.5200920327465354,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004980677675475305,
|
|
"loss": 6.6367,
|
|
"mean_token_accuracy": 0.11677327230572701,
|
|
"num_tokens": 10516596.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.733681726455688,
|
|
"epoch": 0.5206271068542994,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980627644251926,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.1293226294219494,
|
|
"num_tokens": 10528175.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.651979970932007,
|
|
"epoch": 0.5211621809620632,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980577548619489,
|
|
"loss": 6.6329,
|
|
"mean_token_accuracy": 0.11742270663380623,
|
|
"num_tokens": 10540076.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.686881160736084,
|
|
"epoch": 0.5216972550698272,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980527388579437,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.11610461995005608,
|
|
"num_tokens": 10552025.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.746124219894409,
|
|
"epoch": 0.5222323291775911,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004980477164133221,
|
|
"loss": 6.6528,
|
|
"mean_token_accuracy": 0.11348175257444382,
|
|
"num_tokens": 10562535.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.723954057693481,
|
|
"epoch": 0.522767403285355,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498042687528229,
|
|
"loss": 6.574,
|
|
"mean_token_accuracy": 0.12090551033616066,
|
|
"num_tokens": 10572989.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.658336591720581,
|
|
"epoch": 0.523302477393119,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980376522028098,
|
|
"loss": 6.6058,
|
|
"mean_token_accuracy": 0.12160259932279587,
|
|
"num_tokens": 10583033.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.734746789932251,
|
|
"epoch": 0.5238375515008828,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004980326104372095,
|
|
"loss": 6.6853,
|
|
"mean_token_accuracy": 0.11474591270089149,
|
|
"num_tokens": 10595205.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.786480188369751,
|
|
"epoch": 0.5243726256086468,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000498027562231574,
|
|
"loss": 6.5392,
|
|
"mean_token_accuracy": 0.12003358751535416,
|
|
"num_tokens": 10605244.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.718193483352661,
|
|
"epoch": 0.5249076997164107,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498022507586049,
|
|
"loss": 6.6214,
|
|
"mean_token_accuracy": 0.11722708195447921,
|
|
"num_tokens": 10615817.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.725398159027099,
|
|
"epoch": 0.5254427738241747,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980174465007804,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.11559919267892838,
|
|
"num_tokens": 10627160.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.766883087158203,
|
|
"epoch": 0.5259778479319386,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980123789759145,
|
|
"loss": 6.631,
|
|
"mean_token_accuracy": 0.12066573053598403,
|
|
"num_tokens": 10637552.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.666731262207032,
|
|
"epoch": 0.5265129220397025,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004980073050115973,
|
|
"loss": 6.6807,
|
|
"mean_token_accuracy": 0.11911093890666961,
|
|
"num_tokens": 10648773.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.761361503601075,
|
|
"epoch": 0.5270479961474664,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004980022246079755,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.1175591915845871,
|
|
"num_tokens": 10659537.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.820301675796509,
|
|
"epoch": 0.5275830702552303,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497997137765196,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.11372315660119056,
|
|
"num_tokens": 10671390.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.718183946609497,
|
|
"epoch": 0.5281181443629943,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979920444834054,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.12883347496390343,
|
|
"num_tokens": 10682389.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.594164085388184,
|
|
"epoch": 0.5286532184707582,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004979869447627508,
|
|
"loss": 6.606,
|
|
"mean_token_accuracy": 0.12021337449550629,
|
|
"num_tokens": 10692400.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.691273975372314,
|
|
"epoch": 0.5291882925785222,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004979818386033795,
|
|
"loss": 6.526,
|
|
"mean_token_accuracy": 0.12336401715874672,
|
|
"num_tokens": 10702396.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.723889923095703,
|
|
"epoch": 0.5297233666862861,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497976726005439,
|
|
"loss": 6.6549,
|
|
"mean_token_accuracy": 0.11776790469884872,
|
|
"num_tokens": 10712863.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.707800340652466,
|
|
"epoch": 0.5302584407940499,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979716069690768,
|
|
"loss": 6.6556,
|
|
"mean_token_accuracy": 0.11826993152499199,
|
|
"num_tokens": 10724234.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.8028627872467045,
|
|
"epoch": 0.5307935149018139,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004979664814944409,
|
|
"loss": 6.6898,
|
|
"mean_token_accuracy": 0.11730713248252869,
|
|
"num_tokens": 10734405.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.796906423568726,
|
|
"epoch": 0.5313285890095778,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979613495816791,
|
|
"loss": 6.6269,
|
|
"mean_token_accuracy": 0.11673597991466522,
|
|
"num_tokens": 10744573.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.81073899269104,
|
|
"epoch": 0.5318636631173418,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979562112309397,
|
|
"loss": 6.6701,
|
|
"mean_token_accuracy": 0.12054512575268746,
|
|
"num_tokens": 10755555.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.69157977104187,
|
|
"epoch": 0.5323987372251057,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497951066442371,
|
|
"loss": 6.6797,
|
|
"mean_token_accuracy": 0.11503533869981766,
|
|
"num_tokens": 10766493.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.757311391830444,
|
|
"epoch": 0.5329338113328697,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004979459152161215,
|
|
"loss": 6.6385,
|
|
"mean_token_accuracy": 0.11236128360033035,
|
|
"num_tokens": 10776735.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.700515174865723,
|
|
"epoch": 0.5334688854406335,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004979407575523402,
|
|
"loss": 6.6145,
|
|
"mean_token_accuracy": 0.12050373330712319,
|
|
"num_tokens": 10787500.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.703393936157227,
|
|
"epoch": 0.5340039595483974,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979355934511757,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.12052067667245865,
|
|
"num_tokens": 10798002.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.75645604133606,
|
|
"epoch": 0.5345390336561614,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979304229127773,
|
|
"loss": 6.6112,
|
|
"mean_token_accuracy": 0.11992594972252846,
|
|
"num_tokens": 10808982.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.736630868911743,
|
|
"epoch": 0.5350741077639253,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004979252459372944,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.11807732656598091,
|
|
"num_tokens": 10821619.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.699893808364868,
|
|
"epoch": 0.5356091818716893,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004979200625248761,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.12047486156225204,
|
|
"num_tokens": 10832344.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.670212745666504,
|
|
"epoch": 0.5361442559794531,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004979148726756725,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.11860336735844612,
|
|
"num_tokens": 10843149.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.675074863433838,
|
|
"epoch": 0.5366793300872171,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979096763898333,
|
|
"loss": 6.5998,
|
|
"mean_token_accuracy": 0.12452303320169449,
|
|
"num_tokens": 10854590.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.791008424758911,
|
|
"epoch": 0.537214404194981,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004979044736675084,
|
|
"loss": 6.5671,
|
|
"mean_token_accuracy": 0.11767032742500305,
|
|
"num_tokens": 10865500.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.680721569061279,
|
|
"epoch": 0.5377494783027449,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004978992645088483,
|
|
"loss": 6.6021,
|
|
"mean_token_accuracy": 0.12172115072607995,
|
|
"num_tokens": 10876866.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.5734340190887455,
|
|
"epoch": 0.5382845524105089,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497894048914003,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.11841940134763718,
|
|
"num_tokens": 10888627.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.746210193634033,
|
|
"epoch": 0.5388196265182728,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004978888268831236,
|
|
"loss": 6.6696,
|
|
"mean_token_accuracy": 0.11132773160934448,
|
|
"num_tokens": 10900992.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.842794561386109,
|
|
"epoch": 0.5393547006260367,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978835984163606,
|
|
"loss": 6.7276,
|
|
"mean_token_accuracy": 0.10932021215558052,
|
|
"num_tokens": 10912323.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.800081539154053,
|
|
"epoch": 0.5398897747338006,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978783635138649,
|
|
"loss": 6.6771,
|
|
"mean_token_accuracy": 0.11647720038890838,
|
|
"num_tokens": 10923991.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.639073657989502,
|
|
"epoch": 0.5404248488415646,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978731221757878,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.12417407482862472,
|
|
"num_tokens": 10934081.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.727223587036133,
|
|
"epoch": 0.5409599229493285,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004978678744022808,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.117810919880867,
|
|
"num_tokens": 10944729.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.709056615829468,
|
|
"epoch": 0.5414949970570924,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497862620193495,
|
|
"loss": 6.6635,
|
|
"mean_token_accuracy": 0.11320299580693245,
|
|
"num_tokens": 10955708.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.72125997543335,
|
|
"epoch": 0.5420300711648564,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978573595495826,
|
|
"loss": 6.6002,
|
|
"mean_token_accuracy": 0.11878297626972198,
|
|
"num_tokens": 10966427.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.740125894546509,
|
|
"epoch": 0.5425651452726202,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000497852092470695,
|
|
"loss": 6.6485,
|
|
"mean_token_accuracy": 0.11773342937231064,
|
|
"num_tokens": 10977741.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.7118854999542235,
|
|
"epoch": 0.5431002193803842,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004978468189569847,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.12482826039195061,
|
|
"num_tokens": 10989127.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.6592412948608395,
|
|
"epoch": 0.5436352934881481,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004978415390086038,
|
|
"loss": 6.6217,
|
|
"mean_token_accuracy": 0.11322500184178352,
|
|
"num_tokens": 10999791.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.783138751983643,
|
|
"epoch": 0.5441703675959121,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978362526257047,
|
|
"loss": 6.6783,
|
|
"mean_token_accuracy": 0.11360784098505974,
|
|
"num_tokens": 11010045.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.735276794433593,
|
|
"epoch": 0.544705441703676,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004978309598084403,
|
|
"loss": 6.6067,
|
|
"mean_token_accuracy": 0.11822862327098846,
|
|
"num_tokens": 11020729.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.708194351196289,
|
|
"epoch": 0.5452405158114398,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978256605569631,
|
|
"loss": 6.6289,
|
|
"mean_token_accuracy": 0.1177783451974392,
|
|
"num_tokens": 11030641.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.784500598907471,
|
|
"epoch": 0.5457755899192038,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978203548714262,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.12379909828305244,
|
|
"num_tokens": 11041533.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.726690483093262,
|
|
"epoch": 0.5463106640269677,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497815042751983,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.11729968935251237,
|
|
"num_tokens": 11052170.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.652199029922485,
|
|
"epoch": 0.5468457381347317,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978097241987868,
|
|
"loss": 6.5646,
|
|
"mean_token_accuracy": 0.1203967772424221,
|
|
"num_tokens": 11062872.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.719713973999023,
|
|
"epoch": 0.5473808122424956,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000497804399211991,
|
|
"loss": 6.6657,
|
|
"mean_token_accuracy": 0.11651256605982781,
|
|
"num_tokens": 11074199.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.7464769840240475,
|
|
"epoch": 0.5479158863502596,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004977990677917495,
|
|
"loss": 6.6129,
|
|
"mean_token_accuracy": 0.11894905865192414,
|
|
"num_tokens": 11083881.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.6402746677398685,
|
|
"epoch": 0.5484509604580234,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977937299382162,
|
|
"loss": 6.6584,
|
|
"mean_token_accuracy": 0.1151296466588974,
|
|
"num_tokens": 11094374.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.679858827590943,
|
|
"epoch": 0.5489860345657873,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004977883856515453,
|
|
"loss": 6.4958,
|
|
"mean_token_accuracy": 0.1267719380557537,
|
|
"num_tokens": 11105174.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.751749181747437,
|
|
"epoch": 0.5495211086735513,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000497783034931891,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.11584192886948586,
|
|
"num_tokens": 11117223.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.7202818393707275,
|
|
"epoch": 0.5500561827813152,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000497777677779408,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.12366545721888542,
|
|
"num_tokens": 11127240.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.676993894577026,
|
|
"epoch": 0.5505912568890792,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004977723141942509,
|
|
"loss": 6.5678,
|
|
"mean_token_accuracy": 0.1281234510242939,
|
|
"num_tokens": 11137287.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.7371532917022705,
|
|
"epoch": 0.551126330996843,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977669441765743,
|
|
"loss": 6.7007,
|
|
"mean_token_accuracy": 0.11768926754593849,
|
|
"num_tokens": 11148988.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.705612564086914,
|
|
"epoch": 0.551661405104607,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977615677265336,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.12069165110588073,
|
|
"num_tokens": 11159874.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.73426923751831,
|
|
"epoch": 0.5521964792123709,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000497756184844284,
|
|
"loss": 6.6121,
|
|
"mean_token_accuracy": 0.12401502057909966,
|
|
"num_tokens": 11170703.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.744797801971435,
|
|
"epoch": 0.5527315533201348,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004977507955299809,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.1257123127579689,
|
|
"num_tokens": 11182230.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.698776006698608,
|
|
"epoch": 0.5532666274278988,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004977453997837797,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.10981405228376388,
|
|
"num_tokens": 11192897.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.682893180847168,
|
|
"epoch": 0.5538017015356627,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977399976058366,
|
|
"loss": 6.6521,
|
|
"mean_token_accuracy": 0.11399049237370491,
|
|
"num_tokens": 11203942.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.743161678314209,
|
|
"epoch": 0.5543367756434266,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977345889963072,
|
|
"loss": 6.7014,
|
|
"mean_token_accuracy": 0.11261942982673645,
|
|
"num_tokens": 11214361.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.6744081497192385,
|
|
"epoch": 0.5548718497511905,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004977291739553479,
|
|
"loss": 6.5902,
|
|
"mean_token_accuracy": 0.12366337925195695,
|
|
"num_tokens": 11225928.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.682669401168823,
|
|
"epoch": 0.5554069238589545,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977237524831149,
|
|
"loss": 6.5444,
|
|
"mean_token_accuracy": 0.11170822679996491,
|
|
"num_tokens": 11236660.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.714070177078247,
|
|
"epoch": 0.5559419979667184,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977183245797649,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.1271256498992443,
|
|
"num_tokens": 11247272.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.77830867767334,
|
|
"epoch": 0.5564770720744823,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977128902454547,
|
|
"loss": 6.6722,
|
|
"mean_token_accuracy": 0.11327713802456855,
|
|
"num_tokens": 11258472.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.7154069423675535,
|
|
"epoch": 0.5570121461822463,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004977074494803409,
|
|
"loss": 6.5841,
|
|
"mean_token_accuracy": 0.1255582146346569,
|
|
"num_tokens": 11268344.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.722737216949463,
|
|
"epoch": 0.5575472202900101,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977020022845809,
|
|
"loss": 6.6762,
|
|
"mean_token_accuracy": 0.11227439492940902,
|
|
"num_tokens": 11279931.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.80668683052063,
|
|
"epoch": 0.5580822943977741,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976965486583318,
|
|
"loss": 6.6255,
|
|
"mean_token_accuracy": 0.11421727836132049,
|
|
"num_tokens": 11290595.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.7050305843353275,
|
|
"epoch": 0.558617368505538,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976910886017513,
|
|
"loss": 6.6411,
|
|
"mean_token_accuracy": 0.12072176486253738,
|
|
"num_tokens": 11300774.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.6693981170654295,
|
|
"epoch": 0.559152442613302,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004976856221149969,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.12517891749739646,
|
|
"num_tokens": 11310288.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.700547170639038,
|
|
"epoch": 0.5596875167210659,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976801491982263,
|
|
"loss": 6.6109,
|
|
"mean_token_accuracy": 0.11751497983932495,
|
|
"num_tokens": 11321599.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.786514472961426,
|
|
"epoch": 0.5602225908288297,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976746698515977,
|
|
"loss": 6.6606,
|
|
"mean_token_accuracy": 0.11887592300772667,
|
|
"num_tokens": 11331383.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.712525081634522,
|
|
"epoch": 0.5607576649365937,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976691840752694,
|
|
"loss": 6.6195,
|
|
"mean_token_accuracy": 0.11564537510275841,
|
|
"num_tokens": 11342085.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.718255138397216,
|
|
"epoch": 0.5612927390443576,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976636918693996,
|
|
"loss": 6.6574,
|
|
"mean_token_accuracy": 0.11577147841453553,
|
|
"num_tokens": 11354061.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.779119157791138,
|
|
"epoch": 0.5618278131521216,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976581932341471,
|
|
"loss": 6.6136,
|
|
"mean_token_accuracy": 0.12151364013552665,
|
|
"num_tokens": 11364448.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.769805908203125,
|
|
"epoch": 0.5623628872598855,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976526881696706,
|
|
"loss": 6.5791,
|
|
"mean_token_accuracy": 0.12037570253014565,
|
|
"num_tokens": 11374838.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.629622316360473,
|
|
"epoch": 0.5628979613676495,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976471766761288,
|
|
"loss": 6.6105,
|
|
"mean_token_accuracy": 0.12379851192235947,
|
|
"num_tokens": 11385310.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.691438817977906,
|
|
"epoch": 0.5634330354754133,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004976416587536812,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.11430059969425202,
|
|
"num_tokens": 11396590.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.742701053619385,
|
|
"epoch": 0.5639681095831772,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976361344024871,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.12226603850722313,
|
|
"num_tokens": 11407218.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.652452564239502,
|
|
"epoch": 0.5645031836909412,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004976306036227056,
|
|
"loss": 6.5931,
|
|
"mean_token_accuracy": 0.11696631386876107,
|
|
"num_tokens": 11417716.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.721119165420532,
|
|
"epoch": 0.5650382577987051,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497625066414497,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.11784773990511895,
|
|
"num_tokens": 11428295.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.797392892837524,
|
|
"epoch": 0.5655733319064691,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976195227780207,
|
|
"loss": 6.6173,
|
|
"mean_token_accuracy": 0.11284109130501747,
|
|
"num_tokens": 11439044.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.779853343963623,
|
|
"epoch": 0.566108406014233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004976139727134371,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.11817987859249116,
|
|
"num_tokens": 11450029.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.715458774566651,
|
|
"epoch": 0.566643480121997,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976084162209062,
|
|
"loss": 6.7264,
|
|
"mean_token_accuracy": 0.10616886764764785,
|
|
"num_tokens": 11461190.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.745611715316772,
|
|
"epoch": 0.5671785542297608,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976028533005886,
|
|
"loss": 6.5772,
|
|
"mean_token_accuracy": 0.11882699206471443,
|
|
"num_tokens": 11472143.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.771622133255005,
|
|
"epoch": 0.5677136283375247,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004975972839526449,
|
|
"loss": 6.7163,
|
|
"mean_token_accuracy": 0.1069483369588852,
|
|
"num_tokens": 11483745.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.7719972133636475,
|
|
"epoch": 0.5682487024452887,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975917081772358,
|
|
"loss": 6.5791,
|
|
"mean_token_accuracy": 0.1188987985253334,
|
|
"num_tokens": 11495695.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.718594884872436,
|
|
"epoch": 0.5687837765530526,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004975861259745225,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.11705151796340943,
|
|
"num_tokens": 11505576.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.661882305145264,
|
|
"epoch": 0.5693188506608166,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004975805373446662,
|
|
"loss": 6.479,
|
|
"mean_token_accuracy": 0.12648551389575005,
|
|
"num_tokens": 11516614.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.7097954750061035,
|
|
"epoch": 0.5698539247685804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497574942287828,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.11843594536185265,
|
|
"num_tokens": 11528032.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.664940547943115,
|
|
"epoch": 0.5703889988763444,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004975693408041697,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.11421292722225189,
|
|
"num_tokens": 11538822.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.699612236022949,
|
|
"epoch": 0.5709240729841083,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004975637328938529,
|
|
"loss": 6.6399,
|
|
"mean_token_accuracy": 0.11097949370741844,
|
|
"num_tokens": 11548895.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.714142751693726,
|
|
"epoch": 0.5714591470918722,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004975581185570398,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.11886597573757171,
|
|
"num_tokens": 11559613.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.713043832778931,
|
|
"epoch": 0.5719942211996362,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975524977938921,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.12163764908909798,
|
|
"num_tokens": 11571092.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.692736101150513,
|
|
"epoch": 0.5725292953074,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004975468706045722,
|
|
"loss": 6.6814,
|
|
"mean_token_accuracy": 0.11672013476490975,
|
|
"num_tokens": 11581448.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.728510904312134,
|
|
"epoch": 0.573064369415164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975412369892429,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.12553823739290237,
|
|
"num_tokens": 11592273.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.757077264785766,
|
|
"epoch": 0.5735994435229279,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975355969480665,
|
|
"loss": 6.5555,
|
|
"mean_token_accuracy": 0.125929856300354,
|
|
"num_tokens": 11602759.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.640834856033325,
|
|
"epoch": 0.5741345176306919,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975299504812061,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.11442179679870605,
|
|
"num_tokens": 11613977.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.71792254447937,
|
|
"epoch": 0.5746695917384558,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004975242975888246,
|
|
"loss": 6.636,
|
|
"mean_token_accuracy": 0.12084050849080086,
|
|
"num_tokens": 11625425.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.744046688079834,
|
|
"epoch": 0.5752046658462197,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004975186382710854,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.11423679888248443,
|
|
"num_tokens": 11636530.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.741583633422851,
|
|
"epoch": 0.5757397399539836,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975129725281516,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.12342779189348221,
|
|
"num_tokens": 11646516.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.701775741577149,
|
|
"epoch": 0.5762748140617475,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975073003601871,
|
|
"loss": 6.5849,
|
|
"mean_token_accuracy": 0.11874212771654129,
|
|
"num_tokens": 11657424.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.704905319213867,
|
|
"epoch": 0.5768098881695115,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975016217673556,
|
|
"loss": 6.599,
|
|
"mean_token_accuracy": 0.12148372679948807,
|
|
"num_tokens": 11669447.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.697764110565186,
|
|
"epoch": 0.5773449622772754,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497495936749821,
|
|
"loss": 6.5675,
|
|
"mean_token_accuracy": 0.12611041441559792,
|
|
"num_tokens": 11679612.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.683344936370849,
|
|
"epoch": 0.5778800363850394,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004974902453077474,
|
|
"loss": 6.5514,
|
|
"mean_token_accuracy": 0.1218061052262783,
|
|
"num_tokens": 11689527.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.765136861801148,
|
|
"epoch": 0.5784151104928033,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974845474412993,
|
|
"loss": 6.5856,
|
|
"mean_token_accuracy": 0.12035764157772064,
|
|
"num_tokens": 11700452.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.700014257431031,
|
|
"epoch": 0.5789501846005671,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974788431506412,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.1191385418176651,
|
|
"num_tokens": 11710902.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.735801887512207,
|
|
"epoch": 0.5794852587083311,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974731324359378,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.10948319584131241,
|
|
"num_tokens": 11721901.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.765271472930908,
|
|
"epoch": 0.580020332816095,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974674152973538,
|
|
"loss": 6.6146,
|
|
"mean_token_accuracy": 0.11682233065366746,
|
|
"num_tokens": 11733622.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.789870738983154,
|
|
"epoch": 0.580555406923859,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974616917350545,
|
|
"loss": 6.6101,
|
|
"mean_token_accuracy": 0.11982190161943436,
|
|
"num_tokens": 11745116.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.661038208007812,
|
|
"epoch": 0.5810904810316229,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974559617492052,
|
|
"loss": 6.5446,
|
|
"mean_token_accuracy": 0.12379105761647224,
|
|
"num_tokens": 11756203.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.719126272201538,
|
|
"epoch": 0.5816255551393869,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004974502253399712,
|
|
"loss": 6.6041,
|
|
"mean_token_accuracy": 0.12229030430316926,
|
|
"num_tokens": 11766797.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.752104377746582,
|
|
"epoch": 0.5821606292471507,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974444825075182,
|
|
"loss": 6.6896,
|
|
"mean_token_accuracy": 0.11470270082354546,
|
|
"num_tokens": 11778110.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.6274865627288815,
|
|
"epoch": 0.5826957033549146,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000497438733252012,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.12010784074664116,
|
|
"num_tokens": 11788396.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.7564613819122314,
|
|
"epoch": 0.5832307774626786,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004974329775736188,
|
|
"loss": 6.6412,
|
|
"mean_token_accuracy": 0.1130734585225582,
|
|
"num_tokens": 11798691.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.8176110744476315,
|
|
"epoch": 0.5837658515704425,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004974272154725044,
|
|
"loss": 6.6809,
|
|
"mean_token_accuracy": 0.1145077645778656,
|
|
"num_tokens": 11808965.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.655050134658813,
|
|
"epoch": 0.5843009256782065,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974214469488355,
|
|
"loss": 6.5144,
|
|
"mean_token_accuracy": 0.12288807928562165,
|
|
"num_tokens": 11819932.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.678020906448364,
|
|
"epoch": 0.5848359997859703,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004974156720027786,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.11556534245610237,
|
|
"num_tokens": 11831332.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.728974628448486,
|
|
"epoch": 0.5853710738937343,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004974098906345004,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.11275865510106087,
|
|
"num_tokens": 11840947.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.7000159740448,
|
|
"epoch": 0.5859061480014982,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004974041028441679,
|
|
"loss": 6.5377,
|
|
"mean_token_accuracy": 0.11802567318081855,
|
|
"num_tokens": 11851640.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.733285045623779,
|
|
"epoch": 0.5864412221092621,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973983086319481,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.11307286396622658,
|
|
"num_tokens": 11863608.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.722926664352417,
|
|
"epoch": 0.5869762962170261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973925079980085,
|
|
"loss": 6.5586,
|
|
"mean_token_accuracy": 0.11841953471302986,
|
|
"num_tokens": 11874707.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.687315177917481,
|
|
"epoch": 0.58751137032479,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004973867009425164,
|
|
"loss": 6.659,
|
|
"mean_token_accuracy": 0.11953919008374214,
|
|
"num_tokens": 11885118.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.783655786514283,
|
|
"epoch": 0.5880464444325539,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973808874656396,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.11821292191743851,
|
|
"num_tokens": 11895859.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.7643838882446286,
|
|
"epoch": 0.5885815185403178,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004973750675675458,
|
|
"loss": 6.64,
|
|
"mean_token_accuracy": 0.11871552392840386,
|
|
"num_tokens": 11907019.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.729001569747925,
|
|
"epoch": 0.5891165926480818,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973692412484034,
|
|
"loss": 6.5712,
|
|
"mean_token_accuracy": 0.1146469995379448,
|
|
"num_tokens": 11918257.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.721626091003418,
|
|
"epoch": 0.5896516667558457,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004973634085083802,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.12574032694101334,
|
|
"num_tokens": 11929003.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.757476425170898,
|
|
"epoch": 0.5901867408636096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497357569347645,
|
|
"loss": 6.7213,
|
|
"mean_token_accuracy": 0.11348426267504692,
|
|
"num_tokens": 11939786.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.751842021942139,
|
|
"epoch": 0.5907218149713735,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973517237663661,
|
|
"loss": 6.6311,
|
|
"mean_token_accuracy": 0.11161758229136468,
|
|
"num_tokens": 11951042.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.710853910446167,
|
|
"epoch": 0.5912568890791374,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004973458717647124,
|
|
"loss": 6.5283,
|
|
"mean_token_accuracy": 0.12709658294916154,
|
|
"num_tokens": 11961982.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.703456449508667,
|
|
"epoch": 0.5917919631869014,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497340013342853,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.12106578648090363,
|
|
"num_tokens": 11972078.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.719264888763428,
|
|
"epoch": 0.5923270372946653,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497334148500957,
|
|
"loss": 6.6446,
|
|
"mean_token_accuracy": 0.11806860640645027,
|
|
"num_tokens": 11984037.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.7681842803955075,
|
|
"epoch": 0.5928621114024293,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973282772391936,
|
|
"loss": 6.5852,
|
|
"mean_token_accuracy": 0.11801839917898178,
|
|
"num_tokens": 11993688.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.667469120025634,
|
|
"epoch": 0.5933971855101932,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973223995577324,
|
|
"loss": 6.5477,
|
|
"mean_token_accuracy": 0.11981470957398414,
|
|
"num_tokens": 12003759.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.715129756927491,
|
|
"epoch": 0.593932259617957,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973165154567432,
|
|
"loss": 6.5858,
|
|
"mean_token_accuracy": 0.1203451156616211,
|
|
"num_tokens": 12015030.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.72750506401062,
|
|
"epoch": 0.594467333725721,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973106249363959,
|
|
"loss": 6.6509,
|
|
"mean_token_accuracy": 0.11390956789255142,
|
|
"num_tokens": 12026181.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.618847751617432,
|
|
"epoch": 0.5950024078334849,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004973047279968606,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.13287391439080237,
|
|
"num_tokens": 12037336.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.65236268043518,
|
|
"epoch": 0.5955374819412489,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972988246383074,
|
|
"loss": 6.4918,
|
|
"mean_token_accuracy": 0.12340264916419982,
|
|
"num_tokens": 12048425.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.557363128662109,
|
|
"epoch": 0.5960725560490128,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004972929148609068,
|
|
"loss": 6.4594,
|
|
"mean_token_accuracy": 0.13635959550738336,
|
|
"num_tokens": 12059814.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.68271279335022,
|
|
"epoch": 0.5966076301567768,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004972869986648296,
|
|
"loss": 6.54,
|
|
"mean_token_accuracy": 0.12527887672185897,
|
|
"num_tokens": 12069377.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.707939195632934,
|
|
"epoch": 0.5971427042645406,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004972810760502467,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.11514274403452873,
|
|
"num_tokens": 12080277.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.727867317199707,
|
|
"epoch": 0.5976777783723045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972751470173287,
|
|
"loss": 6.5453,
|
|
"mean_token_accuracy": 0.12022876664996147,
|
|
"num_tokens": 12091375.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.676542520523071,
|
|
"epoch": 0.5982128524800685,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972692115662473,
|
|
"loss": 6.5893,
|
|
"mean_token_accuracy": 0.11981748417019844,
|
|
"num_tokens": 12103110.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.751420688629151,
|
|
"epoch": 0.5987479265878324,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004972632696971735,
|
|
"loss": 6.6451,
|
|
"mean_token_accuracy": 0.11599904671311378,
|
|
"num_tokens": 12112454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.6340423107147215,
|
|
"epoch": 0.5992830006955964,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972573214102791,
|
|
"loss": 6.5246,
|
|
"mean_token_accuracy": 0.11687616854906083,
|
|
"num_tokens": 12125140.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.698513317108154,
|
|
"epoch": 0.5998180748033602,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004972513667057358,
|
|
"loss": 6.5691,
|
|
"mean_token_accuracy": 0.12039392963051795,
|
|
"num_tokens": 12136061.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.791307878494263,
|
|
"epoch": 0.6003531489111242,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004972454055837155,
|
|
"loss": 6.6003,
|
|
"mean_token_accuracy": 0.12150818780064583,
|
|
"num_tokens": 12146654.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.723158931732177,
|
|
"epoch": 0.6008882230188881,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004972394380443903,
|
|
"loss": 6.5878,
|
|
"mean_token_accuracy": 0.11757106855511665,
|
|
"num_tokens": 12157881.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.675697088241577,
|
|
"epoch": 0.601423297126652,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004972334640879325,
|
|
"loss": 6.6085,
|
|
"mean_token_accuracy": 0.11922492906451225,
|
|
"num_tokens": 12168534.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.661304664611817,
|
|
"epoch": 0.601958371234416,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004972274837145147,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.11988529115915299,
|
|
"num_tokens": 12178773.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.739487743377685,
|
|
"epoch": 0.6024934453421799,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972214969243096,
|
|
"loss": 6.5808,
|
|
"mean_token_accuracy": 0.11824664920568466,
|
|
"num_tokens": 12188819.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.660564947128296,
|
|
"epoch": 0.6030285194499438,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049721550371749,
|
|
"loss": 6.5607,
|
|
"mean_token_accuracy": 0.12463830485939979,
|
|
"num_tokens": 12199198.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.6687784671783445,
|
|
"epoch": 0.6035635935577077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972095040942289,
|
|
"loss": 6.5644,
|
|
"mean_token_accuracy": 0.1162213332951069,
|
|
"num_tokens": 12210765.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.709344291687012,
|
|
"epoch": 0.6040986676654717,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004972034980546996,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.11544334441423416,
|
|
"num_tokens": 12221067.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.653585481643677,
|
|
"epoch": 0.6046337417732356,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971974855990755,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.11971136629581451,
|
|
"num_tokens": 12232994.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.738733911514283,
|
|
"epoch": 0.6051688158809995,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004971914667275302,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.12072688415646553,
|
|
"num_tokens": 12243327.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.6140237808227536,
|
|
"epoch": 0.6057038899887635,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971854414402377,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.12842355743050576,
|
|
"num_tokens": 12254249.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.662600469589234,
|
|
"epoch": 0.6062389640965273,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971794097373716,
|
|
"loss": 6.5208,
|
|
"mean_token_accuracy": 0.12328208535909653,
|
|
"num_tokens": 12264487.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.569520473480225,
|
|
"epoch": 0.6067740382042913,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971733716191063,
|
|
"loss": 6.5189,
|
|
"mean_token_accuracy": 0.1292000360786915,
|
|
"num_tokens": 12274801.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.636984205245971,
|
|
"epoch": 0.6073091123120552,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004971673270856162,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.11988460049033164,
|
|
"num_tokens": 12284647.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.658068609237671,
|
|
"epoch": 0.6078441864198192,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971612761370756,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.11951280906796455,
|
|
"num_tokens": 12295215.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.673429822921753,
|
|
"epoch": 0.6083792605275831,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971552187736596,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.12064156159758568,
|
|
"num_tokens": 12305324.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.668921661376953,
|
|
"epoch": 0.6089143346353469,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004971491549955427,
|
|
"loss": 6.5372,
|
|
"mean_token_accuracy": 0.12246538251638413,
|
|
"num_tokens": 12316399.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.6165331363677975,
|
|
"epoch": 0.6094494087431109,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971430848029002,
|
|
"loss": 6.5219,
|
|
"mean_token_accuracy": 0.12773501947522165,
|
|
"num_tokens": 12328033.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.681158256530762,
|
|
"epoch": 0.6099844828508748,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971370081959073,
|
|
"loss": 6.5622,
|
|
"mean_token_accuracy": 0.12176148667931556,
|
|
"num_tokens": 12338962.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.697946166992187,
|
|
"epoch": 0.6105195569586388,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004971309251747396,
|
|
"loss": 6.5526,
|
|
"mean_token_accuracy": 0.11940340176224709,
|
|
"num_tokens": 12350216.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.745215272903442,
|
|
"epoch": 0.6110546310664027,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971248357395726,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.11893382146954537,
|
|
"num_tokens": 12361277.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.580714225769043,
|
|
"epoch": 0.6115897051741667,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004971187398905821,
|
|
"loss": 6.4858,
|
|
"mean_token_accuracy": 0.12100339159369469,
|
|
"num_tokens": 12373308.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.731028461456299,
|
|
"epoch": 0.6121247792819305,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004971126376279443,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.11148046106100082,
|
|
"num_tokens": 12383943.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.721910047531128,
|
|
"epoch": 0.6126598533896944,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971065289518354,
|
|
"loss": 6.482,
|
|
"mean_token_accuracy": 0.12279203087091446,
|
|
"num_tokens": 12394575.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.715807628631592,
|
|
"epoch": 0.6131949274974584,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004971004138624315,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.11779340729117393,
|
|
"num_tokens": 12405536.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.606629800796509,
|
|
"epoch": 0.6137300016052223,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004970942923599094,
|
|
"loss": 6.4743,
|
|
"mean_token_accuracy": 0.12641754895448684,
|
|
"num_tokens": 12416148.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.612427473068237,
|
|
"epoch": 0.6142650757129863,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970881644444459,
|
|
"loss": 6.48,
|
|
"mean_token_accuracy": 0.12701191157102584,
|
|
"num_tokens": 12426182.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.647663402557373,
|
|
"epoch": 0.6148001498207502,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004970820301162178,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.11574866473674775,
|
|
"num_tokens": 12437548.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.737516117095947,
|
|
"epoch": 0.6153352239285141,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004970758893754022,
|
|
"loss": 6.5979,
|
|
"mean_token_accuracy": 0.11561758294701577,
|
|
"num_tokens": 12449720.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.817887496948242,
|
|
"epoch": 0.615870298036278,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004970697422221767,
|
|
"loss": 6.574,
|
|
"mean_token_accuracy": 0.1215938724577427,
|
|
"num_tokens": 12460666.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.7063861846923825,
|
|
"epoch": 0.6164053721440419,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004970635886567185,
|
|
"loss": 6.5911,
|
|
"mean_token_accuracy": 0.12281558737158775,
|
|
"num_tokens": 12471472.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.611774969100952,
|
|
"epoch": 0.6169404462518059,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004970574286792054,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.11770694702863693,
|
|
"num_tokens": 12482127.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.611656904220581,
|
|
"epoch": 0.6174755203595698,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970512622898152,
|
|
"loss": 6.5767,
|
|
"mean_token_accuracy": 0.12225481644272804,
|
|
"num_tokens": 12493680.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.65736231803894,
|
|
"epoch": 0.6180105944673338,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000497045089488726,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.12167870178818703,
|
|
"num_tokens": 12505838.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.704753160476685,
|
|
"epoch": 0.6185456685750976,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004970389102761161,
|
|
"loss": 6.5102,
|
|
"mean_token_accuracy": 0.12942416369915008,
|
|
"num_tokens": 12516334.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.661266231536866,
|
|
"epoch": 0.6190807426828616,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004970327246521638,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.12000072821974754,
|
|
"num_tokens": 12526440.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.680879926681518,
|
|
"epoch": 0.6196158167906255,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004970265326170478,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.11807752102613449,
|
|
"num_tokens": 12538127.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.722283792495728,
|
|
"epoch": 0.6201508908983894,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970203341709469,
|
|
"loss": 6.5914,
|
|
"mean_token_accuracy": 0.12216417640447616,
|
|
"num_tokens": 12548459.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.58387131690979,
|
|
"epoch": 0.6206859650061534,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00049701412931404,
|
|
"loss": 6.5481,
|
|
"mean_token_accuracy": 0.12659149914979934,
|
|
"num_tokens": 12558989.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.62721471786499,
|
|
"epoch": 0.6212210391139172,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970079180465064,
|
|
"loss": 6.4916,
|
|
"mean_token_accuracy": 0.1283690959215164,
|
|
"num_tokens": 12569449.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.644355916976929,
|
|
"epoch": 0.6217561132216812,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970017003685253,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.12029706984758377,
|
|
"num_tokens": 12580733.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.65497670173645,
|
|
"epoch": 0.6222911873294451,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004969954762802763,
|
|
"loss": 6.5326,
|
|
"mean_token_accuracy": 0.11786738261580468,
|
|
"num_tokens": 12590869.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.706523609161377,
|
|
"epoch": 0.6228262614372091,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496989245781939,
|
|
"loss": 6.6305,
|
|
"mean_token_accuracy": 0.11878098174929619,
|
|
"num_tokens": 12602109.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.690067100524902,
|
|
"epoch": 0.623361335544973,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969830088736937,
|
|
"loss": 6.5463,
|
|
"mean_token_accuracy": 0.11708159074187278,
|
|
"num_tokens": 12612234.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.761075687408447,
|
|
"epoch": 0.6238964096527368,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00049697676555572,
|
|
"loss": 6.6967,
|
|
"mean_token_accuracy": 0.11268940791487694,
|
|
"num_tokens": 12623252.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.709875154495239,
|
|
"epoch": 0.6244314837605008,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004969705158281985,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.12307255640625954,
|
|
"num_tokens": 12632796.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.652636289596558,
|
|
"epoch": 0.6249665578682647,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004969642596913095,
|
|
"loss": 6.5512,
|
|
"mean_token_accuracy": 0.11847778558731079,
|
|
"num_tokens": 12643278.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.670278692245484,
|
|
"epoch": 0.6255016319760287,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.0004969579971452337,
|
|
"loss": 6.6218,
|
|
"mean_token_accuracy": 0.12104167938232421,
|
|
"num_tokens": 12654446.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.704672002792359,
|
|
"epoch": 0.6260367060837926,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969517281901519,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.12173526436090469,
|
|
"num_tokens": 12664281.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.726960182189941,
|
|
"epoch": 0.6265717801915566,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004969454528262451,
|
|
"loss": 6.5829,
|
|
"mean_token_accuracy": 0.11787922754883766,
|
|
"num_tokens": 12675252.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.665972471237183,
|
|
"epoch": 0.6271068542993204,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004969391710536946,
|
|
"loss": 6.5794,
|
|
"mean_token_accuracy": 0.1184937097132206,
|
|
"num_tokens": 12685764.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.591383934020996,
|
|
"epoch": 0.6276419284070843,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004969328828726817,
|
|
"loss": 6.4757,
|
|
"mean_token_accuracy": 0.12730447500944136,
|
|
"num_tokens": 12696974.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.757170295715332,
|
|
"epoch": 0.6281770025148483,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004969265882833879,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.11200533658266068,
|
|
"num_tokens": 12708217.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.707298660278321,
|
|
"epoch": 0.6287120766226122,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004969202872859952,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.12099341303110123,
|
|
"num_tokens": 12717840.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.622361516952514,
|
|
"epoch": 0.6292471507303762,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004969139798806854,
|
|
"loss": 6.6088,
|
|
"mean_token_accuracy": 0.11309082061052322,
|
|
"num_tokens": 12728390.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.653683233261108,
|
|
"epoch": 0.6297822248381401,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004969076660676405,
|
|
"loss": 6.6113,
|
|
"mean_token_accuracy": 0.11578750982880592,
|
|
"num_tokens": 12738650.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.735027837753296,
|
|
"epoch": 0.630317298945904,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000496901345847043,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.11822382658720017,
|
|
"num_tokens": 12748989.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.689414024353027,
|
|
"epoch": 0.6308523730536679,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968950192190752,
|
|
"loss": 6.559,
|
|
"mean_token_accuracy": 0.12090246379375458,
|
|
"num_tokens": 12761132.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.6849761486053465,
|
|
"epoch": 0.6313874471614318,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00049688868618392,
|
|
"loss": 6.5651,
|
|
"mean_token_accuracy": 0.1228780284523964,
|
|
"num_tokens": 12771478.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.716721773147583,
|
|
"epoch": 0.6319225212691958,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968823467417602,
|
|
"loss": 6.6244,
|
|
"mean_token_accuracy": 0.1174764983355999,
|
|
"num_tokens": 12782096.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.716968536376953,
|
|
"epoch": 0.6324575953769597,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004968760008927788,
|
|
"loss": 6.5262,
|
|
"mean_token_accuracy": 0.12529518380761145,
|
|
"num_tokens": 12792467.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.6767195701599125,
|
|
"epoch": 0.6329926694847237,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000496869648637159,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.12640023306012155,
|
|
"num_tokens": 12803248.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.697324562072754,
|
|
"epoch": 0.6335277435924875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968632899750844,
|
|
"loss": 6.5591,
|
|
"mean_token_accuracy": 0.12147547379136085,
|
|
"num_tokens": 12813701.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.800759792327881,
|
|
"epoch": 0.6340628177002515,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004968569249067383,
|
|
"loss": 6.6272,
|
|
"mean_token_accuracy": 0.11679861545562745,
|
|
"num_tokens": 12824945.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.671930313110352,
|
|
"epoch": 0.6345978918080154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004968505534323047,
|
|
"loss": 6.5786,
|
|
"mean_token_accuracy": 0.1162982702255249,
|
|
"num_tokens": 12836699.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.6336596488952635,
|
|
"epoch": 0.6351329659157794,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004968441755519677,
|
|
"loss": 6.5291,
|
|
"mean_token_accuracy": 0.11951676458120346,
|
|
"num_tokens": 12846905.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.7043437480926515,
|
|
"epoch": 0.6356680400235433,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004968377912659112,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.12340181395411491,
|
|
"num_tokens": 12856919.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.60842661857605,
|
|
"epoch": 0.6362031141313071,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004968314005743196,
|
|
"loss": 6.4565,
|
|
"mean_token_accuracy": 0.12368626967072487,
|
|
"num_tokens": 12867863.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.611450290679931,
|
|
"epoch": 0.6367381882390711,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004968250034773776,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.12223007977008819,
|
|
"num_tokens": 12877877.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.737860918045044,
|
|
"epoch": 0.637273262346835,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004968185999752697,
|
|
"loss": 6.6383,
|
|
"mean_token_accuracy": 0.11434445828199387,
|
|
"num_tokens": 12887954.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.707271003723145,
|
|
"epoch": 0.637808336454599,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004968121900681809,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.12070679739117622,
|
|
"num_tokens": 12897744.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.68266224861145,
|
|
"epoch": 0.6383434105623629,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004968057737562964,
|
|
"loss": 6.617,
|
|
"mean_token_accuracy": 0.12236501500010491,
|
|
"num_tokens": 12909193.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.663351440429688,
|
|
"epoch": 0.6388784846701269,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004967993510398012,
|
|
"loss": 6.4973,
|
|
"mean_token_accuracy": 0.12318923175334931,
|
|
"num_tokens": 12919879.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.623578882217407,
|
|
"epoch": 0.6394135587778907,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004967929219188809,
|
|
"loss": 6.5387,
|
|
"mean_token_accuracy": 0.12540650963783265,
|
|
"num_tokens": 12930297.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.649103832244873,
|
|
"epoch": 0.6399486328856546,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004967864863937212,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.12860941588878633,
|
|
"num_tokens": 12940467.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.6491728782653805,
|
|
"epoch": 0.6404837069934186,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004967800444645079,
|
|
"loss": 6.5204,
|
|
"mean_token_accuracy": 0.11868370845913886,
|
|
"num_tokens": 12950417.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.636889123916626,
|
|
"epoch": 0.6410187811011825,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004967735961314269,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.122308399528265,
|
|
"num_tokens": 12960957.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.666227865219116,
|
|
"epoch": 0.6415538552089465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004967671413946646,
|
|
"loss": 6.575,
|
|
"mean_token_accuracy": 0.12026591822504998,
|
|
"num_tokens": 12971194.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.6303346157073975,
|
|
"epoch": 0.6420889293167104,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004967606802544071,
|
|
"loss": 6.5736,
|
|
"mean_token_accuracy": 0.11933250203728676,
|
|
"num_tokens": 12982479.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6420889293167104,
|
|
"eval_entropy": 6.587495564643263,
|
|
"eval_loss": 6.633632183074951,
|
|
"eval_mean_token_accuracy": 0.123240454485414,
|
|
"eval_num_tokens": 12982479.0,
|
|
"eval_runtime": 22.6134,
|
|
"eval_samples_per_second": 1312.45,
|
|
"eval_steps_per_second": 164.062,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.708343410491944,
|
|
"epoch": 0.6426240034244743,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967542127108412,
|
|
"loss": 6.6257,
|
|
"mean_token_accuracy": 0.1161632239818573,
|
|
"num_tokens": 12994119.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.693649530410767,
|
|
"epoch": 0.6431590775322382,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004967477387641537,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.1253574460744858,
|
|
"num_tokens": 13005437.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.6332213401794435,
|
|
"epoch": 0.6436941516400021,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004967412584145312,
|
|
"loss": 6.555,
|
|
"mean_token_accuracy": 0.12132607325911522,
|
|
"num_tokens": 13017278.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.6542360305786135,
|
|
"epoch": 0.6442292257477661,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004967347716621611,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.12165799587965012,
|
|
"num_tokens": 13028010.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.629656457901001,
|
|
"epoch": 0.64476429985553,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967282785072306,
|
|
"loss": 6.5233,
|
|
"mean_token_accuracy": 0.12609869465231896,
|
|
"num_tokens": 13038740.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.6070208072662355,
|
|
"epoch": 0.645299373963294,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967217789499272,
|
|
"loss": 6.543,
|
|
"mean_token_accuracy": 0.12261505052447319,
|
|
"num_tokens": 13049921.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.6102134704589846,
|
|
"epoch": 0.6458344480710578,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004967152729904386,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.12932628467679025,
|
|
"num_tokens": 13060907.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.6852294445037845,
|
|
"epoch": 0.6463695221788218,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004967087606289527,
|
|
"loss": 6.501,
|
|
"mean_token_accuracy": 0.12574908435344695,
|
|
"num_tokens": 13071720.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.666558074951172,
|
|
"epoch": 0.6469045962865857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967022418656575,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.12468422725796699,
|
|
"num_tokens": 13082474.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.596642351150512,
|
|
"epoch": 0.6474396703943496,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004966957167007412,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.12356942817568779,
|
|
"num_tokens": 13092777.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.594368410110474,
|
|
"epoch": 0.6479747445021136,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004966891851343922,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.12478138655424117,
|
|
"num_tokens": 13104019.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.70648775100708,
|
|
"epoch": 0.6485098186098774,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004966826471667992,
|
|
"loss": 6.4973,
|
|
"mean_token_accuracy": 0.12690474689006806,
|
|
"num_tokens": 13115741.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.651901435852051,
|
|
"epoch": 0.6490448927176414,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966761027981509,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.12609103322029114,
|
|
"num_tokens": 13126838.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.642081689834595,
|
|
"epoch": 0.6495799668254053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004966695520286362,
|
|
"loss": 6.6086,
|
|
"mean_token_accuracy": 0.11905003264546395,
|
|
"num_tokens": 13137485.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.6793499946594235,
|
|
"epoch": 0.6501150409331693,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966629948584444,
|
|
"loss": 6.4684,
|
|
"mean_token_accuracy": 0.1274704895913601,
|
|
"num_tokens": 13147631.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.597648620605469,
|
|
"epoch": 0.6506501150409332,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004966564312877647,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.1260016866028309,
|
|
"num_tokens": 13158468.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.723154020309448,
|
|
"epoch": 0.651185189148697,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004966498613167868,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.11794209703803063,
|
|
"num_tokens": 13169263.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.676345491409302,
|
|
"epoch": 0.651720263256461,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004966432849457002,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.13016888946294786,
|
|
"num_tokens": 13178647.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.582516241073608,
|
|
"epoch": 0.6522553373642249,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000496636702174695,
|
|
"loss": 6.4788,
|
|
"mean_token_accuracy": 0.12643413320183755,
|
|
"num_tokens": 13189883.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.648423719406128,
|
|
"epoch": 0.6527904114719889,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004966301130039611,
|
|
"loss": 6.6022,
|
|
"mean_token_accuracy": 0.12256921008229256,
|
|
"num_tokens": 13200920.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.701182746887207,
|
|
"epoch": 0.6533254855797528,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004966235174336889,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.11332411095499992,
|
|
"num_tokens": 13211765.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.659097290039062,
|
|
"epoch": 0.6538605596875168,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004966169154640687,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.1247679390013218,
|
|
"num_tokens": 13221768.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.609342384338379,
|
|
"epoch": 0.6543956337952807,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966103070952912,
|
|
"loss": 6.5209,
|
|
"mean_token_accuracy": 0.12406276315450668,
|
|
"num_tokens": 13233545.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.693496465682983,
|
|
"epoch": 0.6549307079030445,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966036923275472,
|
|
"loss": 6.5591,
|
|
"mean_token_accuracy": 0.13287978991866112,
|
|
"num_tokens": 13245018.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.604655790328979,
|
|
"epoch": 0.6554657820108085,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004965970711610278,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.12369921505451202,
|
|
"num_tokens": 13255772.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.611993074417114,
|
|
"epoch": 0.6560008561185724,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004965904435959241,
|
|
"loss": 6.5591,
|
|
"mean_token_accuracy": 0.11679132431745529,
|
|
"num_tokens": 13267271.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.685591697692871,
|
|
"epoch": 0.6565359302263364,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004965838096324274,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.12077526301145554,
|
|
"num_tokens": 13278467.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.647955656051636,
|
|
"epoch": 0.6570710043341003,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004965771692707294,
|
|
"loss": 6.625,
|
|
"mean_token_accuracy": 0.11517797484993934,
|
|
"num_tokens": 13288522.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.735994911193847,
|
|
"epoch": 0.6576060784418643,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004965705225110218,
|
|
"loss": 6.5958,
|
|
"mean_token_accuracy": 0.1102604016661644,
|
|
"num_tokens": 13299355.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.69739933013916,
|
|
"epoch": 0.6581411525496281,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004965638693534964,
|
|
"loss": 6.5269,
|
|
"mean_token_accuracy": 0.12430242151021957,
|
|
"num_tokens": 13310334.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.717443895339966,
|
|
"epoch": 0.658676226657392,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004965572097983455,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.11856616660952568,
|
|
"num_tokens": 13320917.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.674542045593261,
|
|
"epoch": 0.659211300765156,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004965505438457613,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.12417368888854981,
|
|
"num_tokens": 13331707.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.640851926803589,
|
|
"epoch": 0.6597463748729199,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004965438714959363,
|
|
"loss": 6.629,
|
|
"mean_token_accuracy": 0.11581350415945053,
|
|
"num_tokens": 13341784.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.735370779037476,
|
|
"epoch": 0.6602814489806839,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000496537192749063,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.11734402552247047,
|
|
"num_tokens": 13351633.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.681562995910644,
|
|
"epoch": 0.6608165230884477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004965305076053345,
|
|
"loss": 6.4794,
|
|
"mean_token_accuracy": 0.12656131833791734,
|
|
"num_tokens": 13362444.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.592486047744751,
|
|
"epoch": 0.6613515971962117,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004965238160649437,
|
|
"loss": 6.6139,
|
|
"mean_token_accuracy": 0.11791914477944374,
|
|
"num_tokens": 13374322.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.651375102996826,
|
|
"epoch": 0.6618866713039756,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004965171181280838,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.11961539909243583,
|
|
"num_tokens": 13384188.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.709027862548828,
|
|
"epoch": 0.6624217454117395,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004965104137949483,
|
|
"loss": 6.5697,
|
|
"mean_token_accuracy": 0.11759102568030358,
|
|
"num_tokens": 13395648.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.718053483963013,
|
|
"epoch": 0.6629568195195035,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004965037030657308,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.12067084982991219,
|
|
"num_tokens": 13406769.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.728432607650757,
|
|
"epoch": 0.6634918936272673,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004964969859406248,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.11147924661636352,
|
|
"num_tokens": 13417509.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.6613959789276125,
|
|
"epoch": 0.6640269677350313,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004964902624198246,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.11563964560627937,
|
|
"num_tokens": 13429441.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.6188640117645265,
|
|
"epoch": 0.6645620418427952,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964835325035243,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.12196975350379943,
|
|
"num_tokens": 13439332.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.617918682098389,
|
|
"epoch": 0.6650971159505592,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964767961919179,
|
|
"loss": 6.4908,
|
|
"mean_token_accuracy": 0.12061900198459626,
|
|
"num_tokens": 13449400.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.680626916885376,
|
|
"epoch": 0.6656321900583231,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004964700534852003,
|
|
"loss": 6.5983,
|
|
"mean_token_accuracy": 0.11767825335264206,
|
|
"num_tokens": 13460134.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.686565780639649,
|
|
"epoch": 0.666167264166087,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004964633043835658,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.12875395640730858,
|
|
"num_tokens": 13469954.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.679265308380127,
|
|
"epoch": 0.666702338273851,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004964565488872097,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.12348946034908295,
|
|
"num_tokens": 13479866.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.563807821273803,
|
|
"epoch": 0.6672374123816148,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004964497869963268,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.12527237683534623,
|
|
"num_tokens": 13490088.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.656466770172119,
|
|
"epoch": 0.6677724864893788,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004964430187111125,
|
|
"loss": 6.5728,
|
|
"mean_token_accuracy": 0.12173057049512863,
|
|
"num_tokens": 13500898.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.687621164321899,
|
|
"epoch": 0.6683075605971427,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004964362440317621,
|
|
"loss": 6.5927,
|
|
"mean_token_accuracy": 0.1209525316953659,
|
|
"num_tokens": 13511537.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.633641624450684,
|
|
"epoch": 0.6688426347049067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964294629584712,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.12212182357907295,
|
|
"num_tokens": 13522916.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.683465242385864,
|
|
"epoch": 0.6693777088126706,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004964226754914357,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.12490794360637665,
|
|
"num_tokens": 13533817.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.711468744277954,
|
|
"epoch": 0.6699127829204344,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004964158816308517,
|
|
"loss": 6.5852,
|
|
"mean_token_accuracy": 0.11734790429472923,
|
|
"num_tokens": 13543723.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.586713552474976,
|
|
"epoch": 0.6704478570281984,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004964090813769151,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.1227193221449852,
|
|
"num_tokens": 13555269.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.64307050704956,
|
|
"epoch": 0.6709829311359623,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004964022747298224,
|
|
"loss": 6.6139,
|
|
"mean_token_accuracy": 0.11729198768734932,
|
|
"num_tokens": 13567465.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.752734518051147,
|
|
"epoch": 0.6715180052437263,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963954616897701,
|
|
"loss": 6.5446,
|
|
"mean_token_accuracy": 0.11841646209359169,
|
|
"num_tokens": 13578637.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.68422417640686,
|
|
"epoch": 0.6720530793514902,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496388642256955,
|
|
"loss": 6.5505,
|
|
"mean_token_accuracy": 0.12172395139932632,
|
|
"num_tokens": 13589074.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.646722793579102,
|
|
"epoch": 0.6725881534592542,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000496381816431574,
|
|
"loss": 6.514,
|
|
"mean_token_accuracy": 0.12342069149017335,
|
|
"num_tokens": 13599624.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.719354677200317,
|
|
"epoch": 0.673123227567018,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004963749842138241,
|
|
"loss": 6.5363,
|
|
"mean_token_accuracy": 0.12487530261278153,
|
|
"num_tokens": 13610293.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.675761699676514,
|
|
"epoch": 0.6736583016747819,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004963681456039027,
|
|
"loss": 6.5611,
|
|
"mean_token_accuracy": 0.11623863652348518,
|
|
"num_tokens": 13621641.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.602420663833618,
|
|
"epoch": 0.6741933757825459,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004963613006020072,
|
|
"loss": 6.5252,
|
|
"mean_token_accuracy": 0.1208052784204483,
|
|
"num_tokens": 13632083.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.604093360900879,
|
|
"epoch": 0.6747284498903098,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004963544492083352,
|
|
"loss": 6.41,
|
|
"mean_token_accuracy": 0.13683966994285585,
|
|
"num_tokens": 13644084.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.6350510597229,
|
|
"epoch": 0.6752635239980738,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004963475914230845,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.11910239085555077,
|
|
"num_tokens": 13656231.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.699683904647827,
|
|
"epoch": 0.6757985981058376,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004963407272464533,
|
|
"loss": 6.5952,
|
|
"mean_token_accuracy": 0.11810294091701508,
|
|
"num_tokens": 13667334.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.724069118499756,
|
|
"epoch": 0.6763336722136016,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004963338566786398,
|
|
"loss": 6.5828,
|
|
"mean_token_accuracy": 0.12107535973191261,
|
|
"num_tokens": 13678615.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.693145990371704,
|
|
"epoch": 0.6768687463213655,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004963269797198422,
|
|
"loss": 6.5874,
|
|
"mean_token_accuracy": 0.12346574515104294,
|
|
"num_tokens": 13689890.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.558933973312378,
|
|
"epoch": 0.6774038204291294,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004963200963702592,
|
|
"loss": 6.4168,
|
|
"mean_token_accuracy": 0.13032166957855223,
|
|
"num_tokens": 13699120.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.581582736968994,
|
|
"epoch": 0.6779388945368934,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963132066300894,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.11724406257271766,
|
|
"num_tokens": 13710016.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.6938841342926025,
|
|
"epoch": 0.6784739686446573,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004963063104995319,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.11238991096615791,
|
|
"num_tokens": 13721576.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.745585584640503,
|
|
"epoch": 0.6790090427524212,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962994079787859,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.12299842238426209,
|
|
"num_tokens": 13732568.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.657323408126831,
|
|
"epoch": 0.6795441168601851,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962924990680504,
|
|
"loss": 6.4794,
|
|
"mean_token_accuracy": 0.12324386537075042,
|
|
"num_tokens": 13742569.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.627435684204102,
|
|
"epoch": 0.6800791909679491,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962855837675252,
|
|
"loss": 6.6034,
|
|
"mean_token_accuracy": 0.11716282293200493,
|
|
"num_tokens": 13752689.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.6892821311950685,
|
|
"epoch": 0.680614265075713,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962786620774099,
|
|
"loss": 6.5905,
|
|
"mean_token_accuracy": 0.11979246288537979,
|
|
"num_tokens": 13763709.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.705752182006836,
|
|
"epoch": 0.6811493391834769,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004962717339979043,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.1252245396375656,
|
|
"num_tokens": 13773726.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.608482742309571,
|
|
"epoch": 0.6816844132912409,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004962647995292084,
|
|
"loss": 6.5296,
|
|
"mean_token_accuracy": 0.12159904614090919,
|
|
"num_tokens": 13785435.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.640556859970093,
|
|
"epoch": 0.6822194873990047,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004962578586715226,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.11594315767288207,
|
|
"num_tokens": 13797104.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.7496202945709225,
|
|
"epoch": 0.6827545615067687,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004962509114250471,
|
|
"loss": 6.6121,
|
|
"mean_token_accuracy": 0.11787962764501572,
|
|
"num_tokens": 13807756.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.491614484786988,
|
|
"epoch": 0.6832896356145326,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962439577899828,
|
|
"loss": 6.314,
|
|
"mean_token_accuracy": 0.13807514384388925,
|
|
"num_tokens": 13818490.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.646625661849976,
|
|
"epoch": 0.6838247097222966,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004962369977665301,
|
|
"loss": 6.5814,
|
|
"mean_token_accuracy": 0.11426923871040344,
|
|
"num_tokens": 13829465.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.783056354522705,
|
|
"epoch": 0.6843597838300605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962300313548903,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.12248866409063339,
|
|
"num_tokens": 13840863.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.695218420028686,
|
|
"epoch": 0.6848948579378243,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004962230585552645,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.12046386897563935,
|
|
"num_tokens": 13851711.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.581887054443359,
|
|
"epoch": 0.6854299320455883,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004962160793678539,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.11757319420576096,
|
|
"num_tokens": 13864576.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.6630912780761715,
|
|
"epoch": 0.6859650061533522,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049620909379286,
|
|
"loss": 6.4883,
|
|
"mean_token_accuracy": 0.12629830315709115,
|
|
"num_tokens": 13875150.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.683273983001709,
|
|
"epoch": 0.6865000802611162,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004962021018304847,
|
|
"loss": 6.5422,
|
|
"mean_token_accuracy": 0.12137580290436745,
|
|
"num_tokens": 13886070.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.600133419036865,
|
|
"epoch": 0.6870351543688801,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004961951034809298,
|
|
"loss": 6.4596,
|
|
"mean_token_accuracy": 0.11954843401908874,
|
|
"num_tokens": 13897898.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.743383502960205,
|
|
"epoch": 0.6875702284766441,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961880987443974,
|
|
"loss": 6.5996,
|
|
"mean_token_accuracy": 0.1191033512353897,
|
|
"num_tokens": 13909578.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.5636146068573,
|
|
"epoch": 0.6881053025844079,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004961810876210897,
|
|
"loss": 6.4561,
|
|
"mean_token_accuracy": 0.12540539875626563,
|
|
"num_tokens": 13920537.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.548890447616577,
|
|
"epoch": 0.6886403766921718,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004961740701112091,
|
|
"loss": 6.5134,
|
|
"mean_token_accuracy": 0.12369008883833885,
|
|
"num_tokens": 13931015.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.668211126327515,
|
|
"epoch": 0.6891754507999358,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961670462149583,
|
|
"loss": 6.5521,
|
|
"mean_token_accuracy": 0.12055359557271003,
|
|
"num_tokens": 13942691.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.767236375808716,
|
|
"epoch": 0.6897105249076997,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961600159325403,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.10908434465527535,
|
|
"num_tokens": 13953945.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.751330995559693,
|
|
"epoch": 0.6902455990154637,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004961529792641577,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.1173236459493637,
|
|
"num_tokens": 13965658.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.731899356842041,
|
|
"epoch": 0.6907806731232276,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961459362100141,
|
|
"loss": 6.5992,
|
|
"mean_token_accuracy": 0.12082590013742447,
|
|
"num_tokens": 13976184.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.6650745391845705,
|
|
"epoch": 0.6913157472309915,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004961388867703125,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.11692757606506347,
|
|
"num_tokens": 13986243.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.65087571144104,
|
|
"epoch": 0.6918508213387554,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004961318309452566,
|
|
"loss": 6.507,
|
|
"mean_token_accuracy": 0.12220369726419449,
|
|
"num_tokens": 13995904.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.659942245483398,
|
|
"epoch": 0.6923858954465193,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004961247687350504,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.12576377019286156,
|
|
"num_tokens": 14006711.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.628136539459229,
|
|
"epoch": 0.6929209695542833,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961177001398974,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.12062407061457633,
|
|
"num_tokens": 14018177.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.665041160583496,
|
|
"epoch": 0.6934560436620472,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004961106251600018,
|
|
"loss": 6.4884,
|
|
"mean_token_accuracy": 0.11637992933392524,
|
|
"num_tokens": 14028725.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.6288951396942135,
|
|
"epoch": 0.6939911177698111,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961035437955681,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.13461530953645706,
|
|
"num_tokens": 14040448.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.62433614730835,
|
|
"epoch": 0.694526191877575,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004960964560468005,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.11507597416639329,
|
|
"num_tokens": 14051731.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.7240547180175785,
|
|
"epoch": 0.695061265985339,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960893619139039,
|
|
"loss": 6.5658,
|
|
"mean_token_accuracy": 0.11801211908459663,
|
|
"num_tokens": 14062330.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.683112001419067,
|
|
"epoch": 0.6955963400931029,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960822613970831,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.12386781573295594,
|
|
"num_tokens": 14073991.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.640247869491577,
|
|
"epoch": 0.6961314142008668,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004960751544965431,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.12210935950279236,
|
|
"num_tokens": 14085132.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.592376041412353,
|
|
"epoch": 0.6966664883086308,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960680412124889,
|
|
"loss": 6.4499,
|
|
"mean_token_accuracy": 0.12720930054783822,
|
|
"num_tokens": 14095371.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.5528076171875,
|
|
"epoch": 0.6972015624163946,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004960609215451261,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.12374990880489349,
|
|
"num_tokens": 14106117.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.649059104919433,
|
|
"epoch": 0.6977366365241586,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004960537954946604,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.12003685981035232,
|
|
"num_tokens": 14117112.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.596162796020508,
|
|
"epoch": 0.6982717106319225,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004960466630612974,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.13205637782812119,
|
|
"num_tokens": 14128037.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.556289529800415,
|
|
"epoch": 0.6988067847396865,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004960395242452429,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.12506138905882835,
|
|
"num_tokens": 14140183.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.6649885177612305,
|
|
"epoch": 0.6993418588474504,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004960323790467033,
|
|
"loss": 6.5995,
|
|
"mean_token_accuracy": 0.12367913722991944,
|
|
"num_tokens": 14151635.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.737906551361084,
|
|
"epoch": 0.6998769329552142,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004960252274658849,
|
|
"loss": 6.5577,
|
|
"mean_token_accuracy": 0.12105544358491897,
|
|
"num_tokens": 14162660.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.671280765533448,
|
|
"epoch": 0.7004120070629782,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004960180695029939,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.12037990167737007,
|
|
"num_tokens": 14173496.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.617800331115722,
|
|
"epoch": 0.7009470811707421,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004960109051582374,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.11847614273428916,
|
|
"num_tokens": 14185479.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.60119400024414,
|
|
"epoch": 0.7014821552785061,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004960037344318221,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.12120893523097039,
|
|
"num_tokens": 14197441.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.566002035140992,
|
|
"epoch": 0.70201722938627,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959965573239548,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12884053736925125,
|
|
"num_tokens": 14207832.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.55321888923645,
|
|
"epoch": 0.702552303494034,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004959893738348432,
|
|
"loss": 6.4945,
|
|
"mean_token_accuracy": 0.12767787277698517,
|
|
"num_tokens": 14217976.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.674604034423828,
|
|
"epoch": 0.7030873776017978,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004959821839646943,
|
|
"loss": 6.4431,
|
|
"mean_token_accuracy": 0.12329324334859848,
|
|
"num_tokens": 14227557.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.662657594680786,
|
|
"epoch": 0.7036224517095617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000495974987713716,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.11384310796856881,
|
|
"num_tokens": 14238912.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.638991737365723,
|
|
"epoch": 0.7041575258173257,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004959677850821159,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.12319194078445435,
|
|
"num_tokens": 14249968.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.620342445373535,
|
|
"epoch": 0.7046925999250896,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959605760701021,
|
|
"loss": 6.5569,
|
|
"mean_token_accuracy": 0.12182011604309081,
|
|
"num_tokens": 14260809.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.663771057128907,
|
|
"epoch": 0.7052276740328536,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004959533606778827,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.1212913878262043,
|
|
"num_tokens": 14271971.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.70226559638977,
|
|
"epoch": 0.7057627481406175,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959461389056661,
|
|
"loss": 6.5913,
|
|
"mean_token_accuracy": 0.12781344801187516,
|
|
"num_tokens": 14283550.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.566189193725586,
|
|
"epoch": 0.7062978222483814,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004959389107536608,
|
|
"loss": 6.4158,
|
|
"mean_token_accuracy": 0.12276504635810852,
|
|
"num_tokens": 14293769.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.642466735839844,
|
|
"epoch": 0.7068328963561453,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004959316762220754,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.11977979466319084,
|
|
"num_tokens": 14304668.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.650493144989014,
|
|
"epoch": 0.7073679704639092,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495924435311119,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.11864884719252586,
|
|
"num_tokens": 14315912.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.61599588394165,
|
|
"epoch": 0.7079030445716732,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959171880210005,
|
|
"loss": 6.5415,
|
|
"mean_token_accuracy": 0.1240161381661892,
|
|
"num_tokens": 14327386.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.61832332611084,
|
|
"epoch": 0.7084381186794371,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004959099343519294,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.11902955025434495,
|
|
"num_tokens": 14338629.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.745673322677613,
|
|
"epoch": 0.7089731927872011,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959026743041148,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.12611126601696016,
|
|
"num_tokens": 14349195.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.707384347915649,
|
|
"epoch": 0.7095082668949649,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004958954078777665,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.11705741733312607,
|
|
"num_tokens": 14359449.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.607598972320557,
|
|
"epoch": 0.7100433410027289,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004958881350730944,
|
|
"loss": 6.4914,
|
|
"mean_token_accuracy": 0.12530679404735565,
|
|
"num_tokens": 14369904.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.640906763076782,
|
|
"epoch": 0.7105784151104928,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958808558903085,
|
|
"loss": 6.502,
|
|
"mean_token_accuracy": 0.12301137670874596,
|
|
"num_tokens": 14382635.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.597404193878174,
|
|
"epoch": 0.7111134892182567,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004958735703296189,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.12635595500469207,
|
|
"num_tokens": 14393238.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.605778455734253,
|
|
"epoch": 0.7116485633260207,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000495866278391236,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.12151379361748696,
|
|
"num_tokens": 14403734.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.662947177886963,
|
|
"epoch": 0.7121836374337845,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004958589800753703,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.12501125037670135,
|
|
"num_tokens": 14414201.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.639647436141968,
|
|
"epoch": 0.7127187115415485,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958516753822326,
|
|
"loss": 6.5273,
|
|
"mean_token_accuracy": 0.12744878232479095,
|
|
"num_tokens": 14425153.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.599532556533814,
|
|
"epoch": 0.7132537856493124,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004958443643120338,
|
|
"loss": 6.5016,
|
|
"mean_token_accuracy": 0.12863869071006775,
|
|
"num_tokens": 14435942.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.614558696746826,
|
|
"epoch": 0.7137888597570764,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000495837046864985,
|
|
"loss": 6.4763,
|
|
"mean_token_accuracy": 0.12335674315690995,
|
|
"num_tokens": 14446371.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.617805099487304,
|
|
"epoch": 0.7143239338648403,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004958297230412976,
|
|
"loss": 6.4252,
|
|
"mean_token_accuracy": 0.127166984975338,
|
|
"num_tokens": 14456598.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.555561685562134,
|
|
"epoch": 0.7148590079726042,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004958223928411829,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.1143219605088234,
|
|
"num_tokens": 14466775.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.574054431915283,
|
|
"epoch": 0.7153940820803681,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004958150562648526,
|
|
"loss": 6.4665,
|
|
"mean_token_accuracy": 0.12366539910435677,
|
|
"num_tokens": 14476876.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.590529203414917,
|
|
"epoch": 0.715929156188132,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004958077133125187,
|
|
"loss": 6.4797,
|
|
"mean_token_accuracy": 0.12587342411279678,
|
|
"num_tokens": 14487698.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.692271709442139,
|
|
"epoch": 0.716464230295896,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000495800363984393,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.12271760776638985,
|
|
"num_tokens": 14498572.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.623218107223511,
|
|
"epoch": 0.7169993044036599,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004957930082806878,
|
|
"loss": 6.5438,
|
|
"mean_token_accuracy": 0.12247662395238876,
|
|
"num_tokens": 14509673.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.70994553565979,
|
|
"epoch": 0.7175343785114239,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004957856462016155,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.1105528324842453,
|
|
"num_tokens": 14519974.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.691906595230103,
|
|
"epoch": 0.7180694526191878,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004957782777473888,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.11652741655707359,
|
|
"num_tokens": 14531194.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.606967735290527,
|
|
"epoch": 0.7186045267269516,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004957709029182203,
|
|
"loss": 6.4862,
|
|
"mean_token_accuracy": 0.12221086099743843,
|
|
"num_tokens": 14542393.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.582061862945556,
|
|
"epoch": 0.7191396008347156,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004957635217143231,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.13097272515296937,
|
|
"num_tokens": 14552934.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.62083740234375,
|
|
"epoch": 0.7196746749424795,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00049575613413591,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.120374695956707,
|
|
"num_tokens": 14563643.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.601111316680909,
|
|
"epoch": 0.7202097490502435,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957487401831947,
|
|
"loss": 6.445,
|
|
"mean_token_accuracy": 0.12362169623374938,
|
|
"num_tokens": 14574422.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.584991502761841,
|
|
"epoch": 0.7207448231580074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957413398563906,
|
|
"loss": 6.4292,
|
|
"mean_token_accuracy": 0.11930982172489166,
|
|
"num_tokens": 14585002.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.625512647628784,
|
|
"epoch": 0.7212798972657714,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004957339331557113,
|
|
"loss": 6.4612,
|
|
"mean_token_accuracy": 0.1259589172899723,
|
|
"num_tokens": 14595172.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.599657821655273,
|
|
"epoch": 0.7218149713735352,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004957265200813706,
|
|
"loss": 6.5742,
|
|
"mean_token_accuracy": 0.11676609218120575,
|
|
"num_tokens": 14606316.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.696068477630615,
|
|
"epoch": 0.7223500454812991,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004957191006335827,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.12656715735793114,
|
|
"num_tokens": 14616394.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.555004119873047,
|
|
"epoch": 0.7228851195890631,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004957116748125618,
|
|
"loss": 6.4925,
|
|
"mean_token_accuracy": 0.11967325806617737,
|
|
"num_tokens": 14627474.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.575228595733643,
|
|
"epoch": 0.723420193696827,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004957042426185223,
|
|
"loss": 6.4314,
|
|
"mean_token_accuracy": 0.13004304990172386,
|
|
"num_tokens": 14638343.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.614687061309814,
|
|
"epoch": 0.723955267804591,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004956968040516789,
|
|
"loss": 6.4941,
|
|
"mean_token_accuracy": 0.12631681188941002,
|
|
"num_tokens": 14649115.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.607396507263184,
|
|
"epoch": 0.7244903419123548,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004956893591122461,
|
|
"loss": 6.5614,
|
|
"mean_token_accuracy": 0.1266578659415245,
|
|
"num_tokens": 14659714.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.730130004882812,
|
|
"epoch": 0.7250254160201188,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004956819078004392,
|
|
"loss": 6.5943,
|
|
"mean_token_accuracy": 0.1168831467628479,
|
|
"num_tokens": 14670481.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.612733459472656,
|
|
"epoch": 0.7255604901278827,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004956744501164732,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.12815224677324294,
|
|
"num_tokens": 14680816.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.573790550231934,
|
|
"epoch": 0.7260955642356466,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004956669860605634,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.12638939991593362,
|
|
"num_tokens": 14692723.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.630371952056885,
|
|
"epoch": 0.7266306383434106,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956595156329254,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.12008581012487411,
|
|
"num_tokens": 14703824.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.706773328781128,
|
|
"epoch": 0.7271657124511745,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000495652038833775,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.12735376432538031,
|
|
"num_tokens": 14715934.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.598440217971802,
|
|
"epoch": 0.7277007865589384,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004956445556633279,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.12028545215725898,
|
|
"num_tokens": 14725617.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.634641218185425,
|
|
"epoch": 0.7282358606667023,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004956370661218003,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.12309338971972465,
|
|
"num_tokens": 14736430.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.666610288619995,
|
|
"epoch": 0.7287709347744663,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004956295702094084,
|
|
"loss": 6.5171,
|
|
"mean_token_accuracy": 0.12309236079454422,
|
|
"num_tokens": 14746740.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.582339763641357,
|
|
"epoch": 0.7293060088822302,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004956220679263687,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.12928269281983376,
|
|
"num_tokens": 14756884.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.589403057098389,
|
|
"epoch": 0.7298410829899941,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956145592728976,
|
|
"loss": 6.4581,
|
|
"mean_token_accuracy": 0.1312728136777878,
|
|
"num_tokens": 14766974.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.623006343841553,
|
|
"epoch": 0.730376157097758,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004956070442492123,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.11667682155966759,
|
|
"num_tokens": 14778449.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.7070536613464355,
|
|
"epoch": 0.7309112312055219,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955995228555296,
|
|
"loss": 6.5422,
|
|
"mean_token_accuracy": 0.1225484624505043,
|
|
"num_tokens": 14788989.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.628703689575195,
|
|
"epoch": 0.7314463053132859,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004955919950920666,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.12728202119469642,
|
|
"num_tokens": 14798454.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.660853433609009,
|
|
"epoch": 0.7319813794210498,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004955844609590408,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.12790426537394523,
|
|
"num_tokens": 14808920.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.635347509384156,
|
|
"epoch": 0.7325164535288138,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004955769204566696,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.1228242613375187,
|
|
"num_tokens": 14819250.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.662122344970703,
|
|
"epoch": 0.7330515276365777,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004955693735851709,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.12443855032324791,
|
|
"num_tokens": 14829789.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.562832450866699,
|
|
"epoch": 0.7335866017443415,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004955618203447625,
|
|
"loss": 6.5037,
|
|
"mean_token_accuracy": 0.1241986483335495,
|
|
"num_tokens": 14840527.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.608736944198609,
|
|
"epoch": 0.7341216758521055,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004955542607356625,
|
|
"loss": 6.5588,
|
|
"mean_token_accuracy": 0.12313508540391922,
|
|
"num_tokens": 14850922.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.655763769149781,
|
|
"epoch": 0.7346567499598694,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004955466947580893,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.12578540593385695,
|
|
"num_tokens": 14862226.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.597611951828003,
|
|
"epoch": 0.7351918240676334,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004955391224122611,
|
|
"loss": 6.4097,
|
|
"mean_token_accuracy": 0.1363422118127346,
|
|
"num_tokens": 14872461.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.608497571945191,
|
|
"epoch": 0.7357268981753973,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000495531543698397,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.12411358803510666,
|
|
"num_tokens": 14883088.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.693577766418457,
|
|
"epoch": 0.7362619722831613,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004955239586167153,
|
|
"loss": 6.5405,
|
|
"mean_token_accuracy": 0.12336590811610222,
|
|
"num_tokens": 14894055.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.6278046607971195,
|
|
"epoch": 0.7367970463909251,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004955163671674354,
|
|
"loss": 6.5092,
|
|
"mean_token_accuracy": 0.1199507437646389,
|
|
"num_tokens": 14904760.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.727400636672973,
|
|
"epoch": 0.737332120498689,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004955087693507764,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.11664849147200584,
|
|
"num_tokens": 14915983.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.65953311920166,
|
|
"epoch": 0.737867194606453,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004955011651669577,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.11811737567186356,
|
|
"num_tokens": 14925959.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.5658063888549805,
|
|
"epoch": 0.7384022687142169,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004954935546161988,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.12480072304606438,
|
|
"num_tokens": 14936138.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.680220413208008,
|
|
"epoch": 0.7389373428219809,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004954859376987195,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.1277581550180912,
|
|
"num_tokens": 14946979.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.584284877777099,
|
|
"epoch": 0.7394724169297447,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004954783144147397,
|
|
"loss": 6.5679,
|
|
"mean_token_accuracy": 0.12042608857154846,
|
|
"num_tokens": 14958324.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.737890386581421,
|
|
"epoch": 0.7400074910375087,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004954706847644796,
|
|
"loss": 6.5574,
|
|
"mean_token_accuracy": 0.11832675114274024,
|
|
"num_tokens": 14969048.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.710620450973511,
|
|
"epoch": 0.7405425651452726,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004954630487481594,
|
|
"loss": 6.5496,
|
|
"mean_token_accuracy": 0.12008848264813424,
|
|
"num_tokens": 14979825.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.595880651473999,
|
|
"epoch": 0.7410776392530365,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004954554063659998,
|
|
"loss": 6.481,
|
|
"mean_token_accuracy": 0.12603807896375657,
|
|
"num_tokens": 14990138.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.596027612686157,
|
|
"epoch": 0.7416127133608005,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004954477576182212,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.1261916309595108,
|
|
"num_tokens": 15002276.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.646682214736939,
|
|
"epoch": 0.7421477874685644,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954401025050445,
|
|
"loss": 6.5709,
|
|
"mean_token_accuracy": 0.12357406765222549,
|
|
"num_tokens": 15013622.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.676917219161988,
|
|
"epoch": 0.7426828615763283,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954324410266909,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.12281017452478409,
|
|
"num_tokens": 15024067.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.628924036026001,
|
|
"epoch": 0.7432179356840922,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004954247731833815,
|
|
"loss": 6.4168,
|
|
"mean_token_accuracy": 0.13402525782585145,
|
|
"num_tokens": 15033646.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.559259271621704,
|
|
"epoch": 0.7437530097918562,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954170989753377,
|
|
"loss": 6.4686,
|
|
"mean_token_accuracy": 0.12331727594137191,
|
|
"num_tokens": 15044655.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.714093255996704,
|
|
"epoch": 0.7442880838996201,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004954094184027813,
|
|
"loss": 6.5556,
|
|
"mean_token_accuracy": 0.11801010146737098,
|
|
"num_tokens": 15055492.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.666389083862304,
|
|
"epoch": 0.744823158007384,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954017314659339,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.1155826836824417,
|
|
"num_tokens": 15066472.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.671958112716675,
|
|
"epoch": 0.745358232115148,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004953940381650174,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.12497956231236458,
|
|
"num_tokens": 15076851.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.544204425811768,
|
|
"epoch": 0.7458933062229118,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004953863385002541,
|
|
"loss": 6.4337,
|
|
"mean_token_accuracy": 0.12553054392337798,
|
|
"num_tokens": 15086997.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.669872713088989,
|
|
"epoch": 0.7464283803306758,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004953786324718661,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.1174256332218647,
|
|
"num_tokens": 15098625.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.628860807418823,
|
|
"epoch": 0.7469634544384397,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004953709200800761,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.1296637736260891,
|
|
"num_tokens": 15108265.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.58307580947876,
|
|
"epoch": 0.7474985285462037,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004953632013251068,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.12321807146072387,
|
|
"num_tokens": 15118794.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.648694610595703,
|
|
"epoch": 0.7480336026539676,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004953554762071811,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.12125022262334824,
|
|
"num_tokens": 15130084.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.664281702041626,
|
|
"epoch": 0.7485686767617316,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004953477447265218,
|
|
"loss": 6.5118,
|
|
"mean_token_accuracy": 0.11916638761758805,
|
|
"num_tokens": 15142193.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.637905645370483,
|
|
"epoch": 0.7491037508694954,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004953400068833524,
|
|
"loss": 6.6153,
|
|
"mean_token_accuracy": 0.12101433128118515,
|
|
"num_tokens": 15152817.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.557371330261231,
|
|
"epoch": 0.7496388249772593,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004953322626778964,
|
|
"loss": 6.317,
|
|
"mean_token_accuracy": 0.13028131946921348,
|
|
"num_tokens": 15162352.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.673658227920532,
|
|
"epoch": 0.7501738990850233,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004953245121103771,
|
|
"loss": 6.4892,
|
|
"mean_token_accuracy": 0.12943382561206818,
|
|
"num_tokens": 15173091.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.693431568145752,
|
|
"epoch": 0.7507089731927872,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953167551810185,
|
|
"loss": 6.6457,
|
|
"mean_token_accuracy": 0.11348064690828323,
|
|
"num_tokens": 15184422.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.567291927337647,
|
|
"epoch": 0.7512440473005512,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004953089918900447,
|
|
"loss": 6.3901,
|
|
"mean_token_accuracy": 0.13483602181077003,
|
|
"num_tokens": 15194765.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.645245218276978,
|
|
"epoch": 0.751779121408315,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953012222376795,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.11706858575344085,
|
|
"num_tokens": 15206007.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.627328014373779,
|
|
"epoch": 0.752314195516079,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952934462241476,
|
|
"loss": 6.489,
|
|
"mean_token_accuracy": 0.12645872682332993,
|
|
"num_tokens": 15216634.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.62941837310791,
|
|
"epoch": 0.7528492696238429,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004952856638496734,
|
|
"loss": 6.5516,
|
|
"mean_token_accuracy": 0.1180113211274147,
|
|
"num_tokens": 15226931.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.64382848739624,
|
|
"epoch": 0.7533843437316068,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004952778751144817,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.12257011234760284,
|
|
"num_tokens": 15239034.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.664216995239258,
|
|
"epoch": 0.7539194178393708,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004952700800187971,
|
|
"loss": 6.5176,
|
|
"mean_token_accuracy": 0.12180257961153984,
|
|
"num_tokens": 15250088.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.677762746810913,
|
|
"epoch": 0.7544544919471347,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000495262278562845,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.12146370336413384,
|
|
"num_tokens": 15261150.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.664985132217407,
|
|
"epoch": 0.7549895660548986,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004952544707468506,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.12395042702555656,
|
|
"num_tokens": 15270865.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.677373027801513,
|
|
"epoch": 0.7555246401626625,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004952466565710391,
|
|
"loss": 6.5552,
|
|
"mean_token_accuracy": 0.118691186606884,
|
|
"num_tokens": 15282809.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.694124698638916,
|
|
"epoch": 0.7560597142704265,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952388360356366,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.12859989702701569,
|
|
"num_tokens": 15293166.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.616050100326538,
|
|
"epoch": 0.7565947883781904,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004952310091408685,
|
|
"loss": 6.4966,
|
|
"mean_token_accuracy": 0.12518092021346092,
|
|
"num_tokens": 15302985.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.651115751266479,
|
|
"epoch": 0.7571298624859543,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004952231758869611,
|
|
"loss": 6.5415,
|
|
"mean_token_accuracy": 0.1267145797610283,
|
|
"num_tokens": 15314737.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.614376068115234,
|
|
"epoch": 0.7576649365937183,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004952153362741403,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.13092187345027922,
|
|
"num_tokens": 15325441.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.599036788940429,
|
|
"epoch": 0.7582000107014821,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004952074903026327,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.12750762775540353,
|
|
"num_tokens": 15334939.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.595050287246704,
|
|
"epoch": 0.7587350848092461,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004951996379726647,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.12048307284712792,
|
|
"num_tokens": 15345655.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.538129758834839,
|
|
"epoch": 0.75927015891701,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004951917792844631,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.13058631792664527,
|
|
"num_tokens": 15356035.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.659978437423706,
|
|
"epoch": 0.759805233024774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004951839142382548,
|
|
"loss": 6.5094,
|
|
"mean_token_accuracy": 0.12489819005131722,
|
|
"num_tokens": 15368509.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.615253734588623,
|
|
"epoch": 0.7603403071325379,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000495176042834267,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.1264044873416424,
|
|
"num_tokens": 15379662.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.601353359222412,
|
|
"epoch": 0.7608753812403017,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004951681650727268,
|
|
"loss": 6.4844,
|
|
"mean_token_accuracy": 0.11898941099643708,
|
|
"num_tokens": 15389698.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.746938896179199,
|
|
"epoch": 0.7614104553480657,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951602809538619,
|
|
"loss": 6.5772,
|
|
"mean_token_accuracy": 0.11864528879523277,
|
|
"num_tokens": 15400724.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.733620023727417,
|
|
"epoch": 0.7619455294558296,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004951523904778997,
|
|
"loss": 6.5659,
|
|
"mean_token_accuracy": 0.11942593604326249,
|
|
"num_tokens": 15410732.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.618440341949463,
|
|
"epoch": 0.7624806035635936,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004951444936450682,
|
|
"loss": 6.4671,
|
|
"mean_token_accuracy": 0.13049914836883544,
|
|
"num_tokens": 15420185.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.591977787017822,
|
|
"epoch": 0.7630156776713575,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004951365904555954,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.1246684692800045,
|
|
"num_tokens": 15431904.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.575604772567749,
|
|
"epoch": 0.7635507517791215,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951286809097094,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.11952223181724549,
|
|
"num_tokens": 15442650.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.564087724685669,
|
|
"epoch": 0.7640858258868853,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004951207650076388,
|
|
"loss": 6.5026,
|
|
"mean_token_accuracy": 0.12019338682293892,
|
|
"num_tokens": 15454273.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.638538455963134,
|
|
"epoch": 0.7646208999946492,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000495112842749612,
|
|
"loss": 6.4855,
|
|
"mean_token_accuracy": 0.1241270050406456,
|
|
"num_tokens": 15465751.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.656053924560547,
|
|
"epoch": 0.7651559741024132,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004951049141358578,
|
|
"loss": 6.5927,
|
|
"mean_token_accuracy": 0.11400035619735718,
|
|
"num_tokens": 15475340.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.713410806655884,
|
|
"epoch": 0.7656910482101771,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004950969791666051,
|
|
"loss": 6.5507,
|
|
"mean_token_accuracy": 0.1195062555372715,
|
|
"num_tokens": 15486246.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.696958923339844,
|
|
"epoch": 0.7662261223179411,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950890378420831,
|
|
"loss": 6.5556,
|
|
"mean_token_accuracy": 0.12101633250713348,
|
|
"num_tokens": 15497331.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.624008226394653,
|
|
"epoch": 0.766761196425705,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000495081090162521,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.1252144269645214,
|
|
"num_tokens": 15508036.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.651372194290161,
|
|
"epoch": 0.7672962705334689,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004950731361281483,
|
|
"loss": 6.4892,
|
|
"mean_token_accuracy": 0.12409828379750251,
|
|
"num_tokens": 15518381.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.648929023742676,
|
|
"epoch": 0.7678313446412328,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950651757391948,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.12453809827566147,
|
|
"num_tokens": 15528939.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.691262435913086,
|
|
"epoch": 0.7683664187489967,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004950572089958904,
|
|
"loss": 6.4844,
|
|
"mean_token_accuracy": 0.11920621544122696,
|
|
"num_tokens": 15539718.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.671784210205078,
|
|
"epoch": 0.7689014928567607,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004950492358984648,
|
|
"loss": 6.6442,
|
|
"mean_token_accuracy": 0.11607598587870598,
|
|
"num_tokens": 15550970.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.673526191711426,
|
|
"epoch": 0.7694365669645246,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950412564471486,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.1274817906320095,
|
|
"num_tokens": 15560490.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.616913270950318,
|
|
"epoch": 0.7699716410722885,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000495033270642172,
|
|
"loss": 6.4266,
|
|
"mean_token_accuracy": 0.1294262781739235,
|
|
"num_tokens": 15570188.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.589165592193604,
|
|
"epoch": 0.7705067151800524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950252784837655,
|
|
"loss": 6.4459,
|
|
"mean_token_accuracy": 0.12019804939627647,
|
|
"num_tokens": 15581446.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.63636999130249,
|
|
"epoch": 0.7710417892878164,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004950172799721601,
|
|
"loss": 6.5597,
|
|
"mean_token_accuracy": 0.12001867443323136,
|
|
"num_tokens": 15594362.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.646881103515625,
|
|
"epoch": 0.7715768633955803,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004950092751075866,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.13300900235772134,
|
|
"num_tokens": 15605531.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.632643985748291,
|
|
"epoch": 0.7721119375033442,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004950012638902763,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.12664539813995362,
|
|
"num_tokens": 15614962.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.527265357971191,
|
|
"epoch": 0.7726470116111082,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004949932463204603,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.12367821410298348,
|
|
"num_tokens": 15625475.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.600604248046875,
|
|
"epoch": 0.773182085718872,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004949852223983703,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.11932418122887611,
|
|
"num_tokens": 15637359.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.792949867248535,
|
|
"epoch": 0.773717159826636,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004949771921242379,
|
|
"loss": 6.5462,
|
|
"mean_token_accuracy": 0.117109165340662,
|
|
"num_tokens": 15648368.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.6926452159881595,
|
|
"epoch": 0.7742522339343999,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004949691554982951,
|
|
"loss": 6.4385,
|
|
"mean_token_accuracy": 0.13027268201112746,
|
|
"num_tokens": 15659295.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.543884658813477,
|
|
"epoch": 0.7747873080421639,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004949611125207737,
|
|
"loss": 6.4051,
|
|
"mean_token_accuracy": 0.12192230448126792,
|
|
"num_tokens": 15669975.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.570065546035766,
|
|
"epoch": 0.7753223821499278,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494953063191906,
|
|
"loss": 6.4946,
|
|
"mean_token_accuracy": 0.11872415691614151,
|
|
"num_tokens": 15680343.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.683220624923706,
|
|
"epoch": 0.7758574562576916,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004949450075119247,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.12026704177260399,
|
|
"num_tokens": 15692246.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.6822953701019285,
|
|
"epoch": 0.7763925303654556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004949369454810621,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.12393845468759537,
|
|
"num_tokens": 15704262.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.547556638717651,
|
|
"epoch": 0.7769276044732195,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004949288770995512,
|
|
"loss": 6.4991,
|
|
"mean_token_accuracy": 0.12381231859326362,
|
|
"num_tokens": 15715078.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.660402727127075,
|
|
"epoch": 0.7774626785809835,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004949208023676249,
|
|
"loss": 6.5459,
|
|
"mean_token_accuracy": 0.1232883907854557,
|
|
"num_tokens": 15726503.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.587308025360107,
|
|
"epoch": 0.7779977526887474,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004949127212855161,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.12670731246471406,
|
|
"num_tokens": 15738854.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.611951589584351,
|
|
"epoch": 0.7785328267965114,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004949046338534587,
|
|
"loss": 6.5893,
|
|
"mean_token_accuracy": 0.12085817605257035,
|
|
"num_tokens": 15750836.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.783895874023438,
|
|
"epoch": 0.7790679009042752,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004948965400716857,
|
|
"loss": 6.5934,
|
|
"mean_token_accuracy": 0.12155032604932785,
|
|
"num_tokens": 15762355.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.6959075927734375,
|
|
"epoch": 0.7796029750120391,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000494888439940431,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.12169316858053207,
|
|
"num_tokens": 15772952.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.562328147888183,
|
|
"epoch": 0.7801380491198031,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004948803334599286,
|
|
"loss": 6.4051,
|
|
"mean_token_accuracy": 0.13314662128686905,
|
|
"num_tokens": 15782997.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.598123836517334,
|
|
"epoch": 0.780673123227567,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948722206304123,
|
|
"loss": 6.5065,
|
|
"mean_token_accuracy": 0.12343615815043449,
|
|
"num_tokens": 15794060.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.707820177078247,
|
|
"epoch": 0.781208197335331,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004948641014521167,
|
|
"loss": 6.5704,
|
|
"mean_token_accuracy": 0.12031665593385696,
|
|
"num_tokens": 15804149.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.668608617782593,
|
|
"epoch": 0.7817432714430949,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000494855975925276,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.12902145832777023,
|
|
"num_tokens": 15814643.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.645229959487915,
|
|
"epoch": 0.7822783455508588,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004948478440501249,
|
|
"loss": 6.4438,
|
|
"mean_token_accuracy": 0.1254532441496849,
|
|
"num_tokens": 15824640.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.553537178039551,
|
|
"epoch": 0.7828134196586227,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004948397058268982,
|
|
"loss": 6.4806,
|
|
"mean_token_accuracy": 0.12377227991819381,
|
|
"num_tokens": 15836160.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.6396448612213135,
|
|
"epoch": 0.7833484937663866,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004948315612558308,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.12054053619503975,
|
|
"num_tokens": 15846886.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.6480477809906,
|
|
"epoch": 0.7838835678741506,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000494823410337158,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.13052470311522485,
|
|
"num_tokens": 15857309.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.601436614990234,
|
|
"epoch": 0.7844186419819145,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004948152530711153,
|
|
"loss": 6.5795,
|
|
"mean_token_accuracy": 0.12191757187247276,
|
|
"num_tokens": 15869620.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.614558506011963,
|
|
"epoch": 0.7849537160896785,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004948070894579378,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.129998816549778,
|
|
"num_tokens": 15880915.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.605517482757568,
|
|
"epoch": 0.7854887901974423,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004947989194978616,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.1268579512834549,
|
|
"num_tokens": 15891150.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.656474876403808,
|
|
"epoch": 0.7860238643052063,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004947907431911225,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.12626128271222115,
|
|
"num_tokens": 15902526.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.591264724731445,
|
|
"epoch": 0.7865589384129702,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004947825605379566,
|
|
"loss": 6.4372,
|
|
"mean_token_accuracy": 0.12627596408128738,
|
|
"num_tokens": 15913425.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.613666772842407,
|
|
"epoch": 0.7870940125207341,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004947743715386,
|
|
"loss": 6.4193,
|
|
"mean_token_accuracy": 0.12343008667230607,
|
|
"num_tokens": 15924324.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.57948784828186,
|
|
"epoch": 0.7876290866284981,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004947661761932894,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.12277128249406814,
|
|
"num_tokens": 15935533.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.5657641887664795,
|
|
"epoch": 0.7881641607362619,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004947579745022613,
|
|
"loss": 6.4295,
|
|
"mean_token_accuracy": 0.12148091346025466,
|
|
"num_tokens": 15947007.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.581766366958618,
|
|
"epoch": 0.7886992348440259,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004947497664657527,
|
|
"loss": 6.4862,
|
|
"mean_token_accuracy": 0.12112942487001419,
|
|
"num_tokens": 15957405.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.61507477760315,
|
|
"epoch": 0.7892343089517898,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004947415520840003,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.12532250955700874,
|
|
"num_tokens": 15969895.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.637605905532837,
|
|
"epoch": 0.7897693830595538,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004947333313572416,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.13630961254239082,
|
|
"num_tokens": 15979854.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.567370319366455,
|
|
"epoch": 0.7903044571673177,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004947251042857137,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.13095270618796348,
|
|
"num_tokens": 15991341.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.531961727142334,
|
|
"epoch": 0.7908395312750816,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004947168708696544,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.12993446215987206,
|
|
"num_tokens": 16001944.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.560093545913697,
|
|
"epoch": 0.7913746053828455,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004947086311093013,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.1281399607658386,
|
|
"num_tokens": 16011771.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.687586164474487,
|
|
"epoch": 0.7919096794906094,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004947003850048924,
|
|
"loss": 6.6005,
|
|
"mean_token_accuracy": 0.11408599764108658,
|
|
"num_tokens": 16023901.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.740469646453858,
|
|
"epoch": 0.7924447535983734,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004946921325566656,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.1196585789322853,
|
|
"num_tokens": 16035014.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.650988531112671,
|
|
"epoch": 0.7929798277061373,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004946838737648595,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.11678230240941048,
|
|
"num_tokens": 16046927.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.613309526443482,
|
|
"epoch": 0.7935149018139013,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004946756086297124,
|
|
"loss": 6.4909,
|
|
"mean_token_accuracy": 0.12795686945319176,
|
|
"num_tokens": 16057341.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.654987621307373,
|
|
"epoch": 0.7940499759216652,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004946673371514628,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.12236208170652389,
|
|
"num_tokens": 16068408.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.5727095127105715,
|
|
"epoch": 0.794585050029429,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004946590593303499,
|
|
"loss": 6.4494,
|
|
"mean_token_accuracy": 0.1296915277838707,
|
|
"num_tokens": 16078693.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.60039119720459,
|
|
"epoch": 0.795120124137193,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004946507751666124,
|
|
"loss": 6.4975,
|
|
"mean_token_accuracy": 0.1274369865655899,
|
|
"num_tokens": 16089127.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.586338949203491,
|
|
"epoch": 0.7956551982449569,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004946424846604897,
|
|
"loss": 6.4071,
|
|
"mean_token_accuracy": 0.13582724407315255,
|
|
"num_tokens": 16099726.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.615121269226075,
|
|
"epoch": 0.7961902723527209,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004946341878122212,
|
|
"loss": 6.4573,
|
|
"mean_token_accuracy": 0.12698574587702752,
|
|
"num_tokens": 16111017.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.624665117263794,
|
|
"epoch": 0.7967253464604848,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004946258846220462,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.12629680335521698,
|
|
"num_tokens": 16121406.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.636161994934082,
|
|
"epoch": 0.7972604205682488,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004946175750902049,
|
|
"loss": 6.4516,
|
|
"mean_token_accuracy": 0.12538782581686975,
|
|
"num_tokens": 16131587.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.5716126441955565,
|
|
"epoch": 0.7977954946760126,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004946092592169368,
|
|
"loss": 6.4116,
|
|
"mean_token_accuracy": 0.12958415150642394,
|
|
"num_tokens": 16142578.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.619257640838623,
|
|
"epoch": 0.7983305687837765,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004946009370024822,
|
|
"loss": 6.426,
|
|
"mean_token_accuracy": 0.1310078866779804,
|
|
"num_tokens": 16153501.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.572661924362182,
|
|
"epoch": 0.7988656428915405,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004945926084470814,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.12284256890416145,
|
|
"num_tokens": 16164273.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.610775899887085,
|
|
"epoch": 0.7994007169993044,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004945842735509749,
|
|
"loss": 6.4856,
|
|
"mean_token_accuracy": 0.12552264481782913,
|
|
"num_tokens": 16175071.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.680575323104859,
|
|
"epoch": 0.7999357911070684,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004945759323144034,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.11573776230216026,
|
|
"num_tokens": 16185404.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.629665231704712,
|
|
"epoch": 0.8004708652148322,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004945675847376077,
|
|
"loss": 6.5139,
|
|
"mean_token_accuracy": 0.12014818266034126,
|
|
"num_tokens": 16196881.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.639012718200684,
|
|
"epoch": 0.8010059393225962,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004945592308208288,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.12018415406346321,
|
|
"num_tokens": 16207534.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.646149730682373,
|
|
"epoch": 0.8015410134303601,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000494550870564308,
|
|
"loss": 6.4188,
|
|
"mean_token_accuracy": 0.13105716928839684,
|
|
"num_tokens": 16217371.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.6225439548492435,
|
|
"epoch": 0.802076087538124,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004945425039682866,
|
|
"loss": 6.467,
|
|
"mean_token_accuracy": 0.1279752753674984,
|
|
"num_tokens": 16227898.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.564583015441895,
|
|
"epoch": 0.802611161645888,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004945341310330064,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.1270508736371994,
|
|
"num_tokens": 16238966.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.590152359008789,
|
|
"epoch": 0.8031462357536518,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004945257517587089,
|
|
"loss": 6.4931,
|
|
"mean_token_accuracy": 0.12701256275177003,
|
|
"num_tokens": 16250129.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.5930369853973385,
|
|
"epoch": 0.8036813098614158,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004945173661456361,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.12291709631681443,
|
|
"num_tokens": 16260877.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.699715852737427,
|
|
"epoch": 0.8042163839691797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004945089741940303,
|
|
"loss": 6.472,
|
|
"mean_token_accuracy": 0.12913578376173973,
|
|
"num_tokens": 16270548.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.676292562484742,
|
|
"epoch": 0.8047514580769437,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004945005759041338,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.12249005734920501,
|
|
"num_tokens": 16281014.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.624485683441162,
|
|
"epoch": 0.8052865321847076,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004944921712761889,
|
|
"loss": 6.5405,
|
|
"mean_token_accuracy": 0.12573966085910798,
|
|
"num_tokens": 16291653.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.5947753429412845,
|
|
"epoch": 0.8058216062924715,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004944837603104383,
|
|
"loss": 6.3863,
|
|
"mean_token_accuracy": 0.13147774934768677,
|
|
"num_tokens": 16301703.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.560491371154785,
|
|
"epoch": 0.8063566804002354,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004944753430071252,
|
|
"loss": 6.4576,
|
|
"mean_token_accuracy": 0.12715979367494584,
|
|
"num_tokens": 16312252.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.584918880462647,
|
|
"epoch": 0.8068917545079993,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004944669193664923,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.12487595155835152,
|
|
"num_tokens": 16324073.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.6717156887054445,
|
|
"epoch": 0.8074268286157633,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004944584893887829,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.12484904229640961,
|
|
"num_tokens": 16334637.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.605461120605469,
|
|
"epoch": 0.8079619027235272,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004944500530742404,
|
|
"loss": 6.5743,
|
|
"mean_token_accuracy": 0.11794036030769348,
|
|
"num_tokens": 16345581.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.6252374172210695,
|
|
"epoch": 0.8084969768312912,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004944416104231086,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.1216730572283268,
|
|
"num_tokens": 16356995.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.688077592849732,
|
|
"epoch": 0.8090320509390551,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004944331614356311,
|
|
"loss": 6.5093,
|
|
"mean_token_accuracy": 0.11890427842736244,
|
|
"num_tokens": 16368841.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.692157506942749,
|
|
"epoch": 0.8095671250468189,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004944247061120519,
|
|
"loss": 6.4279,
|
|
"mean_token_accuracy": 0.12462588772177696,
|
|
"num_tokens": 16379295.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.576985025405884,
|
|
"epoch": 0.8101021991545829,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004944162444526151,
|
|
"loss": 6.4721,
|
|
"mean_token_accuracy": 0.13099455311894417,
|
|
"num_tokens": 16389512.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.476492547988892,
|
|
"epoch": 0.8106372732623468,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004944077764575651,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.13501969650387763,
|
|
"num_tokens": 16400720.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.580502033233643,
|
|
"epoch": 0.8111723473701108,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004943993021271463,
|
|
"loss": 6.4658,
|
|
"mean_token_accuracy": 0.12537092193961144,
|
|
"num_tokens": 16411278.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.67013144493103,
|
|
"epoch": 0.8117074214778747,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004943908214616035,
|
|
"loss": 6.5088,
|
|
"mean_token_accuracy": 0.12090714648365974,
|
|
"num_tokens": 16421665.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.671138763427734,
|
|
"epoch": 0.8122424955856387,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004943823344611818,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.11637551337480545,
|
|
"num_tokens": 16432943.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.666892385482788,
|
|
"epoch": 0.8127775696934025,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004943738411261258,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.12569426372647285,
|
|
"num_tokens": 16444506.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.5838854789733885,
|
|
"epoch": 0.8133126438011664,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004943653414566809,
|
|
"loss": 6.4841,
|
|
"mean_token_accuracy": 0.12255563437938691,
|
|
"num_tokens": 16455403.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.685585021972656,
|
|
"epoch": 0.8138477179089304,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004943568354530927,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.11601466611027718,
|
|
"num_tokens": 16465616.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.6593701362609865,
|
|
"epoch": 0.8143827920166943,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004943483231156068,
|
|
"loss": 6.5438,
|
|
"mean_token_accuracy": 0.12109178379178047,
|
|
"num_tokens": 16476850.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.668148422241211,
|
|
"epoch": 0.8149178661244583,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004943398044444687,
|
|
"loss": 6.4975,
|
|
"mean_token_accuracy": 0.1246594287455082,
|
|
"num_tokens": 16489118.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.676653909683227,
|
|
"epoch": 0.8154529402322221,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004943312794399246,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.12908004522323607,
|
|
"num_tokens": 16499336.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.601690435409546,
|
|
"epoch": 0.8159880143399861,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004943227481022207,
|
|
"loss": 6.5219,
|
|
"mean_token_accuracy": 0.11842733025550842,
|
|
"num_tokens": 16510158.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.564496660232544,
|
|
"epoch": 0.81652308844775,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004943142104316033,
|
|
"loss": 6.4621,
|
|
"mean_token_accuracy": 0.12559000104665757,
|
|
"num_tokens": 16521080.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.656149530410767,
|
|
"epoch": 0.8170581625555139,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004943056664283189,
|
|
"loss": 6.4704,
|
|
"mean_token_accuracy": 0.12910144105553628,
|
|
"num_tokens": 16531072.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.6499816417694095,
|
|
"epoch": 0.8175932366632779,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000494297116092614,
|
|
"loss": 6.5586,
|
|
"mean_token_accuracy": 0.11900619938969612,
|
|
"num_tokens": 16542588.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.663675832748413,
|
|
"epoch": 0.8181283107710418,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004942885594247359,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.12086946368217469,
|
|
"num_tokens": 16553466.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.618226099014282,
|
|
"epoch": 0.8186633848788057,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004942799964249314,
|
|
"loss": 6.4553,
|
|
"mean_token_accuracy": 0.1253214955329895,
|
|
"num_tokens": 16564084.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.56568751335144,
|
|
"epoch": 0.8191984589865696,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942714270934479,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.13621146976947784,
|
|
"num_tokens": 16575665.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.610156917572022,
|
|
"epoch": 0.8197335330943336,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004942628514305326,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.12168620154261589,
|
|
"num_tokens": 16586518.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.63839054107666,
|
|
"epoch": 0.8202686072020975,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004942542694364333,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12710672691464425,
|
|
"num_tokens": 16597345.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.6390495777130125,
|
|
"epoch": 0.8208036813098614,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004942456811113978,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.12848000451922417,
|
|
"num_tokens": 16609586.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.635290050506592,
|
|
"epoch": 0.8213387554176254,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004942370864556741,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.13500959426164627,
|
|
"num_tokens": 16620165.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.571346569061279,
|
|
"epoch": 0.8218738295253892,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004942284854695104,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12547776997089385,
|
|
"num_tokens": 16631200.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.609015321731567,
|
|
"epoch": 0.8224089036331532,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004942198781531549,
|
|
"loss": 6.5048,
|
|
"mean_token_accuracy": 0.1238760806620121,
|
|
"num_tokens": 16642553.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.665633964538574,
|
|
"epoch": 0.8229439777409171,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004942112645068561,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.12217526063323021,
|
|
"num_tokens": 16653431.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.571784734725952,
|
|
"epoch": 0.8234790518486811,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000494202644530863,
|
|
"loss": 6.4593,
|
|
"mean_token_accuracy": 0.12343985810875893,
|
|
"num_tokens": 16664880.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.5380603790283205,
|
|
"epoch": 0.824014125956445,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004941940182254244,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.12872528284788132,
|
|
"num_tokens": 16676224.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.582237911224365,
|
|
"epoch": 0.8245492000642088,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004941853855907892,
|
|
"loss": 6.5396,
|
|
"mean_token_accuracy": 0.12095732614398003,
|
|
"num_tokens": 16687732.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.682282161712647,
|
|
"epoch": 0.8250842741719728,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004941767466272068,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.129934361577034,
|
|
"num_tokens": 16698257.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.666169214248657,
|
|
"epoch": 0.8256193482797367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004941681013349267,
|
|
"loss": 6.4383,
|
|
"mean_token_accuracy": 0.12359966635704041,
|
|
"num_tokens": 16708860.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.602855110168457,
|
|
"epoch": 0.8261544223875007,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004941594497141985,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.12608251199126244,
|
|
"num_tokens": 16719987.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.643445825576782,
|
|
"epoch": 0.8266894964952646,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004941507917652718,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.11999792009592056,
|
|
"num_tokens": 16730861.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.553995418548584,
|
|
"epoch": 0.8272245706030286,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004941421274883969,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.13347533941268921,
|
|
"num_tokens": 16740968.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.578843641281128,
|
|
"epoch": 0.8277596447107924,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494133456883824,
|
|
"loss": 6.4878,
|
|
"mean_token_accuracy": 0.12768243104219437,
|
|
"num_tokens": 16750700.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.617146635055542,
|
|
"epoch": 0.8282947188185563,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004941247799518031,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.12326866835355758,
|
|
"num_tokens": 16760719.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.594090604782105,
|
|
"epoch": 0.8288297929263203,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004941160966925851,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.1272714115679264,
|
|
"num_tokens": 16771331.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.494041490554809,
|
|
"epoch": 0.8293648670340842,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004941074071064205,
|
|
"loss": 6.4433,
|
|
"mean_token_accuracy": 0.12712007239460946,
|
|
"num_tokens": 16781306.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.638606166839599,
|
|
"epoch": 0.8298999411418482,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004940987111935605,
|
|
"loss": 6.4686,
|
|
"mean_token_accuracy": 0.12214233577251435,
|
|
"num_tokens": 16793013.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.612168407440185,
|
|
"epoch": 0.830435015249612,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004940900089542558,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.12796134501695633,
|
|
"num_tokens": 16803987.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.5910180568695065,
|
|
"epoch": 0.830970089357376,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000494081300388758,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.11712961420416831,
|
|
"num_tokens": 16815031.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.678561735153198,
|
|
"epoch": 0.8315051634651399,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004940725854973184,
|
|
"loss": 6.5281,
|
|
"mean_token_accuracy": 0.12335440516471863,
|
|
"num_tokens": 16826313.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.646420955657959,
|
|
"epoch": 0.8320402375729038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004940638642801886,
|
|
"loss": 6.5086,
|
|
"mean_token_accuracy": 0.12422936633229256,
|
|
"num_tokens": 16838470.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.546121120452881,
|
|
"epoch": 0.8325753116806678,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004940551367376205,
|
|
"loss": 6.4028,
|
|
"mean_token_accuracy": 0.12903384640812873,
|
|
"num_tokens": 16849266.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.566736698150635,
|
|
"epoch": 0.8331103857884317,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004940464028698662,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.12425655499100685,
|
|
"num_tokens": 16860720.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.63223614692688,
|
|
"epoch": 0.8336454598961957,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940376626771779,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.12509471029043198,
|
|
"num_tokens": 16872004.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.648682880401611,
|
|
"epoch": 0.8341805340039595,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004940289161598076,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.1173703834414482,
|
|
"num_tokens": 16882898.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.628533267974854,
|
|
"epoch": 0.8347156081117235,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004940201633180084,
|
|
"loss": 6.4511,
|
|
"mean_token_accuracy": 0.11566249057650566,
|
|
"num_tokens": 16894331.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.6906242847442625,
|
|
"epoch": 0.8352506822194874,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004940114041520326,
|
|
"loss": 6.5387,
|
|
"mean_token_accuracy": 0.1246345192193985,
|
|
"num_tokens": 16903656.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.581471395492554,
|
|
"epoch": 0.8357857563272513,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004940026386621333,
|
|
"loss": 6.5019,
|
|
"mean_token_accuracy": 0.12531133443117143,
|
|
"num_tokens": 16915878.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.6755578994750975,
|
|
"epoch": 0.8363208304350153,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004939938668485636,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.1215199887752533,
|
|
"num_tokens": 16926577.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.565039253234863,
|
|
"epoch": 0.8368559045427791,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004939850887115768,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.1319645993411541,
|
|
"num_tokens": 16938012.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.569745969772339,
|
|
"epoch": 0.8373909786505431,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004939763042514263,
|
|
"loss": 6.4132,
|
|
"mean_token_accuracy": 0.12320912629365921,
|
|
"num_tokens": 16949007.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.491839742660522,
|
|
"epoch": 0.837926052758307,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004939675134683658,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.13265551403164863,
|
|
"num_tokens": 16959425.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.643397045135498,
|
|
"epoch": 0.838461126866071,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004939587163626491,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.11856562122702599,
|
|
"num_tokens": 16970002.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.622504758834839,
|
|
"epoch": 0.8389962009738349,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004939499129345302,
|
|
"loss": 6.5261,
|
|
"mean_token_accuracy": 0.12169675678014755,
|
|
"num_tokens": 16980739.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.638087224960327,
|
|
"epoch": 0.8395312750815987,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004939411031842633,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.1255985088646412,
|
|
"num_tokens": 16991643.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.454816770553589,
|
|
"epoch": 0.8400663491893627,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000493932287112103,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.1409579671919346,
|
|
"num_tokens": 17001975.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.637519359588623,
|
|
"epoch": 0.8406014232971266,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004939234647183035,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.12199027836322784,
|
|
"num_tokens": 17012658.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.653904962539673,
|
|
"epoch": 0.8411364974048906,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004939146360031197,
|
|
"loss": 6.4875,
|
|
"mean_token_accuracy": 0.12131756246089935,
|
|
"num_tokens": 17023196.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.606409931182862,
|
|
"epoch": 0.8416715715126545,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004939058009668067,
|
|
"loss": 6.5086,
|
|
"mean_token_accuracy": 0.12194685339927673,
|
|
"num_tokens": 17034589.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.642972040176391,
|
|
"epoch": 0.8422066456204185,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004938969596096194,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.12159970998764039,
|
|
"num_tokens": 17046139.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.589673328399658,
|
|
"epoch": 0.8427417197281823,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000493888111931813,
|
|
"loss": 6.4945,
|
|
"mean_token_accuracy": 0.12014141380786895,
|
|
"num_tokens": 17056926.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.539459180831909,
|
|
"epoch": 0.8432767938359462,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004938792579336433,
|
|
"loss": 6.4375,
|
|
"mean_token_accuracy": 0.12531604021787643,
|
|
"num_tokens": 17067339.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.603718090057373,
|
|
"epoch": 0.8438118679437102,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004938703976153657,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.1254698507487774,
|
|
"num_tokens": 17078037.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.632722282409668,
|
|
"epoch": 0.8443469420514741,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004938615309772362,
|
|
"loss": 6.4862,
|
|
"mean_token_accuracy": 0.11615241914987565,
|
|
"num_tokens": 17089069.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.616069984436035,
|
|
"epoch": 0.8448820161592381,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004938526580195107,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.12840015292167664,
|
|
"num_tokens": 17100006.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.608232641220093,
|
|
"epoch": 0.845417090267002,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004938437787424454,
|
|
"loss": 6.501,
|
|
"mean_token_accuracy": 0.12470883950591087,
|
|
"num_tokens": 17111896.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.601596450805664,
|
|
"epoch": 0.845952164374766,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004938348931462969,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.1278610810637474,
|
|
"num_tokens": 17123202.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.600058317184448,
|
|
"epoch": 0.8464872384825298,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004938260012313215,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.12930461540818214,
|
|
"num_tokens": 17134013.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.536851596832276,
|
|
"epoch": 0.8470223125902937,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004938171029977761,
|
|
"loss": 6.4564,
|
|
"mean_token_accuracy": 0.12916264310479164,
|
|
"num_tokens": 17144041.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.553992843627929,
|
|
"epoch": 0.8475573866980577,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004938081984459176,
|
|
"loss": 6.4397,
|
|
"mean_token_accuracy": 0.12721440196037292,
|
|
"num_tokens": 17155334.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.6116251945495605,
|
|
"epoch": 0.8480924608058216,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000493799287576003,
|
|
"loss": 6.3996,
|
|
"mean_token_accuracy": 0.12881384789943695,
|
|
"num_tokens": 17166243.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.599978303909301,
|
|
"epoch": 0.8486275349135856,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004937903703882898,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.12380218654870986,
|
|
"num_tokens": 17177709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.550316333770752,
|
|
"epoch": 0.8491626090213494,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004937814468830353,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.12615659311413766,
|
|
"num_tokens": 17188275.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.639209222793579,
|
|
"epoch": 0.8496976831291134,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004937725170604975,
|
|
"loss": 6.5549,
|
|
"mean_token_accuracy": 0.12421398386359214,
|
|
"num_tokens": 17199527.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.658242416381836,
|
|
"epoch": 0.8502327572368773,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004937635809209339,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.12579896971583365,
|
|
"num_tokens": 17209500.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.567161989212036,
|
|
"epoch": 0.8507678313446412,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004937546384646027,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.1228828877210617,
|
|
"num_tokens": 17219589.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.668274545669556,
|
|
"epoch": 0.8513029054524052,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004937456896917619,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.1268440864980221,
|
|
"num_tokens": 17230508.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.628099966049194,
|
|
"epoch": 0.851837979560169,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004937367346026702,
|
|
"loss": 6.4648,
|
|
"mean_token_accuracy": 0.12629646956920623,
|
|
"num_tokens": 17240886.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.5766232967376705,
|
|
"epoch": 0.852373053667933,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004937277731975858,
|
|
"loss": 6.4924,
|
|
"mean_token_accuracy": 0.12928350567817687,
|
|
"num_tokens": 17252247.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.573000049591064,
|
|
"epoch": 0.8529081277756969,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004937188054767679,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.12772766575217248,
|
|
"num_tokens": 17262845.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.6421280860900875,
|
|
"epoch": 0.8534432018834609,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004937098314404751,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.12444490268826484,
|
|
"num_tokens": 17274247.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.644790935516357,
|
|
"epoch": 0.8539782759912248,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004937008510889668,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.12767765745520593,
|
|
"num_tokens": 17285471.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.589143466949463,
|
|
"epoch": 0.8545133500989887,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004936918644225021,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.12948852255940438,
|
|
"num_tokens": 17296243.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.579883146286011,
|
|
"epoch": 0.8550484242067526,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004936828714413405,
|
|
"loss": 6.4633,
|
|
"mean_token_accuracy": 0.12740985825657844,
|
|
"num_tokens": 17307301.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.545937824249267,
|
|
"epoch": 0.8555834983145165,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004936738721457417,
|
|
"loss": 6.3969,
|
|
"mean_token_accuracy": 0.13528102710843087,
|
|
"num_tokens": 17318550.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.5888251781463625,
|
|
"epoch": 0.8561185724222805,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936648665359657,
|
|
"loss": 6.4592,
|
|
"mean_token_accuracy": 0.12461457923054695,
|
|
"num_tokens": 17328577.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.586920166015625,
|
|
"epoch": 0.8566536465300444,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004936558546122723,
|
|
"loss": 6.5184,
|
|
"mean_token_accuracy": 0.12257596775889397,
|
|
"num_tokens": 17341013.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.589303112030029,
|
|
"epoch": 0.8571887206378084,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004936468363749217,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.12056496143341064,
|
|
"num_tokens": 17351956.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.6829746723175045,
|
|
"epoch": 0.8577237947455723,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004936378118241746,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.117622260004282,
|
|
"num_tokens": 17363465.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.584981489181518,
|
|
"epoch": 0.8582588688533361,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004936287809602913,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.1258731223642826,
|
|
"num_tokens": 17374458.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.558772945404053,
|
|
"epoch": 0.8587939429611001,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004936197437835329,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.12399565950036048,
|
|
"num_tokens": 17385492.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.684000682830811,
|
|
"epoch": 0.859329017068864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004936107002941599,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.1296046145260334,
|
|
"num_tokens": 17395640.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.621039772033692,
|
|
"epoch": 0.859864091176628,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004936016504924337,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.12447260543704033,
|
|
"num_tokens": 17405211.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.572212600708008,
|
|
"epoch": 0.8603991652843919,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935925943786155,
|
|
"loss": 6.4385,
|
|
"mean_token_accuracy": 0.12494494318962097,
|
|
"num_tokens": 17415421.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.5851781368255615,
|
|
"epoch": 0.8609342393921559,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004935835319529669,
|
|
"loss": 6.4882,
|
|
"mean_token_accuracy": 0.12248977199196816,
|
|
"num_tokens": 17426040.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.55501275062561,
|
|
"epoch": 0.8614693134999197,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004935744632157496,
|
|
"loss": 6.4693,
|
|
"mean_token_accuracy": 0.12371492311358452,
|
|
"num_tokens": 17436305.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.602463960647583,
|
|
"epoch": 0.8620043876076836,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004935653881672253,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.12265571355819702,
|
|
"num_tokens": 17446786.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.612880706787109,
|
|
"epoch": 0.8625394617154476,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935563068076561,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.1300605744123459,
|
|
"num_tokens": 17456613.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.542842960357666,
|
|
"epoch": 0.8630745358232115,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004935472191373044,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.12812848910689353,
|
|
"num_tokens": 17467281.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.56179370880127,
|
|
"epoch": 0.8636096099309755,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004935381251564324,
|
|
"loss": 6.4896,
|
|
"mean_token_accuracy": 0.12458937540650368,
|
|
"num_tokens": 17478271.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.59501895904541,
|
|
"epoch": 0.8641446840387393,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004935290248653027,
|
|
"loss": 6.4665,
|
|
"mean_token_accuracy": 0.12613890841603279,
|
|
"num_tokens": 17489519.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.614124202728272,
|
|
"epoch": 0.8646797581465033,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004935199182641781,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.12557547613978387,
|
|
"num_tokens": 17500076.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.614273643493652,
|
|
"epoch": 0.8652148322542672,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004935108053533216,
|
|
"loss": 6.4453,
|
|
"mean_token_accuracy": 0.12125986739993096,
|
|
"num_tokens": 17509898.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.550960397720337,
|
|
"epoch": 0.8657499063620312,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935016861329964,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.1296715520322323,
|
|
"num_tokens": 17519890.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.530986309051514,
|
|
"epoch": 0.8662849804697951,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004934925606034656,
|
|
"loss": 6.4381,
|
|
"mean_token_accuracy": 0.12463523522019386,
|
|
"num_tokens": 17530927.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.6647419929504395,
|
|
"epoch": 0.866820054577559,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004934834287649928,
|
|
"loss": 6.5129,
|
|
"mean_token_accuracy": 0.12179197296500206,
|
|
"num_tokens": 17541174.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.6586121082305905,
|
|
"epoch": 0.8673551286853229,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004934742906178417,
|
|
"loss": 6.4765,
|
|
"mean_token_accuracy": 0.11956845298409462,
|
|
"num_tokens": 17552460.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.6295825958251955,
|
|
"epoch": 0.8678902027930868,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004934651461622762,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.12741912975907327,
|
|
"num_tokens": 17563908.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.586279296875,
|
|
"epoch": 0.8684252769008508,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004934559953985603,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.1282585471868515,
|
|
"num_tokens": 17574314.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.640317058563232,
|
|
"epoch": 0.8689603510086147,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004934468383269582,
|
|
"loss": 6.4568,
|
|
"mean_token_accuracy": 0.12750404104590415,
|
|
"num_tokens": 17583719.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.520741510391235,
|
|
"epoch": 0.8694954251163787,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004934376749477344,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.1261451207101345,
|
|
"num_tokens": 17594522.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.550720930099487,
|
|
"epoch": 0.8700304992241426,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004934285052611533,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.13392736613750458,
|
|
"num_tokens": 17604632.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.7096068382263185,
|
|
"epoch": 0.8705655733319064,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00049341932926748,
|
|
"loss": 6.5216,
|
|
"mean_token_accuracy": 0.12129078730940819,
|
|
"num_tokens": 17615459.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.650518894195557,
|
|
"epoch": 0.8711006474396704,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004934101469669791,
|
|
"loss": 6.4636,
|
|
"mean_token_accuracy": 0.1257311299443245,
|
|
"num_tokens": 17625800.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.517386484146118,
|
|
"epoch": 0.8716357215474343,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004934009583599159,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.13819433227181435,
|
|
"num_tokens": 17637264.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.515216493606568,
|
|
"epoch": 0.8721707956551983,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004933917634465558,
|
|
"loss": 6.3499,
|
|
"mean_token_accuracy": 0.12682703286409377,
|
|
"num_tokens": 17648256.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.564549684524536,
|
|
"epoch": 0.8727058697629622,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004933825622271642,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.12459777966141701,
|
|
"num_tokens": 17659096.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.629525566101075,
|
|
"epoch": 0.8732409438707261,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004933733547020069,
|
|
"loss": 6.4714,
|
|
"mean_token_accuracy": 0.12370945960283279,
|
|
"num_tokens": 17669808.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.615776252746582,
|
|
"epoch": 0.87377601797849,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004933641408713495,
|
|
"loss": 6.4171,
|
|
"mean_token_accuracy": 0.12331488877534866,
|
|
"num_tokens": 17680375.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.513298511505127,
|
|
"epoch": 0.8743110920862539,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933549207354582,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.13013615384697913,
|
|
"num_tokens": 17690780.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.601052331924438,
|
|
"epoch": 0.8748461661940179,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004933456942945994,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.12874177172780038,
|
|
"num_tokens": 17702170.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.5550049304962155,
|
|
"epoch": 0.8753812403017818,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004933364615490393,
|
|
"loss": 6.4206,
|
|
"mean_token_accuracy": 0.12599021792411805,
|
|
"num_tokens": 17712631.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.611193418502808,
|
|
"epoch": 0.8759163144095458,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004933272224990445,
|
|
"loss": 6.5003,
|
|
"mean_token_accuracy": 0.12176733165979385,
|
|
"num_tokens": 17723692.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.6318916320800785,
|
|
"epoch": 0.8764513885173096,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004933179771448819,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.13463898748159409,
|
|
"num_tokens": 17735264.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.5342247009277346,
|
|
"epoch": 0.8769864626250736,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004933087254868183,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.1375872351229191,
|
|
"num_tokens": 17747060.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.510075902938842,
|
|
"epoch": 0.8775215367328375,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000493299467525121,
|
|
"loss": 6.4422,
|
|
"mean_token_accuracy": 0.12407493069767953,
|
|
"num_tokens": 17758159.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.57683801651001,
|
|
"epoch": 0.8780566108406014,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004932902032600573,
|
|
"loss": 6.4594,
|
|
"mean_token_accuracy": 0.12217129170894622,
|
|
"num_tokens": 17768444.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.646522092819214,
|
|
"epoch": 0.8785916849483654,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004932809326918945,
|
|
"loss": 6.3517,
|
|
"mean_token_accuracy": 0.1339459776878357,
|
|
"num_tokens": 17779303.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.622037935256958,
|
|
"epoch": 0.8791267590561292,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004932716558209005,
|
|
"loss": 6.5405,
|
|
"mean_token_accuracy": 0.11944242864847184,
|
|
"num_tokens": 17789853.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.602828121185302,
|
|
"epoch": 0.8796618331638932,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004932623726473432,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.1371438518166542,
|
|
"num_tokens": 17799232.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.487914800643921,
|
|
"epoch": 0.8801969072716571,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004932530831714904,
|
|
"loss": 6.4097,
|
|
"mean_token_accuracy": 0.12824408933520318,
|
|
"num_tokens": 17808870.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.5319726943969725,
|
|
"epoch": 0.8807319813794211,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004932437873936107,
|
|
"loss": 6.4906,
|
|
"mean_token_accuracy": 0.11963605657219886,
|
|
"num_tokens": 17819394.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.662888050079346,
|
|
"epoch": 0.881267055487185,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004932344853139721,
|
|
"loss": 6.4679,
|
|
"mean_token_accuracy": 0.12477930113673211,
|
|
"num_tokens": 17830220.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.598001623153687,
|
|
"epoch": 0.8818021295949489,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004932251769328436,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.1247767224907875,
|
|
"num_tokens": 17841971.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.5990701675415036,
|
|
"epoch": 0.8823372037027128,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932158622504937,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.12920651137828826,
|
|
"num_tokens": 17851890.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.519874525070191,
|
|
"epoch": 0.8828722778104767,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004932065412671915,
|
|
"loss": 6.4123,
|
|
"mean_token_accuracy": 0.13252334222197532,
|
|
"num_tokens": 17862855.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.629786729812622,
|
|
"epoch": 0.8834073519182407,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004931972139832058,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.12248511165380478,
|
|
"num_tokens": 17873550.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.638599252700805,
|
|
"epoch": 0.8839424260260046,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004931878803988066,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.13054898232221604,
|
|
"num_tokens": 17884067.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.601341295242309,
|
|
"epoch": 0.8844775001337686,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004931785405142627,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.12773810103535652,
|
|
"num_tokens": 17894587.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.557901048660279,
|
|
"epoch": 0.8850125742415325,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004931691943298443,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.12345588281750679,
|
|
"num_tokens": 17905297.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.472777080535889,
|
|
"epoch": 0.8855476483492963,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000493159841845821,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.12871376648545266,
|
|
"num_tokens": 17916225.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.641252183914185,
|
|
"epoch": 0.8860827224570603,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004931504830624629,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.12872292771935462,
|
|
"num_tokens": 17925795.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.560930967330933,
|
|
"epoch": 0.8866177965648242,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004931411179800403,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.12332068607211114,
|
|
"num_tokens": 17936134.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.576021671295166,
|
|
"epoch": 0.8871528706725882,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004931317465988235,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.12288779988884926,
|
|
"num_tokens": 17946393.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.620288515090943,
|
|
"epoch": 0.8876879447803521,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004931223689190832,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.12131898999214172,
|
|
"num_tokens": 17957527.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.60401668548584,
|
|
"epoch": 0.8882230188881161,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004931129849410903,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.12653226852416993,
|
|
"num_tokens": 17968390.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.624185705184937,
|
|
"epoch": 0.8887580929958799,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004931035946651154,
|
|
"loss": 6.424,
|
|
"mean_token_accuracy": 0.13672848865389825,
|
|
"num_tokens": 17978667.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.649472332000732,
|
|
"epoch": 0.8892931671036438,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004930941980914299,
|
|
"loss": 6.484,
|
|
"mean_token_accuracy": 0.12073868960142135,
|
|
"num_tokens": 17989008.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.55554428100586,
|
|
"epoch": 0.8898282412114078,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004930847952203052,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.11992595419287681,
|
|
"num_tokens": 18000199.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.6081115245819095,
|
|
"epoch": 0.8903633153191717,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004930753860520126,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.12737504318356513,
|
|
"num_tokens": 18010941.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.636107873916626,
|
|
"epoch": 0.8908983894269357,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004930659705868237,
|
|
"loss": 6.4755,
|
|
"mean_token_accuracy": 0.12668566182255744,
|
|
"num_tokens": 18021519.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.576786231994629,
|
|
"epoch": 0.8914334635346995,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004930565488250108,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.12401631250977516,
|
|
"num_tokens": 18032773.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.560948514938355,
|
|
"epoch": 0.8919685376424635,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004930471207668456,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.1288905918598175,
|
|
"num_tokens": 18043250.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.577342367172241,
|
|
"epoch": 0.8925036117502274,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004930376864126005,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.13135718554258347,
|
|
"num_tokens": 18055165.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.533294534683227,
|
|
"epoch": 0.8930386858579913,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004930282457625476,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.1319275178015232,
|
|
"num_tokens": 18065296.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.483318853378296,
|
|
"epoch": 0.8935737599657553,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00049301879881696,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.12717922553420066,
|
|
"num_tokens": 18075536.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.523620080947876,
|
|
"epoch": 0.8941088340735192,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930093455761101,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.1299550086259842,
|
|
"num_tokens": 18086253.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.625021934509277,
|
|
"epoch": 0.8946439081812831,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000492999886040271,
|
|
"loss": 6.4867,
|
|
"mean_token_accuracy": 0.12763941064476966,
|
|
"num_tokens": 18097335.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.678513479232788,
|
|
"epoch": 0.895178982289047,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004929904202097159,
|
|
"loss": 6.4165,
|
|
"mean_token_accuracy": 0.1255946137011051,
|
|
"num_tokens": 18107293.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.574617719650268,
|
|
"epoch": 0.895714056396811,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004929809480847179,
|
|
"loss": 6.529,
|
|
"mean_token_accuracy": 0.11832507178187371,
|
|
"num_tokens": 18117705.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.6313234806060795,
|
|
"epoch": 0.8962491305045749,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004929714696655507,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.12140770703554153,
|
|
"num_tokens": 18129003.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.6004438400268555,
|
|
"epoch": 0.8967842046123388,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000492961984952488,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.1367577515542507,
|
|
"num_tokens": 18140843.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.557983160018921,
|
|
"epoch": 0.8973192787201028,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004929524939458037,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.12216648012399674,
|
|
"num_tokens": 18151476.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.597401762008667,
|
|
"epoch": 0.8978543528278666,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004929429966457716,
|
|
"loss": 6.4974,
|
|
"mean_token_accuracy": 0.11995471492409707,
|
|
"num_tokens": 18161304.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.655696821212769,
|
|
"epoch": 0.8983894269356306,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004929334930526662,
|
|
"loss": 6.4287,
|
|
"mean_token_accuracy": 0.13061922267079354,
|
|
"num_tokens": 18173696.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.572501087188721,
|
|
"epoch": 0.8989245010433945,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004929239831667617,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.12057856544852256,
|
|
"num_tokens": 18186024.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.567807579040528,
|
|
"epoch": 0.8994595751511585,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004929144669883329,
|
|
"loss": 6.4628,
|
|
"mean_token_accuracy": 0.13044245541095734,
|
|
"num_tokens": 18196976.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.587893533706665,
|
|
"epoch": 0.8999946492589224,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004929049445176545,
|
|
"loss": 6.4553,
|
|
"mean_token_accuracy": 0.12222403511404992,
|
|
"num_tokens": 18208086.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.598808670043946,
|
|
"epoch": 0.9005297233666862,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004928954157550013,
|
|
"loss": 6.4026,
|
|
"mean_token_accuracy": 0.1364985041320324,
|
|
"num_tokens": 18218468.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.641229772567749,
|
|
"epoch": 0.9010647974744502,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004928858807006488,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.12634748592972755,
|
|
"num_tokens": 18230489.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.616871500015259,
|
|
"epoch": 0.9015998715822141,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004928763393548721,
|
|
"loss": 6.4344,
|
|
"mean_token_accuracy": 0.12947860807180406,
|
|
"num_tokens": 18239968.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.5853495597839355,
|
|
"epoch": 0.9021349456899781,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004928667917179465,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.12196068912744522,
|
|
"num_tokens": 18250902.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.663750267028808,
|
|
"epoch": 0.902670019797742,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004928572377901481,
|
|
"loss": 6.4837,
|
|
"mean_token_accuracy": 0.12794666811823846,
|
|
"num_tokens": 18262094.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.584063005447388,
|
|
"epoch": 0.903205093905506,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004928476775717524,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.12302127629518508,
|
|
"num_tokens": 18272765.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.568285655975342,
|
|
"epoch": 0.9037401680132698,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004928381110630358,
|
|
"loss": 6.3773,
|
|
"mean_token_accuracy": 0.13741017803549765,
|
|
"num_tokens": 18284570.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.740869760513306,
|
|
"epoch": 0.9042752421210337,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004928285382642742,
|
|
"loss": 6.4835,
|
|
"mean_token_accuracy": 0.1234114944934845,
|
|
"num_tokens": 18295170.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.594295454025269,
|
|
"epoch": 0.9048103162287977,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004928189591757443,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.122423455119133,
|
|
"num_tokens": 18306388.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.5661896705627445,
|
|
"epoch": 0.9053453903365616,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004928093737977225,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.13050043657422067,
|
|
"num_tokens": 18316363.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.4683513164520265,
|
|
"epoch": 0.9058804644443256,
|
|
"grad_norm": 8.5625,
|
|
"learning_rate": 0.0004927997821304856,
|
|
"loss": 6.3861,
|
|
"mean_token_accuracy": 0.12661736011505126,
|
|
"num_tokens": 18327397.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.5845592498779295,
|
|
"epoch": 0.9064155385520895,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004927901841743107,
|
|
"loss": 6.4818,
|
|
"mean_token_accuracy": 0.12432613149285317,
|
|
"num_tokens": 18338909.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.639092874526978,
|
|
"epoch": 0.9069506126598534,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004927805799294747,
|
|
"loss": 6.4568,
|
|
"mean_token_accuracy": 0.12108288407325744,
|
|
"num_tokens": 18350110.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.679194068908691,
|
|
"epoch": 0.9074856867676173,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004927709693962551,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.11563151106238365,
|
|
"num_tokens": 18361590.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.59504246711731,
|
|
"epoch": 0.9080207608753812,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004927613525749295,
|
|
"loss": 6.4634,
|
|
"mean_token_accuracy": 0.12366845831274986,
|
|
"num_tokens": 18372602.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.630734634399414,
|
|
"epoch": 0.9085558349831452,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004927517294657753,
|
|
"loss": 6.499,
|
|
"mean_token_accuracy": 0.12221666947007179,
|
|
"num_tokens": 18384653.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.684356164932251,
|
|
"epoch": 0.9090909090909091,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004927421000690705,
|
|
"loss": 6.4559,
|
|
"mean_token_accuracy": 0.12245200499892235,
|
|
"num_tokens": 18395379.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.63131685256958,
|
|
"epoch": 0.909625983198673,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004927324643850933,
|
|
"loss": 6.4256,
|
|
"mean_token_accuracy": 0.12843620777130127,
|
|
"num_tokens": 18405915.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.438924121856689,
|
|
"epoch": 0.9101610573064369,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004927228224141217,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.14597983360290528,
|
|
"num_tokens": 18416656.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.542063999176025,
|
|
"epoch": 0.9106961314142009,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004927131741564342,
|
|
"loss": 6.4477,
|
|
"mean_token_accuracy": 0.12013882920145988,
|
|
"num_tokens": 18427141.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.607851362228393,
|
|
"epoch": 0.9112312055219648,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004927035196123094,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.12988717779517173,
|
|
"num_tokens": 18437135.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.685029554367065,
|
|
"epoch": 0.9117662796297287,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000492693858782026,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.11965355947613716,
|
|
"num_tokens": 18448567.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.679243803024292,
|
|
"epoch": 0.9123013537374927,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000492684191665863,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.11756190657615662,
|
|
"num_tokens": 18459385.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.561179542541504,
|
|
"epoch": 0.9128364278452565,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004926745182640996,
|
|
"loss": 6.4677,
|
|
"mean_token_accuracy": 0.1285193495452404,
|
|
"num_tokens": 18471376.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.649504232406616,
|
|
"epoch": 0.9133715019530205,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004926648385770152,
|
|
"loss": 6.5335,
|
|
"mean_token_accuracy": 0.11931721493601799,
|
|
"num_tokens": 18481950.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.654511833190918,
|
|
"epoch": 0.9139065760607844,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004926551526048891,
|
|
"loss": 6.4524,
|
|
"mean_token_accuracy": 0.12727693393826484,
|
|
"num_tokens": 18492436.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.575570774078369,
|
|
"epoch": 0.9144416501685484,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004926454603480009,
|
|
"loss": 6.2964,
|
|
"mean_token_accuracy": 0.12638833299279212,
|
|
"num_tokens": 18504279.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.573821878433227,
|
|
"epoch": 0.9149767242763123,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004926357618066307,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.12484021857380867,
|
|
"num_tokens": 18515262.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.63035249710083,
|
|
"epoch": 0.9155117983840761,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004926260569810586,
|
|
"loss": 6.4951,
|
|
"mean_token_accuracy": 0.12227512821555138,
|
|
"num_tokens": 18525176.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.5566153049469,
|
|
"epoch": 0.9160468724918401,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004926163458715645,
|
|
"loss": 6.4617,
|
|
"mean_token_accuracy": 0.12596529051661493,
|
|
"num_tokens": 18536674.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.5605353832244875,
|
|
"epoch": 0.916581946599604,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004926066284784292,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.12597779259085656,
|
|
"num_tokens": 18547398.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.563134813308716,
|
|
"epoch": 0.917117020707368,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004925969048019329,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.12652412205934524,
|
|
"num_tokens": 18558838.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.629328727722168,
|
|
"epoch": 0.9176520948151319,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004925871748423566,
|
|
"loss": 6.4395,
|
|
"mean_token_accuracy": 0.1258179649710655,
|
|
"num_tokens": 18569881.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.6013552188873295,
|
|
"epoch": 0.9181871689228959,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004925774385999812,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.13269954398274422,
|
|
"num_tokens": 18579556.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.4663420677185055,
|
|
"epoch": 0.9187222430306597,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004925676960750878,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.1361738361418247,
|
|
"num_tokens": 18590580.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.634561157226562,
|
|
"epoch": 0.9192573171384236,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004925579472679578,
|
|
"loss": 6.4828,
|
|
"mean_token_accuracy": 0.1265283964574337,
|
|
"num_tokens": 18600813.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.598533678054809,
|
|
"epoch": 0.9197923912461876,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004925481921788726,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.1304919548332691,
|
|
"num_tokens": 18610807.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.510357618331909,
|
|
"epoch": 0.9203274653539515,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000492538430808114,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.12540487572550774,
|
|
"num_tokens": 18622108.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.557230615615845,
|
|
"epoch": 0.9208625394617155,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004925286631559636,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.12565935403108597,
|
|
"num_tokens": 18633098.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.648445987701416,
|
|
"epoch": 0.9213976135694794,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004925188892227038,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.12731703594326974,
|
|
"num_tokens": 18643603.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.638711643218994,
|
|
"epoch": 0.9219326876772433,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004925091090086166,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.1319430947303772,
|
|
"num_tokens": 18654354.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.621751213073731,
|
|
"epoch": 0.9224677617850072,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004924993225139845,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.12473874017596245,
|
|
"num_tokens": 18665349.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.635911178588867,
|
|
"epoch": 0.9230028358927711,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004924895297390899,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.1247866302728653,
|
|
"num_tokens": 18676575.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.631935882568359,
|
|
"epoch": 0.9235379100005351,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004924797306842157,
|
|
"loss": 6.4019,
|
|
"mean_token_accuracy": 0.13183975219726562,
|
|
"num_tokens": 18686501.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.582294940948486,
|
|
"epoch": 0.924072984108299,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004924699253496449,
|
|
"loss": 6.474,
|
|
"mean_token_accuracy": 0.1282108373939991,
|
|
"num_tokens": 18697246.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.533542108535767,
|
|
"epoch": 0.924608058216063,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004924601137356605,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.1339188501238823,
|
|
"num_tokens": 18708177.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.60825548171997,
|
|
"epoch": 0.9251431323238268,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000492450295842546,
|
|
"loss": 6.458,
|
|
"mean_token_accuracy": 0.12657491490244865,
|
|
"num_tokens": 18719334.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.618236446380616,
|
|
"epoch": 0.9256782064315908,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004924404716705847,
|
|
"loss": 6.4091,
|
|
"mean_token_accuracy": 0.13286964371800422,
|
|
"num_tokens": 18729174.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.537341594696045,
|
|
"epoch": 0.9262132805393547,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004924306412200603,
|
|
"loss": 6.517,
|
|
"mean_token_accuracy": 0.122911486774683,
|
|
"num_tokens": 18740277.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.627772474288941,
|
|
"epoch": 0.9267483546471186,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004924208044912567,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.12486343458294868,
|
|
"num_tokens": 18751864.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.609443330764771,
|
|
"epoch": 0.9272834287548826,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004924109614844579,
|
|
"loss": 6.3891,
|
|
"mean_token_accuracy": 0.1359869807958603,
|
|
"num_tokens": 18762786.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.555660629272461,
|
|
"epoch": 0.9278185028626464,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004924011121999482,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.13116455525159837,
|
|
"num_tokens": 18772913.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.5695160865783695,
|
|
"epoch": 0.9283535769704104,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004923912566380118,
|
|
"loss": 6.4058,
|
|
"mean_token_accuracy": 0.12949569448828696,
|
|
"num_tokens": 18784204.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.5018853664398195,
|
|
"epoch": 0.9288886510781743,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004923813947989336,
|
|
"loss": 6.4945,
|
|
"mean_token_accuracy": 0.12146714031696319,
|
|
"num_tokens": 18795425.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.64973201751709,
|
|
"epoch": 0.9294237251859383,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004923715266829981,
|
|
"loss": 6.4345,
|
|
"mean_token_accuracy": 0.1265689440071583,
|
|
"num_tokens": 18806850.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.641017436981201,
|
|
"epoch": 0.9299587992937022,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004923616522904903,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.1314132884144783,
|
|
"num_tokens": 18817272.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.597755098342896,
|
|
"epoch": 0.930493873401466,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004923517716216953,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.12215960323810578,
|
|
"num_tokens": 18827075.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.62264838218689,
|
|
"epoch": 0.93102894750923,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004923418846768985,
|
|
"loss": 6.4421,
|
|
"mean_token_accuracy": 0.12476111203432083,
|
|
"num_tokens": 18837635.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.642798328399659,
|
|
"epoch": 0.9315640216169939,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004923319914563852,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.13177590519189836,
|
|
"num_tokens": 18848559.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.670168113708496,
|
|
"epoch": 0.9320990957247579,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004923220919604413,
|
|
"loss": 6.4681,
|
|
"mean_token_accuracy": 0.1240908034145832,
|
|
"num_tokens": 18859327.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.591074991226196,
|
|
"epoch": 0.9326341698325218,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004923121861893525,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.1274246610701084,
|
|
"num_tokens": 18869403.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.583342885971069,
|
|
"epoch": 0.9331692439402858,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923022741434049,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.12099683731794357,
|
|
"num_tokens": 18879890.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.615302467346192,
|
|
"epoch": 0.9337043180480497,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004922923558228846,
|
|
"loss": 6.4721,
|
|
"mean_token_accuracy": 0.12057366967201233,
|
|
"num_tokens": 18890361.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.579403305053711,
|
|
"epoch": 0.9342393921558135,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004922824312280781,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.13047217801213265,
|
|
"num_tokens": 18902344.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.569160079956054,
|
|
"epoch": 0.9347744662635775,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000492272500359272,
|
|
"loss": 6.3847,
|
|
"mean_token_accuracy": 0.13155013620853423,
|
|
"num_tokens": 18911364.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.588317584991455,
|
|
"epoch": 0.9353095403713414,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004922625632167529,
|
|
"loss": 6.488,
|
|
"mean_token_accuracy": 0.11757436320185662,
|
|
"num_tokens": 18922254.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.664959383010864,
|
|
"epoch": 0.9358446144791054,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004922526198008078,
|
|
"loss": 6.4452,
|
|
"mean_token_accuracy": 0.1260450467467308,
|
|
"num_tokens": 18932943.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.618773317337036,
|
|
"epoch": 0.9363796885868693,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004922426701117239,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.12151310667395591,
|
|
"num_tokens": 18943523.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.609319257736206,
|
|
"epoch": 0.9369147626946333,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004922327141497884,
|
|
"loss": 6.508,
|
|
"mean_token_accuracy": 0.1161932684481144,
|
|
"num_tokens": 18955220.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.675847339630127,
|
|
"epoch": 0.9374498368023971,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004922227519152888,
|
|
"loss": 6.5421,
|
|
"mean_token_accuracy": 0.12342641204595566,
|
|
"num_tokens": 18966714.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.56199951171875,
|
|
"epoch": 0.937984910910161,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004922127834085128,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.12646044045686722,
|
|
"num_tokens": 18977998.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.567882633209228,
|
|
"epoch": 0.938519985017925,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004922028086297481,
|
|
"loss": 6.3818,
|
|
"mean_token_accuracy": 0.127099596709013,
|
|
"num_tokens": 18990210.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.6765382289886475,
|
|
"epoch": 0.9390550591256889,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004921928275792828,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.12616633251309395,
|
|
"num_tokens": 19000529.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.628943872451782,
|
|
"epoch": 0.9395901332334529,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004921828402574052,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.13188672289252282,
|
|
"num_tokens": 19011386.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.550263404846191,
|
|
"epoch": 0.9401252073412167,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004921728466644037,
|
|
"loss": 6.4043,
|
|
"mean_token_accuracy": 0.12869123220443726,
|
|
"num_tokens": 19022196.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.533733606338501,
|
|
"epoch": 0.9406602814489807,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004921628468005666,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.13189285323023797,
|
|
"num_tokens": 19033221.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.611112642288208,
|
|
"epoch": 0.9411953555567446,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000492152840666183,
|
|
"loss": 6.4878,
|
|
"mean_token_accuracy": 0.12585045173764228,
|
|
"num_tokens": 19044953.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.711111831665039,
|
|
"epoch": 0.9417304296645085,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004921428282615415,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.12096112072467805,
|
|
"num_tokens": 19055512.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.635407400131226,
|
|
"epoch": 0.9422655037722725,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004921328095869313,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.1203993707895279,
|
|
"num_tokens": 19065659.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.658339595794677,
|
|
"epoch": 0.9428005778800364,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004921227846426418,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.1371263563632965,
|
|
"num_tokens": 19076955.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.572042465209961,
|
|
"epoch": 0.9433356519878003,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004921127534289624,
|
|
"loss": 6.5106,
|
|
"mean_token_accuracy": 0.11860493347048759,
|
|
"num_tokens": 19088305.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.568140172958374,
|
|
"epoch": 0.9438707260955642,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004921027159461829,
|
|
"loss": 6.5098,
|
|
"mean_token_accuracy": 0.12441008612513542,
|
|
"num_tokens": 19098046.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.6841308116912845,
|
|
"epoch": 0.9444058002033282,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004920926721945927,
|
|
"loss": 6.4226,
|
|
"mean_token_accuracy": 0.12864333316683768,
|
|
"num_tokens": 19109019.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.662001609802246,
|
|
"epoch": 0.9449408743110921,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004920826221744823,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.12871572971343995,
|
|
"num_tokens": 19119624.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.636339902877808,
|
|
"epoch": 0.945475948418856,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004920725658861417,
|
|
"loss": 6.4741,
|
|
"mean_token_accuracy": 0.12303901016712189,
|
|
"num_tokens": 19130577.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.589366340637207,
|
|
"epoch": 0.94601102252662,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004920625033298611,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.12903112173080444,
|
|
"num_tokens": 19140254.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.569903993606568,
|
|
"epoch": 0.9465460966343838,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004920524345059314,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.12659077122807502,
|
|
"num_tokens": 19151357.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.6806480884552,
|
|
"epoch": 0.9470811707421478,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004920423594146431,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.13126432448625563,
|
|
"num_tokens": 19162069.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.546973991394043,
|
|
"epoch": 0.9476162448499117,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004920322780562872,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.13278165608644485,
|
|
"num_tokens": 19172515.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.469416666030884,
|
|
"epoch": 0.9481513189576757,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004920221904311546,
|
|
"loss": 6.3304,
|
|
"mean_token_accuracy": 0.1281422682106495,
|
|
"num_tokens": 19182450.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.6383439064025875,
|
|
"epoch": 0.9486863930654396,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004920120965395369,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.12080127596855164,
|
|
"num_tokens": 19193833.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.678140926361084,
|
|
"epoch": 0.9492214671732034,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004920019963817253,
|
|
"loss": 6.4762,
|
|
"mean_token_accuracy": 0.1225566104054451,
|
|
"num_tokens": 19204970.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.609140682220459,
|
|
"epoch": 0.9497565412809674,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004919918899580117,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.1269660323858261,
|
|
"num_tokens": 19215795.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.611617612838745,
|
|
"epoch": 0.9502916153887313,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004919817772686876,
|
|
"loss": 6.4649,
|
|
"mean_token_accuracy": 0.11650814116001129,
|
|
"num_tokens": 19226375.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.680630016326904,
|
|
"epoch": 0.9508266894964953,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004919716583140453,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.13823570236563681,
|
|
"num_tokens": 19236066.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.529271268844605,
|
|
"epoch": 0.9513617636042592,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004919615330943769,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.1377024307847023,
|
|
"num_tokens": 19246757.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.614864778518677,
|
|
"epoch": 0.9518968377120232,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004919514016099746,
|
|
"loss": 6.5,
|
|
"mean_token_accuracy": 0.12600353509187698,
|
|
"num_tokens": 19257875.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.6503785133361815,
|
|
"epoch": 0.952431911819787,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000491941263861131,
|
|
"loss": 6.4781,
|
|
"mean_token_accuracy": 0.125810706615448,
|
|
"num_tokens": 19270236.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.588436317443848,
|
|
"epoch": 0.9529669859275509,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000491931119848139,
|
|
"loss": 6.4612,
|
|
"mean_token_accuracy": 0.12382268756628037,
|
|
"num_tokens": 19280877.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.525938892364502,
|
|
"epoch": 0.9535020600353149,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004919209695712915,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.13123888075351714,
|
|
"num_tokens": 19292852.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.636586141586304,
|
|
"epoch": 0.9540371341430788,
|
|
"grad_norm": 7.90625,
|
|
"learning_rate": 0.0004919108130308814,
|
|
"loss": 6.5481,
|
|
"mean_token_accuracy": 0.11724269837141037,
|
|
"num_tokens": 19305516.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.625235986709595,
|
|
"epoch": 0.9545722082508428,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004919006502272019,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.13500440642237663,
|
|
"num_tokens": 19315436.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.508727741241455,
|
|
"epoch": 0.9551072823586066,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004918904811605468,
|
|
"loss": 6.4376,
|
|
"mean_token_accuracy": 0.1264245629310608,
|
|
"num_tokens": 19325393.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.5293982982635494,
|
|
"epoch": 0.9556423564663706,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004918803058312094,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.12973214834928512,
|
|
"num_tokens": 19336722.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.7406854152679445,
|
|
"epoch": 0.9561774305741345,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004918701242394837,
|
|
"loss": 6.5851,
|
|
"mean_token_accuracy": 0.11917414888739586,
|
|
"num_tokens": 19348406.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.599468946456909,
|
|
"epoch": 0.9567125046818984,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004918599363856637,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.1359890453517437,
|
|
"num_tokens": 19359714.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.630413579940796,
|
|
"epoch": 0.9572475787896624,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004918497422700434,
|
|
"loss": 6.4143,
|
|
"mean_token_accuracy": 0.12925480753183366,
|
|
"num_tokens": 19370833.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.610364055633545,
|
|
"epoch": 0.9577826528974263,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004918395418929174,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.12302698343992233,
|
|
"num_tokens": 19382098.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.624408388137818,
|
|
"epoch": 0.9583177270051902,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00049182933525458,
|
|
"loss": 6.4757,
|
|
"mean_token_accuracy": 0.12349115982651711,
|
|
"num_tokens": 19393595.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.640421295166016,
|
|
"epoch": 0.9588528011129541,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000491819122355326,
|
|
"loss": 6.4125,
|
|
"mean_token_accuracy": 0.13156883418560028,
|
|
"num_tokens": 19405296.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.634973096847534,
|
|
"epoch": 0.9593878752207181,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004918089031954503,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.12182890325784683,
|
|
"num_tokens": 19415693.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.580959510803223,
|
|
"epoch": 0.959922949328482,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000491798677775248,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.12708681151270868,
|
|
"num_tokens": 19426140.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.693287134170532,
|
|
"epoch": 0.9604580234362459,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004917884460950144,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.1222914569079876,
|
|
"num_tokens": 19437543.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.634545707702637,
|
|
"epoch": 0.9609930975440099,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000491778208155045,
|
|
"loss": 6.4384,
|
|
"mean_token_accuracy": 0.1252037465572357,
|
|
"num_tokens": 19447788.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.65233883857727,
|
|
"epoch": 0.9615281716517737,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004917679639556351,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.12330029979348182,
|
|
"num_tokens": 19457587.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.6310333728790285,
|
|
"epoch": 0.9620632457595377,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004917577134970808,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.1255684621632099,
|
|
"num_tokens": 19467422.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.586491394042969,
|
|
"epoch": 0.9625983198673016,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004917474567796778,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.12582321763038634,
|
|
"num_tokens": 19479037.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.5694173812866214,
|
|
"epoch": 0.9631333939750656,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004917371938037226,
|
|
"loss": 6.3603,
|
|
"mean_token_accuracy": 0.1418306939303875,
|
|
"num_tokens": 19489639.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.9631333939750656,
|
|
"eval_entropy": 6.45046752675203,
|
|
"eval_loss": 6.510419845581055,
|
|
"eval_mean_token_accuracy": 0.12865163465319177,
|
|
"eval_num_tokens": 19489639.0,
|
|
"eval_runtime": 22.7134,
|
|
"eval_samples_per_second": 1306.673,
|
|
"eval_steps_per_second": 163.34,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.621413230895996,
|
|
"epoch": 0.9636684680828295,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004917269245695114,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.12253487184643745,
|
|
"num_tokens": 19500592.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.647409582138062,
|
|
"epoch": 0.9642035421905933,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004917166490773406,
|
|
"loss": 6.4926,
|
|
"mean_token_accuracy": 0.12586249634623528,
|
|
"num_tokens": 19510818.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.684140062332153,
|
|
"epoch": 0.9647386162983573,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004917063673275071,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.12470211908221245,
|
|
"num_tokens": 19521283.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.619394111633301,
|
|
"epoch": 0.9652736904061212,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916960793203077,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.12334120795130729,
|
|
"num_tokens": 19531799.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.572729444503784,
|
|
"epoch": 0.9658087645138852,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004916857850560394,
|
|
"loss": 6.3481,
|
|
"mean_token_accuracy": 0.13819931223988532,
|
|
"num_tokens": 19542377.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.545560359954834,
|
|
"epoch": 0.9663438386216491,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004916754845349996,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.12935152798891067,
|
|
"num_tokens": 19552654.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.592235040664673,
|
|
"epoch": 0.9668789127294131,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004916651777574856,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.126383750885725,
|
|
"num_tokens": 19563439.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.6113365650177,
|
|
"epoch": 0.9674139868371769,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000491654864723795,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.12931786999106407,
|
|
"num_tokens": 19574264.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.457882881164551,
|
|
"epoch": 0.9679490609449408,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004916445454342256,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.14026236683130264,
|
|
"num_tokens": 19585293.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.6120201587677006,
|
|
"epoch": 0.9684841350527048,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004916342198890754,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.1260765090584755,
|
|
"num_tokens": 19594384.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.587450313568115,
|
|
"epoch": 0.9690192091604687,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004916238880886426,
|
|
"loss": 6.4658,
|
|
"mean_token_accuracy": 0.12822272032499313,
|
|
"num_tokens": 19605144.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.570050573348999,
|
|
"epoch": 0.9695542832682327,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916135500332255,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.13149576559662818,
|
|
"num_tokens": 19615885.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.556726026535034,
|
|
"epoch": 0.9700893573759966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004916032057231225,
|
|
"loss": 6.3891,
|
|
"mean_token_accuracy": 0.12656096294522284,
|
|
"num_tokens": 19625749.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.5713582038879395,
|
|
"epoch": 0.9706244314837605,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004915928551586324,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.11975899636745453,
|
|
"num_tokens": 19638285.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.670734453201294,
|
|
"epoch": 0.9711595055915244,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004915824983400541,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.12083764597773552,
|
|
"num_tokens": 19649697.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.689089012145996,
|
|
"epoch": 0.9716945796992883,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004915721352676864,
|
|
"loss": 6.4909,
|
|
"mean_token_accuracy": 0.12309880778193474,
|
|
"num_tokens": 19659668.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.5748748779296875,
|
|
"epoch": 0.9722296538070523,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004915617659418289,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.12820305898785592,
|
|
"num_tokens": 19670301.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.569716072082519,
|
|
"epoch": 0.9727647279148162,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004915513903627807,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12332535162568092,
|
|
"num_tokens": 19680926.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.497462606430053,
|
|
"epoch": 0.9732998020225802,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004915410085308417,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.13348619192838668,
|
|
"num_tokens": 19691467.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.5884847164154055,
|
|
"epoch": 0.973834876130344,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004915306204463115,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.12888719141483307,
|
|
"num_tokens": 19701139.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.624570894241333,
|
|
"epoch": 0.974369950238108,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00049152022610949,
|
|
"loss": 6.4026,
|
|
"mean_token_accuracy": 0.11958568394184113,
|
|
"num_tokens": 19710628.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.628446578979492,
|
|
"epoch": 0.9749050243458719,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004915098255206773,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.12999779507517814,
|
|
"num_tokens": 19721824.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.6438335418701175,
|
|
"epoch": 0.9754400984536358,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000491499418680174,
|
|
"loss": 6.436,
|
|
"mean_token_accuracy": 0.12116050198674203,
|
|
"num_tokens": 19732557.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.596571922302246,
|
|
"epoch": 0.9759751725613998,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004914890055882804,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.11970045194029807,
|
|
"num_tokens": 19743436.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.541895818710327,
|
|
"epoch": 0.9765102466691636,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000491478586245297,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.13265810012817383,
|
|
"num_tokens": 19755305.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.5737539768219,
|
|
"epoch": 0.9770453207769276,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.000491468160651525,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.13324624821543693,
|
|
"num_tokens": 19766223.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.501796293258667,
|
|
"epoch": 0.9775803948846915,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004914577288072652,
|
|
"loss": 6.4192,
|
|
"mean_token_accuracy": 0.12503207176923753,
|
|
"num_tokens": 19777268.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.616298341751099,
|
|
"epoch": 0.9781154689924555,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004914472907128189,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.12278926596045495,
|
|
"num_tokens": 19787875.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.621466541290284,
|
|
"epoch": 0.9786505431002194,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004914368463684876,
|
|
"loss": 6.4216,
|
|
"mean_token_accuracy": 0.12677970305085182,
|
|
"num_tokens": 19798919.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.5782746315002445,
|
|
"epoch": 0.9791856172079834,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004914263957745726,
|
|
"loss": 6.4,
|
|
"mean_token_accuracy": 0.13413854390382768,
|
|
"num_tokens": 19809320.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.655309772491455,
|
|
"epoch": 0.9797206913157472,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004914159389313759,
|
|
"loss": 6.4725,
|
|
"mean_token_accuracy": 0.12751644253730773,
|
|
"num_tokens": 19819511.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.6865781307220455,
|
|
"epoch": 0.9802557654235111,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004914054758391994,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.11886487379670144,
|
|
"num_tokens": 19830381.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.536502122879028,
|
|
"epoch": 0.9807908395312751,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004913950064983452,
|
|
"loss": 6.3499,
|
|
"mean_token_accuracy": 0.1259816624224186,
|
|
"num_tokens": 19840806.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.508013916015625,
|
|
"epoch": 0.981325913639039,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004913845309091156,
|
|
"loss": 6.353,
|
|
"mean_token_accuracy": 0.1387888766825199,
|
|
"num_tokens": 19851095.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.542148590087891,
|
|
"epoch": 0.981860987746803,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004913740490718131,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.13859621435403824,
|
|
"num_tokens": 19860235.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.554223346710205,
|
|
"epoch": 0.9823960618545668,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004913635609867403,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.12288685292005538,
|
|
"num_tokens": 19872264.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.637903070449829,
|
|
"epoch": 0.9829311359623308,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004913530666542001,
|
|
"loss": 6.5237,
|
|
"mean_token_accuracy": 0.12131133228540421,
|
|
"num_tokens": 19883628.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.589421558380127,
|
|
"epoch": 0.9834662100700947,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004913425660744955,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.12491015046834945,
|
|
"num_tokens": 19894624.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.6095788955688475,
|
|
"epoch": 0.9840012841778586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004913320592479297,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.12497465535998345,
|
|
"num_tokens": 19904882.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.5338897705078125,
|
|
"epoch": 0.9845363582856226,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004913215461748061,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.1354656219482422,
|
|
"num_tokens": 19915344.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.583229351043701,
|
|
"epoch": 0.9850714323933865,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004913110268554282,
|
|
"loss": 6.4896,
|
|
"mean_token_accuracy": 0.11940996870398521,
|
|
"num_tokens": 19927527.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.597001934051514,
|
|
"epoch": 0.9856065065011504,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004913005012900998,
|
|
"loss": 6.4305,
|
|
"mean_token_accuracy": 0.12389865592122078,
|
|
"num_tokens": 19938893.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.603095245361328,
|
|
"epoch": 0.9861415806089143,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004912899694791248,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.13044048398733138,
|
|
"num_tokens": 19949297.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.545996809005738,
|
|
"epoch": 0.9866766547166783,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004912794314228074,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.12906254455447197,
|
|
"num_tokens": 19959194.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.5977085590362545,
|
|
"epoch": 0.9872117288244422,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004912688871214518,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.1233506016433239,
|
|
"num_tokens": 19969896.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.582791805267334,
|
|
"epoch": 0.9877468029322061,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004912583365753625,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13166438192129135,
|
|
"num_tokens": 19981505.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.570750141143799,
|
|
"epoch": 0.9882818770399701,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004912477797848441,
|
|
"loss": 6.3744,
|
|
"mean_token_accuracy": 0.12995605915784836,
|
|
"num_tokens": 19992770.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.570767831802368,
|
|
"epoch": 0.9888169511477339,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004912372167502014,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.13007648289203644,
|
|
"num_tokens": 20003572.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.511661434173584,
|
|
"epoch": 0.9893520252554979,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004912266474717394,
|
|
"loss": 6.414,
|
|
"mean_token_accuracy": 0.13034561201930045,
|
|
"num_tokens": 20014500.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.571699094772339,
|
|
"epoch": 0.9898870993632618,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004912160719497635,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.12786453440785409,
|
|
"num_tokens": 20025745.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.561632347106934,
|
|
"epoch": 0.9904221734710258,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004912054901845788,
|
|
"loss": 6.2986,
|
|
"mean_token_accuracy": 0.1291518561542034,
|
|
"num_tokens": 20036346.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.533315896987915,
|
|
"epoch": 0.9909572475787897,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000491194902176491,
|
|
"loss": 6.4616,
|
|
"mean_token_accuracy": 0.12814752161502838,
|
|
"num_tokens": 20048162.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.559889030456543,
|
|
"epoch": 0.9914923216865535,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004911843079258057,
|
|
"loss": 6.5379,
|
|
"mean_token_accuracy": 0.11548658013343811,
|
|
"num_tokens": 20058947.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.702791309356689,
|
|
"epoch": 0.9920273957943175,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004911737074328289,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.12429900467395782,
|
|
"num_tokens": 20069282.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.621148729324341,
|
|
"epoch": 0.9925624699020814,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004911631006978667,
|
|
"loss": 6.4334,
|
|
"mean_token_accuracy": 0.1263555720448494,
|
|
"num_tokens": 20078347.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.581938457489014,
|
|
"epoch": 0.9930975440098454,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004911524877212254,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.12386744022369385,
|
|
"num_tokens": 20089129.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.5865562915802,
|
|
"epoch": 0.9936326181176093,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004911418685032114,
|
|
"loss": 6.4354,
|
|
"mean_token_accuracy": 0.12295543402433395,
|
|
"num_tokens": 20101008.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.520455312728882,
|
|
"epoch": 0.9941676922253733,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004911312430441312,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.12910244837403298,
|
|
"num_tokens": 20112272.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.548386669158935,
|
|
"epoch": 0.9947027663331371,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004911206113442918,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.1382080502808094,
|
|
"num_tokens": 20122814.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.514030599594117,
|
|
"epoch": 0.995237840440901,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004911099734040001,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.13078407868742942,
|
|
"num_tokens": 20133169.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.61966381072998,
|
|
"epoch": 0.995772914548665,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004910993292235634,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.1179257057607174,
|
|
"num_tokens": 20144355.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.63772873878479,
|
|
"epoch": 0.9963079886564289,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004910886788032887,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.12375867813825607,
|
|
"num_tokens": 20154486.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.580125761032105,
|
|
"epoch": 0.9968430627641929,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004910780221434839,
|
|
"loss": 6.4081,
|
|
"mean_token_accuracy": 0.1301169626414776,
|
|
"num_tokens": 20166359.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.582270002365112,
|
|
"epoch": 0.9973781368719568,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004910673592444566,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.1259844958782196,
|
|
"num_tokens": 20176469.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.605635404586792,
|
|
"epoch": 0.9979132109797207,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004910566901065147,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.129373699426651,
|
|
"num_tokens": 20188334.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.553080797195435,
|
|
"epoch": 0.9984482850874846,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004910460147299661,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.13515611216425896,
|
|
"num_tokens": 20198594.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.559202575683594,
|
|
"epoch": 0.9989833591952485,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004910353331151193,
|
|
"loss": 6.4468,
|
|
"mean_token_accuracy": 0.12875296920537949,
|
|
"num_tokens": 20209456.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.580421400070191,
|
|
"epoch": 0.9995184333030125,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004910246452622825,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.13052132055163385,
|
|
"num_tokens": 20219835.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.6216433842976885,
|
|
"epoch": 1.0,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004910139511717646,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.1245041439930598,
|
|
"num_tokens": 20228258.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.589415073394775,
|
|
"epoch": 1.0005350741077639,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004910032508438739,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.12991154193878174,
|
|
"num_tokens": 20238875.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.589252042770386,
|
|
"epoch": 1.0010701482155278,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00049099254427892,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.12358415201306343,
|
|
"num_tokens": 20249750.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.6447954177856445,
|
|
"epoch": 1.0016052223232919,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004909818314772116,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.12229088544845582,
|
|
"num_tokens": 20259772.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.541646099090576,
|
|
"epoch": 1.0021402964310557,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004909711124390582,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13751042485237122,
|
|
"num_tokens": 20270230.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.444565153121948,
|
|
"epoch": 1.0026753705388196,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909603871647692,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.1495958887040615,
|
|
"num_tokens": 20280317.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.489602088928223,
|
|
"epoch": 1.0032104446465835,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004909496556546544,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.13361010998487471,
|
|
"num_tokens": 20291147.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.506109571456909,
|
|
"epoch": 1.0037455187543476,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004909389179090238,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.13419800773262977,
|
|
"num_tokens": 20301095.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.544373941421509,
|
|
"epoch": 1.0042805928621115,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004909281739281871,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.13655227348208426,
|
|
"num_tokens": 20311216.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.626815271377564,
|
|
"epoch": 1.0048156669698753,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004909174237124548,
|
|
"loss": 6.3962,
|
|
"mean_token_accuracy": 0.1186282604932785,
|
|
"num_tokens": 20321719.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.612100839614868,
|
|
"epoch": 1.0053507410776392,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004909066672621372,
|
|
"loss": 6.3819,
|
|
"mean_token_accuracy": 0.1340535432100296,
|
|
"num_tokens": 20331997.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.547275447845459,
|
|
"epoch": 1.005885815185403,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004908959045775449,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.126530484855175,
|
|
"num_tokens": 20342973.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.510686302185059,
|
|
"epoch": 1.0064208892931672,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004908851356589887,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.13099054470658303,
|
|
"num_tokens": 20352652.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.583318471908569,
|
|
"epoch": 1.006955963400931,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004908743605067796,
|
|
"loss": 6.3757,
|
|
"mean_token_accuracy": 0.13030261918902397,
|
|
"num_tokens": 20364577.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.587148284912109,
|
|
"epoch": 1.007491037508695,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004908635791212287,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.1268289640545845,
|
|
"num_tokens": 20375451.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.597857093811035,
|
|
"epoch": 1.0080261116164588,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004908527915026472,
|
|
"loss": 6.3258,
|
|
"mean_token_accuracy": 0.1297917626798153,
|
|
"num_tokens": 20385174.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.577202701568604,
|
|
"epoch": 1.0085611857242227,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004908419976513467,
|
|
"loss": 6.2784,
|
|
"mean_token_accuracy": 0.13403301909565926,
|
|
"num_tokens": 20395710.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.479523420333862,
|
|
"epoch": 1.0090962598319868,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004908311975676388,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.1319771207869053,
|
|
"num_tokens": 20406572.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.497412395477295,
|
|
"epoch": 1.0096313339397507,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004908203912518355,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.14010654836893083,
|
|
"num_tokens": 20417786.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.63450174331665,
|
|
"epoch": 1.0101664080475146,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004908095787042487,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.12953511774539947,
|
|
"num_tokens": 20427680.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.517748641967773,
|
|
"epoch": 1.0107014821552784,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004907987599251907,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.1292630322277546,
|
|
"num_tokens": 20438640.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.547880840301514,
|
|
"epoch": 1.0112365562630425,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004907879349149737,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.1381923846900463,
|
|
"num_tokens": 20449939.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.499249458312988,
|
|
"epoch": 1.0117716303708064,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004907771036739105,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.1351288966834545,
|
|
"num_tokens": 20460845.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.507327079772949,
|
|
"epoch": 1.0123067044785703,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004907662662023137,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.1253681182861328,
|
|
"num_tokens": 20472407.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.543278932571411,
|
|
"epoch": 1.0128417785863342,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004907554225004962,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.12943721190094948,
|
|
"num_tokens": 20483192.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.645859479904175,
|
|
"epoch": 1.013376852694098,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004907445725687714,
|
|
"loss": 6.4457,
|
|
"mean_token_accuracy": 0.12626103758811952,
|
|
"num_tokens": 20493498.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.599184513092041,
|
|
"epoch": 1.0139119268018622,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004907337164074523,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.13376811072230338,
|
|
"num_tokens": 20503781.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.534925746917724,
|
|
"epoch": 1.014447000909626,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004907228540168523,
|
|
"loss": 6.4217,
|
|
"mean_token_accuracy": 0.1251296542584896,
|
|
"num_tokens": 20515142.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.585486030578613,
|
|
"epoch": 1.01498207501739,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004907119853972854,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.12869108244776725,
|
|
"num_tokens": 20527568.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.50612735748291,
|
|
"epoch": 1.0155171491251538,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004907011105490651,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.1366148717701435,
|
|
"num_tokens": 20538198.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.540985012054444,
|
|
"epoch": 1.0160522232329177,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004906902294725056,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.13617482855916024,
|
|
"num_tokens": 20549355.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.516599655151367,
|
|
"epoch": 1.0165872973406818,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000490679342167921,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.12939720898866652,
|
|
"num_tokens": 20558984.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.594373750686645,
|
|
"epoch": 1.0171223714484456,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004906684486356258,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.12316248491406441,
|
|
"num_tokens": 20570143.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.620317459106445,
|
|
"epoch": 1.0176574455562095,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004906575488759343,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.12629298642277717,
|
|
"num_tokens": 20580973.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.574526023864746,
|
|
"epoch": 1.0181925196639734,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004906466428891616,
|
|
"loss": 6.3549,
|
|
"mean_token_accuracy": 0.1243422269821167,
|
|
"num_tokens": 20591473.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.545525693893433,
|
|
"epoch": 1.0187275937717375,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004906357306756222,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1300820916891098,
|
|
"num_tokens": 20602347.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.587276935577393,
|
|
"epoch": 1.0192626678795014,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004906248122356315,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.13239624947309495,
|
|
"num_tokens": 20613168.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.53687310218811,
|
|
"epoch": 1.0197977419872652,
|
|
"grad_norm": 13.375,
|
|
"learning_rate": 0.0004906138875695045,
|
|
"loss": 6.2746,
|
|
"mean_token_accuracy": 0.13048959001898766,
|
|
"num_tokens": 20623523.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.475817775726318,
|
|
"epoch": 1.0203328160950291,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004906029566775569,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.13328663110733033,
|
|
"num_tokens": 20634085.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.563428783416748,
|
|
"epoch": 1.020867890202793,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004905920195601042,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.128290406614542,
|
|
"num_tokens": 20644747.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.546395969390869,
|
|
"epoch": 1.021402964310557,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004905810762174622,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.12163680791854858,
|
|
"num_tokens": 20655704.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.570021915435791,
|
|
"epoch": 1.021938038418321,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004905701266499469,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.13585362434387208,
|
|
"num_tokens": 20665844.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.592724752426148,
|
|
"epoch": 1.0224731125260849,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004905591708578746,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.12019759565591812,
|
|
"num_tokens": 20676921.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.617676448822022,
|
|
"epoch": 1.0230081866338487,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004905482088415615,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.12580151185393335,
|
|
"num_tokens": 20688476.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.616480588912964,
|
|
"epoch": 1.0235432607416126,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004905372406013241,
|
|
"loss": 6.3717,
|
|
"mean_token_accuracy": 0.1287165805697441,
|
|
"num_tokens": 20698588.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.528187704086304,
|
|
"epoch": 1.0240783348493767,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004905262661374792,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.13266078233718873,
|
|
"num_tokens": 20709181.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.4876031398773195,
|
|
"epoch": 1.0246134089571406,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004905152854503436,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.13735133409500122,
|
|
"num_tokens": 20719724.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.579593276977539,
|
|
"epoch": 1.0251484830649045,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004905042985402345,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.12752212211489677,
|
|
"num_tokens": 20730548.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.5738812446594235,
|
|
"epoch": 1.0256835571726683,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000490493305407469,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.12526717260479928,
|
|
"num_tokens": 20742124.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.638371753692627,
|
|
"epoch": 1.0262186312804324,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004904823060523646,
|
|
"loss": 6.4466,
|
|
"mean_token_accuracy": 0.12435985058546066,
|
|
"num_tokens": 20753313.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.6241978168487545,
|
|
"epoch": 1.0267537053881963,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004904713004752389,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.1303039439022541,
|
|
"num_tokens": 20763539.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.558483028411866,
|
|
"epoch": 1.0272887794959602,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004904602886764097,
|
|
"loss": 6.4966,
|
|
"mean_token_accuracy": 0.1237233228981495,
|
|
"num_tokens": 20775849.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.523603439331055,
|
|
"epoch": 1.027823853603724,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004904492706561948,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.12396602630615235,
|
|
"num_tokens": 20787460.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.61628360748291,
|
|
"epoch": 1.028358927711488,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004904382464149127,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.13349589630961417,
|
|
"num_tokens": 20798478.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.609794998168946,
|
|
"epoch": 1.028894001819252,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904272159528814,
|
|
"loss": 6.3822,
|
|
"mean_token_accuracy": 0.12963185608386993,
|
|
"num_tokens": 20809730.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.557106971740723,
|
|
"epoch": 1.029429075927016,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004904161792704195,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.13708847612142563,
|
|
"num_tokens": 20821438.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.5635278701782225,
|
|
"epoch": 1.0299641500347798,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004904051363678457,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.12266776263713837,
|
|
"num_tokens": 20832328.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.50533971786499,
|
|
"epoch": 1.0304992241425437,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004903940872454789,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.1316038779914379,
|
|
"num_tokens": 20843956.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.623028230667114,
|
|
"epoch": 1.0310342982503076,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004903830319036381,
|
|
"loss": 6.3571,
|
|
"mean_token_accuracy": 0.13210696056485177,
|
|
"num_tokens": 20854578.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.519392490386963,
|
|
"epoch": 1.0315693723580717,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004903719703426425,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.1291162833571434,
|
|
"num_tokens": 20865190.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.5408073425292965,
|
|
"epoch": 1.0321044464658355,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004903609025628115,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.12836557105183602,
|
|
"num_tokens": 20875733.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.474796438217163,
|
|
"epoch": 1.0326395205735994,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004903498285644647,
|
|
"loss": 6.3463,
|
|
"mean_token_accuracy": 0.1265176258981228,
|
|
"num_tokens": 20886900.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.55428729057312,
|
|
"epoch": 1.0331745946813633,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004903387483479219,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.12576237097382545,
|
|
"num_tokens": 20898125.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.662082672119141,
|
|
"epoch": 1.0337096687891274,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903276619135029,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.1248619869351387,
|
|
"num_tokens": 20909788.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.666777038574219,
|
|
"epoch": 1.0342447428968913,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000490316569261528,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.12725045755505562,
|
|
"num_tokens": 20921853.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.609588003158569,
|
|
"epoch": 1.0347798170046552,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004903054703923175,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.12214237824082375,
|
|
"num_tokens": 20932574.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.505526494979859,
|
|
"epoch": 1.035314891112419,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004902943653061916,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.12515838891267778,
|
|
"num_tokens": 20943458.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.551134777069092,
|
|
"epoch": 1.035849965220183,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004902832540034712,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.13630713000893593,
|
|
"num_tokens": 20953213.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.527917861938477,
|
|
"epoch": 1.036385039327947,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004902721364844773,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.12731200829148293,
|
|
"num_tokens": 20963885.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.504400396347046,
|
|
"epoch": 1.0369201134357109,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004902610127495305,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.1349087744951248,
|
|
"num_tokens": 20975529.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.549321889877319,
|
|
"epoch": 1.0374551875434748,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004902498827989523,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.13757401034235955,
|
|
"num_tokens": 20985279.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.609812068939209,
|
|
"epoch": 1.0379902616512386,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004902387466330639,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.13019999638199806,
|
|
"num_tokens": 20995818.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.4939371109008786,
|
|
"epoch": 1.0385253357590025,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000490227604252187,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.13090986832976342,
|
|
"num_tokens": 21006786.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.515184926986694,
|
|
"epoch": 1.0390604098667666,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004902164556566433,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.13896063342690468,
|
|
"num_tokens": 21017441.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.437628364562988,
|
|
"epoch": 1.0395954839745305,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004902053008467546,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.13861987590789795,
|
|
"num_tokens": 21027812.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.534468650817871,
|
|
"epoch": 1.0401305580822944,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004901941398228431,
|
|
"loss": 6.3941,
|
|
"mean_token_accuracy": 0.13089548125863076,
|
|
"num_tokens": 21038960.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.597829294204712,
|
|
"epoch": 1.0406656321900583,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004901829725852311,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.13462072163820266,
|
|
"num_tokens": 21050467.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.52369499206543,
|
|
"epoch": 1.0412007062978224,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000490171799134241,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.12630092725157738,
|
|
"num_tokens": 21061208.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.523263645172119,
|
|
"epoch": 1.0417357804055862,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004901606194701954,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.13332309275865556,
|
|
"num_tokens": 21072872.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.555621576309204,
|
|
"epoch": 1.04227085451335,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004901494335934172,
|
|
"loss": 6.3524,
|
|
"mean_token_accuracy": 0.13275277987122536,
|
|
"num_tokens": 21084878.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.6262726306915285,
|
|
"epoch": 1.042805928621114,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004901382415042293,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.12680527493357657,
|
|
"num_tokens": 21095289.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.616176795959473,
|
|
"epoch": 1.0433410027288779,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004901270432029549,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.1305427983403206,
|
|
"num_tokens": 21106077.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.423315238952637,
|
|
"epoch": 1.043876076836642,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004901158386899174,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.13529875352978707,
|
|
"num_tokens": 21116548.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.516621541976929,
|
|
"epoch": 1.0444111509444058,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004901046279654402,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.13983293026685714,
|
|
"num_tokens": 21126163.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.61842679977417,
|
|
"epoch": 1.0449462250521697,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004900934110298471,
|
|
"loss": 6.385,
|
|
"mean_token_accuracy": 0.12512520104646682,
|
|
"num_tokens": 21136830.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.571760177612305,
|
|
"epoch": 1.0454812991599336,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004900821878834621,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.1342024587094784,
|
|
"num_tokens": 21146793.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.573628664016724,
|
|
"epoch": 1.0460163732676975,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000490070958526609,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.13071634098887444,
|
|
"num_tokens": 21156799.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.540488243103027,
|
|
"epoch": 1.0465514473754616,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004900597229596124,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.12690124064683914,
|
|
"num_tokens": 21167757.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.6183329105377195,
|
|
"epoch": 1.0470865214832255,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004900484811827963,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.12883857786655425,
|
|
"num_tokens": 21178832.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.58182463645935,
|
|
"epoch": 1.0476215955909893,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004900372331964856,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.13159751370549203,
|
|
"num_tokens": 21189637.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.507457113265991,
|
|
"epoch": 1.0481566696987532,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000490025979001005,
|
|
"loss": 6.321,
|
|
"mean_token_accuracy": 0.13030252754688262,
|
|
"num_tokens": 21200194.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.490743494033813,
|
|
"epoch": 1.0486917438065173,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004900147185966795,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.13105009645223617,
|
|
"num_tokens": 21211405.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.59748592376709,
|
|
"epoch": 1.0492268179142812,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004900034519838342,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.12743570655584335,
|
|
"num_tokens": 21222722.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.541789150238037,
|
|
"epoch": 1.049761892022045,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004899921791627945,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.13372819796204566,
|
|
"num_tokens": 21233510.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.541411399841309,
|
|
"epoch": 1.050296966129809,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004899809001338857,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.12047207728028297,
|
|
"num_tokens": 21243235.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.536032104492188,
|
|
"epoch": 1.0508320402375728,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004899696148974338,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.13035102561116219,
|
|
"num_tokens": 21254680.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.51158652305603,
|
|
"epoch": 1.051367114345337,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004899583234537644,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.13114088550209999,
|
|
"num_tokens": 21265116.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.5533318519592285,
|
|
"epoch": 1.0519021884531008,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004899470258032034,
|
|
"loss": 6.3005,
|
|
"mean_token_accuracy": 0.13146693632006645,
|
|
"num_tokens": 21277066.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.582359695434571,
|
|
"epoch": 1.0524372625608647,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004899357219460775,
|
|
"loss": 6.3492,
|
|
"mean_token_accuracy": 0.13322116136550904,
|
|
"num_tokens": 21287332.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.456721401214599,
|
|
"epoch": 1.0529723366686286,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004899244118827128,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.13221352621912957,
|
|
"num_tokens": 21298377.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.571355152130127,
|
|
"epoch": 1.0535074107763924,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004899130956134358,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.13347491770982742,
|
|
"num_tokens": 21309966.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.511975812911987,
|
|
"epoch": 1.0540424848841565,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004899017731385735,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.13985393643379213,
|
|
"num_tokens": 21320399.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.545067501068115,
|
|
"epoch": 1.0545775589919204,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004898904444584527,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.1301308900117874,
|
|
"num_tokens": 21331716.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.575881576538086,
|
|
"epoch": 1.0551126330996843,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004898791095734004,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.12489353939890861,
|
|
"num_tokens": 21341664.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.569723415374756,
|
|
"epoch": 1.0556477072074482,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000489867768483744,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.12841244488954545,
|
|
"num_tokens": 21352220.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.63442759513855,
|
|
"epoch": 1.0561827813152123,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004898564211898111,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.12361843287944793,
|
|
"num_tokens": 21363947.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.601479339599609,
|
|
"epoch": 1.0567178554229761,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004898450676919291,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.13290739953517913,
|
|
"num_tokens": 21374011.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.56652512550354,
|
|
"epoch": 1.05725292953074,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489833707990426,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.1321233369410038,
|
|
"num_tokens": 21384232.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.523163557052612,
|
|
"epoch": 1.057788003638504,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004898223420856298,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.12886636033654214,
|
|
"num_tokens": 21395928.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.558263635635376,
|
|
"epoch": 1.0583230777462678,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004898109699778686,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.1277891717851162,
|
|
"num_tokens": 21406391.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.548861646652222,
|
|
"epoch": 1.0588581518540319,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000489799591667471,
|
|
"loss": 6.398,
|
|
"mean_token_accuracy": 0.1259136602282524,
|
|
"num_tokens": 21417859.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.499192619323731,
|
|
"epoch": 1.0593932259617957,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004897882071547651,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.13391533121466637,
|
|
"num_tokens": 21428284.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.542983675003052,
|
|
"epoch": 1.0599283000695596,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004897768164400801,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.12659377828240395,
|
|
"num_tokens": 21439610.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.6037352085113525,
|
|
"epoch": 1.0604633741773235,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004897654195237446,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.1266575463116169,
|
|
"num_tokens": 21449319.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.607220649719238,
|
|
"epoch": 1.0609984482850874,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004897540164060879,
|
|
"loss": 6.3995,
|
|
"mean_token_accuracy": 0.13648231849074363,
|
|
"num_tokens": 21459851.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.528581809997559,
|
|
"epoch": 1.0615335223928515,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004897426070874392,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.13578662425279617,
|
|
"num_tokens": 21469717.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.5819432735443115,
|
|
"epoch": 1.0620685965006154,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004897311915681278,
|
|
"loss": 6.4526,
|
|
"mean_token_accuracy": 0.12497929334640503,
|
|
"num_tokens": 21480815.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.634674501419068,
|
|
"epoch": 1.0626036706083792,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004897197698484834,
|
|
"loss": 6.3432,
|
|
"mean_token_accuracy": 0.129038904607296,
|
|
"num_tokens": 21492000.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.515308094024658,
|
|
"epoch": 1.0631387447161431,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004897083419288358,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.12596094235777855,
|
|
"num_tokens": 21502006.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.500771331787109,
|
|
"epoch": 1.0636738188239072,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000489696907809515,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.13541009426116943,
|
|
"num_tokens": 21513066.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.547796964645386,
|
|
"epoch": 1.064208892931671,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004896854674908512,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.1268548533320427,
|
|
"num_tokens": 21524853.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.571991872787476,
|
|
"epoch": 1.064743967039435,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004896740209731746,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.13072544783353807,
|
|
"num_tokens": 21536497.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.4796923160552975,
|
|
"epoch": 1.0652790411471988,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004896625682568159,
|
|
"loss": 6.298,
|
|
"mean_token_accuracy": 0.13346593901515008,
|
|
"num_tokens": 21546213.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.449840402603149,
|
|
"epoch": 1.0658141152549627,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004896511093421057,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.13981223478913307,
|
|
"num_tokens": 21556990.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.532204484939575,
|
|
"epoch": 1.0663491893627268,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004896396442293749,
|
|
"loss": 6.3005,
|
|
"mean_token_accuracy": 0.1295848861336708,
|
|
"num_tokens": 21567567.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.556431913375855,
|
|
"epoch": 1.0668842634704907,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004896281729189544,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.1309622846543789,
|
|
"num_tokens": 21577457.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.5115550518035885,
|
|
"epoch": 1.0674193375782546,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004896166954111758,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.13812632784247397,
|
|
"num_tokens": 21588173.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.543576431274414,
|
|
"epoch": 1.0679544116860185,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048960521170637,
|
|
"loss": 6.3571,
|
|
"mean_token_accuracy": 0.12762073799967766,
|
|
"num_tokens": 21599154.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.546718549728394,
|
|
"epoch": 1.0684894857937826,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004895937218048692,
|
|
"loss": 6.4033,
|
|
"mean_token_accuracy": 0.12653964534401893,
|
|
"num_tokens": 21610134.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.515305852890014,
|
|
"epoch": 1.0690245599015464,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004895822257070046,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.131786098331213,
|
|
"num_tokens": 21619989.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.557422780990601,
|
|
"epoch": 1.0695596340093103,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004895707234131084,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.1355228066444397,
|
|
"num_tokens": 21632707.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.578034830093384,
|
|
"epoch": 1.0700947081170742,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004895592149235128,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.1315545454621315,
|
|
"num_tokens": 21643001.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.560757112503052,
|
|
"epoch": 1.070629782224838,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048954770023855,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.12268463671207427,
|
|
"num_tokens": 21653425.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.578395557403565,
|
|
"epoch": 1.0711648563326022,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004895361793585525,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.1271112874150276,
|
|
"num_tokens": 21664212.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.552493667602539,
|
|
"epoch": 1.071699930440366,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004895246522838529,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.12997190952301024,
|
|
"num_tokens": 21675564.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.538548183441162,
|
|
"epoch": 1.07223500454813,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004895131190147842,
|
|
"loss": 6.3603,
|
|
"mean_token_accuracy": 0.13544045239686966,
|
|
"num_tokens": 21686225.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.533993816375732,
|
|
"epoch": 1.0727700786558938,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004895015795516793,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.13008347228169442,
|
|
"num_tokens": 21697479.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.575708866119385,
|
|
"epoch": 1.0733051527636577,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004894900338948714,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.12802261039614676,
|
|
"num_tokens": 21708496.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.565115308761596,
|
|
"epoch": 1.0738402268714218,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004894784820446939,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.1375642567873001,
|
|
"num_tokens": 21718290.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.503127574920654,
|
|
"epoch": 1.0743753009791857,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004894669240014804,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.13177290111780166,
|
|
"num_tokens": 21729185.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.518919229507446,
|
|
"epoch": 1.0749103750869495,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004894553597655646,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.12472319975495338,
|
|
"num_tokens": 21740787.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.650041389465332,
|
|
"epoch": 1.0754454491947134,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004894437893372804,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.12599473372101783,
|
|
"num_tokens": 21751804.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.662219142913818,
|
|
"epoch": 1.0759805233024773,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000489432212716962,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.12913210690021515,
|
|
"num_tokens": 21762730.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.495162582397461,
|
|
"epoch": 1.0765155974102414,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004894206299049436,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.12958017587661744,
|
|
"num_tokens": 21773470.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.566137409210205,
|
|
"epoch": 1.0770506715180053,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004894090409015595,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.12679021656513215,
|
|
"num_tokens": 21783385.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.519651746749878,
|
|
"epoch": 1.0775857456257691,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004893974457071445,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.1318201705813408,
|
|
"num_tokens": 21794857.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.582787752151489,
|
|
"epoch": 1.078120819733533,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004893858443220335,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.12606494948267938,
|
|
"num_tokens": 21804296.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.57329306602478,
|
|
"epoch": 1.0786558938412971,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004893742367465613,
|
|
"loss": 6.36,
|
|
"mean_token_accuracy": 0.12605967298150061,
|
|
"num_tokens": 21815899.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.566723203659057,
|
|
"epoch": 1.079190967949061,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004893626229810631,
|
|
"loss": 6.3356,
|
|
"mean_token_accuracy": 0.1350504457950592,
|
|
"num_tokens": 21825964.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.5852015018463135,
|
|
"epoch": 1.0797260420568249,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004893510030258743,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.12873302549123763,
|
|
"num_tokens": 21836656.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.59387173652649,
|
|
"epoch": 1.0802611161645888,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004893393768813305,
|
|
"loss": 6.421,
|
|
"mean_token_accuracy": 0.12757074385881423,
|
|
"num_tokens": 21847658.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.651180601119995,
|
|
"epoch": 1.0807961902723526,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004893277445477673,
|
|
"loss": 6.3916,
|
|
"mean_token_accuracy": 0.12199634462594985,
|
|
"num_tokens": 21858338.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.55932469367981,
|
|
"epoch": 1.0813312643801167,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004893161060255206,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.13296918123960494,
|
|
"num_tokens": 21870656.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.572396087646484,
|
|
"epoch": 1.0818663384878806,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004893044613149263,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.13754768669605255,
|
|
"num_tokens": 21881806.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.48524956703186,
|
|
"epoch": 1.0824014125956445,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004892928104163209,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.13149532154202462,
|
|
"num_tokens": 21892277.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.491385459899902,
|
|
"epoch": 1.0829364867034084,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004892811533300407,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.13023179545998573,
|
|
"num_tokens": 21903509.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.581822729110717,
|
|
"epoch": 1.0834715608111725,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004892694900564223,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.12440016642212867,
|
|
"num_tokens": 21914308.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.546678495407105,
|
|
"epoch": 1.0840066349189363,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004892578205958025,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.14137799441814422,
|
|
"num_tokens": 21924302.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.530106067657471,
|
|
"epoch": 1.0845417090267002,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004892461449485182,
|
|
"loss": 6.3636,
|
|
"mean_token_accuracy": 0.12199231162667275,
|
|
"num_tokens": 21935066.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.544826984405518,
|
|
"epoch": 1.085076783134464,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004892344631149066,
|
|
"loss": 6.2529,
|
|
"mean_token_accuracy": 0.1391059972345829,
|
|
"num_tokens": 21945798.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.537466096878052,
|
|
"epoch": 1.085611857242228,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000489222775095305,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.12511541321873665,
|
|
"num_tokens": 21955667.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.5176506519317625,
|
|
"epoch": 1.086146931349992,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004892110808900509,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.12824971377849578,
|
|
"num_tokens": 21966107.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.5623456001281735,
|
|
"epoch": 1.086682005457756,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004891993804994818,
|
|
"loss": 6.3372,
|
|
"mean_token_accuracy": 0.13260870128870011,
|
|
"num_tokens": 21976408.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.648627758026123,
|
|
"epoch": 1.0872170795655198,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004891876739239358,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.13422903493046762,
|
|
"num_tokens": 21986481.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.541556930541992,
|
|
"epoch": 1.0877521536732837,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004891759611637508,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.1273925334215164,
|
|
"num_tokens": 21997554.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.594119644165039,
|
|
"epoch": 1.0882872277810476,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000489164242219265,
|
|
"loss": 6.4354,
|
|
"mean_token_accuracy": 0.12317250669002533,
|
|
"num_tokens": 22009048.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.651549434661865,
|
|
"epoch": 1.0888223018888117,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004891525170908169,
|
|
"loss": 6.4482,
|
|
"mean_token_accuracy": 0.1263985179364681,
|
|
"num_tokens": 22020625.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.634617900848388,
|
|
"epoch": 1.0893573759965756,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004891407857787448,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.12857749983668326,
|
|
"num_tokens": 22032298.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.534213542938232,
|
|
"epoch": 1.0898924501043394,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004891290482833876,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.13334605246782302,
|
|
"num_tokens": 22043693.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.520200777053833,
|
|
"epoch": 1.0904275242121033,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004891173046050844,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.1346238724887371,
|
|
"num_tokens": 22054373.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.534080505371094,
|
|
"epoch": 1.0909625983198672,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000489105554744174,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.1305387571454048,
|
|
"num_tokens": 22065039.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.6202747344970705,
|
|
"epoch": 1.0914976724276313,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004890937987009958,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.1298222564160824,
|
|
"num_tokens": 22077003.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.60672516822815,
|
|
"epoch": 1.0920327465353952,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004890820364758892,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.1274056114256382,
|
|
"num_tokens": 22088558.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.552365064620972,
|
|
"epoch": 1.092567820643159,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000489070268069194,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.13213638737797737,
|
|
"num_tokens": 22097777.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.541152143478394,
|
|
"epoch": 1.093102894750923,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004890584934812498,
|
|
"loss": 6.2634,
|
|
"mean_token_accuracy": 0.1303601458668709,
|
|
"num_tokens": 22107803.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.498277282714843,
|
|
"epoch": 1.093637968858687,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004890467127123967,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.13142024949193,
|
|
"num_tokens": 22117965.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.5624823570251465,
|
|
"epoch": 1.094173042966451,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004890349257629749,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.13246248736977578,
|
|
"num_tokens": 22127759.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.550729131698608,
|
|
"epoch": 1.0947081170742148,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004890231326333246,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.1269809238612652,
|
|
"num_tokens": 22138477.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.5772411823272705,
|
|
"epoch": 1.0952431911819787,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004890113333237865,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.12684160023927687,
|
|
"num_tokens": 22149568.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.5642256259918215,
|
|
"epoch": 1.0957782652897425,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004889995278347012,
|
|
"loss": 6.3269,
|
|
"mean_token_accuracy": 0.13090576231479645,
|
|
"num_tokens": 22159949.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.539562940597534,
|
|
"epoch": 1.0963133393975066,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 6.3634,
|
|
"mean_token_accuracy": 0.12523729503154754,
|
|
"num_tokens": 22170115.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.588288640975952,
|
|
"epoch": 1.0968484135052705,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004889758983192528,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.13425422385334967,
|
|
"num_tokens": 22181323.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.555928516387939,
|
|
"epoch": 1.0973834876130344,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004889640742935719,
|
|
"loss": 6.2993,
|
|
"mean_token_accuracy": 0.12734182626008989,
|
|
"num_tokens": 22192078.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.603155136108398,
|
|
"epoch": 1.0979185617207983,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004889522440897085,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.13014934435486794,
|
|
"num_tokens": 22203211.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.523215007781983,
|
|
"epoch": 1.0984536358285624,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004889404077080041,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.1271577313542366,
|
|
"num_tokens": 22213487.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.6091859340667725,
|
|
"epoch": 1.0989887099363262,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004889285651488005,
|
|
"loss": 6.348,
|
|
"mean_token_accuracy": 0.1246352657675743,
|
|
"num_tokens": 22223717.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.56798095703125,
|
|
"epoch": 1.0995237840440901,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004889167164124396,
|
|
"loss": 6.3425,
|
|
"mean_token_accuracy": 0.13307574465870858,
|
|
"num_tokens": 22235141.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.584205436706543,
|
|
"epoch": 1.100058858151854,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004889048614992636,
|
|
"loss": 6.4057,
|
|
"mean_token_accuracy": 0.11987434178590775,
|
|
"num_tokens": 22246601.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.577657842636109,
|
|
"epoch": 1.1005939322596179,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004888930004096148,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.12910846546292304,
|
|
"num_tokens": 22257206.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.545556259155274,
|
|
"epoch": 1.101129006367382,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004888811331438356,
|
|
"loss": 6.4003,
|
|
"mean_token_accuracy": 0.1228591412305832,
|
|
"num_tokens": 22267799.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.606423711776733,
|
|
"epoch": 1.1016640804751459,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004888692597022689,
|
|
"loss": 6.4521,
|
|
"mean_token_accuracy": 0.12880235388875008,
|
|
"num_tokens": 22279368.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.553431987762451,
|
|
"epoch": 1.1021991545829097,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004888573800852572,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13669133111834525,
|
|
"num_tokens": 22289998.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.504615068435669,
|
|
"epoch": 1.1027342286906736,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004888454942931438,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.1390775963664055,
|
|
"num_tokens": 22300058.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.565959692001343,
|
|
"epoch": 1.1032693027984375,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004888336023262718,
|
|
"loss": 6.4207,
|
|
"mean_token_accuracy": 0.124299506098032,
|
|
"num_tokens": 22310962.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.608157634735107,
|
|
"epoch": 1.1038043769062016,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004888217041849846,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.1316367991268635,
|
|
"num_tokens": 22321526.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.573012971878052,
|
|
"epoch": 1.1043394510139655,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004888097998696256,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.12790393680334092,
|
|
"num_tokens": 22332558.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.550169897079468,
|
|
"epoch": 1.1048745251217293,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004887978893805387,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.13281012028455735,
|
|
"num_tokens": 22342392.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.571234178543091,
|
|
"epoch": 1.1054095992294932,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004887859727180679,
|
|
"loss": 6.3905,
|
|
"mean_token_accuracy": 0.12326234579086304,
|
|
"num_tokens": 22353089.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.522563552856445,
|
|
"epoch": 1.105944673337257,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004887740498825572,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.13173036724328996,
|
|
"num_tokens": 22364314.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.497900485992432,
|
|
"epoch": 1.1064797474450212,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004887621208743507,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.12728115022182465,
|
|
"num_tokens": 22374985.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.526889419555664,
|
|
"epoch": 1.107014821552785,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004887501856937932,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.13864122256636618,
|
|
"num_tokens": 22385618.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.631136274337768,
|
|
"epoch": 1.107549895660549,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000488738244341229,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.14008405432105064,
|
|
"num_tokens": 22395871.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.570936012268066,
|
|
"epoch": 1.1080849697683128,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000488726296817003,
|
|
"loss": 6.3666,
|
|
"mean_token_accuracy": 0.13187873214483262,
|
|
"num_tokens": 22406707.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.53339991569519,
|
|
"epoch": 1.108620043876077,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004887143431214602,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.12708743512630463,
|
|
"num_tokens": 22417543.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.502883052825927,
|
|
"epoch": 1.1091551179838408,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004887023832549459,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.13298214301466943,
|
|
"num_tokens": 22428283.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.499336004257202,
|
|
"epoch": 1.1096901920916047,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004886904172178052,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.13327440321445466,
|
|
"num_tokens": 22439860.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.63573694229126,
|
|
"epoch": 1.1102252661993686,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004886784450103838,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.13110646083950997,
|
|
"num_tokens": 22451250.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.561157751083374,
|
|
"epoch": 1.1107603403071324,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004886664666330273,
|
|
"loss": 6.293,
|
|
"mean_token_accuracy": 0.12992360070347786,
|
|
"num_tokens": 22461112.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.530084323883057,
|
|
"epoch": 1.1112954144148965,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004886544820860816,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.13429150208830834,
|
|
"num_tokens": 22471368.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.522792387008667,
|
|
"epoch": 1.1118304885226604,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004886424913698927,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.1302389308810234,
|
|
"num_tokens": 22482011.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.528932523727417,
|
|
"epoch": 1.1123655626304243,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004886304944848069,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.13808312863111497,
|
|
"num_tokens": 22493648.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.57400918006897,
|
|
"epoch": 1.1129006367381882,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004886184914311706,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.12496653497219086,
|
|
"num_tokens": 22505577.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.564892768859863,
|
|
"epoch": 1.1134357108459523,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004886064822093305,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.12236398756504059,
|
|
"num_tokens": 22515546.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.527905750274658,
|
|
"epoch": 1.1139707849537162,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004885944668196332,
|
|
"loss": 6.2631,
|
|
"mean_token_accuracy": 0.13738187327980994,
|
|
"num_tokens": 22526710.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.569247817993164,
|
|
"epoch": 1.11450585906148,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004885824452624254,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.12691551223397254,
|
|
"num_tokens": 22537809.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.581798887252807,
|
|
"epoch": 1.115040933169244,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004885704175380548,
|
|
"loss": 6.3638,
|
|
"mean_token_accuracy": 0.1270926281809807,
|
|
"num_tokens": 22549301.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.6548303127288815,
|
|
"epoch": 1.1155760072770078,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004885583836468683,
|
|
"loss": 6.2725,
|
|
"mean_token_accuracy": 0.13279347419738768,
|
|
"num_tokens": 22560483.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.529315996170044,
|
|
"epoch": 1.1161110813847719,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004885463435892136,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.12554011717438698,
|
|
"num_tokens": 22570524.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.552693557739258,
|
|
"epoch": 1.1166461554925358,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000488534297365438,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.1273189067840576,
|
|
"num_tokens": 22581120.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.6206999778747555,
|
|
"epoch": 1.1171812296002996,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004885222449758899,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.12862497866153716,
|
|
"num_tokens": 22592658.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.5843626976013185,
|
|
"epoch": 1.1177163037080635,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004885101864209167,
|
|
"loss": 6.3188,
|
|
"mean_token_accuracy": 0.13105077669024467,
|
|
"num_tokens": 22603497.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.508558559417724,
|
|
"epoch": 1.1182513778158274,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000488498121700867,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.13314962089061738,
|
|
"num_tokens": 22612916.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.510771703720093,
|
|
"epoch": 1.1187864519235915,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004884860508160891,
|
|
"loss": 6.3776,
|
|
"mean_token_accuracy": 0.12925844565033912,
|
|
"num_tokens": 22625345.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.510384511947632,
|
|
"epoch": 1.1193215260313554,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004884739737669314,
|
|
"loss": 6.2801,
|
|
"mean_token_accuracy": 0.1355935327708721,
|
|
"num_tokens": 22637000.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.549340534210205,
|
|
"epoch": 1.1198566001391193,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004884618905537427,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.1341861017048359,
|
|
"num_tokens": 22647025.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.493887281417846,
|
|
"epoch": 1.1203916742468831,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004884498011768719,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.137028082460165,
|
|
"num_tokens": 22657253.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.463266134262085,
|
|
"epoch": 1.120926748354647,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000488437705636668,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.131851152330637,
|
|
"num_tokens": 22668432.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.525684833526611,
|
|
"epoch": 1.121461822462411,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004884256039334805,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.12723028883337975,
|
|
"num_tokens": 22678538.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.573268985748291,
|
|
"epoch": 1.121996896570175,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004884134960676586,
|
|
"loss": 6.3296,
|
|
"mean_token_accuracy": 0.12801336348056794,
|
|
"num_tokens": 22688994.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.627550745010376,
|
|
"epoch": 1.1225319706779389,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000488401382039552,
|
|
"loss": 6.3599,
|
|
"mean_token_accuracy": 0.13166107088327408,
|
|
"num_tokens": 22699584.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.498450517654419,
|
|
"epoch": 1.1230670447857027,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004883892618495104,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.1293816864490509,
|
|
"num_tokens": 22710093.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.543735408782959,
|
|
"epoch": 1.1236021188934668,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000488377135497884,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.1305043265223503,
|
|
"num_tokens": 22720533.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.546299886703491,
|
|
"epoch": 1.1241371930012307,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004883650029850226,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.1354456789791584,
|
|
"num_tokens": 22731010.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.520023155212402,
|
|
"epoch": 1.1246722671089946,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004883528643112769,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.1299326941370964,
|
|
"num_tokens": 22743045.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.5189900398254395,
|
|
"epoch": 1.1252073412167585,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004883407194769972,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.13178498074412345,
|
|
"num_tokens": 22753746.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.565853261947632,
|
|
"epoch": 1.1257424153245223,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004883285684825342,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.13648682385683059,
|
|
"num_tokens": 22765264.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.57284836769104,
|
|
"epoch": 1.1262774894322864,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004883164113282386,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.13097459301352501,
|
|
"num_tokens": 22775727.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.56453914642334,
|
|
"epoch": 1.1268125635400503,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004883042480144618,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.1291578531265259,
|
|
"num_tokens": 22787228.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.653687572479248,
|
|
"epoch": 1.1273476376478142,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004882920785415547,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.12908954098820685,
|
|
"num_tokens": 22797467.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.573576211929321,
|
|
"epoch": 1.127882711755578,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004882799029098689,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.12570706456899644,
|
|
"num_tokens": 22808281.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.537278699874878,
|
|
"epoch": 1.1284177858633422,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048826772111975583,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.1296780101954937,
|
|
"num_tokens": 22819387.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.540688848495483,
|
|
"epoch": 1.128952859971106,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048825553317156717,
|
|
"loss": 6.3638,
|
|
"mean_token_accuracy": 0.12886037230491637,
|
|
"num_tokens": 22829649.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.494860124588013,
|
|
"epoch": 1.12948793407887,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004882433390656551,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.13145121783018113,
|
|
"num_tokens": 22840667.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.538703346252442,
|
|
"epoch": 1.1300230081866338,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004882311388023715,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.13190669789910317,
|
|
"num_tokens": 22852461.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.632486295700073,
|
|
"epoch": 1.1305580822943977,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004882189323820688,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.1251945301890373,
|
|
"num_tokens": 22862781.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.648410177230835,
|
|
"epoch": 1.1310931564021618,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048820671980509935,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12716651260852813,
|
|
"num_tokens": 22873393.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.624794340133667,
|
|
"epoch": 1.1316282305099257,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048819450107181583,
|
|
"loss": 6.3687,
|
|
"mean_token_accuracy": 0.1276544764637947,
|
|
"num_tokens": 22883931.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.597856330871582,
|
|
"epoch": 1.1321633046176895,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004881822761825711,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.12900567129254342,
|
|
"num_tokens": 22894829.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.510784578323364,
|
|
"epoch": 1.1326983787254534,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000488170045137718,
|
|
"loss": 6.3531,
|
|
"mean_token_accuracy": 0.12778317630290986,
|
|
"num_tokens": 22906059.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.541378164291382,
|
|
"epoch": 1.1332334528332173,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004881578079376099,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.12626659497618675,
|
|
"num_tokens": 22917834.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.579113960266113,
|
|
"epoch": 1.1337685269409814,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048814556458259996,
|
|
"loss": 6.2577,
|
|
"mean_token_accuracy": 0.14158050939440728,
|
|
"num_tokens": 22929157.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.6599236011505125,
|
|
"epoch": 1.1343036010487453,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004881333150730419,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.13018642514944076,
|
|
"num_tokens": 22939396.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.537628221511841,
|
|
"epoch": 1.1348386751565092,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048812105940928917,
|
|
"loss": 6.3538,
|
|
"mean_token_accuracy": 0.12922895923256875,
|
|
"num_tokens": 22950253.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.5369837284088135,
|
|
"epoch": 1.135373749264273,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048810879759169593,
|
|
"loss": 6.3596,
|
|
"mean_token_accuracy": 0.1285732626914978,
|
|
"num_tokens": 22960417.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.495455932617188,
|
|
"epoch": 1.135908823372037,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.000488096529620616,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.1290543757379055,
|
|
"num_tokens": 22971763.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.603179931640625,
|
|
"epoch": 1.136443897479801,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048808425549640383,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.1303618311882019,
|
|
"num_tokens": 22981571.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.563053131103516,
|
|
"epoch": 1.136978971587565,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048807197521941366,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.1328694626688957,
|
|
"num_tokens": 22991644.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.505655574798584,
|
|
"epoch": 1.1375140456953288,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004880596887900002,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.13284799605607986,
|
|
"num_tokens": 23001557.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.5576403617858885,
|
|
"epoch": 1.1380491198030926,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048804739620851806,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.12697471380233766,
|
|
"num_tokens": 23012715.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.530397510528564,
|
|
"epoch": 1.1385841939108567,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048803509747532235,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.12833357527852057,
|
|
"num_tokens": 23023016.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.556599807739258,
|
|
"epoch": 1.1391192680186206,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004880227925907682,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.1297280579805374,
|
|
"num_tokens": 23033511.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.620222473144532,
|
|
"epoch": 1.1396543421263845,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004880104815552108,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.13871046230196954,
|
|
"num_tokens": 23045149.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.542651987075805,
|
|
"epoch": 1.1401894162341484,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004879981643690056,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.1345951810479164,
|
|
"num_tokens": 23054489.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.546128368377685,
|
|
"epoch": 1.1407244903419125,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048798584103250847,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.12695099115371705,
|
|
"num_tokens": 23064725.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.49794864654541,
|
|
"epoch": 1.1412595644496764,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000487973511546075,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.12610558271408082,
|
|
"num_tokens": 23076473.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.61476240158081,
|
|
"epoch": 1.1417946385574402,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004879611759100614,
|
|
"loss": 6.325,
|
|
"mean_token_accuracy": 0.13806122466921805,
|
|
"num_tokens": 23087449.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.619863605499267,
|
|
"epoch": 1.1423297126652041,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004879488341248237,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.1350557804107666,
|
|
"num_tokens": 23098284.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.49966254234314,
|
|
"epoch": 1.142864786772968,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048793648619071834,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.13502648174762727,
|
|
"num_tokens": 23108545.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.558721446990967,
|
|
"epoch": 1.143399860880732,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004879241321081019,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.13182588443160057,
|
|
"num_tokens": 23118568.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.612079620361328,
|
|
"epoch": 1.143934934988496,
|
|
"grad_norm": 7.46875,
|
|
"learning_rate": 0.00048791177187733104,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.12453131675720215,
|
|
"num_tokens": 23129189.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.61033616065979,
|
|
"epoch": 1.1444700090962598,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004878994054987627,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.12639420479536057,
|
|
"num_tokens": 23140238.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.52753849029541,
|
|
"epoch": 1.1450050832040237,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004878870329727539,
|
|
"loss": 6.2835,
|
|
"mean_token_accuracy": 0.1355196289718151,
|
|
"num_tokens": 23149567.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.512339735031128,
|
|
"epoch": 1.1455401573117876,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000487874654299662,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.1337184876203537,
|
|
"num_tokens": 23159208.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.466184949874878,
|
|
"epoch": 1.1460752314195517,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048786226947984435,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.13029128834605216,
|
|
"num_tokens": 23169092.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.5020448684692385,
|
|
"epoch": 1.1466103055273156,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004878498785136586,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.13344621732831002,
|
|
"num_tokens": 23180385.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.58619179725647,
|
|
"epoch": 1.1471453796350795,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048783748140146245,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.12785167694091798,
|
|
"num_tokens": 23191180.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.571190071105957,
|
|
"epoch": 1.1476804537428433,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000487825078143614,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.13744020015001296,
|
|
"num_tokens": 23200920.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.519334125518799,
|
|
"epoch": 1.1482155278506072,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004878126687404713,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.1358323097229004,
|
|
"num_tokens": 23211140.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.552707242965698,
|
|
"epoch": 1.1487506019583713,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004878002531923927,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.12355867698788643,
|
|
"num_tokens": 23222039.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.627868509292602,
|
|
"epoch": 1.1492856760661352,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048778783149973674,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.12598269581794738,
|
|
"num_tokens": 23232502.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.597220039367675,
|
|
"epoch": 1.149820750173899,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048777540366286195,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.13383150175213815,
|
|
"num_tokens": 23243172.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.588002014160156,
|
|
"epoch": 1.150355824281663,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004877629696821273,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.12852920964360237,
|
|
"num_tokens": 23254558.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.596088075637818,
|
|
"epoch": 1.1508908983894268,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048775052955789185,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.12670576050877572,
|
|
"num_tokens": 23266283.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.510305166244507,
|
|
"epoch": 1.151425972497191,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004877380832905147,
|
|
"loss": 6.2731,
|
|
"mean_token_accuracy": 0.13248199224472046,
|
|
"num_tokens": 23277823.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.5186646461486815,
|
|
"epoch": 1.1519610466049548,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048772563088035533,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.13238389566540718,
|
|
"num_tokens": 23288159.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.4919130325317385,
|
|
"epoch": 1.1524961207127187,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004877131723277732,
|
|
"loss": 6.2853,
|
|
"mean_token_accuracy": 0.13082748800516128,
|
|
"num_tokens": 23299379.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.533123350143432,
|
|
"epoch": 1.1530311948204826,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004877007076331282,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.12611317709088327,
|
|
"num_tokens": 23310572.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.587215518951416,
|
|
"epoch": 1.1535662689282467,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004876882367967801,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.13565945401787757,
|
|
"num_tokens": 23320782.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.552771425247192,
|
|
"epoch": 1.1541013430360105,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048767575981908907,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.1259394496679306,
|
|
"num_tokens": 23331427.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.604757595062256,
|
|
"epoch": 1.1546364171437744,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048766327670041534,
|
|
"loss": 6.488,
|
|
"mean_token_accuracy": 0.12195928543806075,
|
|
"num_tokens": 23344250.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.604654550552368,
|
|
"epoch": 1.1551714912515383,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004876507874411194,
|
|
"loss": 6.3477,
|
|
"mean_token_accuracy": 0.13034091219305993,
|
|
"num_tokens": 23354404.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.561950302124023,
|
|
"epoch": 1.1557065653593024,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048763829204156187,
|
|
"loss": 6.3585,
|
|
"mean_token_accuracy": 0.1264335334300995,
|
|
"num_tokens": 23364634.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.492505645751953,
|
|
"epoch": 1.1562416394670663,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048762579050210344,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.1356184884905815,
|
|
"num_tokens": 23375816.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.603830242156983,
|
|
"epoch": 1.1567767135748301,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048761328282310534,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.13077081739902496,
|
|
"num_tokens": 23386583.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.525880002975464,
|
|
"epoch": 1.157311787682594,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048760076900492846,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.13986414223909377,
|
|
"num_tokens": 23396826.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.552999544143677,
|
|
"epoch": 1.157846861790358,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004875882490479343,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.13021600022912025,
|
|
"num_tokens": 23408661.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.541066122055054,
|
|
"epoch": 1.158381935898122,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048757572295248425,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.13274050131440163,
|
|
"num_tokens": 23419308.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.486504793167114,
|
|
"epoch": 1.1589170100058859,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004875631907189402,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.13612111359834672,
|
|
"num_tokens": 23430043.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.4684511661529545,
|
|
"epoch": 1.1594520841136498,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004875506523476638,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.13488834574818612,
|
|
"num_tokens": 23441246.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.606773376464844,
|
|
"epoch": 1.1599871582214136,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048753810783901716,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.12804771736264228,
|
|
"num_tokens": 23452250.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.583228635787964,
|
|
"epoch": 1.1605222323291775,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048752555719336257,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.1309939667582512,
|
|
"num_tokens": 23464174.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.51217737197876,
|
|
"epoch": 1.1610573064369416,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004875130004110623,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.13723542168736458,
|
|
"num_tokens": 23475159.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.514151525497437,
|
|
"epoch": 1.1615923805447055,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048750043749247907,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.13446007221937178,
|
|
"num_tokens": 23486210.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.514532136917114,
|
|
"epoch": 1.1621274546524694,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004874878684379756,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.12789803966879845,
|
|
"num_tokens": 23497122.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.4596717834472654,
|
|
"epoch": 1.1626625287602332,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004874752932479148,
|
|
"loss": 6.232,
|
|
"mean_token_accuracy": 0.13754346147179602,
|
|
"num_tokens": 23507765.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.545322704315185,
|
|
"epoch": 1.1631976028679971,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048746271192265974,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.1301468774676323,
|
|
"num_tokens": 23517686.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.523095512390137,
|
|
"epoch": 1.1637326769757612,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004874501244625737,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.1309164471924305,
|
|
"num_tokens": 23528325.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.566447162628174,
|
|
"epoch": 1.164267751083525,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004874375308680202,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.13206291794776917,
|
|
"num_tokens": 23540006.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.632190322875976,
|
|
"epoch": 1.164802825191289,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048742493113936274,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.12856976315379143,
|
|
"num_tokens": 23550419.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.595448780059814,
|
|
"epoch": 1.1653378992990528,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004874123252769653,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.12579906359314919,
|
|
"num_tokens": 23561227.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.535502672195435,
|
|
"epoch": 1.1658729734068167,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048739971328119194,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.12940651550889015,
|
|
"num_tokens": 23571357.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.5147114276885985,
|
|
"epoch": 1.1664080475145808,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004873870951524066,
|
|
"loss": 6.3553,
|
|
"mean_token_accuracy": 0.132980278134346,
|
|
"num_tokens": 23581875.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.559042978286743,
|
|
"epoch": 1.1669431216223447,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048737447089097373,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.1240346796810627,
|
|
"num_tokens": 23594251.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.577066469192505,
|
|
"epoch": 1.1674781957301086,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004873618404972579,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.12563381120562553,
|
|
"num_tokens": 23605159.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.621804046630859,
|
|
"epoch": 1.1680132698378725,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048734920397162376,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.13350120931863785,
|
|
"num_tokens": 23615737.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.506545734405518,
|
|
"epoch": 1.1685483439456366,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004873365613144361,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.12694838345050813,
|
|
"num_tokens": 23626207.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.5473815441131595,
|
|
"epoch": 1.1690834180534004,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004873239125260602,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.12902920097112655,
|
|
"num_tokens": 23637900.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.621821451187134,
|
|
"epoch": 1.1696184921611643,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048731125760686106,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13506797328591347,
|
|
"num_tokens": 23647867.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.5687356948852536,
|
|
"epoch": 1.1701535662689282,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048729859655720424,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.12940352633595467,
|
|
"num_tokens": 23658055.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.455961608886719,
|
|
"epoch": 1.1706886403766923,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004872859293774553,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.13185800462961197,
|
|
"num_tokens": 23669458.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.526072645187378,
|
|
"epoch": 1.1712237144844562,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048727325606797995,
|
|
"loss": 6.3277,
|
|
"mean_token_accuracy": 0.1271936185657978,
|
|
"num_tokens": 23679702.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.563662910461426,
|
|
"epoch": 1.17175878859222,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004872605766291441,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.13145660236477852,
|
|
"num_tokens": 23690844.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.457307958602906,
|
|
"epoch": 1.172293862699984,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000487247891061314,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.1314682736992836,
|
|
"num_tokens": 23701484.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.5671031951904295,
|
|
"epoch": 1.1728289368077478,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004872351993648559,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.13159382194280625,
|
|
"num_tokens": 23711452.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.516592884063721,
|
|
"epoch": 1.173364010915512,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048722250154013613,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.12494777664542198,
|
|
"num_tokens": 23723514.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.534799480438233,
|
|
"epoch": 1.1738990850232758,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004872097975875216,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.13144171759486198,
|
|
"num_tokens": 23733722.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.602074098587036,
|
|
"epoch": 1.1744341591310397,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004871970875073789,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.1271186165511608,
|
|
"num_tokens": 23743403.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.524165916442871,
|
|
"epoch": 1.1749692332388035,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004871843713000751,
|
|
"loss": 6.31,
|
|
"mean_token_accuracy": 0.13159505203366278,
|
|
"num_tokens": 23754558.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.523883056640625,
|
|
"epoch": 1.1755043073465674,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048717164896597737,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.130098707228899,
|
|
"num_tokens": 23766346.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.574266242980957,
|
|
"epoch": 1.1760393814543315,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004871589205054532,
|
|
"loss": 6.3338,
|
|
"mean_token_accuracy": 0.13770927786827086,
|
|
"num_tokens": 23776851.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.6048688888549805,
|
|
"epoch": 1.1765744555620954,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048714618591886997,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.1288090780377388,
|
|
"num_tokens": 23787350.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.472964715957642,
|
|
"epoch": 1.1771095296698593,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004871334452065954,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.13515733554959297,
|
|
"num_tokens": 23797738.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.5069136142730715,
|
|
"epoch": 1.1776446037776231,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004871206983689974,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.1382341854274273,
|
|
"num_tokens": 23809516.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.545322513580322,
|
|
"epoch": 1.178179677885387,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000487107945406444,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.13261336386203765,
|
|
"num_tokens": 23819850.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.545321655273438,
|
|
"epoch": 1.1787147519931511,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004870951863193036,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.13330233544111253,
|
|
"num_tokens": 23829891.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.491222715377807,
|
|
"epoch": 1.179249826100915,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004870824211079444,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.13427258878946305,
|
|
"num_tokens": 23840816.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.571009492874145,
|
|
"epoch": 1.1797849002086789,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048706964977273515,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.12626400142908095,
|
|
"num_tokens": 23852595.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.543050241470337,
|
|
"epoch": 1.1803199743164428,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048705687231404455,
|
|
"loss": 6.37,
|
|
"mean_token_accuracy": 0.12795960977673532,
|
|
"num_tokens": 23863048.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.558866834640503,
|
|
"epoch": 1.1808550484242066,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048704408873224156,
|
|
"loss": 6.3253,
|
|
"mean_token_accuracy": 0.1322480097413063,
|
|
"num_tokens": 23873499.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.527097129821778,
|
|
"epoch": 1.1813901225319707,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00048703129902769526,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.13709414824843408,
|
|
"num_tokens": 23885129.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.608933782577514,
|
|
"epoch": 1.1819251966397346,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004870185032007751,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.12893082946538925,
|
|
"num_tokens": 23895538.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.558342838287354,
|
|
"epoch": 1.1824602707474985,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004870057012518504,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.12423129379749298,
|
|
"num_tokens": 23907341.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.485474681854248,
|
|
"epoch": 1.1829953448552624,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048699289318129087,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.13878285884857178,
|
|
"num_tokens": 23918501.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.59085054397583,
|
|
"epoch": 1.1835304189630265,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004869800789894663,
|
|
"loss": 6.3249,
|
|
"mean_token_accuracy": 0.13167556896805763,
|
|
"num_tokens": 23929204.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.554622602462769,
|
|
"epoch": 1.1840654930707903,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004869672586767468,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.1355223499238491,
|
|
"num_tokens": 23939855.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.566775178909301,
|
|
"epoch": 1.1846005671785542,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004869544322435024,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.1322241321206093,
|
|
"num_tokens": 23949871.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.572175312042236,
|
|
"epoch": 1.185135641286318,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004869415996901036,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.12741668447852134,
|
|
"num_tokens": 23961650.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.581905651092529,
|
|
"epoch": 1.1856707153940822,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004869287610169209,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.12726534977555276,
|
|
"num_tokens": 23973103.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.532610130310059,
|
|
"epoch": 1.186205789501846,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000486915916224325,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.1320612519979477,
|
|
"num_tokens": 23982972.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.477892637252808,
|
|
"epoch": 1.18674086360961,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004869030653126868,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.13647703006863593,
|
|
"num_tokens": 23993044.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.5596959590911865,
|
|
"epoch": 1.1872759377173738,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004868902082823774,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.13060884401202202,
|
|
"num_tokens": 24003871.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.564113616943359,
|
|
"epoch": 1.1878110118251377,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004868773451337679,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.12881432026624678,
|
|
"num_tokens": 24014613.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.534707164764404,
|
|
"epoch": 1.1883460859329018,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048686447586722995,
|
|
"loss": 6.3303,
|
|
"mean_token_accuracy": 0.13396827429533004,
|
|
"num_tokens": 24024172.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.56379804611206,
|
|
"epoch": 1.1888811600406657,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048685160048313506,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.12522574216127397,
|
|
"num_tokens": 24035301.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.6384741306304935,
|
|
"epoch": 1.1894162341484296,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048683871898185486,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1386343792080879,
|
|
"num_tokens": 24045661.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.530051803588867,
|
|
"epoch": 1.1899513082561934,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048682583136376145,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.12972315177321433,
|
|
"num_tokens": 24057027.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.561061763763428,
|
|
"epoch": 1.1904863823639573,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004868129376292269,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.12427093610167503,
|
|
"num_tokens": 24068322.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.577089643478393,
|
|
"epoch": 1.1910214564717214,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048680003777862356,
|
|
"loss": 6.262,
|
|
"mean_token_accuracy": 0.13514962196350097,
|
|
"num_tokens": 24078506.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.5337562084198,
|
|
"epoch": 1.1915565305794853,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048678713181232394,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.13127023577690125,
|
|
"num_tokens": 24090296.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.478974437713623,
|
|
"epoch": 1.1920916046872492,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048677421973070063,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.12612876519560814,
|
|
"num_tokens": 24101478.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.569290971755981,
|
|
"epoch": 1.192626678795013,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048676130153412644,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.13295480459928513,
|
|
"num_tokens": 24112552.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.528984689712525,
|
|
"epoch": 1.193161752902777,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004867483772229745,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.13378995954990386,
|
|
"num_tokens": 24124210.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.576374435424805,
|
|
"epoch": 1.193696827010541,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004867354467976178,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.1304231107234955,
|
|
"num_tokens": 24133525.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.539589309692383,
|
|
"epoch": 1.194231901118305,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048672251025842994,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.1295190930366516,
|
|
"num_tokens": 24145400.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.521314668655395,
|
|
"epoch": 1.1947669752260688,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004867095676057843,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.12734123542904854,
|
|
"num_tokens": 24155596.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.597847414016724,
|
|
"epoch": 1.1953020493338327,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048669661884005467,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.12178555279970169,
|
|
"num_tokens": 24166683.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.577947998046875,
|
|
"epoch": 1.1958371234415965,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048668366396161503,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.13432841673493384,
|
|
"num_tokens": 24177649.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.522364282608033,
|
|
"epoch": 1.1963721975493606,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004866707029708392,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.137134151160717,
|
|
"num_tokens": 24188522.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.529253196716309,
|
|
"epoch": 1.1969072716571245,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004866577358681015,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.12979593575000764,
|
|
"num_tokens": 24199285.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.514498519897461,
|
|
"epoch": 1.1974423457648884,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004866447626537765,
|
|
"loss": 6.2671,
|
|
"mean_token_accuracy": 0.12873406931757927,
|
|
"num_tokens": 24210929.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.5354969024658205,
|
|
"epoch": 1.1979774198726523,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004866317833282387,
|
|
"loss": 6.3273,
|
|
"mean_token_accuracy": 0.13138288259506226,
|
|
"num_tokens": 24221394.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.541649389266968,
|
|
"epoch": 1.1985124939804164,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048661879789186295,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.13947225138545036,
|
|
"num_tokens": 24230297.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.477359199523926,
|
|
"epoch": 1.1990475680881802,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048660580634502415,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.1276162840425968,
|
|
"num_tokens": 24241505.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.58246431350708,
|
|
"epoch": 1.1995826421959441,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048659280868809744,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.13593244180083275,
|
|
"num_tokens": 24252638.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.544987678527832,
|
|
"epoch": 1.200117716303708,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000486579804921458,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.13251487016677857,
|
|
"num_tokens": 24263156.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.491865015029907,
|
|
"epoch": 1.200652790411472,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048656679504548145,
|
|
"loss": 6.2094,
|
|
"mean_token_accuracy": 0.14105861783027648,
|
|
"num_tokens": 24274384.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.590060424804688,
|
|
"epoch": 1.201187864519236,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004865537790605435,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.1250110797584057,
|
|
"num_tokens": 24285159.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.5946595668792725,
|
|
"epoch": 1.2017229386269999,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004865407569670198,
|
|
"loss": 6.3782,
|
|
"mean_token_accuracy": 0.12558842301368714,
|
|
"num_tokens": 24296202.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.573181533813477,
|
|
"epoch": 1.2022580127347637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004865277287652866,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.13199632614850998,
|
|
"num_tokens": 24306691.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.529475450515747,
|
|
"epoch": 1.2027930868425276,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004865146944557199,
|
|
"loss": 6.3309,
|
|
"mean_token_accuracy": 0.13316164761781693,
|
|
"num_tokens": 24317499.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.524376726150512,
|
|
"epoch": 1.2033281609502917,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004865016540386961,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.12565939500927925,
|
|
"num_tokens": 24328096.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.5775762557983395,
|
|
"epoch": 1.2038632350580556,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048648860751459173,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.12669195979833603,
|
|
"num_tokens": 24338188.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.611456346511841,
|
|
"epoch": 1.2043983091658195,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048647555488378355,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.1369207866489887,
|
|
"num_tokens": 24348578.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.4663220882415775,
|
|
"epoch": 1.2049333832735833,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004864624961466485,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.13434598073363305,
|
|
"num_tokens": 24358807.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.532084560394287,
|
|
"epoch": 1.2054684573813472,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004864494313035635,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.12798592671751977,
|
|
"num_tokens": 24369074.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.560862922668457,
|
|
"epoch": 1.2060035314891113,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000486436360354906,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.13494868949055672,
|
|
"num_tokens": 24380655.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.523475408554077,
|
|
"epoch": 1.2065386055968752,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048642328330105323,
|
|
"loss": 6.298,
|
|
"mean_token_accuracy": 0.1289362497627735,
|
|
"num_tokens": 24391701.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.4451531887054445,
|
|
"epoch": 1.207073679704639,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048641020014238286,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.1261564612388611,
|
|
"num_tokens": 24403690.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.575537538528442,
|
|
"epoch": 1.207608753812403,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004863971108792727,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.13011251464486123,
|
|
"num_tokens": 24414670.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.56957893371582,
|
|
"epoch": 1.2081438279201668,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048638401551210063,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.12319833263754845,
|
|
"num_tokens": 24425237.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.624338102340698,
|
|
"epoch": 1.208678902027931,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048637091404124484,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.12925269529223443,
|
|
"num_tokens": 24437142.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.535131216049194,
|
|
"epoch": 1.2092139761356948,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004863578064670837,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.13685486912727357,
|
|
"num_tokens": 24448819.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.461548089981079,
|
|
"epoch": 1.2097490502434587,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048634469278999545,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.13641059249639512,
|
|
"num_tokens": 24459392.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.54414005279541,
|
|
"epoch": 1.2102841243512226,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048633157301035895,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.13257984444499016,
|
|
"num_tokens": 24470298.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.531377696990967,
|
|
"epoch": 1.2108191984589864,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000486318447128553,
|
|
"loss": 6.2782,
|
|
"mean_token_accuracy": 0.13613951429724694,
|
|
"num_tokens": 24480477.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.52601203918457,
|
|
"epoch": 1.2113542725667505,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004863053151449566,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.12074363008141517,
|
|
"num_tokens": 24491890.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.586244249343872,
|
|
"epoch": 1.2118893466745144,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048629217705994883,
|
|
"loss": 6.3083,
|
|
"mean_token_accuracy": 0.13098841160535812,
|
|
"num_tokens": 24502583.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.6022148609161375,
|
|
"epoch": 1.2124244207822783,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004862790328739091,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.12709670886397362,
|
|
"num_tokens": 24514491.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.534934377670288,
|
|
"epoch": 1.2129594948900422,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048626588258721717,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.1416369266808033,
|
|
"num_tokens": 24524788.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.484699773788452,
|
|
"epoch": 1.2134945689978063,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004862527262002524,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.1266206443309784,
|
|
"num_tokens": 24535699.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.476378440856934,
|
|
"epoch": 1.2140296431055702,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048623956371339494,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.13135870769619942,
|
|
"num_tokens": 24547339.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.561729049682617,
|
|
"epoch": 1.214564717213334,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048622639512702477,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.12762944996356965,
|
|
"num_tokens": 24558778.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.593435049057007,
|
|
"epoch": 1.215099791321098,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048621322044152207,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.13191851750016212,
|
|
"num_tokens": 24569032.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.583175373077393,
|
|
"epoch": 1.215634865428862,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048620003965726727,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.11859198734164238,
|
|
"num_tokens": 24581356.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.534153842926026,
|
|
"epoch": 1.2161699395366259,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048618685277464116,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.13176984637975692,
|
|
"num_tokens": 24591809.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.411161661148071,
|
|
"epoch": 1.2167050136443898,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048617365979402417,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.13641507998108865,
|
|
"num_tokens": 24603492.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.517438983917236,
|
|
"epoch": 1.2172400877521536,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004861604607157975,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.1288558103144169,
|
|
"num_tokens": 24614837.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.6012519836425785,
|
|
"epoch": 1.2177751618599175,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004861472555403423,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.13232268989086152,
|
|
"num_tokens": 24624714.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.557205009460449,
|
|
"epoch": 1.2183102359676816,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048613404426803964,
|
|
"loss": 6.4042,
|
|
"mean_token_accuracy": 0.12305559441447259,
|
|
"num_tokens": 24635758.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.575355005264282,
|
|
"epoch": 1.2188453100754455,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048612082689927116,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.13127371445298194,
|
|
"num_tokens": 24645362.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.561426973342895,
|
|
"epoch": 1.2193803841832094,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004861076034344185,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12842421904206275,
|
|
"num_tokens": 24656898.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.53923807144165,
|
|
"epoch": 1.2199154582909733,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004860943738738634,
|
|
"loss": 6.3062,
|
|
"mean_token_accuracy": 0.13347529992461205,
|
|
"num_tokens": 24668191.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.624059057235717,
|
|
"epoch": 1.2204505323987371,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048608113821798786,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.13543845787644387,
|
|
"num_tokens": 24678034.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.529640436172485,
|
|
"epoch": 1.2209856065065012,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004860678964671743,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.1315036676824093,
|
|
"num_tokens": 24689062.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.508565950393677,
|
|
"epoch": 1.221520680614265,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048605464862180474,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.1287380076944828,
|
|
"num_tokens": 24699787.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.607008266448974,
|
|
"epoch": 1.222055754722029,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004860413946822619,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.13421041816473006,
|
|
"num_tokens": 24711233.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.556663608551025,
|
|
"epoch": 1.2225908288297929,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004860281346489284,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12159497067332267,
|
|
"num_tokens": 24722414.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.543051385879517,
|
|
"epoch": 1.2231259029375567,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004860148685221873,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.12858733609318734,
|
|
"num_tokens": 24733093.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.498806571960449,
|
|
"epoch": 1.2236609770453208,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048600159630242135,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.1355809085071087,
|
|
"num_tokens": 24743195.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.597199249267578,
|
|
"epoch": 1.2241960511530847,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048598831799001406,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.13153010681271554,
|
|
"num_tokens": 24753680.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.554786682128906,
|
|
"epoch": 1.2247311252608486,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004859750335853488,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.13536786139011384,
|
|
"num_tokens": 24764135.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.403936672210693,
|
|
"epoch": 1.2252661993686125,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000485961743088809,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.14579313546419143,
|
|
"num_tokens": 24775740.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.5270256996154785,
|
|
"epoch": 1.2258012734763766,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004859484465007784,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.12632556781172752,
|
|
"num_tokens": 24786169.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.585242223739624,
|
|
"epoch": 1.2263363475841405,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048593514382164123,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.1336404174566269,
|
|
"num_tokens": 24796218.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.583890581130982,
|
|
"epoch": 1.2268714216919043,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004859218350517814,
|
|
"loss": 6.3979,
|
|
"mean_token_accuracy": 0.12642351686954498,
|
|
"num_tokens": 24806957.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.583371877670288,
|
|
"epoch": 1.2274064957996682,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004859085201915831,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.13102125078439714,
|
|
"num_tokens": 24818761.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.531420612335205,
|
|
"epoch": 1.227941569907432,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004858951992414311,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.14173662960529326,
|
|
"num_tokens": 24829163.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.497774124145508,
|
|
"epoch": 1.2284766440151962,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004858818722017097,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.13168734014034272,
|
|
"num_tokens": 24839334.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.438531589508057,
|
|
"epoch": 1.22901171812296,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048586853907280395,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13705965429544448,
|
|
"num_tokens": 24850312.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.46503438949585,
|
|
"epoch": 1.229546792230724,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004858551998550987,
|
|
"loss": 6.2499,
|
|
"mean_token_accuracy": 0.13945921510457993,
|
|
"num_tokens": 24861835.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.5869134902954105,
|
|
"epoch": 1.2300818663384878,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048584185454897925,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.13292859718203545,
|
|
"num_tokens": 24872489.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.543988800048828,
|
|
"epoch": 1.230616940446252,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004858285031548309,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.1338948406279087,
|
|
"num_tokens": 24882553.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.562069129943848,
|
|
"epoch": 1.2311520145540158,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004858151456730391,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.13700807690620423,
|
|
"num_tokens": 24894386.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.503233861923218,
|
|
"epoch": 1.2316870886617797,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048580178210398954,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.1292463280260563,
|
|
"num_tokens": 24905049.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.498210716247558,
|
|
"epoch": 1.2322221627695435,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048578841244806823,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.13507410660386085,
|
|
"num_tokens": 24914831.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.542500925064087,
|
|
"epoch": 1.2327572368773074,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048577503670566116,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.1338055945932865,
|
|
"num_tokens": 24925668.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.526769018173217,
|
|
"epoch": 1.2332923109850715,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048576165487715443,
|
|
"loss": 6.3151,
|
|
"mean_token_accuracy": 0.12994013503193855,
|
|
"num_tokens": 24935983.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.503340578079223,
|
|
"epoch": 1.2338273850928354,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048574826696293455,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.13225105702877044,
|
|
"num_tokens": 24946673.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.51578311920166,
|
|
"epoch": 1.2343624592005993,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048573487296338814,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.1413614720106125,
|
|
"num_tokens": 24957075.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.567255687713623,
|
|
"epoch": 1.2348975333083632,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048572147287890183,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.12877800017595292,
|
|
"num_tokens": 24967261.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.520781135559082,
|
|
"epoch": 1.235432607416127,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048570806670986263,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.13159753754734993,
|
|
"num_tokens": 24978097.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.535343837738037,
|
|
"epoch": 1.2359676815238911,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048569465445665754,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.13654093891382219,
|
|
"num_tokens": 24987932.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.523883533477783,
|
|
"epoch": 1.236502755631655,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048568123611967396,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.1302984580397606,
|
|
"num_tokens": 24998919.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.539691972732544,
|
|
"epoch": 1.237037829739419,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004856678116992993,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13371165171265603,
|
|
"num_tokens": 25010545.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.553024625778198,
|
|
"epoch": 1.2375729038471828,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004856543811959212,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.1440042093396187,
|
|
"num_tokens": 25021133.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.498435544967651,
|
|
"epoch": 1.2381079779549466,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004856409446099274,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.1292448416352272,
|
|
"num_tokens": 25031838.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.48333420753479,
|
|
"epoch": 1.2386430520627107,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048562750194170595,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.1293560743331909,
|
|
"num_tokens": 25042737.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.554791212081909,
|
|
"epoch": 1.2391781261704746,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000485614053191645,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.13055189922451974,
|
|
"num_tokens": 25054442.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.489489889144897,
|
|
"epoch": 1.2397132002782385,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004856005983601328,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.1456099934875965,
|
|
"num_tokens": 25065509.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.5698034286499025,
|
|
"epoch": 1.2402482743860024,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048558713744755794,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.12442174926400185,
|
|
"num_tokens": 25077306.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.521883249282837,
|
|
"epoch": 1.2407833484937665,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004855736704543091,
|
|
"loss": 6.3081,
|
|
"mean_token_accuracy": 0.13450614660978316,
|
|
"num_tokens": 25088230.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.6110950946807865,
|
|
"epoch": 1.2413184226015304,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004855601973807751,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.12289422452449798,
|
|
"num_tokens": 25099658.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.573994112014771,
|
|
"epoch": 1.2418534967092942,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048554671822734495,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.13023086190223693,
|
|
"num_tokens": 25110512.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.5347192764282225,
|
|
"epoch": 1.2423885708170581,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048553323299440807,
|
|
"loss": 6.3089,
|
|
"mean_token_accuracy": 0.13401264771819116,
|
|
"num_tokens": 25120193.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.528376770019531,
|
|
"epoch": 1.242923644924822,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048551974168235346,
|
|
"loss": 6.321,
|
|
"mean_token_accuracy": 0.12739662155508996,
|
|
"num_tokens": 25131752.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.599687719345093,
|
|
"epoch": 1.243458719032586,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000485506244291571,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.13200697377324105,
|
|
"num_tokens": 25141541.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.466404867172241,
|
|
"epoch": 1.24399379314035,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004854927408224503,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.1312132328748703,
|
|
"num_tokens": 25152219.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.591228199005127,
|
|
"epoch": 1.2445288672481138,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048547923127538126,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.12918494567275046,
|
|
"num_tokens": 25163030.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.499180746078491,
|
|
"epoch": 1.2450639413558777,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048546571565075396,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.13481747061014177,
|
|
"num_tokens": 25174637.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.426168441772461,
|
|
"epoch": 1.2455990154636418,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004854521939489587,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14389699101448059,
|
|
"num_tokens": 25185067.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.467606449127198,
|
|
"epoch": 1.2461340895714057,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048543866617038604,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.13719036281108857,
|
|
"num_tokens": 25195046.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.517219161987304,
|
|
"epoch": 1.2466691636791696,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048542513231542635,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.12623920813202857,
|
|
"num_tokens": 25206265.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.581112813949585,
|
|
"epoch": 1.2472042377869335,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004854115923844705,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.1283203311264515,
|
|
"num_tokens": 25217690.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.549913930892944,
|
|
"epoch": 1.2477393118946973,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004853980463779096,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.12955136895179747,
|
|
"num_tokens": 25228229.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.473557043075561,
|
|
"epoch": 1.2482743860024614,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004853844942961346,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.13080960735678673,
|
|
"num_tokens": 25240073.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.530133438110352,
|
|
"epoch": 1.2488094601102253,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000485370936139537,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.1356102332472801,
|
|
"num_tokens": 25251915.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.512946271896363,
|
|
"epoch": 1.2493445342179892,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000485357371908508,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.1290469728410244,
|
|
"num_tokens": 25262932.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.533622694015503,
|
|
"epoch": 1.249879608325753,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004853438016034396,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.12990323528647424,
|
|
"num_tokens": 25274693.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.59214186668396,
|
|
"epoch": 1.250414682433517,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048533022522472344,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.13764603063464165,
|
|
"num_tokens": 25285359.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.497456979751587,
|
|
"epoch": 1.250949756541281,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048531664277275154,
|
|
"loss": 6.284,
|
|
"mean_token_accuracy": 0.12981810346245765,
|
|
"num_tokens": 25296730.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.502764129638672,
|
|
"epoch": 1.251484830649045,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004853030542479162,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.1384017750620842,
|
|
"num_tokens": 25306422.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.5642656803131105,
|
|
"epoch": 1.2520199047568088,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004852894596506096,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.1314690053462982,
|
|
"num_tokens": 25317980.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.534403991699219,
|
|
"epoch": 1.2525549788645727,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004852758589812245,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.13768871873617172,
|
|
"num_tokens": 25329905.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.602970790863037,
|
|
"epoch": 1.2530900529723366,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048526225224015355,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.12489748820662498,
|
|
"num_tokens": 25340759.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.553256988525391,
|
|
"epoch": 1.2536251270801007,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004852486394277896,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.12719984650611876,
|
|
"num_tokens": 25351124.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.591535377502441,
|
|
"epoch": 1.2541602011878645,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048523502054452565,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.1319223664700985,
|
|
"num_tokens": 25361337.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.585754776000977,
|
|
"epoch": 1.2546952752956284,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048522139559075507,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.13189950287342073,
|
|
"num_tokens": 25371893.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.456956672668457,
|
|
"epoch": 1.2552303494033923,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004852077645668712,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.14131250604987144,
|
|
"num_tokens": 25383365.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.5274192810058596,
|
|
"epoch": 1.2557654235111562,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004851941274732678,
|
|
"loss": 6.3123,
|
|
"mean_token_accuracy": 0.13500531166791915,
|
|
"num_tokens": 25393211.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.4369782447814945,
|
|
"epoch": 1.2563004976189203,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004851804843103384,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.13275761157274246,
|
|
"num_tokens": 25404828.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.571536111831665,
|
|
"epoch": 1.2568355717266841,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048516683507847705,
|
|
"loss": 6.3314,
|
|
"mean_token_accuracy": 0.13917914777994156,
|
|
"num_tokens": 25416016.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.576375675201416,
|
|
"epoch": 1.257370645834448,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004851531797780779,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.13366828113794327,
|
|
"num_tokens": 25426173.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.525392293930054,
|
|
"epoch": 1.2579057199422121,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004851395184095352,
|
|
"loss": 6.246,
|
|
"mean_token_accuracy": 0.138031068444252,
|
|
"num_tokens": 25437507.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.542758798599243,
|
|
"epoch": 1.258440794049976,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004851258509732434,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.1226758360862732,
|
|
"num_tokens": 25448201.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.596157741546631,
|
|
"epoch": 1.2589758681577399,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00048511217746959723,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.13061847537755966,
|
|
"num_tokens": 25458640.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.558047437667847,
|
|
"epoch": 1.2595109422655038,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048509849789899146,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.137232506275177,
|
|
"num_tokens": 25469474.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.561356449127198,
|
|
"epoch": 1.2600460163732676,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000485084812261821,
|
|
"loss": 6.4076,
|
|
"mean_token_accuracy": 0.12736963108181953,
|
|
"num_tokens": 25479565.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.5499156475067135,
|
|
"epoch": 1.2605810904810317,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004850711205584812,
|
|
"loss": 6.2692,
|
|
"mean_token_accuracy": 0.1392711654305458,
|
|
"num_tokens": 25490142.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.516708469390869,
|
|
"epoch": 1.2611161645887956,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048505742278936726,
|
|
"loss": 6.3754,
|
|
"mean_token_accuracy": 0.13398413434624673,
|
|
"num_tokens": 25500824.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.591862440109253,
|
|
"epoch": 1.2616512386965595,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048504371895487474,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.13289703279733658,
|
|
"num_tokens": 25511251.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.547235202789307,
|
|
"epoch": 1.2621863128043234,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048503000905539945,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.12680892273783684,
|
|
"num_tokens": 25521368.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.541527271270752,
|
|
"epoch": 1.2627213869120872,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048501629309133707,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.12748572900891303,
|
|
"num_tokens": 25532486.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.5395254611969,
|
|
"epoch": 1.2632564610198513,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004850025710630838,
|
|
"loss": 6.3163,
|
|
"mean_token_accuracy": 0.13559018895030023,
|
|
"num_tokens": 25542867.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.500273132324219,
|
|
"epoch": 1.2637915351276152,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048498884297103575,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.1332220569252968,
|
|
"num_tokens": 25553564.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.533845472335815,
|
|
"epoch": 1.264326609235379,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004849751088155894,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.13092882707715034,
|
|
"num_tokens": 25564017.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.506636095046997,
|
|
"epoch": 1.264861683343143,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004849613685971413,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.13756049647927285,
|
|
"num_tokens": 25575125.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.572484350204467,
|
|
"epoch": 1.2653967574509069,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004849476223160882,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.12898685410618782,
|
|
"num_tokens": 25586405.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.514791965484619,
|
|
"epoch": 1.265931831558671,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004849338699728269,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.12814901471138002,
|
|
"num_tokens": 25597494.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.529297876358032,
|
|
"epoch": 1.2664669056664348,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048492011156775467,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.13860967606306077,
|
|
"num_tokens": 25608425.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.5342460632324215,
|
|
"epoch": 1.2670019797741987,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004849063471012688,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1266927093267441,
|
|
"num_tokens": 25619411.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.566569089889526,
|
|
"epoch": 1.2675370538819626,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004848925765737665,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.12526525929570198,
|
|
"num_tokens": 25630477.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.587625980377197,
|
|
"epoch": 1.2680721279897265,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048487879998564565,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.1306361250579357,
|
|
"num_tokens": 25640129.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.512728309631347,
|
|
"epoch": 1.2686072020974906,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048486501733730386,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.132972913980484,
|
|
"num_tokens": 25650592.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.506902265548706,
|
|
"epoch": 1.2691422762052544,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048485122862913934,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.1407736212015152,
|
|
"num_tokens": 25660408.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.493857097625733,
|
|
"epoch": 1.2696773503130183,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048483743386154994,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.13489907830953599,
|
|
"num_tokens": 25671563.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.558619737625122,
|
|
"epoch": 1.2702124244207824,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048482363303493415,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.13159688413143159,
|
|
"num_tokens": 25682474.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.642208576202393,
|
|
"epoch": 1.270747498528546,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004848098261496905,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.12964960634708406,
|
|
"num_tokens": 25692594.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.392217111587525,
|
|
"epoch": 1.2712825726363102,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004847960132062175,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.1474221259355545,
|
|
"num_tokens": 25703724.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.513773727416992,
|
|
"epoch": 1.271817646744074,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004847821942049142,
|
|
"loss": 6.4354,
|
|
"mean_token_accuracy": 0.11740069463849068,
|
|
"num_tokens": 25714911.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.638753223419189,
|
|
"epoch": 1.272352720851838,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048476836914617945,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.13183923736214637,
|
|
"num_tokens": 25725098.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.572930812835693,
|
|
"epoch": 1.272887794959602,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048475453803041254,
|
|
"loss": 6.2628,
|
|
"mean_token_accuracy": 0.12592896148562432,
|
|
"num_tokens": 25735099.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.4913472652435305,
|
|
"epoch": 1.273422869067366,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004847407008580128,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.13161098584532738,
|
|
"num_tokens": 25746852.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.512494039535523,
|
|
"epoch": 1.2739579431751298,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048472685762937983,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.13382739797234536,
|
|
"num_tokens": 25758579.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.512800168991089,
|
|
"epoch": 1.2744930172828937,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048471300834491325,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.13117347955703734,
|
|
"num_tokens": 25769965.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.554977321624756,
|
|
"epoch": 1.2750280913906575,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004846991530050132,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.1322600245475769,
|
|
"num_tokens": 25780264.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.54880313873291,
|
|
"epoch": 1.2755631654984216,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004846852916100794,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.13358540534973146,
|
|
"num_tokens": 25791228.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.540342521667481,
|
|
"epoch": 1.2760982396061855,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004846714241605123,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.1332520917057991,
|
|
"num_tokens": 25802428.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.563567304611206,
|
|
"epoch": 1.2766333137139494,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048465755065671233,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.1317474439740181,
|
|
"num_tokens": 25814220.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.554912805557251,
|
|
"epoch": 1.2771683878217133,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048464367109908005,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.12791907414793968,
|
|
"num_tokens": 25824382.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.450937795639038,
|
|
"epoch": 1.2777034619294771,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004846297854880162,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.1334068424999714,
|
|
"num_tokens": 25834896.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.576845788955689,
|
|
"epoch": 1.2782385360372412,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048461589382392176,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.12662025466561316,
|
|
"num_tokens": 25847300.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.584928846359253,
|
|
"epoch": 1.2787736101450051,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004846019961071978,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.13572727739810944,
|
|
"num_tokens": 25858599.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.483222579956054,
|
|
"epoch": 1.279308684252769,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004845880923382457,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.13509821593761445,
|
|
"num_tokens": 25869135.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.516763973236084,
|
|
"epoch": 1.2798437583605329,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048457418251746695,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.13429969400167466,
|
|
"num_tokens": 25879234.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.5868120193481445,
|
|
"epoch": 1.2803788324682968,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004845602666452629,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.13416241556406022,
|
|
"num_tokens": 25888230.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.562831401824951,
|
|
"epoch": 1.2809139065760609,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004845463447220358,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.14075978919863702,
|
|
"num_tokens": 25899429.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.486060523986817,
|
|
"epoch": 1.2814489806838247,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004845324167481874,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.14120842665433883,
|
|
"num_tokens": 25911042.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.555566024780274,
|
|
"epoch": 1.2819840547915886,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004845184827241199,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.13459475412964822,
|
|
"num_tokens": 25921466.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.56078405380249,
|
|
"epoch": 1.2825191288993525,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004845045426502357,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.1237009696662426,
|
|
"num_tokens": 25931059.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.523500299453735,
|
|
"epoch": 1.2830542030071164,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048449059652693724,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1334775298833847,
|
|
"num_tokens": 25941669.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.488269805908203,
|
|
"epoch": 1.2835892771148805,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004844766443546272,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.13760485649108886,
|
|
"num_tokens": 25952066.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.551593017578125,
|
|
"epoch": 1.2841243512226443,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004844626861337085,
|
|
"loss": 6.2276,
|
|
"mean_token_accuracy": 0.1375007748603821,
|
|
"num_tokens": 25962388.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.2841243512226443,
|
|
"eval_entropy": 6.386375296148007,
|
|
"eval_loss": 6.437783241271973,
|
|
"eval_mean_token_accuracy": 0.13334858964907753,
|
|
"eval_num_tokens": 25962388.0,
|
|
"eval_runtime": 22.5367,
|
|
"eval_samples_per_second": 1316.92,
|
|
"eval_steps_per_second": 164.621,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.476883220672607,
|
|
"epoch": 1.2846594253304082,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004844487218645843,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.13293329626321793,
|
|
"num_tokens": 25973865.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.5142007827758786,
|
|
"epoch": 1.2851944994381723,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004844347515476575,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.13389490097761153,
|
|
"num_tokens": 25985113.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.539774703979492,
|
|
"epoch": 1.285729573545936,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048442077518333175,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.1449642926454544,
|
|
"num_tokens": 25995980.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.491984510421753,
|
|
"epoch": 1.2862646476537,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048440679277201063,
|
|
"loss": 6.2924,
|
|
"mean_token_accuracy": 0.13728865012526512,
|
|
"num_tokens": 26006362.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.5380847454071045,
|
|
"epoch": 1.286799721761464,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048439280431409774,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.13121474161744118,
|
|
"num_tokens": 26016623.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.455700159072876,
|
|
"epoch": 1.2873347958692278,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048437880980999694,
|
|
"loss": 6.1831,
|
|
"mean_token_accuracy": 0.13906619623303412,
|
|
"num_tokens": 26027202.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.473853254318238,
|
|
"epoch": 1.287869869976992,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004843648092601125,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.12801167741417885,
|
|
"num_tokens": 26037330.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.525657653808594,
|
|
"epoch": 1.2884049440847558,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004843508026648487,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.13337891325354576,
|
|
"num_tokens": 26047661.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.634007549285888,
|
|
"epoch": 1.2889400181925197,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004843367900246098,
|
|
"loss": 6.3625,
|
|
"mean_token_accuracy": 0.12507258877158164,
|
|
"num_tokens": 26058582.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.537368679046631,
|
|
"epoch": 1.2894750923002836,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048432277133980055,
|
|
"loss": 6.3396,
|
|
"mean_token_accuracy": 0.12189410924911499,
|
|
"num_tokens": 26069117.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.537881183624267,
|
|
"epoch": 1.2900101664080474,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048430874661082565,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.12988518327474594,
|
|
"num_tokens": 26079327.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.580955171585083,
|
|
"epoch": 1.2905452405158115,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048429471583809016,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.13474506214261056,
|
|
"num_tokens": 26090709.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.6343930721282955,
|
|
"epoch": 1.2910803146235754,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004842806790219991,
|
|
"loss": 6.3157,
|
|
"mean_token_accuracy": 0.12702692076563835,
|
|
"num_tokens": 26101570.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.503259086608887,
|
|
"epoch": 1.2916153887313393,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048426663616295783,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.13804319500923157,
|
|
"num_tokens": 26112827.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.492285490036011,
|
|
"epoch": 1.2921504628391032,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048425258726137187,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.1263483129441738,
|
|
"num_tokens": 26124141.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.516628980636597,
|
|
"epoch": 1.292685536946867,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048423853231764684,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.13210719525814058,
|
|
"num_tokens": 26135372.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.52798318862915,
|
|
"epoch": 1.2932206110546312,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048422447133218867,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.13133319541811944,
|
|
"num_tokens": 26145933.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.561259794235229,
|
|
"epoch": 1.293755685162395,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048421040430540323,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.12620900720357894,
|
|
"num_tokens": 26155948.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.478076982498169,
|
|
"epoch": 1.294290759270159,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004841963312376967,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.1421545147895813,
|
|
"num_tokens": 26166410.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.462507247924805,
|
|
"epoch": 1.2948258333779228,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048418225212947566,
|
|
"loss": 6.2768,
|
|
"mean_token_accuracy": 0.13346440643072127,
|
|
"num_tokens": 26177334.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.6124979019165036,
|
|
"epoch": 1.2953609074856867,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004841681669811464,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.12650283202528953,
|
|
"num_tokens": 26187987.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.576649856567383,
|
|
"epoch": 1.2958959815934508,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004841540757931157,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.12536120936274528,
|
|
"num_tokens": 26198600.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.487023544311524,
|
|
"epoch": 1.2964310557012146,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004841399785657904,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.12932894751429558,
|
|
"num_tokens": 26210977.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.540788698196411,
|
|
"epoch": 1.2969661298089785,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048412587529957774,
|
|
"loss": 6.2888,
|
|
"mean_token_accuracy": 0.1334947131574154,
|
|
"num_tokens": 26220813.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.564545059204102,
|
|
"epoch": 1.2975012039167424,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004841117659948848,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.13227230161428452,
|
|
"num_tokens": 26232042.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.589853429794312,
|
|
"epoch": 1.2980362780245063,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048409765065211884,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.13484857305884362,
|
|
"num_tokens": 26242968.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.575265645980835,
|
|
"epoch": 1.2985713521322704,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048408352927168774,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.13241580054163932,
|
|
"num_tokens": 26252751.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.520197963714599,
|
|
"epoch": 1.2991064262400343,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004840694018539991,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.12634991630911827,
|
|
"num_tokens": 26263270.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.5590331077575685,
|
|
"epoch": 1.2996415003477981,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048405526839946086,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.1273276686668396,
|
|
"num_tokens": 26274279.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.57621922492981,
|
|
"epoch": 1.3001765744555622,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048404112890848105,
|
|
"loss": 6.3838,
|
|
"mean_token_accuracy": 0.13533301502466202,
|
|
"num_tokens": 26286020.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.560911464691162,
|
|
"epoch": 1.3007116485633259,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048402698338146803,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.13460245206952096,
|
|
"num_tokens": 26296798.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.485049200057984,
|
|
"epoch": 1.30124672267109,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004840128318188303,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.1385771855711937,
|
|
"num_tokens": 26306952.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.646480941772461,
|
|
"epoch": 1.3017817967788539,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048399867422097644,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.13204823806881905,
|
|
"num_tokens": 26317686.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.595529508590698,
|
|
"epoch": 1.3023168708866177,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048398451058831514,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.13236458525061606,
|
|
"num_tokens": 26327997.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.483434581756592,
|
|
"epoch": 1.3028519449943818,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048397034092125554,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.13000286892056465,
|
|
"num_tokens": 26340227.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.63649435043335,
|
|
"epoch": 1.3033870191021457,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048395616522020667,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.1249793030321598,
|
|
"num_tokens": 26350549.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.5887518405914305,
|
|
"epoch": 1.3039220932099096,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004839419834855779,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.13172085583209991,
|
|
"num_tokens": 26361822.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.4851236820220945,
|
|
"epoch": 1.3044571673176735,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004839277957177787,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.13301774114370346,
|
|
"num_tokens": 26372720.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.454987621307373,
|
|
"epoch": 1.3049922414254373,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004839136019172188,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.1354654051363468,
|
|
"num_tokens": 26383092.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.499829721450806,
|
|
"epoch": 1.3055273155332014,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000483899402084308,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.14037376120686532,
|
|
"num_tokens": 26395188.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.556978702545166,
|
|
"epoch": 1.3060623896409653,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004838851962194563,
|
|
"loss": 6.3664,
|
|
"mean_token_accuracy": 0.13069112375378608,
|
|
"num_tokens": 26406338.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.521770095825195,
|
|
"epoch": 1.3065974637487292,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004838709843230739,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.1294810354709625,
|
|
"num_tokens": 26416983.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.528356266021729,
|
|
"epoch": 1.307132537856493,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004838567663955712,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.13848564326763152,
|
|
"num_tokens": 26426966.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.528638315200806,
|
|
"epoch": 1.307667611964257,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004838425424373587,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.1309279464185238,
|
|
"num_tokens": 26437711.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.545057106018066,
|
|
"epoch": 1.308202686072021,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004838283124488472,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.13038895800709724,
|
|
"num_tokens": 26448657.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.607879734039306,
|
|
"epoch": 1.308737760179785,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.00048381407643044737,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.13647112473845482,
|
|
"num_tokens": 26459363.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.498840999603272,
|
|
"epoch": 1.3092728342875488,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004837998343825705,
|
|
"loss": 6.2933,
|
|
"mean_token_accuracy": 0.1369725577533245,
|
|
"num_tokens": 26470149.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.4808508396148685,
|
|
"epoch": 1.3098079083953127,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048378558630562783,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.13962852880358695,
|
|
"num_tokens": 26480424.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.498993587493897,
|
|
"epoch": 1.3103429825030766,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004837713322000306,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.12992604449391365,
|
|
"num_tokens": 26490312.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.48661847114563,
|
|
"epoch": 1.3108780566108407,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004837570720661905,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.14373423680663108,
|
|
"num_tokens": 26501119.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.580825424194336,
|
|
"epoch": 1.3114131307186045,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048374280590451934,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.13384997844696045,
|
|
"num_tokens": 26512438.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.5407239437103275,
|
|
"epoch": 1.3119482048263684,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048372853371542895,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.12450519725680351,
|
|
"num_tokens": 26523930.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.56227297782898,
|
|
"epoch": 1.3124832789341323,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004837142554993315,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.13300466015934945,
|
|
"num_tokens": 26534937.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.476114416122437,
|
|
"epoch": 1.3130183530418962,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004836999712566392,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.13274189084768295,
|
|
"num_tokens": 26544555.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.5541692733764645,
|
|
"epoch": 1.3135534271496603,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048368568098776463,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.1406101442873478,
|
|
"num_tokens": 26556144.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.571285533905029,
|
|
"epoch": 1.3140885012574242,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004836713846931203,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.1273029126226902,
|
|
"num_tokens": 26567350.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.56294436454773,
|
|
"epoch": 1.314623575365188,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048365708237311904,
|
|
"loss": 6.2877,
|
|
"mean_token_accuracy": 0.13095688074827194,
|
|
"num_tokens": 26579486.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.5144415378570555,
|
|
"epoch": 1.3151586494729521,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004836427740281739,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13191987350583076,
|
|
"num_tokens": 26589665.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.529788827896118,
|
|
"epoch": 1.3156937235807158,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048362845965869793,
|
|
"loss": 6.2901,
|
|
"mean_token_accuracy": 0.13123327121138573,
|
|
"num_tokens": 26600187.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.502836656570435,
|
|
"epoch": 1.31622879768848,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004836141392651046,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.1337031193077564,
|
|
"num_tokens": 26612155.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.548255729675293,
|
|
"epoch": 1.3167638717962438,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048359981284780727,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.12883710488677025,
|
|
"num_tokens": 26623077.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.491298675537109,
|
|
"epoch": 1.3172989459040076,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004835854804072196,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.13802778869867324,
|
|
"num_tokens": 26632979.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.495585870742798,
|
|
"epoch": 1.3178340200117717,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048357114194375555,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.1271979182958603,
|
|
"num_tokens": 26644377.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.573164081573486,
|
|
"epoch": 1.3183690941195356,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000483556797457829,
|
|
"loss": 6.3333,
|
|
"mean_token_accuracy": 0.12611328884959222,
|
|
"num_tokens": 26655538.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.536789274215698,
|
|
"epoch": 1.3189041682272995,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048354244694985435,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.12973858788609505,
|
|
"num_tokens": 26668011.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.486205053329468,
|
|
"epoch": 1.3194392423350634,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004835280904202457,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.13040204644203185,
|
|
"num_tokens": 26678996.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.5596967220306395,
|
|
"epoch": 1.3199743164428273,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004835137278694178,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.13785816729068756,
|
|
"num_tokens": 26689041.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.5753649234771725,
|
|
"epoch": 1.3205093905505914,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004834993592977854,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.13826132118701934,
|
|
"num_tokens": 26699459.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.549886798858642,
|
|
"epoch": 1.3210444646583552,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004834849847057632,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.12919416651129723,
|
|
"num_tokens": 26711663.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.558913803100586,
|
|
"epoch": 1.321579538766119,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048347060409376644,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.123536217212677,
|
|
"num_tokens": 26722960.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.54972996711731,
|
|
"epoch": 1.322114612873883,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048345621746221024,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.13708956986665727,
|
|
"num_tokens": 26733274.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.5588398456573485,
|
|
"epoch": 1.3226496869816469,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048344182481151003,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.12774837762117386,
|
|
"num_tokens": 26743906.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.462081623077393,
|
|
"epoch": 1.323184761089411,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048342742614208145,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.12888485714793205,
|
|
"num_tokens": 26755093.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.510008096694946,
|
|
"epoch": 1.3237198351971748,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004834130214543402,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.133803091943264,
|
|
"num_tokens": 26765614.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.513565587997436,
|
|
"epoch": 1.3242549093049387,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048339861074870227,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.1330991990864277,
|
|
"num_tokens": 26778078.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.604484891891479,
|
|
"epoch": 1.3247899834127026,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048338419402558375,
|
|
"loss": 6.3154,
|
|
"mean_token_accuracy": 0.13245146498084068,
|
|
"num_tokens": 26788707.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.58511905670166,
|
|
"epoch": 1.3253250575204665,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004833697712854009,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.13194304704666138,
|
|
"num_tokens": 26798650.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.517331314086914,
|
|
"epoch": 1.3258601316282306,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048335534252857016,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.13552766814827918,
|
|
"num_tokens": 26809822.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.5462925910949705,
|
|
"epoch": 1.3263952057359945,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004833409077555082,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.12845633625984193,
|
|
"num_tokens": 26821061.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.6133284091949465,
|
|
"epoch": 1.3269302798437583,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048332646696663177,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.12829353287816048,
|
|
"num_tokens": 26832020.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.596477937698364,
|
|
"epoch": 1.3274653539515222,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004833120201623579,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.128353201597929,
|
|
"num_tokens": 26844287.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.412652969360352,
|
|
"epoch": 1.328000428059286,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048329756734310375,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.14178198873996734,
|
|
"num_tokens": 26855790.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.452540540695191,
|
|
"epoch": 1.3285355021670502,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048328310850928656,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.134925177693367,
|
|
"num_tokens": 26867391.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.551491546630859,
|
|
"epoch": 1.329070576274814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048326864366132397,
|
|
"loss": 6.3253,
|
|
"mean_token_accuracy": 0.13360649049282075,
|
|
"num_tokens": 26879173.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.559604692459106,
|
|
"epoch": 1.329605650382578,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004832541727996335,
|
|
"loss": 6.2344,
|
|
"mean_token_accuracy": 0.13868265673518182,
|
|
"num_tokens": 26889839.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.486599254608154,
|
|
"epoch": 1.330140724490342,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000483239695924633,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.13732991963624955,
|
|
"num_tokens": 26900217.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.532090044021606,
|
|
"epoch": 1.330675798598106,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048322521303674064,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.13312758281826972,
|
|
"num_tokens": 26911366.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.597012996673584,
|
|
"epoch": 1.3312108727058698,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048321072413637454,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.12487093731760979,
|
|
"num_tokens": 26922135.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.551101970672607,
|
|
"epoch": 1.3317459468136337,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004831962292239529,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.13313136473298073,
|
|
"num_tokens": 26932502.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.499680852890014,
|
|
"epoch": 1.3322810209213976,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048318172829989447,
|
|
"loss": 6.3364,
|
|
"mean_token_accuracy": 0.13847661167383193,
|
|
"num_tokens": 26944607.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.529852628707886,
|
|
"epoch": 1.3328160950291617,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004831672213646179,
|
|
"loss": 6.3356,
|
|
"mean_token_accuracy": 0.1344766914844513,
|
|
"num_tokens": 26955205.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.512268972396851,
|
|
"epoch": 1.3333511691369255,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004831527084185421,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.1448250100016594,
|
|
"num_tokens": 26965558.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.497064542770386,
|
|
"epoch": 1.3338862432446894,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.000483138189462086,
|
|
"loss": 6.288,
|
|
"mean_token_accuracy": 0.13134488835930824,
|
|
"num_tokens": 26976176.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.550390195846558,
|
|
"epoch": 1.3344213173524533,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048312366449566895,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.13253561332821845,
|
|
"num_tokens": 26987099.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.521877908706665,
|
|
"epoch": 1.3349563914602172,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004831091335197104,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.13181954994797707,
|
|
"num_tokens": 26998122.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.4629723072052006,
|
|
"epoch": 1.3354914655679813,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004830945965346298,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.1338569551706314,
|
|
"num_tokens": 27009427.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.5822224617004395,
|
|
"epoch": 1.3360265396757451,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000483080053540847,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.12383663654327393,
|
|
"num_tokens": 27020701.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.582948064804077,
|
|
"epoch": 1.336561613783509,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004830655045387818,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.1241733305156231,
|
|
"num_tokens": 27033215.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.554017066955566,
|
|
"epoch": 1.337096687891273,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048305094952885453,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.12772757932543755,
|
|
"num_tokens": 27043846.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.511205577850342,
|
|
"epoch": 1.3376317619990368,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004830363885114853,
|
|
"loss": 6.305,
|
|
"mean_token_accuracy": 0.13151946440339088,
|
|
"num_tokens": 27054783.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.494199800491333,
|
|
"epoch": 1.3381668361068009,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004830218214870946,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.1325196735560894,
|
|
"num_tokens": 27066051.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.558785486221313,
|
|
"epoch": 1.3387019102145647,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004830072484561029,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.13402727320790292,
|
|
"num_tokens": 27078210.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.569102621078491,
|
|
"epoch": 1.3392369843223286,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004829926694189312,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.12516780570149422,
|
|
"num_tokens": 27089693.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.528443145751953,
|
|
"epoch": 1.3397720584300925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004829780843760005,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.1275798462331295,
|
|
"num_tokens": 27099856.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.54946722984314,
|
|
"epoch": 1.3403071325378564,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004829634933277317,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.1284944772720337,
|
|
"num_tokens": 27110218.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.52546067237854,
|
|
"epoch": 1.3408422066456205,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048294889627454636,
|
|
"loss": 6.2923,
|
|
"mean_token_accuracy": 0.13666339591145515,
|
|
"num_tokens": 27120911.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.4948999881744385,
|
|
"epoch": 1.3413772807533844,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048293429321686585,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.13520927503705024,
|
|
"num_tokens": 27130964.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.506992530822754,
|
|
"epoch": 1.3419123548611482,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048291968415511174,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.1324952982366085,
|
|
"num_tokens": 27141641.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.544699478149414,
|
|
"epoch": 1.3424474289689121,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048290506908970607,
|
|
"loss": 6.3666,
|
|
"mean_token_accuracy": 0.12738464027643204,
|
|
"num_tokens": 27152591.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.571207761764526,
|
|
"epoch": 1.342982503076676,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004828904480210707,
|
|
"loss": 6.4297,
|
|
"mean_token_accuracy": 0.12691449224948884,
|
|
"num_tokens": 27163839.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.624313831329346,
|
|
"epoch": 1.34351757718444,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004828758209496278,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.13590908646583558,
|
|
"num_tokens": 27174480.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.500087404251099,
|
|
"epoch": 1.344052651292204,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048286118787579983,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.13080087080597877,
|
|
"num_tokens": 27184546.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.451597452163696,
|
|
"epoch": 1.3445877253999678,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048284654880000933,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.13953398764133454,
|
|
"num_tokens": 27195093.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.476680326461792,
|
|
"epoch": 1.345122799507732,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048283190372267886,
|
|
"loss": 6.3436,
|
|
"mean_token_accuracy": 0.1333930142223835,
|
|
"num_tokens": 27206416.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.5952800750732425,
|
|
"epoch": 1.3456578736154958,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004828172526442314,
|
|
"loss": 6.2663,
|
|
"mean_token_accuracy": 0.12958376929163934,
|
|
"num_tokens": 27215533.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.5549458980560305,
|
|
"epoch": 1.3461929477232597,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048280259556509,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.13110331296920777,
|
|
"num_tokens": 27225985.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.515612268447876,
|
|
"epoch": 1.3467280218310236,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004827879324856778,
|
|
"loss": 6.2924,
|
|
"mean_token_accuracy": 0.13066375404596328,
|
|
"num_tokens": 27235967.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.529239511489868,
|
|
"epoch": 1.3472630959387875,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048277326340641835,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.1346130132675171,
|
|
"num_tokens": 27246854.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.448957109451294,
|
|
"epoch": 1.3477981700465516,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000482758588327735,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.13244736939668655,
|
|
"num_tokens": 27256640.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.524251413345337,
|
|
"epoch": 1.3483332441543154,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004827439072500516,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.12838973328471184,
|
|
"num_tokens": 27266907.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.599645519256592,
|
|
"epoch": 1.3488683182620793,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048272922017379217,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.13354076966643333,
|
|
"num_tokens": 27277089.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.567108678817749,
|
|
"epoch": 1.3494033923698432,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004827145270993807,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13490659818053247,
|
|
"num_tokens": 27286781.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.525397729873657,
|
|
"epoch": 1.349938466477607,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004826998280272414,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.13888752982020378,
|
|
"num_tokens": 27298011.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.501267433166504,
|
|
"epoch": 1.3504735405853712,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048268512295779873,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.1331058345735073,
|
|
"num_tokens": 27309052.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.4906703472137455,
|
|
"epoch": 1.351008614693135,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004826704118914773,
|
|
"loss": 6.2625,
|
|
"mean_token_accuracy": 0.1372261181473732,
|
|
"num_tokens": 27319945.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.496233177185059,
|
|
"epoch": 1.351543688800899,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000482655694828702,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.14131269082427025,
|
|
"num_tokens": 27330543.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.551932334899902,
|
|
"epoch": 1.3520787629086628,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004826409717698976,
|
|
"loss": 6.3359,
|
|
"mean_token_accuracy": 0.1282445326447487,
|
|
"num_tokens": 27341957.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.498799562454224,
|
|
"epoch": 1.3526138370164267,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048262624271548936,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.1311979576945305,
|
|
"num_tokens": 27351506.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.543243360519409,
|
|
"epoch": 1.3531489111241908,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048261150766590257,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.1310368560254574,
|
|
"num_tokens": 27362208.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.580874872207642,
|
|
"epoch": 1.3536839852319547,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048259676662156263,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.13347921073436736,
|
|
"num_tokens": 27372890.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.492420673370361,
|
|
"epoch": 1.3542190593397185,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004825820195828952,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.14195676296949386,
|
|
"num_tokens": 27382879.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.432550573348999,
|
|
"epoch": 1.3547541334474824,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004825672665503262,
|
|
"loss": 6.2608,
|
|
"mean_token_accuracy": 0.13371035531163217,
|
|
"num_tokens": 27393878.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.532358169555664,
|
|
"epoch": 1.3552892075552463,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004825525075242815,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.12923340126872063,
|
|
"num_tokens": 27404928.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.567361783981323,
|
|
"epoch": 1.3558242816630104,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004825377425051873,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.13399578258395195,
|
|
"num_tokens": 27417473.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.553698968887329,
|
|
"epoch": 1.3563593557707743,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048252297149346997,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.12742808535695077,
|
|
"num_tokens": 27428378.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.461050653457642,
|
|
"epoch": 1.3568944298785381,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048250819448955595,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.13851417005062103,
|
|
"num_tokens": 27438815.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.620155000686646,
|
|
"epoch": 1.357429503986302,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000482493411493872,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.13085796013474466,
|
|
"num_tokens": 27449295.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.530794715881347,
|
|
"epoch": 1.357964578094066,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000482478622506845,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.13837912008166314,
|
|
"num_tokens": 27459357.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.514059400558471,
|
|
"epoch": 1.35849965220183,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004824638275289019,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.13738563656806946,
|
|
"num_tokens": 27469405.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.534468078613282,
|
|
"epoch": 1.3590347263095939,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004824490265604699,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.1373660996556282,
|
|
"num_tokens": 27478818.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.556286001205445,
|
|
"epoch": 1.3595698004173578,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004824342196019764,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.13968622982501983,
|
|
"num_tokens": 27488631.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.528377485275269,
|
|
"epoch": 1.3601048745251219,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048241940665384904,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.13143832832574845,
|
|
"num_tokens": 27500895.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.492169332504273,
|
|
"epoch": 1.3606399486328857,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004824045877165154,
|
|
"loss": 6.3509,
|
|
"mean_token_accuracy": 0.12758940383791922,
|
|
"num_tokens": 27512578.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.511027574539185,
|
|
"epoch": 1.3611750227406496,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048238976279040344,
|
|
"loss": 6.2984,
|
|
"mean_token_accuracy": 0.1308564618229866,
|
|
"num_tokens": 27523448.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.53885703086853,
|
|
"epoch": 1.3617100968484135,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004823749318759413,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.1290444739162922,
|
|
"num_tokens": 27534919.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.464112186431885,
|
|
"epoch": 1.3622451709561774,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000482360094973557,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.13654556199908258,
|
|
"num_tokens": 27545603.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.567755889892578,
|
|
"epoch": 1.3627802450639415,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004823452520836792,
|
|
"loss": 6.32,
|
|
"mean_token_accuracy": 0.13071177452802657,
|
|
"num_tokens": 27556868.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.62355055809021,
|
|
"epoch": 1.3633153191717053,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048233040320673634,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.12471303418278694,
|
|
"num_tokens": 27567200.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.48751277923584,
|
|
"epoch": 1.3638503932794692,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048231554834315716,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.13486199751496314,
|
|
"num_tokens": 27577759.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.522989892959595,
|
|
"epoch": 1.364385467387233,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004823006874933708,
|
|
"loss": 6.372,
|
|
"mean_token_accuracy": 0.12554556503891945,
|
|
"num_tokens": 27588935.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.5447916984558105,
|
|
"epoch": 1.364920541494997,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004822858206578061,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.12772670835256578,
|
|
"num_tokens": 27600306.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.590607786178589,
|
|
"epoch": 1.365455615602761,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048227094783689244,
|
|
"loss": 6.3372,
|
|
"mean_token_accuracy": 0.1335367240011692,
|
|
"num_tokens": 27612322.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.557591819763184,
|
|
"epoch": 1.365990689710525,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004822560690310594,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.1375129908323288,
|
|
"num_tokens": 27623812.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.446960735321045,
|
|
"epoch": 1.3665257638182888,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048224118424073644,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.13489142134785653,
|
|
"num_tokens": 27633848.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.483105087280274,
|
|
"epoch": 1.3670608379260527,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048222629346635336,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1376944363117218,
|
|
"num_tokens": 27644641.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.522060775756836,
|
|
"epoch": 1.3675959120338166,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048221139670834025,
|
|
"loss": 6.2826,
|
|
"mean_token_accuracy": 0.135152880102396,
|
|
"num_tokens": 27655552.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.499984788894653,
|
|
"epoch": 1.3681309861415807,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004821964939671272,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.14179115146398544,
|
|
"num_tokens": 27666396.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.579394149780273,
|
|
"epoch": 1.3686660602493446,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004821815852431444,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1391332305967808,
|
|
"num_tokens": 27676522.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.472452926635742,
|
|
"epoch": 1.3692011343571084,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048216667053682243,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.13712335973978043,
|
|
"num_tokens": 27687088.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.498577833175659,
|
|
"epoch": 1.3697362084648723,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048215174984859207,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.13670048490166664,
|
|
"num_tokens": 27697587.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.483075046539307,
|
|
"epoch": 1.3702712825726362,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000482136823178884,
|
|
"loss": 6.1907,
|
|
"mean_token_accuracy": 0.13942957371473313,
|
|
"num_tokens": 27708345.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.571651983261108,
|
|
"epoch": 1.3708063566804003,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004821218905281292,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.12706556767225266,
|
|
"num_tokens": 27719592.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.53343505859375,
|
|
"epoch": 1.3713414307881642,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000482106951896759,
|
|
"loss": 6.2827,
|
|
"mean_token_accuracy": 0.13870616182684897,
|
|
"num_tokens": 27730071.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.509290456771851,
|
|
"epoch": 1.371876504895928,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048209200728520466,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.13058488443493843,
|
|
"num_tokens": 27740514.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.605209112167358,
|
|
"epoch": 1.372411579003692,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048207705669389765,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.13331700637936592,
|
|
"num_tokens": 27752088.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.623941564559937,
|
|
"epoch": 1.3729466531114558,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048206210012326976,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.12817930206656455,
|
|
"num_tokens": 27763401.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.548435020446777,
|
|
"epoch": 1.37348172721922,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048204713757375283,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.13656549155712128,
|
|
"num_tokens": 27773665.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.5042959690094,
|
|
"epoch": 1.3740168013269838,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004820321690457789,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.1364237405359745,
|
|
"num_tokens": 27785474.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.532441282272339,
|
|
"epoch": 1.3745518754347477,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048201719453978023,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.13314425200223923,
|
|
"num_tokens": 27796520.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.591953563690185,
|
|
"epoch": 1.3750869495425118,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004820022140561891,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.12598699182271958,
|
|
"num_tokens": 27807559.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.571205520629883,
|
|
"epoch": 1.3756220236502756,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004819872275954381,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.1316391684114933,
|
|
"num_tokens": 27818208.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.507162141799927,
|
|
"epoch": 1.3761570977580395,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048197223515796,
|
|
"loss": 6.23,
|
|
"mean_token_accuracy": 0.13968217819929124,
|
|
"num_tokens": 27828238.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.523963165283203,
|
|
"epoch": 1.3766921718658034,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004819572367441877,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.14231058806180955,
|
|
"num_tokens": 27837885.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.457921075820923,
|
|
"epoch": 1.3772272459735673,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004819422323545543,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.14155658707022667,
|
|
"num_tokens": 27847425.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.413833951950073,
|
|
"epoch": 1.3777623200813314,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000481927221989493,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.13291521817445756,
|
|
"num_tokens": 27859606.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.5869935035705565,
|
|
"epoch": 1.3782973941890952,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004819122056494373,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.13277041912078857,
|
|
"num_tokens": 27871651.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.59212965965271,
|
|
"epoch": 1.3788324682968591,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048189718333482064,
|
|
"loss": 6.2782,
|
|
"mean_token_accuracy": 0.13503665924072267,
|
|
"num_tokens": 27883138.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.614982795715332,
|
|
"epoch": 1.379367542404623,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000481882155046077,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.13419492915272713,
|
|
"num_tokens": 27893597.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.516837644577026,
|
|
"epoch": 1.3799026165123869,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048186712078364006,
|
|
"loss": 6.2529,
|
|
"mean_token_accuracy": 0.13822920396924018,
|
|
"num_tokens": 27904249.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.477723407745361,
|
|
"epoch": 1.380437690620151,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048185208054794414,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.1323131412267685,
|
|
"num_tokens": 27914713.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.482716989517212,
|
|
"epoch": 1.3809727647279149,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004818370343394235,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.14247043877840043,
|
|
"num_tokens": 27926257.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.544012641906738,
|
|
"epoch": 1.3815078388356787,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004818219821585125,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.13584071174263954,
|
|
"num_tokens": 27936839.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.61454963684082,
|
|
"epoch": 1.3820429129434426,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048180692400564586,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.1286683276295662,
|
|
"num_tokens": 27946318.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.628933334350586,
|
|
"epoch": 1.3825779870512065,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048179185988125834,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.13161879852414132,
|
|
"num_tokens": 27956990.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.619915962219238,
|
|
"epoch": 1.3831130611589706,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000481776789785785,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.12722400948405266,
|
|
"num_tokens": 27968187.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.575854349136352,
|
|
"epoch": 1.3836481352667345,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048176171371966083,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.13226662948727608,
|
|
"num_tokens": 27978337.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.500992679595948,
|
|
"epoch": 1.3841832093744983,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004817466316833212,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.1280041068792343,
|
|
"num_tokens": 27988681.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.48139591217041,
|
|
"epoch": 1.3847182834822622,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004817315436772017,
|
|
"loss": 6.2111,
|
|
"mean_token_accuracy": 0.14233975857496262,
|
|
"num_tokens": 27999233.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.597472620010376,
|
|
"epoch": 1.385253357590026,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004817164497017379,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.13093181997537612,
|
|
"num_tokens": 28010242.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.530687379837036,
|
|
"epoch": 1.3857884316977902,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004817013497573656,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.13088319599628448,
|
|
"num_tokens": 28020424.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.562989664077759,
|
|
"epoch": 1.386323505805554,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000481686243844521,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.12782736048102378,
|
|
"num_tokens": 28030287.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.579535293579101,
|
|
"epoch": 1.386858579913318,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048167113196364,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.13902048543095588,
|
|
"num_tokens": 28039997.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.541631889343262,
|
|
"epoch": 1.387393654021082,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004816560141151593,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.12617392912507058,
|
|
"num_tokens": 28051381.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.521060180664063,
|
|
"epoch": 1.3879287281288457,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004816408902995151,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.13256800323724746,
|
|
"num_tokens": 28063603.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.4855201721191404,
|
|
"epoch": 1.3884638022366098,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004816257605171442,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.13902541249990463,
|
|
"num_tokens": 28073942.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.497772598266602,
|
|
"epoch": 1.3889988763443737,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048161062476848363,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.13788814544677735,
|
|
"num_tokens": 28083837.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.4824666500091555,
|
|
"epoch": 1.3895339504521376,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004815954830539702,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.13570400699973106,
|
|
"num_tokens": 28094150.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.518013954162598,
|
|
"epoch": 1.3900690245599017,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048158033537404126,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.1387584075331688,
|
|
"num_tokens": 28106345.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.5225001811981205,
|
|
"epoch": 1.3906040986676655,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048156518172913417,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.13286010921001434,
|
|
"num_tokens": 28116858.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.501324033737182,
|
|
"epoch": 1.3911391727754294,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004815500221196865,
|
|
"loss": 6.3845,
|
|
"mean_token_accuracy": 0.12992180436849593,
|
|
"num_tokens": 28128390.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.47907657623291,
|
|
"epoch": 1.3916742468831933,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048153485654613587,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.13855567947030067,
|
|
"num_tokens": 28139421.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.533262300491333,
|
|
"epoch": 1.3922093209909572,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048151968500892043,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.13610239028930665,
|
|
"num_tokens": 28151076.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.589778709411621,
|
|
"epoch": 1.3927443950987213,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048150450750847795,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.12930934131145477,
|
|
"num_tokens": 28162079.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.53804030418396,
|
|
"epoch": 1.3932794692064852,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000481489324045247,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.13030591681599618,
|
|
"num_tokens": 28174442.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.552037954330444,
|
|
"epoch": 1.393814543314249,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048147413461966564,
|
|
"loss": 6.2198,
|
|
"mean_token_accuracy": 0.1378868341445923,
|
|
"num_tokens": 28184643.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.455650091171265,
|
|
"epoch": 1.394349617422013,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048145893923217276,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.1368380829691887,
|
|
"num_tokens": 28194021.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.57091875076294,
|
|
"epoch": 1.3948846915297768,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004814437378832071,
|
|
"loss": 6.3144,
|
|
"mean_token_accuracy": 0.12892460078001022,
|
|
"num_tokens": 28204750.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.6161461353302,
|
|
"epoch": 1.3954197656375409,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004814285305732074,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.1290208302438259,
|
|
"num_tokens": 28216499.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.584888553619384,
|
|
"epoch": 1.3959548397453048,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048141331730261293,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.1345869742333889,
|
|
"num_tokens": 28226573.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.55465612411499,
|
|
"epoch": 1.3964899138530686,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000481398098071863,
|
|
"loss": 6.2448,
|
|
"mean_token_accuracy": 0.14011548906564714,
|
|
"num_tokens": 28236688.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.517119026184082,
|
|
"epoch": 1.3970249879608325,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048138287288139686,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.13438064157962798,
|
|
"num_tokens": 28247477.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.4921595573425295,
|
|
"epoch": 1.3975600620685964,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004813676417316543,
|
|
"loss": 6.3186,
|
|
"mean_token_accuracy": 0.13378834277391433,
|
|
"num_tokens": 28258286.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.6379228115081785,
|
|
"epoch": 1.3980951361763605,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004813524046230751,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.12076324447989464,
|
|
"num_tokens": 28268587.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.696167945861816,
|
|
"epoch": 1.3986302102841244,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048133716155609926,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.1276852436363697,
|
|
"num_tokens": 28279352.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.568699979782105,
|
|
"epoch": 1.3991652843918883,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004813219125311668,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.13418687954545022,
|
|
"num_tokens": 28290114.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.516354560852051,
|
|
"epoch": 1.3997003584996521,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048130665754871814,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.12834639623761177,
|
|
"num_tokens": 28301845.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.586096525192261,
|
|
"epoch": 1.400235432607416,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048129139660919374,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.1293413132429123,
|
|
"num_tokens": 28313162.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.549271535873413,
|
|
"epoch": 1.40077050671518,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048127612971303425,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.1319861926138401,
|
|
"num_tokens": 28323888.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.5844615459442135,
|
|
"epoch": 1.401305580822944,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004812608568606805,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.1313139483332634,
|
|
"num_tokens": 28333735.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.566430997848511,
|
|
"epoch": 1.4018406549307079,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004812455780525735,
|
|
"loss": 6.3089,
|
|
"mean_token_accuracy": 0.13157719522714614,
|
|
"num_tokens": 28343947.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.550437593460083,
|
|
"epoch": 1.402375729038472,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004812302932891544,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.1243227556347847,
|
|
"num_tokens": 28354635.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.563779306411743,
|
|
"epoch": 1.4029108031462356,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004812150025708646,
|
|
"loss": 6.2903,
|
|
"mean_token_accuracy": 0.13009085580706597,
|
|
"num_tokens": 28365392.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.57616081237793,
|
|
"epoch": 1.4034458772539997,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048119970589814557,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.12210134267807007,
|
|
"num_tokens": 28376527.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.541454315185547,
|
|
"epoch": 1.4039809513617636,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004811844032714389,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.13677758798003198,
|
|
"num_tokens": 28387178.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.539116430282593,
|
|
"epoch": 1.4045160254695275,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048116909469118663,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13399127945303918,
|
|
"num_tokens": 28397578.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.506171226501465,
|
|
"epoch": 1.4050510995772916,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004811537801578308,
|
|
"loss": 6.3397,
|
|
"mean_token_accuracy": 0.1259517602622509,
|
|
"num_tokens": 28408933.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.503382349014283,
|
|
"epoch": 1.4055861736850555,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048113845967181346,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.12405535578727722,
|
|
"num_tokens": 28421906.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.5776450634002686,
|
|
"epoch": 1.4061212477928193,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000481123133233577,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.1332197055220604,
|
|
"num_tokens": 28432677.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.573045492172241,
|
|
"epoch": 1.4066563219005832,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048110780084356414,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.13100109472870827,
|
|
"num_tokens": 28443795.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.55504298210144,
|
|
"epoch": 1.407191396008347,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004810924625022174,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.13072033673524858,
|
|
"num_tokens": 28455727.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.61231427192688,
|
|
"epoch": 1.4077264701161112,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004810771182099799,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.12492276728153229,
|
|
"num_tokens": 28467554.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.603960275650024,
|
|
"epoch": 1.408261544223875,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004810617679672945,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.13161554783582688,
|
|
"num_tokens": 28479268.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.55245041847229,
|
|
"epoch": 1.408796618331639,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.00048104641177460443,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.12731072753667833,
|
|
"num_tokens": 28489887.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.468415307998657,
|
|
"epoch": 1.4093316924394028,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004810310496323533,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.1380733884871006,
|
|
"num_tokens": 28500736.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.470671081542969,
|
|
"epoch": 1.4098667665471667,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048101568154098446,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.13929775431752206,
|
|
"num_tokens": 28511458.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.591119432449341,
|
|
"epoch": 1.4104018406549308,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048100030750094185,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.12569592297077178,
|
|
"num_tokens": 28522354.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.534553337097168,
|
|
"epoch": 1.4109369147626947,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004809849275126693,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.1420965887606144,
|
|
"num_tokens": 28533061.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.543464422225952,
|
|
"epoch": 1.4114719888704585,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048096954157661085,
|
|
"loss": 6.3327,
|
|
"mean_token_accuracy": 0.13191912025213243,
|
|
"num_tokens": 28544230.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.528650999069214,
|
|
"epoch": 1.4120070629782224,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048095414969321086,
|
|
"loss": 6.3278,
|
|
"mean_token_accuracy": 0.13371477872133256,
|
|
"num_tokens": 28555461.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.5493683338165285,
|
|
"epoch": 1.4125421370859863,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048093875186291376,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.13574814945459365,
|
|
"num_tokens": 28565992.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.565684080123901,
|
|
"epoch": 1.4130772111937504,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048092334808616413,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.1374378241598606,
|
|
"num_tokens": 28575802.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.535583209991455,
|
|
"epoch": 1.4136122853015143,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004809079383634067,
|
|
"loss": 6.2492,
|
|
"mean_token_accuracy": 0.1376635640859604,
|
|
"num_tokens": 28586982.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.541072654724121,
|
|
"epoch": 1.4141473594092782,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048089252269508656,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.13196105509996414,
|
|
"num_tokens": 28598267.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.574584054946899,
|
|
"epoch": 1.414682433517042,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048087710108164874,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.1319591633975506,
|
|
"num_tokens": 28608213.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.5331920146942135,
|
|
"epoch": 1.415217507624806,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004808616735235385,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.12543027997016906,
|
|
"num_tokens": 28619674.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.551663255691528,
|
|
"epoch": 1.41575258173257,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004808462400212014,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.1338550068438053,
|
|
"num_tokens": 28630824.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.50926718711853,
|
|
"epoch": 1.416287655840334,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048083080057508313,
|
|
"loss": 6.3517,
|
|
"mean_token_accuracy": 0.13014202639460565,
|
|
"num_tokens": 28642270.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.521674776077271,
|
|
"epoch": 1.4168227299480978,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048081535518562933,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.12918935641646384,
|
|
"num_tokens": 28653649.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.502331113815307,
|
|
"epoch": 1.4173578040558619,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000480799903853286,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.13268271312117577,
|
|
"num_tokens": 28664044.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.542404127120972,
|
|
"epoch": 1.4178928781636255,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004807844465784995,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.1345588520169258,
|
|
"num_tokens": 28675394.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.529404735565185,
|
|
"epoch": 1.4184279522713896,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048076898336171596,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.14060317277908324,
|
|
"num_tokens": 28686292.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.55095157623291,
|
|
"epoch": 1.4189630263791535,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048075351420338196,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.1346028797328472,
|
|
"num_tokens": 28696928.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.495355653762817,
|
|
"epoch": 1.4194981004869174,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004807380391039441,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.1321026124060154,
|
|
"num_tokens": 28707986.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.614403247833252,
|
|
"epoch": 1.4200331745946815,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048072255806384936,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.1340144731104374,
|
|
"num_tokens": 28719296.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.521930789947509,
|
|
"epoch": 1.4205682487024454,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004807070710835447,
|
|
"loss": 6.1843,
|
|
"mean_token_accuracy": 0.13900391533970832,
|
|
"num_tokens": 28729523.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.557798910140991,
|
|
"epoch": 1.4211033228102092,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004806915781634771,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.1333258867263794,
|
|
"num_tokens": 28739026.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.586025190353394,
|
|
"epoch": 1.4216383969179731,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004806760793040942,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.12926854342222213,
|
|
"num_tokens": 28749513.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.60874834060669,
|
|
"epoch": 1.422173471025737,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048066057450584334,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.1329214371740818,
|
|
"num_tokens": 28760722.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.559692621231079,
|
|
"epoch": 1.422708545133501,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004806450637691723,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.14297338128089904,
|
|
"num_tokens": 28771235.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.531833028793335,
|
|
"epoch": 1.423243619241265,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048062954709452907,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.13588109463453293,
|
|
"num_tokens": 28782642.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.541342067718506,
|
|
"epoch": 1.4237786933490288,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004806140244823615,
|
|
"loss": 6.2651,
|
|
"mean_token_accuracy": 0.13098229318857194,
|
|
"num_tokens": 28793628.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.587154912948608,
|
|
"epoch": 1.4243137674567927,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048059849593311776,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.13464922532439233,
|
|
"num_tokens": 28804034.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.551678323745728,
|
|
"epoch": 1.4248488415645566,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004805829614472464,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.13238443210721015,
|
|
"num_tokens": 28814679.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.510989809036255,
|
|
"epoch": 1.4253839156723207,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048056742102519593,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.12994106039404868,
|
|
"num_tokens": 28825130.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.543405151367187,
|
|
"epoch": 1.4259189897800846,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048055187466741506,
|
|
"loss": 6.3261,
|
|
"mean_token_accuracy": 0.12828193083405495,
|
|
"num_tokens": 28835500.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.533200263977051,
|
|
"epoch": 1.4264540638878485,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004805363223743527,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.13435445576906205,
|
|
"num_tokens": 28845794.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.59534273147583,
|
|
"epoch": 1.4269891379956123,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004805207641464579,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.13006314858794213,
|
|
"num_tokens": 28856326.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.506957912445069,
|
|
"epoch": 1.4275242121033762,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004805051999841799,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.13344307169318198,
|
|
"num_tokens": 28867592.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.606613874435425,
|
|
"epoch": 1.4280592862111403,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004804896298879682,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.12649569064378738,
|
|
"num_tokens": 28880352.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.59653148651123,
|
|
"epoch": 1.4285943603189042,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004804740538582723,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.1322682738304138,
|
|
"num_tokens": 28892012.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.579413747787475,
|
|
"epoch": 1.429129434426668,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004804584718955419,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.13726244121789932,
|
|
"num_tokens": 28902247.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.508374929428101,
|
|
"epoch": 1.429664508534432,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000480442884000227,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.13232571333646775,
|
|
"num_tokens": 28913222.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.51956524848938,
|
|
"epoch": 1.4301995826421958,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004804272901727778,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.1339123398065567,
|
|
"num_tokens": 28924038.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.582114124298096,
|
|
"epoch": 1.43073465674996,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048041169041364437,
|
|
"loss": 6.3048,
|
|
"mean_token_accuracy": 0.13865149021148682,
|
|
"num_tokens": 28934448.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.542791557312012,
|
|
"epoch": 1.4312697308577238,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048039608472327724,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.13437252789735793,
|
|
"num_tokens": 28945175.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.499612092971802,
|
|
"epoch": 1.4318048049654877,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048038047310212706,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.13937258571386338,
|
|
"num_tokens": 28955116.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.548843431472778,
|
|
"epoch": 1.4323398790732518,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048036485555064454,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.13031953051686287,
|
|
"num_tokens": 28966999.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.54577784538269,
|
|
"epoch": 1.4328749531810157,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048034923206928065,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.12904799953103066,
|
|
"num_tokens": 28977388.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.539524078369141,
|
|
"epoch": 1.4334100272887795,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048033360265848664,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.13839732706546784,
|
|
"num_tokens": 28987792.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.613337612152099,
|
|
"epoch": 1.4339451013965434,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048031796731871364,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.13307096138596536,
|
|
"num_tokens": 28998319.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.5337625503540036,
|
|
"epoch": 1.4344801755043073,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048030232605041323,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.13027154058218002,
|
|
"num_tokens": 29007942.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.594687223434448,
|
|
"epoch": 1.4350152496120714,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004802866788540369,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.13362317085266112,
|
|
"num_tokens": 29018217.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.587049055099487,
|
|
"epoch": 1.4355503237198353,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004802710257300367,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.131132273375988,
|
|
"num_tokens": 29028472.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.5456602573394775,
|
|
"epoch": 1.4360853978275991,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004802553666788644,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.13706605061888694,
|
|
"num_tokens": 29040553.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.571896696090699,
|
|
"epoch": 1.436620471935363,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048023970170097226,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.13039797320961952,
|
|
"num_tokens": 29050142.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.510137319564819,
|
|
"epoch": 1.437155546043127,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048022403079681254,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.12999855652451514,
|
|
"num_tokens": 29061762.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.549421262741089,
|
|
"epoch": 1.437690620150891,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048020835396683775,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.1308118633925915,
|
|
"num_tokens": 29072095.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.60357551574707,
|
|
"epoch": 1.4382256942586549,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048019267121150066,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.13163482919335365,
|
|
"num_tokens": 29082561.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.5486468315124515,
|
|
"epoch": 1.4387607683664188,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048017698253125397,
|
|
"loss": 6.2671,
|
|
"mean_token_accuracy": 0.13364253789186478,
|
|
"num_tokens": 29093813.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.52044939994812,
|
|
"epoch": 1.4392958424741826,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004801612879265507,
|
|
"loss": 6.2736,
|
|
"mean_token_accuracy": 0.1357661746442318,
|
|
"num_tokens": 29104064.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.494532108306885,
|
|
"epoch": 1.4398309165819465,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004801455873978442,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.12913288176059723,
|
|
"num_tokens": 29115086.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.536068773269653,
|
|
"epoch": 1.4403659906897106,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004801298809455876,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.14133179932832718,
|
|
"num_tokens": 29125536.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.583189058303833,
|
|
"epoch": 1.4409010647974745,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004801141685702345,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.13120611384510994,
|
|
"num_tokens": 29137007.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.567616033554077,
|
|
"epoch": 1.4414361389052384,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048009845027223864,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.12379435449838638,
|
|
"num_tokens": 29147072.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.576822185516358,
|
|
"epoch": 1.4419712130130022,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048008272605205377,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.13404594883322715,
|
|
"num_tokens": 29157803.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.559188413619995,
|
|
"epoch": 1.4425062871207661,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048006699591013417,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.13357484936714173,
|
|
"num_tokens": 29168173.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.614182090759277,
|
|
"epoch": 1.4430413612285302,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004800512598469337,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.1211496539413929,
|
|
"num_tokens": 29179377.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.5842859745025635,
|
|
"epoch": 1.443576435336294,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000480035517862907,
|
|
"loss": 6.3174,
|
|
"mean_token_accuracy": 0.13456696942448615,
|
|
"num_tokens": 29190909.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.492300939559937,
|
|
"epoch": 1.444111509444058,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048001976995850856,
|
|
"loss": 6.2312,
|
|
"mean_token_accuracy": 0.13400312289595603,
|
|
"num_tokens": 29200977.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.5454717636108395,
|
|
"epoch": 1.4446465835518219,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048000401613419296,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.12763061225414277,
|
|
"num_tokens": 29210702.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.604302883148193,
|
|
"epoch": 1.4451816576595857,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047998825639041534,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.12395200505852699,
|
|
"num_tokens": 29221338.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.613165950775146,
|
|
"epoch": 1.4457167317673498,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004799724907276306,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.1429674044251442,
|
|
"num_tokens": 29232091.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.482897043228149,
|
|
"epoch": 1.4462518058751137,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004799567191462939,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.13581477701663972,
|
|
"num_tokens": 29241903.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.5058026790618895,
|
|
"epoch": 1.4467868799828776,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047994094164686074,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.13214331939816476,
|
|
"num_tokens": 29253414.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.605631923675537,
|
|
"epoch": 1.4473219540906417,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004799251582297868,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.14136453941464425,
|
|
"num_tokens": 29264066.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.567365121841431,
|
|
"epoch": 1.4478570281984056,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047990936889552767,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.13597942665219306,
|
|
"num_tokens": 29274915.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.507847166061401,
|
|
"epoch": 1.4483921023061694,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004798935736445392,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.12975036427378656,
|
|
"num_tokens": 29287345.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.491131067276001,
|
|
"epoch": 1.4489271764139333,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004798777724772777,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.14119713753461838,
|
|
"num_tokens": 29297432.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.509729433059692,
|
|
"epoch": 1.4494622505216972,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047986196539419936,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.14158949628472328,
|
|
"num_tokens": 29307534.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.549173402786255,
|
|
"epoch": 1.4499973246294613,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004798461523957604,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.1374451108276844,
|
|
"num_tokens": 29319412.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.498152875900269,
|
|
"epoch": 1.4505323987372252,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047983033348241767,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.14251604452729225,
|
|
"num_tokens": 29330477.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.484377861022949,
|
|
"epoch": 1.451067472844989,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004798145086546278,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.13428061753511428,
|
|
"num_tokens": 29341481.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.485887670516968,
|
|
"epoch": 1.451602546952753,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004797986779128478,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.13639950677752494,
|
|
"num_tokens": 29353273.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.57791223526001,
|
|
"epoch": 1.4521376210605168,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004797828412575348,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.1361882768571377,
|
|
"num_tokens": 29364108.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.495282173156738,
|
|
"epoch": 1.452672695168281,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047976699868914594,
|
|
"loss": 6.2636,
|
|
"mean_token_accuracy": 0.13775565326213837,
|
|
"num_tokens": 29375272.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.505160570144653,
|
|
"epoch": 1.4532077692760448,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004797511502081388,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.1332462415099144,
|
|
"num_tokens": 29385749.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.517300844192505,
|
|
"epoch": 1.4537428433838087,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000479735295814971,
|
|
"loss": 6.2187,
|
|
"mean_token_accuracy": 0.13782110810279846,
|
|
"num_tokens": 29396430.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.536860084533691,
|
|
"epoch": 1.4542779174915725,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047971943551010035,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.1307387612760067,
|
|
"num_tokens": 29407020.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.546886920928955,
|
|
"epoch": 1.4548129915993364,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047970356929398467,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13745293468236924,
|
|
"num_tokens": 29418428.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.565701627731324,
|
|
"epoch": 1.4553480657071005,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004796876971670822,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.13378758504986762,
|
|
"num_tokens": 29430611.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.5439074516296385,
|
|
"epoch": 1.4558831398148644,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004796718191298512,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.1257310539484024,
|
|
"num_tokens": 29441545.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.5851068019866945,
|
|
"epoch": 1.4564182139226283,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004796559351827503,
|
|
"loss": 6.3695,
|
|
"mean_token_accuracy": 0.12765171527862548,
|
|
"num_tokens": 29452529.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.539608526229858,
|
|
"epoch": 1.4569532880303921,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000479640045326238,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.1369820587337017,
|
|
"num_tokens": 29463860.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.653084325790405,
|
|
"epoch": 1.457488362138156,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004796241495607731,
|
|
"loss": 6.3325,
|
|
"mean_token_accuracy": 0.1349804438650608,
|
|
"num_tokens": 29475004.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.55041766166687,
|
|
"epoch": 1.4580234362459201,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004796082478868146,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.12528412342071532,
|
|
"num_tokens": 29485921.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.542591524124146,
|
|
"epoch": 1.458558510353684,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047959234030482185,
|
|
"loss": 6.2517,
|
|
"mean_token_accuracy": 0.14472676813602448,
|
|
"num_tokens": 29495729.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.577525520324707,
|
|
"epoch": 1.4590935844614479,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004795764268152538,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.12774155661463737,
|
|
"num_tokens": 29506051.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.524970769882202,
|
|
"epoch": 1.4596286585692118,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004795605074185704,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.13325700610876084,
|
|
"num_tokens": 29516234.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.549506521224975,
|
|
"epoch": 1.4601637326769756,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047954458211523095,
|
|
"loss": 6.2701,
|
|
"mean_token_accuracy": 0.1349295660853386,
|
|
"num_tokens": 29527649.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.586029481887818,
|
|
"epoch": 1.4606988067847397,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047952865090569545,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.12580158188939095,
|
|
"num_tokens": 29539150.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.520464706420898,
|
|
"epoch": 1.4612338808925036,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047951271379042393,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.13591403812170028,
|
|
"num_tokens": 29550058.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.423491668701172,
|
|
"epoch": 1.4617689550002675,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004794967707698765,
|
|
"loss": 6.2296,
|
|
"mean_token_accuracy": 0.1430532529950142,
|
|
"num_tokens": 29560377.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.435001087188721,
|
|
"epoch": 1.4623040291080316,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004794808218445136,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.14599157869815826,
|
|
"num_tokens": 29571378.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.5370715141296385,
|
|
"epoch": 1.4628391032157955,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047946486701479576,
|
|
"loss": 6.3144,
|
|
"mean_token_accuracy": 0.13308701068162918,
|
|
"num_tokens": 29582187.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.541687440872193,
|
|
"epoch": 1.4633741773235593,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004794489062811835,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.12842457219958306,
|
|
"num_tokens": 29592982.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.587422132492065,
|
|
"epoch": 1.4639092514313232,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004794329396441378,
|
|
"loss": 6.2746,
|
|
"mean_token_accuracy": 0.13194804191589354,
|
|
"num_tokens": 29603639.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.5431897163391115,
|
|
"epoch": 1.464444325539087,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047941696710411975,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.14435758888721467,
|
|
"num_tokens": 29615103.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.532386589050293,
|
|
"epoch": 1.4649793996468512,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004794009886615904,
|
|
"loss": 6.2905,
|
|
"mean_token_accuracy": 0.13263922408223153,
|
|
"num_tokens": 29626184.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.555911445617676,
|
|
"epoch": 1.465514473754615,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047938500431701135,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.14328787550330163,
|
|
"num_tokens": 29637615.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.551273775100708,
|
|
"epoch": 1.466049547862379,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000479369014070844,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.13311365023255348,
|
|
"num_tokens": 29648648.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.516896438598633,
|
|
"epoch": 1.4665846219701428,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047935301792355003,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.13810425996780396,
|
|
"num_tokens": 29660542.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.551743841171264,
|
|
"epoch": 1.4671196960779067,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004793370158755914,
|
|
"loss": 6.3163,
|
|
"mean_token_accuracy": 0.13373398035764694,
|
|
"num_tokens": 29670342.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.513361167907715,
|
|
"epoch": 1.4676547701856708,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047932100792743014,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.13930255994200708,
|
|
"num_tokens": 29681191.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.534385299682617,
|
|
"epoch": 1.4681898442934347,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047930499407952855,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.14330771416425706,
|
|
"num_tokens": 29691299.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.518677663803101,
|
|
"epoch": 1.4687249184011986,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047928897433234893,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.1339192159473896,
|
|
"num_tokens": 29702125.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.5021195888519285,
|
|
"epoch": 1.4692599925089624,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004792729486863539,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.1327348917722702,
|
|
"num_tokens": 29712679.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.5093645572662355,
|
|
"epoch": 1.4697950666167263,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004792569171420061,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.13891081213951112,
|
|
"num_tokens": 29723833.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.586244106292725,
|
|
"epoch": 1.4703301407244904,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004792408796997687,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.13556601256132125,
|
|
"num_tokens": 29734646.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.5740937232971195,
|
|
"epoch": 1.4708652148322543,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004792248363601044,
|
|
"loss": 6.2924,
|
|
"mean_token_accuracy": 0.1350928321480751,
|
|
"num_tokens": 29745129.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.5654994487762455,
|
|
"epoch": 1.4714002889400182,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004792087871234767,
|
|
"loss": 6.2918,
|
|
"mean_token_accuracy": 0.12818465679883956,
|
|
"num_tokens": 29756308.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.4984032154083256,
|
|
"epoch": 1.471935363047782,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000479192731990349,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.13055193796753883,
|
|
"num_tokens": 29767835.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.546389532089234,
|
|
"epoch": 1.472470437155546,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004791766709611849,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.13507338240742683,
|
|
"num_tokens": 29778776.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.670673084259033,
|
|
"epoch": 1.47300551126331,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000479160604036448,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.12552779018878937,
|
|
"num_tokens": 29788800.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.547731256484985,
|
|
"epoch": 1.473540585371074,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004791445312166025,
|
|
"loss": 6.2572,
|
|
"mean_token_accuracy": 0.14021070525050164,
|
|
"num_tokens": 29799375.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.555331897735596,
|
|
"epoch": 1.4740756594788378,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004791284525021122,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.124832434207201,
|
|
"num_tokens": 29811267.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.5536736965179445,
|
|
"epoch": 1.4746107335866017,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004791123678934416,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.13412302434444429,
|
|
"num_tokens": 29821616.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.535737466812134,
|
|
"epoch": 1.4751458076943655,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004790962773910551,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.13453632444143296,
|
|
"num_tokens": 29832233.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.596752595901489,
|
|
"epoch": 1.4756808818021296,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047908018099541717,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13443198055028915,
|
|
"num_tokens": 29843465.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.515512847900391,
|
|
"epoch": 1.4762159559098935,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004790640787069927,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.1415461152791977,
|
|
"num_tokens": 29854123.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.578099298477173,
|
|
"epoch": 1.4767510300176574,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004790479705262467,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.12471452876925468,
|
|
"num_tokens": 29864831.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.5273661613464355,
|
|
"epoch": 1.4772861041254215,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004790318564536441,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.1310821369290352,
|
|
"num_tokens": 29876273.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.530851984024048,
|
|
"epoch": 1.4778211782331854,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047901573648965047,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.1352597825229168,
|
|
"num_tokens": 29886560.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.513718509674073,
|
|
"epoch": 1.4783562523409493,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000478999610634731,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.13684219866991043,
|
|
"num_tokens": 29896916.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.504454469680786,
|
|
"epoch": 1.4788913264487131,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004789834788893515,
|
|
"loss": 6.3091,
|
|
"mean_token_accuracy": 0.1282836228609085,
|
|
"num_tokens": 29907288.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.495414209365845,
|
|
"epoch": 1.479426400556477,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004789673412539777,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13465062901377678,
|
|
"num_tokens": 29918194.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.546362638473511,
|
|
"epoch": 1.479961474664241,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047895119772907566,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.13627072498202325,
|
|
"num_tokens": 29928521.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.507249212265014,
|
|
"epoch": 1.480496548772005,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004789350483151113,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.1304092951118946,
|
|
"num_tokens": 29938885.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.5725428581237795,
|
|
"epoch": 1.4810316228797689,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004789188930125512,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.14193991646170617,
|
|
"num_tokens": 29948921.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.509477281570435,
|
|
"epoch": 1.4815666969875327,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004789027318218616,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.1386758007109165,
|
|
"num_tokens": 29959633.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.521372222900391,
|
|
"epoch": 1.4821017710952966,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004788865647435093,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.12845197916030884,
|
|
"num_tokens": 29970639.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.569345569610595,
|
|
"epoch": 1.4826368452030607,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004788703917779612,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.13183851465582846,
|
|
"num_tokens": 29981752.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.550051879882813,
|
|
"epoch": 1.4831719193108246,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004788542129256841,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.13968370780348777,
|
|
"num_tokens": 29991037.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.495801591873169,
|
|
"epoch": 1.4837069934185885,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047883802818714526,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.12434751689434051,
|
|
"num_tokens": 30001980.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.548546266555786,
|
|
"epoch": 1.4842420675263523,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000478821837562812,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.1336070977151394,
|
|
"num_tokens": 30013377.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.556598281860351,
|
|
"epoch": 1.4847771416341162,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004788056410531518,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.1366582117974758,
|
|
"num_tokens": 30023909.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.483535861968994,
|
|
"epoch": 1.4853122157418803,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004787894386586324,
|
|
"loss": 6.2288,
|
|
"mean_token_accuracy": 0.13616093918681144,
|
|
"num_tokens": 30034069.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.478453683853149,
|
|
"epoch": 1.4858472898496442,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047877323037972153,
|
|
"loss": 6.2289,
|
|
"mean_token_accuracy": 0.14070839509367944,
|
|
"num_tokens": 30043940.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.490971994400025,
|
|
"epoch": 1.486382363957408,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004787570162168874,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.13903133794665337,
|
|
"num_tokens": 30054985.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.538230991363525,
|
|
"epoch": 1.486917438065172,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047874079617059783,
|
|
"loss": 6.2364,
|
|
"mean_token_accuracy": 0.13630077689886094,
|
|
"num_tokens": 30065675.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.529196262359619,
|
|
"epoch": 1.4874525121729358,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004787245702413216,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.13694037944078447,
|
|
"num_tokens": 30075305.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.554997396469116,
|
|
"epoch": 1.4879875862807,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047870833842952697,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.1343739703297615,
|
|
"num_tokens": 30087309.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.530051851272583,
|
|
"epoch": 1.4885226603884638,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004786921007356827,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.13209329545497894,
|
|
"num_tokens": 30097262.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.552338790893555,
|
|
"epoch": 1.4890577344962277,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047867585716025767,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.13659584522247314,
|
|
"num_tokens": 30107067.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.586587572097779,
|
|
"epoch": 1.4895928086039918,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004786596077037209,
|
|
"loss": 6.3192,
|
|
"mean_token_accuracy": 0.13181559294462203,
|
|
"num_tokens": 30117115.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.603874158859253,
|
|
"epoch": 1.4901278827117554,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047864335236654144,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.13400094211101532,
|
|
"num_tokens": 30127202.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.465754890441895,
|
|
"epoch": 1.4906629568195195,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004786270911491889,
|
|
"loss": 6.2487,
|
|
"mean_token_accuracy": 0.1353141985833645,
|
|
"num_tokens": 30138608.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.546110582351685,
|
|
"epoch": 1.4911980309272834,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004786108240521327,
|
|
"loss": 6.3064,
|
|
"mean_token_accuracy": 0.137214232981205,
|
|
"num_tokens": 30148500.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.447632646560669,
|
|
"epoch": 1.4917331050350473,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047859455107584256,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.13803261518478394,
|
|
"num_tokens": 30159062.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.514106750488281,
|
|
"epoch": 1.4922681791428114,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047857827222078835,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.1323826126754284,
|
|
"num_tokens": 30170468.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.460741758346558,
|
|
"epoch": 1.4928032532505753,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004785619874874402,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.14026360735297203,
|
|
"num_tokens": 30180944.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.476769304275512,
|
|
"epoch": 1.4933383273583392,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004785456968762682,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.14123549163341523,
|
|
"num_tokens": 30191614.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.498686170578003,
|
|
"epoch": 1.493873401466103,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047852940038774276,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.13988643661141395,
|
|
"num_tokens": 30202035.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.434373903274536,
|
|
"epoch": 1.494408475573867,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047851309802233457,
|
|
"loss": 6.2865,
|
|
"mean_token_accuracy": 0.13843541741371154,
|
|
"num_tokens": 30213205.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.578490686416626,
|
|
"epoch": 1.494943549681631,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004784967897805143,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.13502900078892707,
|
|
"num_tokens": 30223971.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.575396299362183,
|
|
"epoch": 1.495478623789395,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004784804756627528,
|
|
"loss": 6.2904,
|
|
"mean_token_accuracy": 0.1325635604560375,
|
|
"num_tokens": 30235346.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.551068210601807,
|
|
"epoch": 1.4960136978971588,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047846415566952106,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.13519833534955977,
|
|
"num_tokens": 30246033.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.463932752609253,
|
|
"epoch": 1.4965487720049226,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047844782980129057,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.13278683871030808,
|
|
"num_tokens": 30258208.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.499045562744141,
|
|
"epoch": 1.4970838461126865,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047843149805853254,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.13239005208015442,
|
|
"num_tokens": 30268824.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.578220367431641,
|
|
"epoch": 1.4976189202204506,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004784151604417185,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.12390814051032066,
|
|
"num_tokens": 30280078.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.530854082107544,
|
|
"epoch": 1.4981539943282145,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047839881695132034,
|
|
"loss": 6.2298,
|
|
"mean_token_accuracy": 0.142520771920681,
|
|
"num_tokens": 30290939.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.495736074447632,
|
|
"epoch": 1.4986890684359784,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047838246758780996,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.13784620389342309,
|
|
"num_tokens": 30301198.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.5063807487487795,
|
|
"epoch": 1.4992241425437423,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004783661123516593,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.13562998846173285,
|
|
"num_tokens": 30312021.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.539398670196533,
|
|
"epoch": 1.4997592166515061,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004783497512433408,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13483910784125328,
|
|
"num_tokens": 30323335.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.546143436431885,
|
|
"epoch": 1.5002942907592702,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004783333842633268,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.14089713245630264,
|
|
"num_tokens": 30334389.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.457803583145141,
|
|
"epoch": 1.500829364867034,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047831701141208994,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.13121172934770584,
|
|
"num_tokens": 30345407.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.502495861053466,
|
|
"epoch": 1.501364438974798,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047830063269010286,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.1314643941819668,
|
|
"num_tokens": 30356718.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.511676168441772,
|
|
"epoch": 1.501899513082562,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047828424809783865,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.13534914702177048,
|
|
"num_tokens": 30367617.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.525033664703369,
|
|
"epoch": 1.5024345871903257,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004782678576357703,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.1353394605219364,
|
|
"num_tokens": 30377923.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.498504686355591,
|
|
"epoch": 1.5029696612980898,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004782514613043711,
|
|
"loss": 6.2498,
|
|
"mean_token_accuracy": 0.13915505409240722,
|
|
"num_tokens": 30388719.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.5068888664245605,
|
|
"epoch": 1.5035047354058537,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047823505910411465,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.1380567654967308,
|
|
"num_tokens": 30400191.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.531849670410156,
|
|
"epoch": 1.5040398095136176,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047821865103547437,
|
|
"loss": 6.2835,
|
|
"mean_token_accuracy": 0.1362235277891159,
|
|
"num_tokens": 30410267.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.547566223144531,
|
|
"epoch": 1.5045748836213817,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000478202237098924,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.131100395321846,
|
|
"num_tokens": 30420852.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.565202426910401,
|
|
"epoch": 1.5051099577291454,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004781858172949376,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.1344304248690605,
|
|
"num_tokens": 30432214.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.567050838470459,
|
|
"epoch": 1.5056450318369095,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004781693916239894,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12420830205082893,
|
|
"num_tokens": 30443919.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.571396207809448,
|
|
"epoch": 1.5061801059446733,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00047815296008655347,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.1250197820365429,
|
|
"num_tokens": 30453930.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.539173603057861,
|
|
"epoch": 1.5067151800524372,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00047813652268310436,
|
|
"loss": 6.2897,
|
|
"mean_token_accuracy": 0.12643647491931914,
|
|
"num_tokens": 30464612.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.526119232177734,
|
|
"epoch": 1.5072502541602013,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047812007941411673,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.13565285205841066,
|
|
"num_tokens": 30474819.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.497172927856445,
|
|
"epoch": 1.507785328267965,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047810363028006535,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.14370110183954238,
|
|
"num_tokens": 30485481.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.500015735626221,
|
|
"epoch": 1.508320402375729,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004780871752814252,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.1386760003864765,
|
|
"num_tokens": 30496321.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.493804264068603,
|
|
"epoch": 1.508855476483493,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004780707144186714,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.13237425908446313,
|
|
"num_tokens": 30507578.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.619511842727661,
|
|
"epoch": 1.5093905505912568,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047805424769227923,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.13486289009451866,
|
|
"num_tokens": 30518328.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.507578802108765,
|
|
"epoch": 1.509925624699021,
|
|
"grad_norm": 7.46875,
|
|
"learning_rate": 0.00047803777510272425,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.1352337084710598,
|
|
"num_tokens": 30528555.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.45980315208435,
|
|
"epoch": 1.5104606988067846,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000478021296650482,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.13908951058983804,
|
|
"num_tokens": 30540217.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.581186199188233,
|
|
"epoch": 1.5109957729145487,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004780048123360283,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.13534327372908592,
|
|
"num_tokens": 30550937.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.610339212417602,
|
|
"epoch": 1.5115308470223126,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047798832215983916,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.13681161478161813,
|
|
"num_tokens": 30562248.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.576951932907105,
|
|
"epoch": 1.5120659211300764,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004779718261223908,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.13611859753727912,
|
|
"num_tokens": 30573362.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.5235360622406,
|
|
"epoch": 1.5126009952378405,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047795532422415947,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.13528222739696502,
|
|
"num_tokens": 30584052.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.521787309646607,
|
|
"epoch": 1.5131360693456044,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004779388164656217,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.12935080379247665,
|
|
"num_tokens": 30594630.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.546995544433594,
|
|
"epoch": 1.5136711434533683,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047792230284725415,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.13568148985505105,
|
|
"num_tokens": 30605625.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.531518650054932,
|
|
"epoch": 1.5142062175611322,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047790578336953356,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.13517610654234885,
|
|
"num_tokens": 30616520.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.540752983093261,
|
|
"epoch": 1.514741291668896,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000477889258032937,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.14312789514660834,
|
|
"num_tokens": 30627372.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.500818586349487,
|
|
"epoch": 1.5152763657766601,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047787272683794157,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.14515245854854583,
|
|
"num_tokens": 30636974.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.509118890762329,
|
|
"epoch": 1.515811439884424,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004778561897850247,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.13736924827098845,
|
|
"num_tokens": 30648202.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.517179250717163,
|
|
"epoch": 1.516346513992188,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047783964687466384,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.1314311482012272,
|
|
"num_tokens": 30657981.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.537102222442627,
|
|
"epoch": 1.516881588099952,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047782309810733676,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.12622129172086716,
|
|
"num_tokens": 30668496.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.487250185012817,
|
|
"epoch": 1.5174166622077156,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.00047780654348352115,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.1400587297976017,
|
|
"num_tokens": 30678868.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.53211088180542,
|
|
"epoch": 1.5179517363154797,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047778998300369516,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.1377688691020012,
|
|
"num_tokens": 30690066.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.4703638553619385,
|
|
"epoch": 1.5184868104232436,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004777734166683368,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.14053755551576613,
|
|
"num_tokens": 30700624.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.486501932144165,
|
|
"epoch": 1.5190218845310075,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047775684447792457,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.13751474767923355,
|
|
"num_tokens": 30711183.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.509814453125,
|
|
"epoch": 1.5195569586387716,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000477740266432937,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.14190192744135857,
|
|
"num_tokens": 30721446.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.549847173690796,
|
|
"epoch": 1.5200920327465353,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00047772368253385267,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.12940879687666892,
|
|
"num_tokens": 30731901.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.535141515731811,
|
|
"epoch": 1.5206271068542994,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004777070927811505,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.13085372596979142,
|
|
"num_tokens": 30741701.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.526335382461548,
|
|
"epoch": 1.5211621809620632,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047769049717530956,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.13423371836543083,
|
|
"num_tokens": 30751594.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.504735708236694,
|
|
"epoch": 1.5216972550698271,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047767389571680896,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.126288815587759,
|
|
"num_tokens": 30764418.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.558633089065552,
|
|
"epoch": 1.5222323291775912,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004776572884061281,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.13761670440435408,
|
|
"num_tokens": 30773976.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.582456445693969,
|
|
"epoch": 1.5227674032853549,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004776406752437465,
|
|
"loss": 6.294,
|
|
"mean_token_accuracy": 0.13682678043842317,
|
|
"num_tokens": 30784210.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.518918085098266,
|
|
"epoch": 1.523302477393119,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004776240562301438,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.12842216491699218,
|
|
"num_tokens": 30794322.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.564871597290039,
|
|
"epoch": 1.5238375515008828,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004776074313658001,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.14118874147534372,
|
|
"num_tokens": 30805264.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.4882111072540285,
|
|
"epoch": 1.5243726256086467,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004775908006511952,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.1359029680490494,
|
|
"num_tokens": 30815909.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.599324750900268,
|
|
"epoch": 1.5249076997164108,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004775741640868095,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.13517858684062958,
|
|
"num_tokens": 30826867.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.58244743347168,
|
|
"epoch": 1.5254427738241747,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047755752167312314,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.13037005066871643,
|
|
"num_tokens": 30837696.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.473442888259887,
|
|
"epoch": 1.5259778479319386,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004775408734106169,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.13493726029992104,
|
|
"num_tokens": 30848155.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.436830806732178,
|
|
"epoch": 1.5265129220397025,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047752421929977143,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.14483771175146104,
|
|
"num_tokens": 30857804.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.536058521270752,
|
|
"epoch": 1.5270479961474663,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004775075593410675,
|
|
"loss": 6.2746,
|
|
"mean_token_accuracy": 0.13746241480112076,
|
|
"num_tokens": 30867290.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.5432713508605955,
|
|
"epoch": 1.5275830702552304,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047749089353498625,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.13378921225667,
|
|
"num_tokens": 30877634.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.527502536773682,
|
|
"epoch": 1.5281181443629943,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000477474221882009,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13290925249457358,
|
|
"num_tokens": 30889176.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.57243766784668,
|
|
"epoch": 1.5286532184707582,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004774575443826169,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.13979230374097823,
|
|
"num_tokens": 30899516.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.54964919090271,
|
|
"epoch": 1.5291882925785223,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004774408610372918,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.13416342735290526,
|
|
"num_tokens": 30910155.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.551747894287109,
|
|
"epoch": 1.529723366686286,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004774241718465152,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.1300183728337288,
|
|
"num_tokens": 30921486.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.567112255096435,
|
|
"epoch": 1.53025844079405,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004774074768107691,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.13543465435504914,
|
|
"num_tokens": 30932361.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.5201342582702635,
|
|
"epoch": 1.530793514901814,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047739077593053554,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.13535121381282805,
|
|
"num_tokens": 30943033.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.5211255073547365,
|
|
"epoch": 1.5313285890095778,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047737406920629675,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.13891438469290734,
|
|
"num_tokens": 30953094.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.535080623626709,
|
|
"epoch": 1.531863663117342,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047735735663853514,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.13467931300401687,
|
|
"num_tokens": 30964604.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.569497537612915,
|
|
"epoch": 1.5323987372251056,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004773406382277334,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.13067164942622184,
|
|
"num_tokens": 30975681.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.575937509536743,
|
|
"epoch": 1.5329338113328697,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004773239139743741,
|
|
"loss": 6.2984,
|
|
"mean_token_accuracy": 0.12989215925335884,
|
|
"num_tokens": 30986319.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.52880539894104,
|
|
"epoch": 1.5334688854406335,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004773071838789402,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.13588482588529588,
|
|
"num_tokens": 30997077.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.48135142326355,
|
|
"epoch": 1.5340039595483974,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004772904479419148,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.13954296559095383,
|
|
"num_tokens": 31007485.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.50969672203064,
|
|
"epoch": 1.5345390336561615,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004772737061637811,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.14038911312818528,
|
|
"num_tokens": 31017827.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.547337579727173,
|
|
"epoch": 1.5350741077639252,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047725695854502267,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.1367683343589306,
|
|
"num_tokens": 31028167.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.506247043609619,
|
|
"epoch": 1.5356091818716893,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047724020508612287,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.13793734312057496,
|
|
"num_tokens": 31038941.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.509874773025513,
|
|
"epoch": 1.5361442559794531,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047722344578756564,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.13013634383678435,
|
|
"num_tokens": 31049949.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.57332935333252,
|
|
"epoch": 1.536679330087217,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047720668064983476,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.13523405343294143,
|
|
"num_tokens": 31059299.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.518624258041382,
|
|
"epoch": 1.5372144041949811,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004771899096734145,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12761058509349824,
|
|
"num_tokens": 31070508.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.454201030731201,
|
|
"epoch": 1.5377494783027448,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047717313285878886,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.13824471086263657,
|
|
"num_tokens": 31082354.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.685629796981812,
|
|
"epoch": 1.5382845524105089,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047715635020644247,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.1280341513454914,
|
|
"num_tokens": 31093496.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.581520366668701,
|
|
"epoch": 1.5388196265182728,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047713956171685994,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.13955939933657646,
|
|
"num_tokens": 31104289.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.408662891387939,
|
|
"epoch": 1.5393547006260366,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000477122767390526,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.1459297515451908,
|
|
"num_tokens": 31114998.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.475273132324219,
|
|
"epoch": 1.5398897747338007,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047710596722792543,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.13103958070278168,
|
|
"num_tokens": 31127393.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.476905965805054,
|
|
"epoch": 1.5404248488415646,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004770891612295435,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.15151217132806777,
|
|
"num_tokens": 31137484.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.524506330490112,
|
|
"epoch": 1.5409599229493285,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004770723493958654,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.13329991921782494,
|
|
"num_tokens": 31147863.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.464319705963135,
|
|
"epoch": 1.5414949970570924,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004770555317273767,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.13622017651796342,
|
|
"num_tokens": 31159018.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.558589506149292,
|
|
"epoch": 1.5420300711648562,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047703870822456287,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.13448593094944955,
|
|
"num_tokens": 31170673.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.438023281097412,
|
|
"epoch": 1.5425651452726203,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004770218788879097,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.14730842560529708,
|
|
"num_tokens": 31181165.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.370760583877564,
|
|
"epoch": 1.5431002193803842,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004770050437179033,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.13814024552702903,
|
|
"num_tokens": 31192976.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.539438915252686,
|
|
"epoch": 1.543635293488148,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004769882027150295,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.13710992708802222,
|
|
"num_tokens": 31203979.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.561808919906616,
|
|
"epoch": 1.5441703675959122,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047697135587977473,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.14149817302823067,
|
|
"num_tokens": 31214972.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.556917285919189,
|
|
"epoch": 1.5447054417036759,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047695450321262546,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.13588785231113434,
|
|
"num_tokens": 31224726.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.527967166900635,
|
|
"epoch": 1.54524051581144,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004769376447140683,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.13984608128666878,
|
|
"num_tokens": 31235761.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.522278881072998,
|
|
"epoch": 1.5457755899192038,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047692078038459015,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.14084505960345267,
|
|
"num_tokens": 31246221.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.535905742645264,
|
|
"epoch": 1.5463106640269677,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004769039102246777,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.12931643798947334,
|
|
"num_tokens": 31257364.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.5485001564025875,
|
|
"epoch": 1.5468457381347318,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047688703423481827,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.13121291548013686,
|
|
"num_tokens": 31268343.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.530178070068359,
|
|
"epoch": 1.5473808122424955,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047687015241549896,
|
|
"loss": 6.3008,
|
|
"mean_token_accuracy": 0.13335917592048646,
|
|
"num_tokens": 31278335.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.505687570571899,
|
|
"epoch": 1.5479158863502596,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004768532647672075,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.12822186350822448,
|
|
"num_tokens": 31288537.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.440744066238404,
|
|
"epoch": 1.5484509604580234,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004768363712904314,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.14038474783301352,
|
|
"num_tokens": 31299353.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.5596130847930905,
|
|
"epoch": 1.5489860345657873,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004768194719856584,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1316815972328186,
|
|
"num_tokens": 31309655.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.525741004943848,
|
|
"epoch": 1.5495211086735514,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004768025668533765,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.13498535379767418,
|
|
"num_tokens": 31321008.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.472729158401489,
|
|
"epoch": 1.550056182781315,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047678565589407383,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.1401698887348175,
|
|
"num_tokens": 31331978.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.510477113723755,
|
|
"epoch": 1.5505912568890792,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004767687391082387,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.1391635164618492,
|
|
"num_tokens": 31341703.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.5434596061706545,
|
|
"epoch": 1.551126330996843,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047675181649635965,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.13907155245542527,
|
|
"num_tokens": 31352787.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.4846821308135985,
|
|
"epoch": 1.551661405104607,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047673488805892515,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.13517796471714974,
|
|
"num_tokens": 31363702.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.530848407745362,
|
|
"epoch": 1.552196479212371,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047671795379642415,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.12709226831793785,
|
|
"num_tokens": 31374719.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.620404386520386,
|
|
"epoch": 1.5527315533201347,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004767010137093456,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.12480267137289047,
|
|
"num_tokens": 31386289.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.537449836730957,
|
|
"epoch": 1.5532666274278988,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047668406779817864,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.14198817759752275,
|
|
"num_tokens": 31397103.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.51537299156189,
|
|
"epoch": 1.5538017015356627,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004766671160634125,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.13656345903873443,
|
|
"num_tokens": 31408715.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.582148265838623,
|
|
"epoch": 1.5543367756434265,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004766501585055367,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.1285000301897526,
|
|
"num_tokens": 31420365.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.546790933609008,
|
|
"epoch": 1.5548718497511906,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000476633195125041,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.13490134105086327,
|
|
"num_tokens": 31431635.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.520722341537476,
|
|
"epoch": 1.5554069238589545,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047661622592241507,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.13644103407859803,
|
|
"num_tokens": 31442513.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.521498155593872,
|
|
"epoch": 1.5559419979667184,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004765992508981489,
|
|
"loss": 6.2933,
|
|
"mean_token_accuracy": 0.1281339019536972,
|
|
"num_tokens": 31453726.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.541304016113282,
|
|
"epoch": 1.5564770720744823,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004765822700527328,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.1394302561879158,
|
|
"num_tokens": 31463980.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.500122165679931,
|
|
"epoch": 1.5570121461822461,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004765652833866569,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.12963479459285737,
|
|
"num_tokens": 31474615.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.462019920349121,
|
|
"epoch": 1.5575472202900102,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004765482909004118,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.14140638411045076,
|
|
"num_tokens": 31485283.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.535767030715943,
|
|
"epoch": 1.5580822943977741,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004765312925944881,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.13080894574522972,
|
|
"num_tokens": 31496997.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.6297478675842285,
|
|
"epoch": 1.558617368505538,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047651428846937673,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.1357246607542038,
|
|
"num_tokens": 31507585.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.511379718780518,
|
|
"epoch": 1.559152442613302,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047649727852556854,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.13770078867673874,
|
|
"num_tokens": 31517078.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.370854806900025,
|
|
"epoch": 1.5596875167210658,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004764802627635547,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.14397168532013893,
|
|
"num_tokens": 31528576.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.582043838500977,
|
|
"epoch": 1.5602225908288299,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004764632411838266,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.12686383947730065,
|
|
"num_tokens": 31540095.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.544200801849366,
|
|
"epoch": 1.5607576649365937,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047644621378687573,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.13072769418358804,
|
|
"num_tokens": 31550980.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.3452962875366214,
|
|
"epoch": 1.5612927390443576,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00047642918057319377,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15695239156484603,
|
|
"num_tokens": 31561842.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.525337028503418,
|
|
"epoch": 1.5618278131521217,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004764121415432725,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.12762523368000983,
|
|
"num_tokens": 31572798.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.54258165359497,
|
|
"epoch": 1.5623628872598854,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004763950966976039,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.13119860887527465,
|
|
"num_tokens": 31584774.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.536434745788574,
|
|
"epoch": 1.5628979613676495,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004763780460366803,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.13397064805030823,
|
|
"num_tokens": 31596197.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.550236940383911,
|
|
"epoch": 1.5634330354754133,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004763609895609939,
|
|
"loss": 6.2697,
|
|
"mean_token_accuracy": 0.13484611362218857,
|
|
"num_tokens": 31607455.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.561938524246216,
|
|
"epoch": 1.5639681095831772,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047634392727103714,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.13227349519729614,
|
|
"num_tokens": 31618995.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.468525743484497,
|
|
"epoch": 1.5645031836909413,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004763268591673028,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.13631799519062043,
|
|
"num_tokens": 31629984.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.492383766174316,
|
|
"epoch": 1.565038257798705,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004763097852502837,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.13692545443773269,
|
|
"num_tokens": 31641362.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.5297730445861815,
|
|
"epoch": 1.565573331906469,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00047629270552047284,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.12706034481525422,
|
|
"num_tokens": 31652650.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.5213886260986325,
|
|
"epoch": 1.566108406014233,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047627561997836337,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.12873518839478493,
|
|
"num_tokens": 31664201.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.579891300201416,
|
|
"epoch": 1.5666434801219968,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004762585286244487,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.13287581130862236,
|
|
"num_tokens": 31674480.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.5407298564910885,
|
|
"epoch": 1.567178554229761,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047624143145922227,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.1364641495049,
|
|
"num_tokens": 31685377.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.54713773727417,
|
|
"epoch": 1.5677136283375246,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047622432848317775,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.13927348628640174,
|
|
"num_tokens": 31695199.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.462022686004639,
|
|
"epoch": 1.5682487024452887,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004762072196968091,
|
|
"loss": 6.268,
|
|
"mean_token_accuracy": 0.13694618120789528,
|
|
"num_tokens": 31705528.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.4519548416137695,
|
|
"epoch": 1.5687837765530526,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004761901051006102,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.14057985618710517,
|
|
"num_tokens": 31718156.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.518571949005127,
|
|
"epoch": 1.5693188506608164,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047617298469507534,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.1364244446158409,
|
|
"num_tokens": 31729783.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.5569658279418945,
|
|
"epoch": 1.5698539247685805,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004761558584806988,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.1388966977596283,
|
|
"num_tokens": 31740796.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.588993740081787,
|
|
"epoch": 1.5703889988763444,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004761387264579751,
|
|
"loss": 6.3151,
|
|
"mean_token_accuracy": 0.13168300688266754,
|
|
"num_tokens": 31750559.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.521017694473267,
|
|
"epoch": 1.5709240729841083,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004761215886273989,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.13765431344509124,
|
|
"num_tokens": 31761559.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.494146347045898,
|
|
"epoch": 1.5714591470918722,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047610444498946507,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.13926137760281562,
|
|
"num_tokens": 31771677.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.539397382736206,
|
|
"epoch": 1.571994221199636,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004760872955446688,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.12628690302371978,
|
|
"num_tokens": 31783028.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.554657936096191,
|
|
"epoch": 1.5725292953074002,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047607014029350504,
|
|
"loss": 6.2933,
|
|
"mean_token_accuracy": 0.13701235502958298,
|
|
"num_tokens": 31793110.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.496626329421997,
|
|
"epoch": 1.573064369415164,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047605297923646923,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.13291990309953688,
|
|
"num_tokens": 31804193.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.518072462081909,
|
|
"epoch": 1.573599443522928,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047603581237405684,
|
|
"loss": 6.2548,
|
|
"mean_token_accuracy": 0.13917799517512322,
|
|
"num_tokens": 31815752.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.575625705718994,
|
|
"epoch": 1.574134517630692,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047601863970676367,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.1280118577182293,
|
|
"num_tokens": 31825936.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.54962010383606,
|
|
"epoch": 1.5746695917384557,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047600146123508554,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.13201195001602173,
|
|
"num_tokens": 31836601.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.3876525402069095,
|
|
"epoch": 1.5752046658462198,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047598427695951846,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.14671236798167228,
|
|
"num_tokens": 31846476.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.38327260017395,
|
|
"epoch": 1.5757397399539836,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047596708688055857,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.1459612712264061,
|
|
"num_tokens": 31856151.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.544833850860596,
|
|
"epoch": 1.5762748140617475,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004759498909987023,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.1280362620949745,
|
|
"num_tokens": 31867419.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.5832963466644285,
|
|
"epoch": 1.5768098881695116,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004759326893144462,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.13490021526813506,
|
|
"num_tokens": 31878036.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.542579221725464,
|
|
"epoch": 1.5773449622772753,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000475915481828287,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13082825392484665,
|
|
"num_tokens": 31887919.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.434671688079834,
|
|
"epoch": 1.5778800363850394,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047589826854072133,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.13572418168187142,
|
|
"num_tokens": 31898962.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.579334545135498,
|
|
"epoch": 1.5784151104928033,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047588104945224654,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.13001709431409836,
|
|
"num_tokens": 31911027.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.5912518978118895,
|
|
"epoch": 1.5789501846005671,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004758638245633595,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13635631650686264,
|
|
"num_tokens": 31921226.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.496388244628906,
|
|
"epoch": 1.5794852587083312,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004758465938745579,
|
|
"loss": 6.2114,
|
|
"mean_token_accuracy": 0.13777147978544235,
|
|
"num_tokens": 31932848.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.460186386108399,
|
|
"epoch": 1.5800203328160949,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047582935738633915,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.13729973658919334,
|
|
"num_tokens": 31943757.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.520174598693847,
|
|
"epoch": 1.580555406923859,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004758121150992009,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.12971630915999413,
|
|
"num_tokens": 31954391.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.51693320274353,
|
|
"epoch": 1.5810904810316229,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047579486701364093,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.13650548011064528,
|
|
"num_tokens": 31964497.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.5695905685424805,
|
|
"epoch": 1.5816255551393867,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004757776131301575,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.130709208548069,
|
|
"num_tokens": 31974466.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.557105636596679,
|
|
"epoch": 1.5821606292471508,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004757603534492487,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.13409281075000762,
|
|
"num_tokens": 31985890.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.504603242874145,
|
|
"epoch": 1.5826957033549145,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004757430879714128,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.13219767883419992,
|
|
"num_tokens": 31996865.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.460845565795898,
|
|
"epoch": 1.5832307774626786,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004757258166971485,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.1445557326078415,
|
|
"num_tokens": 32008121.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.570254182815551,
|
|
"epoch": 1.5837658515704425,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004757085396269545,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.1301535189151764,
|
|
"num_tokens": 32020552.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.561383485794067,
|
|
"epoch": 1.5843009256782064,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047569125676132963,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.13402550369501115,
|
|
"num_tokens": 32032361.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.55854434967041,
|
|
"epoch": 1.5848359997859705,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047567396810077286,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.12737912312150002,
|
|
"num_tokens": 32043233.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.552183437347412,
|
|
"epoch": 1.5853710738937343,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047565667364578344,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.14003728479146957,
|
|
"num_tokens": 32054273.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.523531103134156,
|
|
"epoch": 1.5859061480014982,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004756393733968608,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.14313824102282524,
|
|
"num_tokens": 32064200.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.451785039901734,
|
|
"epoch": 1.586441222109262,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004756220673545045,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.14075903221964836,
|
|
"num_tokens": 32074823.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.533991765975952,
|
|
"epoch": 1.586976296217026,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047560475551921416,
|
|
"loss": 6.3073,
|
|
"mean_token_accuracy": 0.13615889325737954,
|
|
"num_tokens": 32085333.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.625106430053711,
|
|
"epoch": 1.58751137032479,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004755874378914897,
|
|
"loss": 6.2903,
|
|
"mean_token_accuracy": 0.13102672025561332,
|
|
"num_tokens": 32095827.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.524811744689941,
|
|
"epoch": 1.588046444432554,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004755701144718311,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.13742618560791015,
|
|
"num_tokens": 32106949.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.501339530944824,
|
|
"epoch": 1.5885815185403178,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047555278526073867,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.14211768209934234,
|
|
"num_tokens": 32118269.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.4988819599151615,
|
|
"epoch": 1.589116592648082,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004755354502587127,
|
|
"loss": 6.2626,
|
|
"mean_token_accuracy": 0.13281174525618553,
|
|
"num_tokens": 32128406.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.5138648509979244,
|
|
"epoch": 1.5896516667558456,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047551810946625385,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.1371403641998768,
|
|
"num_tokens": 32140112.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.533293962478638,
|
|
"epoch": 1.5901867408636097,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047550076288386276,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.14420999884605407,
|
|
"num_tokens": 32150010.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.5140081405639645,
|
|
"epoch": 1.5907218149713735,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004754834105120403,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.12911390140652657,
|
|
"num_tokens": 32160694.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.499224996566772,
|
|
"epoch": 1.5912568890791374,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047546605235128755,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1340811789035797,
|
|
"num_tokens": 32171947.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.5859424591064455,
|
|
"epoch": 1.5917919631869015,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004754486884021057,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.13230689167976378,
|
|
"num_tokens": 32182849.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.548197221755982,
|
|
"epoch": 1.5923270372946652,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004754313186649961,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.13477448523044586,
|
|
"num_tokens": 32192871.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.562755441665649,
|
|
"epoch": 1.5928621114024293,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047541394314046037,
|
|
"loss": 6.3227,
|
|
"mean_token_accuracy": 0.1299983151257038,
|
|
"num_tokens": 32203289.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.5510444164276125,
|
|
"epoch": 1.5933971855101932,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004753965618290002,
|
|
"loss": 6.2676,
|
|
"mean_token_accuracy": 0.13420026302337645,
|
|
"num_tokens": 32213238.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.424655485153198,
|
|
"epoch": 1.593932259617957,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004753791747311175,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.13797398135066033,
|
|
"num_tokens": 32223384.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.520129299163818,
|
|
"epoch": 1.5944673337257211,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047536178184731426,
|
|
"loss": 6.2804,
|
|
"mean_token_accuracy": 0.13506588339805603,
|
|
"num_tokens": 32235358.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.643621444702148,
|
|
"epoch": 1.5950024078334848,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004753443831780927,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.12936478480696678,
|
|
"num_tokens": 32246459.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.506386947631836,
|
|
"epoch": 1.595537481941249,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004753269787239552,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.13538266569375992,
|
|
"num_tokens": 32257798.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.502975988388061,
|
|
"epoch": 1.5960725560490128,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047530956848540435,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.1334786370396614,
|
|
"num_tokens": 32268118.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.445563507080078,
|
|
"epoch": 1.5966076301567766,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004752921524629429,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.13638549968600272,
|
|
"num_tokens": 32279676.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.503003644943237,
|
|
"epoch": 1.5971427042645407,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004752747306570737,
|
|
"loss": 6.2293,
|
|
"mean_token_accuracy": 0.13795944750308992,
|
|
"num_tokens": 32290613.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.5680375576019285,
|
|
"epoch": 1.5976777783723044,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047525730306829977,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.13554463014006615,
|
|
"num_tokens": 32300873.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.557008171081543,
|
|
"epoch": 1.5982128524800685,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004752398696971244,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.13355937376618385,
|
|
"num_tokens": 32312326.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.5607640743255615,
|
|
"epoch": 1.5987479265878324,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047522243054405085,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.12972980067133905,
|
|
"num_tokens": 32324322.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.560641956329346,
|
|
"epoch": 1.5992830006955963,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004752049856095828,
|
|
"loss": 6.2231,
|
|
"mean_token_accuracy": 0.13305347710847854,
|
|
"num_tokens": 32334397.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.470574998855591,
|
|
"epoch": 1.5998180748033604,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047518753489422393,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.1374221198260784,
|
|
"num_tokens": 32345131.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.4330222606658936,
|
|
"epoch": 1.6003531489111242,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047517007839847816,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.13534148335456847,
|
|
"num_tokens": 32355520.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.536291217803955,
|
|
"epoch": 1.6008882230188881,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004751526161228494,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.14231665730476378,
|
|
"num_tokens": 32366695.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.454723787307739,
|
|
"epoch": 1.601423297126652,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000475135148067842,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.13280131667852402,
|
|
"num_tokens": 32377467.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.581510353088379,
|
|
"epoch": 1.6019583712344159,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047511767423396033,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.1360831081867218,
|
|
"num_tokens": 32388021.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.5882233619689945,
|
|
"epoch": 1.60249344534218,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000475100194621709,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.14279873743653299,
|
|
"num_tokens": 32398105.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.526843452453614,
|
|
"epoch": 1.6030285194499438,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004750827092315926,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.13159868866205215,
|
|
"num_tokens": 32409876.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.51892728805542,
|
|
"epoch": 1.6035635935577077,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047506521806411613,
|
|
"loss": 6.2424,
|
|
"mean_token_accuracy": 0.14545759409666062,
|
|
"num_tokens": 32420283.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.54042501449585,
|
|
"epoch": 1.6040986676654718,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047504772111978463,
|
|
"loss": 6.3343,
|
|
"mean_token_accuracy": 0.12750672101974486,
|
|
"num_tokens": 32431164.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.5425420761108395,
|
|
"epoch": 1.6046337417732355,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004750302183991032,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.132595930993557,
|
|
"num_tokens": 32442253.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.50988450050354,
|
|
"epoch": 1.6051688158809996,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004750127099025774,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.1360313430428505,
|
|
"num_tokens": 32452800.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6051688158809996,
|
|
"eval_entropy": 6.419160812048899,
|
|
"eval_loss": 6.373970031738281,
|
|
"eval_mean_token_accuracy": 0.13763191947648226,
|
|
"eval_num_tokens": 32452800.0,
|
|
"eval_runtime": 22.5526,
|
|
"eval_samples_per_second": 1315.992,
|
|
"eval_steps_per_second": 164.505,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.596367835998535,
|
|
"epoch": 1.6057038899887635,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004749951956307126,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.1296849727630615,
|
|
"num_tokens": 32462890.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.485629034042359,
|
|
"epoch": 1.6062389640965273,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004749776755840148,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.14182380735874175,
|
|
"num_tokens": 32473422.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.500695705413818,
|
|
"epoch": 1.6067740382042914,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00047496014976298957,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.13322071507573127,
|
|
"num_tokens": 32483980.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.603447580337525,
|
|
"epoch": 1.607309112312055,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004749426181681432,
|
|
"loss": 6.3083,
|
|
"mean_token_accuracy": 0.13130330070853233,
|
|
"num_tokens": 32494905.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.614582967758179,
|
|
"epoch": 1.6078441864198192,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00047492508079998173,
|
|
"loss": 6.3397,
|
|
"mean_token_accuracy": 0.12839462533593177,
|
|
"num_tokens": 32505799.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.563151884078979,
|
|
"epoch": 1.608379260527583,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004749075376590117,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.12912078201770782,
|
|
"num_tokens": 32516328.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.532871294021606,
|
|
"epoch": 1.608914334635347,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004748899887457396,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.13482635021209716,
|
|
"num_tokens": 32526335.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.4955644607543945,
|
|
"epoch": 1.609449408743111,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047487243406067227,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.1365067608654499,
|
|
"num_tokens": 32536896.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.512849569320679,
|
|
"epoch": 1.6099844828508747,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004748548736043164,
|
|
"loss": 6.1869,
|
|
"mean_token_accuracy": 0.1340150237083435,
|
|
"num_tokens": 32547604.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.575725650787353,
|
|
"epoch": 1.6105195569586388,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047483730737717914,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.12914739921689034,
|
|
"num_tokens": 32558539.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.5589573860168455,
|
|
"epoch": 1.6110546310664027,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004748197353797677,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.12705627977848052,
|
|
"num_tokens": 32569787.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.542858552932739,
|
|
"epoch": 1.6115897051741666,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004748021576125895,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.13655368536710738,
|
|
"num_tokens": 32580146.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.52427453994751,
|
|
"epoch": 1.6121247792819307,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004747845740761521,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13791619762778282,
|
|
"num_tokens": 32591243.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.557205581665039,
|
|
"epoch": 1.6126598533896943,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004747669847709631,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.13091632947325707,
|
|
"num_tokens": 32602424.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.61011905670166,
|
|
"epoch": 1.6131949274974584,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004747493896975306,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.12900158390402794,
|
|
"num_tokens": 32613703.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.564071750640869,
|
|
"epoch": 1.6137300016052223,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004747317888563625,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.1308335021138191,
|
|
"num_tokens": 32624371.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.55357985496521,
|
|
"epoch": 1.6142650757129862,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047471418224796704,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.13879068642854692,
|
|
"num_tokens": 32634039.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.536784744262695,
|
|
"epoch": 1.6148001498207503,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004746965698728526,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.1380273535847664,
|
|
"num_tokens": 32644644.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.567042064666748,
|
|
"epoch": 1.6153352239285141,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047467895173152787,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.13522871881723403,
|
|
"num_tokens": 32655961.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.488573694229126,
|
|
"epoch": 1.615870298036278,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047466132782450146,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.14545413851737976,
|
|
"num_tokens": 32665506.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.465070581436157,
|
|
"epoch": 1.616405372144042,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047464369815228215,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.13768779933452607,
|
|
"num_tokens": 32676278.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.525582218170166,
|
|
"epoch": 1.6169404462518058,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004746260627153792,
|
|
"loss": 6.2163,
|
|
"mean_token_accuracy": 0.13862458914518355,
|
|
"num_tokens": 32686835.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.599107980728149,
|
|
"epoch": 1.6174755203595699,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047460842151430166,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.1358664244413376,
|
|
"num_tokens": 32696856.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.569884347915649,
|
|
"epoch": 1.6180105944673338,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047459077454955914,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.13096022456884385,
|
|
"num_tokens": 32707514.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.548951768875122,
|
|
"epoch": 1.6185456685750976,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047457312182166094,
|
|
"loss": 6.3643,
|
|
"mean_token_accuracy": 0.12981587499380112,
|
|
"num_tokens": 32718934.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.544709396362305,
|
|
"epoch": 1.6190807426828617,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004745554633311169,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.13406705260276794,
|
|
"num_tokens": 32729249.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.551851797103882,
|
|
"epoch": 1.6196158167906254,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047453779907843686,
|
|
"loss": 6.3175,
|
|
"mean_token_accuracy": 0.12954918518662453,
|
|
"num_tokens": 32739948.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.527648115158081,
|
|
"epoch": 1.6201508908983895,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047452012906413105,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.13055140003561974,
|
|
"num_tokens": 32751482.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.499547004699707,
|
|
"epoch": 1.6206859650061534,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047450245328870943,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.14658984839916228,
|
|
"num_tokens": 32761260.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.502904844284058,
|
|
"epoch": 1.6212210391139172,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047448477175268255,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.13591463193297387,
|
|
"num_tokens": 32772684.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.370807075500489,
|
|
"epoch": 1.6217561132216813,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047446708445656095,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.15149276256561278,
|
|
"num_tokens": 32784022.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.514007139205932,
|
|
"epoch": 1.622291187329445,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004744493914008552,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.13973695337772368,
|
|
"num_tokens": 32794104.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.574914264678955,
|
|
"epoch": 1.622826261437209,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004744316925860764,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.14187313616275787,
|
|
"num_tokens": 32804038.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.470356845855713,
|
|
"epoch": 1.623361335544973,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004744139880127355,
|
|
"loss": 6.2865,
|
|
"mean_token_accuracy": 0.13450952768325805,
|
|
"num_tokens": 32815620.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.478771495819092,
|
|
"epoch": 1.6238964096527368,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047439627768134366,
|
|
"loss": 6.1972,
|
|
"mean_token_accuracy": 0.14077696353197097,
|
|
"num_tokens": 32826353.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.505884885787964,
|
|
"epoch": 1.624431483760501,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004743785615924124,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.13557258620858192,
|
|
"num_tokens": 32836582.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.511706876754761,
|
|
"epoch": 1.6249665578682646,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004743608397464531,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.13595101088285447,
|
|
"num_tokens": 32848073.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.5341103076934814,
|
|
"epoch": 1.6255016319760287,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047434311214397765,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.1354230597615242,
|
|
"num_tokens": 32857839.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.495816612243653,
|
|
"epoch": 1.6260367060837926,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047432537878549786,
|
|
"loss": 6.2163,
|
|
"mean_token_accuracy": 0.1448695421218872,
|
|
"num_tokens": 32868087.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.557143068313598,
|
|
"epoch": 1.6265717801915565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047430763967152564,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.13106158301234244,
|
|
"num_tokens": 32880622.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.61873950958252,
|
|
"epoch": 1.6271068542993206,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047428989480257337,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.1311236575245857,
|
|
"num_tokens": 32891405.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.528134870529175,
|
|
"epoch": 1.6276419284070842,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004742721441791535,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.1388081818819046,
|
|
"num_tokens": 32900487.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.432776355743409,
|
|
"epoch": 1.6281770025148483,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004742543878017784,
|
|
"loss": 6.1764,
|
|
"mean_token_accuracy": 0.14578463062644004,
|
|
"num_tokens": 32912139.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.506275987625122,
|
|
"epoch": 1.6287120766226122,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047423662567096085,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.1333197571337223,
|
|
"num_tokens": 32922972.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.512710762023926,
|
|
"epoch": 1.629247150730376,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047421885778721376,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.14148302972316742,
|
|
"num_tokens": 32932609.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.473397874832154,
|
|
"epoch": 1.6297822248381402,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047420108415105006,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.1474070742726326,
|
|
"num_tokens": 32942706.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.515003728866577,
|
|
"epoch": 1.630317298945904,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047418330476298317,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.13718311563134195,
|
|
"num_tokens": 32952240.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.555767250061035,
|
|
"epoch": 1.630852373053668,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004741655196235262,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.1296004444360733,
|
|
"num_tokens": 32963249.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.544875812530518,
|
|
"epoch": 1.6313874471614318,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047414772873319294,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.14131317362189294,
|
|
"num_tokens": 32974004.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.5474451065063475,
|
|
"epoch": 1.6319225212691957,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000474129932092497,
|
|
"loss": 6.2414,
|
|
"mean_token_accuracy": 0.13400815799832344,
|
|
"num_tokens": 32985236.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.577800703048706,
|
|
"epoch": 1.6324575953769598,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004741121297019522,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.13068798258900644,
|
|
"num_tokens": 32995155.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.53216872215271,
|
|
"epoch": 1.6329926694847237,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047409432156207264,
|
|
"loss": 6.284,
|
|
"mean_token_accuracy": 0.1431720234453678,
|
|
"num_tokens": 33007562.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.5164182662963865,
|
|
"epoch": 1.6335277435924875,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047407650767337256,
|
|
"loss": 6.2507,
|
|
"mean_token_accuracy": 0.132377927005291,
|
|
"num_tokens": 33018653.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.605610656738281,
|
|
"epoch": 1.6340628177002516,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004740586880363663,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.12530876249074935,
|
|
"num_tokens": 33029470.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.5277331352233885,
|
|
"epoch": 1.6345978918080153,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047404086265156835,
|
|
"loss": 6.2094,
|
|
"mean_token_accuracy": 0.14064295142889022,
|
|
"num_tokens": 33039597.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.5205522060394285,
|
|
"epoch": 1.6351329659157794,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004740230315194935,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.1316556826233864,
|
|
"num_tokens": 33050984.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.524631404876709,
|
|
"epoch": 1.6356680400235433,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047400519464065656,
|
|
"loss": 6.3191,
|
|
"mean_token_accuracy": 0.1310469351708889,
|
|
"num_tokens": 33062250.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.543263912200928,
|
|
"epoch": 1.6362031141313071,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004739873520155726,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.1317575253546238,
|
|
"num_tokens": 33072129.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.553985691070556,
|
|
"epoch": 1.6367381882390712,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004739695036447568,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.1361164018511772,
|
|
"num_tokens": 33082475.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.4877923965454105,
|
|
"epoch": 1.637273262346835,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047395164952872455,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.14455458000302315,
|
|
"num_tokens": 33093791.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.51265869140625,
|
|
"epoch": 1.637808336454599,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004739337896679914,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.14008307158946992,
|
|
"num_tokens": 33104231.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.52463812828064,
|
|
"epoch": 1.6383434105623629,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047391592406307296,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.13311854079365731,
|
|
"num_tokens": 33115118.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.545754528045654,
|
|
"epoch": 1.6388784846701268,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004738980527144852,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.143442365527153,
|
|
"num_tokens": 33126154.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.524981355667114,
|
|
"epoch": 1.6394135587778909,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004738801756227441,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.1365656517446041,
|
|
"num_tokens": 33137342.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.469981956481933,
|
|
"epoch": 1.6399486328856545,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047386229278836595,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.14113932177424432,
|
|
"num_tokens": 33147661.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.564016675949096,
|
|
"epoch": 1.6404837069934186,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047384440421186695,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.13328296020627023,
|
|
"num_tokens": 33157106.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.559274578094483,
|
|
"epoch": 1.6410187811011825,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004738265098937638,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.13367382884025575,
|
|
"num_tokens": 33169451.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.596626472473145,
|
|
"epoch": 1.6415538552089464,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000473808609834573,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.1338217854499817,
|
|
"num_tokens": 33180799.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.581587791442871,
|
|
"epoch": 1.6420889293167105,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047379070403481165,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12887900546193123,
|
|
"num_tokens": 33191948.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.529717302322387,
|
|
"epoch": 1.6426240034244743,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047377279249499656,
|
|
"loss": 6.2631,
|
|
"mean_token_accuracy": 0.1293257676064968,
|
|
"num_tokens": 33203536.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.542965984344482,
|
|
"epoch": 1.6431590775322382,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004737548752156451,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.13613931387662886,
|
|
"num_tokens": 33214526.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.493067502975464,
|
|
"epoch": 1.643694151640002,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004737369521972745,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.13954372256994246,
|
|
"num_tokens": 33226560.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.482340002059937,
|
|
"epoch": 1.644229225747766,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047371902344040234,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.13352166935801507,
|
|
"num_tokens": 33237441.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.506029081344605,
|
|
"epoch": 1.64476429985553,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047370108894554633,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.13105529099702834,
|
|
"num_tokens": 33248229.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.478899192810059,
|
|
"epoch": 1.645299373963294,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004736831487132243,
|
|
"loss": 6.1587,
|
|
"mean_token_accuracy": 0.1475966066122055,
|
|
"num_tokens": 33258992.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.500133895874024,
|
|
"epoch": 1.6458344480710578,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004736652027439542,
|
|
"loss": 6.1869,
|
|
"mean_token_accuracy": 0.13673374876379968,
|
|
"num_tokens": 33269583.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.548278188705444,
|
|
"epoch": 1.646369522178822,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047364725103825437,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.13247542828321457,
|
|
"num_tokens": 33280236.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.523178243637085,
|
|
"epoch": 1.6469045962865856,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000473629293596643,
|
|
"loss": 6.2145,
|
|
"mean_token_accuracy": 0.1371418498456478,
|
|
"num_tokens": 33291327.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.583948993682862,
|
|
"epoch": 1.6474396703943497,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047361133041963873,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.13246541023254393,
|
|
"num_tokens": 33302125.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.507024955749512,
|
|
"epoch": 1.6479747445021136,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004735933615077602,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.13589197397232056,
|
|
"num_tokens": 33312576.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.500837564468384,
|
|
"epoch": 1.6485098186098774,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047357538686152627,
|
|
"loss": 6.2317,
|
|
"mean_token_accuracy": 0.1352829158306122,
|
|
"num_tokens": 33322821.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.553674840927124,
|
|
"epoch": 1.6490448927176415,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047355740648145596,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.13334212675690651,
|
|
"num_tokens": 33333951.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.602206516265869,
|
|
"epoch": 1.6495799668254052,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004735394203680684,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.13933424800634384,
|
|
"num_tokens": 33344739.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.525042295455933,
|
|
"epoch": 1.6501150409331693,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047352142852188304,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.14079620391130448,
|
|
"num_tokens": 33354956.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.363925170898438,
|
|
"epoch": 1.6506501150409332,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004735034309434193,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.14333223477005957,
|
|
"num_tokens": 33364809.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.555759572982788,
|
|
"epoch": 1.651185189148697,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004734854276331968,
|
|
"loss": 6.2706,
|
|
"mean_token_accuracy": 0.14230604097247124,
|
|
"num_tokens": 33375324.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.5867352962493895,
|
|
"epoch": 1.6517202632564612,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047346741859173564,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.132570631057024,
|
|
"num_tokens": 33385963.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.571739339828492,
|
|
"epoch": 1.6522553373642248,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004734494038195555,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.13507345393300058,
|
|
"num_tokens": 33395927.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.549274349212647,
|
|
"epoch": 1.652790411471989,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004734313833171768,
|
|
"loss": 6.2415,
|
|
"mean_token_accuracy": 0.13801701590418816,
|
|
"num_tokens": 33406294.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.4921557903289795,
|
|
"epoch": 1.6533254855797528,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004734133570851198,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14175853729248047,
|
|
"num_tokens": 33416995.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.4246721267700195,
|
|
"epoch": 1.6538605596875167,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004733953251239049,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.13845812678337097,
|
|
"num_tokens": 33428087.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.5247784614562985,
|
|
"epoch": 1.6543956337952808,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004733772874340529,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.1310659483075142,
|
|
"num_tokens": 33439151.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.54686393737793,
|
|
"epoch": 1.6549307079030444,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004733592440160846,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.1391957312822342,
|
|
"num_tokens": 33449257.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.527724838256836,
|
|
"epoch": 1.6554657820108085,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047334119487052104,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.13526543900370597,
|
|
"num_tokens": 33460472.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.489955234527588,
|
|
"epoch": 1.6560008561185724,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047332313999788334,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.13044157400727271,
|
|
"num_tokens": 33470193.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.404095649719238,
|
|
"epoch": 1.6565359302263363,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047330507939869284,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.13785995692014694,
|
|
"num_tokens": 33481098.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.56090350151062,
|
|
"epoch": 1.6570710043341004,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000473287013073471,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.13516671136021613,
|
|
"num_tokens": 33492514.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 6.55650486946106,
|
|
"epoch": 1.6576060784418643,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004732689410227396,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.13520386070013046,
|
|
"num_tokens": 33504254.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.490405035018921,
|
|
"epoch": 1.6581411525496281,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004732508632470203,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.13007647171616554,
|
|
"num_tokens": 33515101.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.487555599212646,
|
|
"epoch": 1.658676226657392,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004732327797468352,
|
|
"loss": 6.2507,
|
|
"mean_token_accuracy": 0.137110199034214,
|
|
"num_tokens": 33525052.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.578079605102539,
|
|
"epoch": 1.6592113007651559,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004732146905227065,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.12686768770217896,
|
|
"num_tokens": 33536841.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.614656734466553,
|
|
"epoch": 1.65974637487292,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004731965955751564,
|
|
"loss": 6.2692,
|
|
"mean_token_accuracy": 0.13630660995841026,
|
|
"num_tokens": 33547292.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.525318765640259,
|
|
"epoch": 1.6602814489806839,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004731784949047075,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.13373274132609367,
|
|
"num_tokens": 33557674.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.527735948562622,
|
|
"epoch": 1.6608165230884477,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004731603885118824,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.1279158003628254,
|
|
"num_tokens": 33568396.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.577741956710815,
|
|
"epoch": 1.6613515971962118,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004731422763972039,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.1327934257686138,
|
|
"num_tokens": 33579688.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.578317785263062,
|
|
"epoch": 1.6618866713039755,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047312415856119505,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.131970302015543,
|
|
"num_tokens": 33591550.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.561192989349365,
|
|
"epoch": 1.6624217454117396,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047310603500437895,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.1381398282945156,
|
|
"num_tokens": 33600792.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.4599748134613035,
|
|
"epoch": 1.6629568195195035,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047308790572727895,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.13727160319685935,
|
|
"num_tokens": 33611873.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.529527378082276,
|
|
"epoch": 1.6634918936272673,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004730697707304184,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.13597349151968957,
|
|
"num_tokens": 33622960.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.592627620697021,
|
|
"epoch": 1.6640269677350314,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004730516300143211,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.13005867078900338,
|
|
"num_tokens": 33635391.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.593164157867432,
|
|
"epoch": 1.664562041842795,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004730334835795109,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.13071415051817895,
|
|
"num_tokens": 33647942.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.55129189491272,
|
|
"epoch": 1.6650971159505592,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004730153314265116,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.13420569971203805,
|
|
"num_tokens": 33658425.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.494670486450195,
|
|
"epoch": 1.665632190058323,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004729971735558475,
|
|
"loss": 6.2166,
|
|
"mean_token_accuracy": 0.1414251834154129,
|
|
"num_tokens": 33669645.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.555915451049804,
|
|
"epoch": 1.666167264166087,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004729790099680428,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1325235716998577,
|
|
"num_tokens": 33680415.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.485175704956054,
|
|
"epoch": 1.666702338273851,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000472960840663622,
|
|
"loss": 6.3214,
|
|
"mean_token_accuracy": 0.13352945372462272,
|
|
"num_tokens": 33691425.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.568507814407349,
|
|
"epoch": 1.6672374123816147,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004729426656431097,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.1349485158920288,
|
|
"num_tokens": 33703845.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.600763368606567,
|
|
"epoch": 1.6677724864893788,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004729244849070308,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.1353510484099388,
|
|
"num_tokens": 33714737.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.468076753616333,
|
|
"epoch": 1.6683075605971427,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047290629845591026,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.1312122106552124,
|
|
"num_tokens": 33725042.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.511102628707886,
|
|
"epoch": 1.6688426347049066,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000472888106290273,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.13453252837061883,
|
|
"num_tokens": 33736306.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.615510892868042,
|
|
"epoch": 1.6693777088126707,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047286990841064467,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.12460464984178543,
|
|
"num_tokens": 33747327.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.528128290176392,
|
|
"epoch": 1.6699127829204343,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004728517048175504,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.1368679001927376,
|
|
"num_tokens": 33757723.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.407970523834228,
|
|
"epoch": 1.6704478570281984,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000472833495511516,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.13751262351870536,
|
|
"num_tokens": 33769958.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.484128856658936,
|
|
"epoch": 1.6709829311359623,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047281528049306727,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.1377895474433899,
|
|
"num_tokens": 33780107.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.513759183883667,
|
|
"epoch": 1.6715180052437262,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004727970597627301,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.1330281265079975,
|
|
"num_tokens": 33791023.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.469873380661011,
|
|
"epoch": 1.6720530793514903,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004727788333210305,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1425516687333584,
|
|
"num_tokens": 33801195.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.515677213668823,
|
|
"epoch": 1.6725881534592542,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000472760601168495,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.14181752800941466,
|
|
"num_tokens": 33812957.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.5297685146331785,
|
|
"epoch": 1.673123227567018,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047274236330564995,
|
|
"loss": 6.2826,
|
|
"mean_token_accuracy": 0.13435860499739646,
|
|
"num_tokens": 33823874.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.525163459777832,
|
|
"epoch": 1.673658301674782,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004727241197330219,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.13939717635512353,
|
|
"num_tokens": 33834284.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.56245265007019,
|
|
"epoch": 1.6741933757825458,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004727058704511376,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.13500021770596504,
|
|
"num_tokens": 33845544.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.579645442962646,
|
|
"epoch": 1.67472844989031,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004726876154605242,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.1337307557463646,
|
|
"num_tokens": 33855420.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.535953426361084,
|
|
"epoch": 1.6752635239980738,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004726693547617086,
|
|
"loss": 6.1453,
|
|
"mean_token_accuracy": 0.14049242064356804,
|
|
"num_tokens": 33864904.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.4508716583251955,
|
|
"epoch": 1.6757985981058376,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047265108835521825,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.13712649717926978,
|
|
"num_tokens": 33875139.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.452628326416016,
|
|
"epoch": 1.6763336722136017,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004726328162415804,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.14112431481480597,
|
|
"num_tokens": 33886401.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.5320008277893065,
|
|
"epoch": 1.6768687463213654,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047261453842132277,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.1391934409737587,
|
|
"num_tokens": 33896382.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.561520433425903,
|
|
"epoch": 1.6774038204291295,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047259625489497317,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.13969543278217317,
|
|
"num_tokens": 33906403.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.435149383544922,
|
|
"epoch": 1.6779388945368934,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047257796566305946,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.13980668783187866,
|
|
"num_tokens": 33916992.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.529124116897583,
|
|
"epoch": 1.6784739686446573,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004725596707261097,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.13304452002048492,
|
|
"num_tokens": 33927599.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.55642671585083,
|
|
"epoch": 1.6790090427524214,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004725413700846522,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.1294899970293045,
|
|
"num_tokens": 33938957.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.5513214588165285,
|
|
"epoch": 1.679544116860185,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047252306373921543,
|
|
"loss": 6.2424,
|
|
"mean_token_accuracy": 0.13886384218931197,
|
|
"num_tokens": 33950169.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.535861158370972,
|
|
"epoch": 1.680079190967949,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047250475169032804,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.13359253630042076,
|
|
"num_tokens": 33960800.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.4771155834198,
|
|
"epoch": 1.680614265075713,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004724864339385185,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.1288799077272415,
|
|
"num_tokens": 33973060.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.5491858959198,
|
|
"epoch": 1.6811493391834769,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004724681104843161,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.13036111146211624,
|
|
"num_tokens": 33983185.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.601888990402221,
|
|
"epoch": 1.681684413291241,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004724497813282497,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.13604292944073676,
|
|
"num_tokens": 33993373.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.476183605194092,
|
|
"epoch": 1.6822194873990046,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004724314464708486,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.1464055560529232,
|
|
"num_tokens": 34005793.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.529676342010498,
|
|
"epoch": 1.6827545615067687,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004724131059126423,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.1304813355207443,
|
|
"num_tokens": 34016415.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.5095258235931395,
|
|
"epoch": 1.6832896356145326,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047239475965416016,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.13945785760879517,
|
|
"num_tokens": 34026859.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.513905572891235,
|
|
"epoch": 1.6838247097222965,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00047237640769593224,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.15040467530488968,
|
|
"num_tokens": 34037942.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.506213903427124,
|
|
"epoch": 1.6843597838300606,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004723580500384882,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.13819267526268958,
|
|
"num_tokens": 34048659.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.464280605316162,
|
|
"epoch": 1.6848948579378242,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047233968668235817,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.1391046404838562,
|
|
"num_tokens": 34059961.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.515230655670166,
|
|
"epoch": 1.6854299320455883,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047232131762807244,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.1414615035057068,
|
|
"num_tokens": 34069978.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.545376348495483,
|
|
"epoch": 1.6859650061533522,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004723029428761614,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.1336756817996502,
|
|
"num_tokens": 34080301.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.458175468444824,
|
|
"epoch": 1.686500080261116,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00047228456242715564,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.1380471520125866,
|
|
"num_tokens": 34092376.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.509817409515381,
|
|
"epoch": 1.6870351543688802,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004722661762815858,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.14321028292179108,
|
|
"num_tokens": 34102761.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.539234590530396,
|
|
"epoch": 1.687570228476644,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004722477844399829,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.1323903277516365,
|
|
"num_tokens": 34113370.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.537856483459473,
|
|
"epoch": 1.688105302584408,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004722293869028779,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.14107812196016312,
|
|
"num_tokens": 34125038.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.542143440246582,
|
|
"epoch": 1.6886403766921718,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004722109836708021,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.1316600888967514,
|
|
"num_tokens": 34135595.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.539742279052734,
|
|
"epoch": 1.6891754507999357,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047219257474428685,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1312544487416744,
|
|
"num_tokens": 34146755.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.484871435165405,
|
|
"epoch": 1.6897105249076998,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047217416012386367,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.14985355362296104,
|
|
"num_tokens": 34158465.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.510846424102783,
|
|
"epoch": 1.6902455990154637,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004721557398100644,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.13456518054008484,
|
|
"num_tokens": 34170007.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.538952875137329,
|
|
"epoch": 1.6907806731232276,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047213731380342077,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.1294082783162594,
|
|
"num_tokens": 34181595.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.546925115585327,
|
|
"epoch": 1.6913157472309917,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000472118882104465,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.13665975481271744,
|
|
"num_tokens": 34191791.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.549110746383667,
|
|
"epoch": 1.6918508213387553,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047210044471372915,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.13872140422463416,
|
|
"num_tokens": 34202636.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.570005178451538,
|
|
"epoch": 1.6923858954465194,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004720820016317456,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.13125923350453378,
|
|
"num_tokens": 34213333.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.547509574890137,
|
|
"epoch": 1.6929209695542833,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000472063552859047,
|
|
"loss": 6.2655,
|
|
"mean_token_accuracy": 0.1336832843720913,
|
|
"num_tokens": 34223679.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.515771150588989,
|
|
"epoch": 1.6934560436620472,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047204509839616604,
|
|
"loss": 6.3751,
|
|
"mean_token_accuracy": 0.12890572771430014,
|
|
"num_tokens": 34234528.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.502412509918213,
|
|
"epoch": 1.6939911177698113,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004720266382436355,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.13582652881741525,
|
|
"num_tokens": 34246203.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.513867616653442,
|
|
"epoch": 1.694526191877575,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00047200817240198846,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.13635388165712356,
|
|
"num_tokens": 34257231.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.518395709991455,
|
|
"epoch": 1.695061265985339,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047198970087175817,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.13498940616846083,
|
|
"num_tokens": 34268900.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.494491291046143,
|
|
"epoch": 1.695596340093103,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004719712236534779,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.12909621819853784,
|
|
"num_tokens": 34279343.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.494324111938477,
|
|
"epoch": 1.6961314142008668,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004719527407476812,
|
|
"loss": 6.2459,
|
|
"mean_token_accuracy": 0.1420057773590088,
|
|
"num_tokens": 34291952.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.555724811553955,
|
|
"epoch": 1.6966664883086309,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047193425215490186,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.1280573323369026,
|
|
"num_tokens": 34302516.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.5335493087768555,
|
|
"epoch": 1.6972015624163945,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047191575787567373,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.1397932641208172,
|
|
"num_tokens": 34313094.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.547899580001831,
|
|
"epoch": 1.6977366365241586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004718972579105306,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.13232587426900863,
|
|
"num_tokens": 34324803.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.49736008644104,
|
|
"epoch": 1.6982717106319225,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004718787522600069,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.12415364533662795,
|
|
"num_tokens": 34336386.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.550452852249146,
|
|
"epoch": 1.6988067847396864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004718602409246369,
|
|
"loss": 6.2936,
|
|
"mean_token_accuracy": 0.12681039273738862,
|
|
"num_tokens": 34347085.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.48975772857666,
|
|
"epoch": 1.6993418588474505,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047184172390495505,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.1400773286819458,
|
|
"num_tokens": 34358146.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.538142299652099,
|
|
"epoch": 1.6998769329552141,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004718232012014961,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.1347523719072342,
|
|
"num_tokens": 34370403.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.582979202270508,
|
|
"epoch": 1.7004120070629782,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00047180467281479496,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.1374131441116333,
|
|
"num_tokens": 34381130.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.479326438903809,
|
|
"epoch": 1.7009470811707421,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004717861387453865,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.13613806441426277,
|
|
"num_tokens": 34391610.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.517370939254761,
|
|
"epoch": 1.701482155278506,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004717675989938059,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.13521123230457305,
|
|
"num_tokens": 34402262.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.533929634094238,
|
|
"epoch": 1.70201722938627,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047174905356058857,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.13481214940547942,
|
|
"num_tokens": 34412707.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.501676940917969,
|
|
"epoch": 1.702552303494034,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047173050244626993,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.14371191561222077,
|
|
"num_tokens": 34423203.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.498485040664673,
|
|
"epoch": 1.7030873776017978,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004717119456513857,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13548828661441803,
|
|
"num_tokens": 34433279.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.535174369812012,
|
|
"epoch": 1.7036224517095617,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047169338317647164,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.13515316545963288,
|
|
"num_tokens": 34444601.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.563399600982666,
|
|
"epoch": 1.7041575258173256,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047167481502206383,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.13447251841425895,
|
|
"num_tokens": 34455103.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.5051501274108885,
|
|
"epoch": 1.7046925999250897,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047165624118869834,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.1337140329182148,
|
|
"num_tokens": 34465835.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.628179454803467,
|
|
"epoch": 1.7052276740328536,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004716376616769115,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.13249458372592926,
|
|
"num_tokens": 34476602.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.5752206325531,
|
|
"epoch": 1.7057627481406175,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004716190764872399,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.13616498783230782,
|
|
"num_tokens": 34488026.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.512110948562622,
|
|
"epoch": 1.7062978222483816,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047160048562022006,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.1379050388932228,
|
|
"num_tokens": 34497837.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.486044931411743,
|
|
"epoch": 1.7068328963561452,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004715818890763888,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.13753306791186332,
|
|
"num_tokens": 34507727.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.549686336517334,
|
|
"epoch": 1.7073679704639093,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047156328685628307,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.1331082597374916,
|
|
"num_tokens": 34518595.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.456800651550293,
|
|
"epoch": 1.7079030445716732,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004715446789604401,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.1428788721561432,
|
|
"num_tokens": 34529415.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.492120552062988,
|
|
"epoch": 1.708438118679437,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004715260653893972,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.14320783391594888,
|
|
"num_tokens": 34539593.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.537639427185058,
|
|
"epoch": 1.7089731927872012,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004715074461436917,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.13498525097966194,
|
|
"num_tokens": 34549441.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.523940563201904,
|
|
"epoch": 1.7095082668949648,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047148882122386126,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.14013878330588342,
|
|
"num_tokens": 34560211.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.5388068675994875,
|
|
"epoch": 1.710043341002729,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047147019063044387,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.1317762777209282,
|
|
"num_tokens": 34570479.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.541228723526001,
|
|
"epoch": 1.7105784151104928,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047145155436397726,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.13681796863675116,
|
|
"num_tokens": 34581382.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.5268425941467285,
|
|
"epoch": 1.7111134892182567,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004714329124249996,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.14237518087029458,
|
|
"num_tokens": 34592131.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.565146017074585,
|
|
"epoch": 1.7116485633260208,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004714142648140492,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.13531598448753357,
|
|
"num_tokens": 34604407.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.500683689117432,
|
|
"epoch": 1.7121836374337844,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004713956115316645,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.1376279339194298,
|
|
"num_tokens": 34614842.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.39294056892395,
|
|
"epoch": 1.7127187115415485,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004713769525783841,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.14383530020713806,
|
|
"num_tokens": 34625991.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.4572838306427,
|
|
"epoch": 1.7132537856493124,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004713582879547469,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.13821927458047867,
|
|
"num_tokens": 34637317.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.557463788986206,
|
|
"epoch": 1.7137888597570763,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004713396176612916,
|
|
"loss": 6.2749,
|
|
"mean_token_accuracy": 0.13008446544408797,
|
|
"num_tokens": 34648282.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.550800371170044,
|
|
"epoch": 1.7143239338648404,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004713209416985575,
|
|
"loss": 6.2374,
|
|
"mean_token_accuracy": 0.13565487340092658,
|
|
"num_tokens": 34658638.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.4996785640716555,
|
|
"epoch": 1.714859007972604,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047130226006708375,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.1346914291381836,
|
|
"num_tokens": 34669308.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.495907831192016,
|
|
"epoch": 1.7153940820803681,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047128357276740986,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.13608802780508994,
|
|
"num_tokens": 34679513.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.542607116699219,
|
|
"epoch": 1.715929156188132,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004712648798000754,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.1372469075024128,
|
|
"num_tokens": 34690736.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.527480745315552,
|
|
"epoch": 1.716464230295896,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047124618116562003,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.13630061373114585,
|
|
"num_tokens": 34701272.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.434833574295044,
|
|
"epoch": 1.71699930440366,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004712274768645839,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.14119511395692824,
|
|
"num_tokens": 34712486.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.547205400466919,
|
|
"epoch": 1.7175343785114239,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047120876689750685,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1389646753668785,
|
|
"num_tokens": 34721979.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.502142906188965,
|
|
"epoch": 1.7180694526191878,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004711900512649292,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.13534836918115617,
|
|
"num_tokens": 34733496.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.52419753074646,
|
|
"epoch": 1.7186045267269516,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004711713299673914,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.13493360206484795,
|
|
"num_tokens": 34744223.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.485661029815674,
|
|
"epoch": 1.7191396008347155,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047115260300543407,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.1354266181588173,
|
|
"num_tokens": 34754931.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.456936025619507,
|
|
"epoch": 1.7196746749424796,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004711338703795978,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.14075466692447663,
|
|
"num_tokens": 34766285.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.499564981460571,
|
|
"epoch": 1.7202097490502435,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004711151320904237,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.14091445803642272,
|
|
"num_tokens": 34776979.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.55362229347229,
|
|
"epoch": 1.7207448231580074,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004710963881384527,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.13049443140625955,
|
|
"num_tokens": 34787466.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.589805269241333,
|
|
"epoch": 1.7212798972657715,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000471077638524226,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.1367537833750248,
|
|
"num_tokens": 34797664.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.486291074752808,
|
|
"epoch": 1.7218149713735351,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047105888324828506,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.14723237380385398,
|
|
"num_tokens": 34809082.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.523463010787964,
|
|
"epoch": 1.7223500454812992,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047104012231117143,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.1389696106314659,
|
|
"num_tokens": 34820223.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.435459613800049,
|
|
"epoch": 1.722885119589063,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047102135571342683,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.1369843900203705,
|
|
"num_tokens": 34830428.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.462934303283691,
|
|
"epoch": 1.723420193696827,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047100258345559307,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.1307723380625248,
|
|
"num_tokens": 34842787.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.507791662216187,
|
|
"epoch": 1.723955267804591,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004709838055382123,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.13265354037284852,
|
|
"num_tokens": 34854323.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.4878136157989506,
|
|
"epoch": 1.7244903419123547,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004709650219618266,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.13792682066559792,
|
|
"num_tokens": 34865279.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.48901333808899,
|
|
"epoch": 1.7250254160201188,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004709462327269785,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.13436542078852654,
|
|
"num_tokens": 34875951.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.490832757949829,
|
|
"epoch": 1.7255604901278827,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004709274378342105,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.1372871771454811,
|
|
"num_tokens": 34885815.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.560395050048828,
|
|
"epoch": 1.7260955642356466,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047090863728406517,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.13472879230976104,
|
|
"num_tokens": 34897158.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.59221568107605,
|
|
"epoch": 1.7266306383434107,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004708898310770856,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.1327106237411499,
|
|
"num_tokens": 34907815.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.531020069122315,
|
|
"epoch": 1.7271657124511743,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004708710192138146,
|
|
"loss": 6.237,
|
|
"mean_token_accuracy": 0.1372152455151081,
|
|
"num_tokens": 34918820.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.56586446762085,
|
|
"epoch": 1.7277007865589384,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004708522016947954,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.13564084842801094,
|
|
"num_tokens": 34929998.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.4926958084106445,
|
|
"epoch": 1.7282358606667023,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004708333785205715,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.14865463376045226,
|
|
"num_tokens": 34940989.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.5131425857543945,
|
|
"epoch": 1.7287709347744662,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004708145496916862,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.13459616228938104,
|
|
"num_tokens": 34952433.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.573882055282593,
|
|
"epoch": 1.7293060088822303,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047079571520868344,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.1309241198003292,
|
|
"num_tokens": 34963074.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.493603801727295,
|
|
"epoch": 1.729841082989994,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047077687507210674,
|
|
"loss": 6.2163,
|
|
"mean_token_accuracy": 0.1405037112534046,
|
|
"num_tokens": 34974315.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.457288455963135,
|
|
"epoch": 1.730376157097758,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004707580292825004,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.15218150988221169,
|
|
"num_tokens": 34985059.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.480514097213745,
|
|
"epoch": 1.730911231205522,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004707391778404085,
|
|
"loss": 6.3326,
|
|
"mean_token_accuracy": 0.12655592635273932,
|
|
"num_tokens": 34996156.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.564816570281982,
|
|
"epoch": 1.7314463053132858,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004707203207463752,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.13536330088973045,
|
|
"num_tokens": 35007410.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.5748625755310055,
|
|
"epoch": 1.73198137942105,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004707014580009453,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.14098969027400016,
|
|
"num_tokens": 35018492.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.557524681091309,
|
|
"epoch": 1.7325164535288138,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004706825896046632,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.1356653481721878,
|
|
"num_tokens": 35029923.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.505240440368652,
|
|
"epoch": 1.7330515276365777,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047066371555807386,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.13501440957188607,
|
|
"num_tokens": 35040370.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.526643562316894,
|
|
"epoch": 1.7335866017443415,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004706448358617222,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.1304975025355816,
|
|
"num_tokens": 35051414.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.581493234634399,
|
|
"epoch": 1.7341216758521054,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047062595051615343,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.14306259751319886,
|
|
"num_tokens": 35061015.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.513972759246826,
|
|
"epoch": 1.7346567499598695,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004706070595219128,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.1341689184308052,
|
|
"num_tokens": 35071757.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.516111135482788,
|
|
"epoch": 1.7351918240676334,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047058816287954587,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.13728854209184646,
|
|
"num_tokens": 35082912.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.561192560195923,
|
|
"epoch": 1.7357268981753973,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047056926058959813,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.1454016536474228,
|
|
"num_tokens": 35094103.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.521594715118408,
|
|
"epoch": 1.7362619722831614,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004705503526526155,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.13738676756620408,
|
|
"num_tokens": 35105960.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.445529317855835,
|
|
"epoch": 1.736797046390925,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047053143906914405,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.14483401402831078,
|
|
"num_tokens": 35116482.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.52421383857727,
|
|
"epoch": 1.7373321204986891,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047051251983972966,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.1380905956029892,
|
|
"num_tokens": 35127976.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.5142865657806395,
|
|
"epoch": 1.737867194606453,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004704935949649187,
|
|
"loss": 6.2711,
|
|
"mean_token_accuracy": 0.13424955755472184,
|
|
"num_tokens": 35137712.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.436436986923217,
|
|
"epoch": 1.7384022687142169,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004704746644452577,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.13780921846628189,
|
|
"num_tokens": 35148524.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.491331481933594,
|
|
"epoch": 1.738937342821981,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047045572828129323,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.13721957728266715,
|
|
"num_tokens": 35159080.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.366399574279785,
|
|
"epoch": 1.7394724169297446,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000470436786473572,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.13959982618689537,
|
|
"num_tokens": 35169993.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.465382099151611,
|
|
"epoch": 1.7400074910375087,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004704178390226411,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.13708374574780463,
|
|
"num_tokens": 35181413.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.476068544387817,
|
|
"epoch": 1.7405425651452726,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047039888592904753,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.14310968890786172,
|
|
"num_tokens": 35191600.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.515720224380493,
|
|
"epoch": 1.7410776392530365,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047037992719333864,
|
|
"loss": 6.2098,
|
|
"mean_token_accuracy": 0.13760415241122245,
|
|
"num_tokens": 35202535.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.517277812957763,
|
|
"epoch": 1.7416127133608006,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047036096281606176,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.130896158516407,
|
|
"num_tokens": 35214798.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.5141020774841305,
|
|
"epoch": 1.7421477874685642,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047034199279776456,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.1439959242939949,
|
|
"num_tokens": 35224870.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.490610218048095,
|
|
"epoch": 1.7426828615763283,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004703230171389948,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.1389573745429516,
|
|
"num_tokens": 35235408.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.441397047042846,
|
|
"epoch": 1.7432179356840922,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047030403584030024,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.14157229885458947,
|
|
"num_tokens": 35246310.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.481639003753662,
|
|
"epoch": 1.743753009791856,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004702850489022292,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.13529093638062478,
|
|
"num_tokens": 35257027.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.591700649261474,
|
|
"epoch": 1.7442880838996202,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047026605632532976,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.13825585916638375,
|
|
"num_tokens": 35267397.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.4336450576782225,
|
|
"epoch": 1.7448231580073839,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047024705811015045,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.14259003922343255,
|
|
"num_tokens": 35278775.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.446195077896118,
|
|
"epoch": 1.745358232115148,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004702280542572397,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.14629908427596092,
|
|
"num_tokens": 35288818.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.5565478801727295,
|
|
"epoch": 1.7458933062229118,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004702090447671464,
|
|
"loss": 6.317,
|
|
"mean_token_accuracy": 0.1260501079261303,
|
|
"num_tokens": 35299385.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.503725910186768,
|
|
"epoch": 1.7464283803306757,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004701900296404193,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.14620715752243996,
|
|
"num_tokens": 35310626.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.545715284347534,
|
|
"epoch": 1.7469634544384398,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004701710088776075,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.13202030956745148,
|
|
"num_tokens": 35321615.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.573356199264526,
|
|
"epoch": 1.7474985285462037,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047015198247926025,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.13973275944590569,
|
|
"num_tokens": 35332012.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.562140321731567,
|
|
"epoch": 1.7480336026539676,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000470132950445927,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.12587928250432015,
|
|
"num_tokens": 35342153.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.530314254760742,
|
|
"epoch": 1.7485686767617317,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004701139127781571,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.13639529570937156,
|
|
"num_tokens": 35352858.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.514222860336304,
|
|
"epoch": 1.7491037508694953,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004700948694765005,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.14512947499752044,
|
|
"num_tokens": 35363489.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.55261082649231,
|
|
"epoch": 1.7496388249772594,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004700758205415069,
|
|
"loss": 6.3504,
|
|
"mean_token_accuracy": 0.13262177556753157,
|
|
"num_tokens": 35375816.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.506987237930298,
|
|
"epoch": 1.7501738990850233,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00047005676597372645,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.13197326436638832,
|
|
"num_tokens": 35386708.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.4838512420654295,
|
|
"epoch": 1.7507089731927872,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047003770577370925,
|
|
"loss": 6.2964,
|
|
"mean_token_accuracy": 0.13025422096252443,
|
|
"num_tokens": 35397734.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.612907648086548,
|
|
"epoch": 1.7512440473005513,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047001863994200574,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.13965339437127114,
|
|
"num_tokens": 35408870.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.496535873413086,
|
|
"epoch": 1.751779121408315,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004699995684791664,
|
|
"loss": 6.1831,
|
|
"mean_token_accuracy": 0.1359889529645443,
|
|
"num_tokens": 35419498.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.436664390563965,
|
|
"epoch": 1.752314195516079,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046998049138574177,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.14066151529550552,
|
|
"num_tokens": 35430690.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.455047512054444,
|
|
"epoch": 1.752849269623843,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000469961408662283,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.14213127717375756,
|
|
"num_tokens": 35441007.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.447874355316162,
|
|
"epoch": 1.7533843437316068,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000469942320309341,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.14288512840867043,
|
|
"num_tokens": 35453202.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.465952157974243,
|
|
"epoch": 1.7539194178393709,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046992322632746677,
|
|
"loss": 6.227,
|
|
"mean_token_accuracy": 0.14558738470077515,
|
|
"num_tokens": 35463303.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.510498428344727,
|
|
"epoch": 1.7544544919471345,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046990412671721186,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.14194708690047264,
|
|
"num_tokens": 35474104.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.53613052368164,
|
|
"epoch": 1.7549895660548986,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004698850214791276,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.1344727098941803,
|
|
"num_tokens": 35486412.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.533957195281983,
|
|
"epoch": 1.7555246401626625,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004698659106137658,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.1366186335682869,
|
|
"num_tokens": 35497505.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.578169441223144,
|
|
"epoch": 1.7560597142704264,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 0.0004698467941216782,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.13750482201576233,
|
|
"num_tokens": 35508397.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.60500431060791,
|
|
"epoch": 1.7565947883781905,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046982767200341675,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.13072726875543594,
|
|
"num_tokens": 35520261.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.531397581100464,
|
|
"epoch": 1.7571298624859542,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046980854425953365,
|
|
"loss": 6.1989,
|
|
"mean_token_accuracy": 0.13409352228045462,
|
|
"num_tokens": 35531816.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.530423879623413,
|
|
"epoch": 1.7576649365937183,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004697894108905813,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.13641773015260697,
|
|
"num_tokens": 35542233.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.508632040023803,
|
|
"epoch": 1.7582000107014821,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046977027189711197,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.1387732908129692,
|
|
"num_tokens": 35552881.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.4908287048339846,
|
|
"epoch": 1.758735084809246,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004697511272796785,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.13812109753489493,
|
|
"num_tokens": 35562392.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.495633935928344,
|
|
"epoch": 1.75927015891701,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004697319770388335,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.13243331611156464,
|
|
"num_tokens": 35574587.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.49248194694519,
|
|
"epoch": 1.759805233024774,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004697128211751301,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.1406071349978447,
|
|
"num_tokens": 35585178.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.460205698013306,
|
|
"epoch": 1.7603403071325379,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004696936596891213,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.13646092414855956,
|
|
"num_tokens": 35595501.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.509033679962158,
|
|
"epoch": 1.7608753812403017,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004696744925813605,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.13326306268572807,
|
|
"num_tokens": 35606794.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.5370752811431885,
|
|
"epoch": 1.7614104553480656,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004696553198524011,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.1357016831636429,
|
|
"num_tokens": 35618732.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.498097991943359,
|
|
"epoch": 1.7619455294558297,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004696361415027966,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.1408173367381096,
|
|
"num_tokens": 35629802.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.475509119033814,
|
|
"epoch": 1.7624806035635936,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004696169575331009,
|
|
"loss": 6.2751,
|
|
"mean_token_accuracy": 0.13238577544689178,
|
|
"num_tokens": 35640826.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.536092138290405,
|
|
"epoch": 1.7630156776713575,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000469597767943868,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.13249727264046668,
|
|
"num_tokens": 35651613.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.469944190979004,
|
|
"epoch": 1.7635507517791216,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004695785727356517,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.13989657014608384,
|
|
"num_tokens": 35662334.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.536354923248291,
|
|
"epoch": 1.7640858258868852,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004695593719090066,
|
|
"loss": 6.2903,
|
|
"mean_token_accuracy": 0.13316132500767708,
|
|
"num_tokens": 35673466.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.53029580116272,
|
|
"epoch": 1.7646208999946493,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004695401654644869,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.13935657143592833,
|
|
"num_tokens": 35684708.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.461583137512207,
|
|
"epoch": 1.7651559741024132,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046952095340264727,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.14150693714618684,
|
|
"num_tokens": 35694888.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.519178009033203,
|
|
"epoch": 1.765691048210177,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046950173572404255,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.13781533762812614,
|
|
"num_tokens": 35704844.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.50765905380249,
|
|
"epoch": 1.7662261223179412,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004694825124292275,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.13843735828995704,
|
|
"num_tokens": 35715468.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.509899616241455,
|
|
"epoch": 1.7667611964257048,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004694632835187572,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.13584157973527908,
|
|
"num_tokens": 35725542.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.535692405700684,
|
|
"epoch": 1.767296270533469,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046944404899318685,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.1380226269364357,
|
|
"num_tokens": 35737032.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.53953366279602,
|
|
"epoch": 1.7678313446412328,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000469424808853072,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.1371114008128643,
|
|
"num_tokens": 35747742.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.465522813796997,
|
|
"epoch": 1.7683664187489967,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004694055630989681,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.13816195577383042,
|
|
"num_tokens": 35757795.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.460051870346069,
|
|
"epoch": 1.7689014928567608,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004693863117314308,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.1464919239282608,
|
|
"num_tokens": 35767962.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.489283609390259,
|
|
"epoch": 1.7694365669645244,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004693670547510161,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.13113914132118226,
|
|
"num_tokens": 35778564.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.5667181491851805,
|
|
"epoch": 1.7699716410722885,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046934779215828006,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.14195646718144417,
|
|
"num_tokens": 35788417.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.496956443786621,
|
|
"epoch": 1.7705067151800524,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004693285239537788,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.13466702327132224,
|
|
"num_tokens": 35799724.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.557682847976684,
|
|
"epoch": 1.7710417892878163,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046930925013806873,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.1405516743659973,
|
|
"num_tokens": 35810306.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.579492568969727,
|
|
"epoch": 1.7715768633955804,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004692899707117064,
|
|
"loss": 6.2244,
|
|
"mean_token_accuracy": 0.13569827675819396,
|
|
"num_tokens": 35821103.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.487555932998657,
|
|
"epoch": 1.772111937503344,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004692706856752484,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.14339053258299828,
|
|
"num_tokens": 35832271.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.505621671676636,
|
|
"epoch": 1.7726470116111082,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046925139502925167,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.13330883160233498,
|
|
"num_tokens": 35843875.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.5568187713623045,
|
|
"epoch": 1.773182085718872,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004692320987742732,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.13371218591928483,
|
|
"num_tokens": 35854085.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.614805221557617,
|
|
"epoch": 1.773717159826636,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004692127969108702,
|
|
"loss": 6.2952,
|
|
"mean_token_accuracy": 0.13505346402525903,
|
|
"num_tokens": 35864777.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.561323356628418,
|
|
"epoch": 1.7742522339344,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004691934894396,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.13224760219454765,
|
|
"num_tokens": 35876822.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.579904937744141,
|
|
"epoch": 1.774787308042164,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046917417636102,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.14425080120563508,
|
|
"num_tokens": 35886997.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.514540147781372,
|
|
"epoch": 1.7753223821499278,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000469154857675688,
|
|
"loss": 6.2636,
|
|
"mean_token_accuracy": 0.13917053490877151,
|
|
"num_tokens": 35897871.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.437257766723633,
|
|
"epoch": 1.7758574562576916,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004691355333841617,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.14573031067848205,
|
|
"num_tokens": 35908791.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.539524126052856,
|
|
"epoch": 1.7763925303654555,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004691162034869993,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.13325378373265268,
|
|
"num_tokens": 35919436.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.599057722091675,
|
|
"epoch": 1.7769276044732196,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004690968679847586,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.14074254035949707,
|
|
"num_tokens": 35929851.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.528794050216675,
|
|
"epoch": 1.7774626785809835,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004690775268779983,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.13964374586939812,
|
|
"num_tokens": 35940271.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.45616717338562,
|
|
"epoch": 1.7779977526887474,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004690581801672765,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.12977162078022958,
|
|
"num_tokens": 35951460.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.472211790084839,
|
|
"epoch": 1.7785328267965115,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046903882785315215,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.13858510851860045,
|
|
"num_tokens": 35961530.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.500081157684326,
|
|
"epoch": 1.7790679009042751,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004690194699361839,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.15004311949014665,
|
|
"num_tokens": 35971085.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.478543996810913,
|
|
"epoch": 1.7796029750120392,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00046900010641693073,
|
|
"loss": 6.2366,
|
|
"mean_token_accuracy": 0.1306772880256176,
|
|
"num_tokens": 35981393.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 6.47922649383545,
|
|
"epoch": 1.7801380491198031,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004689807372959517,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.13808380663394929,
|
|
"num_tokens": 35992847.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.471188974380493,
|
|
"epoch": 1.780673123227567,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046896136257380615,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.1351441413164139,
|
|
"num_tokens": 36002991.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.500436925888062,
|
|
"epoch": 1.781208197335331,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046894198225105356,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.1417154736816883,
|
|
"num_tokens": 36015140.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.471897602081299,
|
|
"epoch": 1.7817432714430947,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004689225963282534,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.1382371798157692,
|
|
"num_tokens": 36026014.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.607560014724731,
|
|
"epoch": 1.7822783455508588,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004689032048059656,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.13198384642601013,
|
|
"num_tokens": 36035926.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.506697368621826,
|
|
"epoch": 1.7828134196586227,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046888380768475,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.14066673815250397,
|
|
"num_tokens": 36046406.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.467809438705444,
|
|
"epoch": 1.7833484937663866,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004688644049651667,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.14082129970192908,
|
|
"num_tokens": 36056440.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.491926813125611,
|
|
"epoch": 1.7838835678741507,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046884499664777586,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.13191643580794335,
|
|
"num_tokens": 36067244.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.499668931961059,
|
|
"epoch": 1.7844186419819144,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004688255827331381,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14353570342063904,
|
|
"num_tokens": 36078110.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.489797687530517,
|
|
"epoch": 1.7849537160896785,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004688061632218137,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.13878354877233506,
|
|
"num_tokens": 36088805.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.5043909549713135,
|
|
"epoch": 1.7854887901974423,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00046878673811436375,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.14111408069729806,
|
|
"num_tokens": 36098619.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.577878761291504,
|
|
"epoch": 1.7860238643052062,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004687673074113489,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.13543611243367196,
|
|
"num_tokens": 36110604.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.630790567398071,
|
|
"epoch": 1.7865589384129703,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004687478711133303,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.13638934642076492,
|
|
"num_tokens": 36121669.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.3852990627288815,
|
|
"epoch": 1.787094012520734,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004687284292208691,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.15399005711078645,
|
|
"num_tokens": 36132165.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.428806734085083,
|
|
"epoch": 1.787629086628498,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046870898173452676,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.140548275411129,
|
|
"num_tokens": 36142830.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.477385234832764,
|
|
"epoch": 1.788164160736262,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004686895286548648,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.1369605541229248,
|
|
"num_tokens": 36153812.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.511514568328858,
|
|
"epoch": 1.7886992348440258,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046867006998244494,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.1401585191488266,
|
|
"num_tokens": 36163599.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.5018744468688965,
|
|
"epoch": 1.78923430895179,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046865060571782896,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.13398018553853036,
|
|
"num_tokens": 36173815.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.63695878982544,
|
|
"epoch": 1.7897693830595538,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046863113586157894,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.1324778087437153,
|
|
"num_tokens": 36186131.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.553009986877441,
|
|
"epoch": 1.7903044571673177,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004686116604142572,
|
|
"loss": 6.1798,
|
|
"mean_token_accuracy": 0.14324358105659485,
|
|
"num_tokens": 36196084.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.467611074447632,
|
|
"epoch": 1.7908395312750816,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004685921793764259,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.14632472023367882,
|
|
"num_tokens": 36206948.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.550565099716186,
|
|
"epoch": 1.7913746053828454,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004685726927486476,
|
|
"loss": 6.286,
|
|
"mean_token_accuracy": 0.1330634005367756,
|
|
"num_tokens": 36217202.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.596937656402588,
|
|
"epoch": 1.7919096794906095,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046855320053148505,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.1310865469276905,
|
|
"num_tokens": 36227914.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.573777103424073,
|
|
"epoch": 1.7924447535983734,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000468533702725501,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.13632940426468848,
|
|
"num_tokens": 36239344.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.520642805099487,
|
|
"epoch": 1.7929798277061373,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046851419933125843,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.13871801942586898,
|
|
"num_tokens": 36250438.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.513595962524414,
|
|
"epoch": 1.7935149018139014,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004684946903493206,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.13100792467594147,
|
|
"num_tokens": 36260545.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.419894027709961,
|
|
"epoch": 1.794049975921665,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004684751757802508,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.14160364121198654,
|
|
"num_tokens": 36272577.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.516346645355225,
|
|
"epoch": 1.7945850500294291,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00046845565562461243,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14187682345509528,
|
|
"num_tokens": 36284161.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.527055025100708,
|
|
"epoch": 1.795120124137193,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046843612988296926,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.13396796360611915,
|
|
"num_tokens": 36294910.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.552798748016357,
|
|
"epoch": 1.795655198244957,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004684165985558849,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.13618710413575172,
|
|
"num_tokens": 36305388.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.4872008800506595,
|
|
"epoch": 1.796190272352721,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004683970616439236,
|
|
"loss": 6.2451,
|
|
"mean_token_accuracy": 0.145309716463089,
|
|
"num_tokens": 36316696.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.467041683197022,
|
|
"epoch": 1.7967253464604847,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004683775191476492,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.14676120951771737,
|
|
"num_tokens": 36327246.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.554820346832275,
|
|
"epoch": 1.7972604205682488,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004683579710676262,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.1309548445045948,
|
|
"num_tokens": 36338089.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.50324125289917,
|
|
"epoch": 1.7977954946760126,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046833841740441886,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.14037265926599501,
|
|
"num_tokens": 36350285.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.577779293060303,
|
|
"epoch": 1.7983305687837765,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004683188581585919,
|
|
"loss": 6.2266,
|
|
"mean_token_accuracy": 0.13420821651816367,
|
|
"num_tokens": 36360431.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.581452989578247,
|
|
"epoch": 1.7988656428915406,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004682992933307101,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.14042315185070037,
|
|
"num_tokens": 36371257.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.424906253814697,
|
|
"epoch": 1.7994007169993043,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046827972292133835,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14297413006424903,
|
|
"num_tokens": 36382613.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.5323937892913815,
|
|
"epoch": 1.7999357911070684,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004682601469310418,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.1366001270711422,
|
|
"num_tokens": 36393799.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.505597305297852,
|
|
"epoch": 1.8004708652148322,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046824056536038565,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.13767699897289276,
|
|
"num_tokens": 36403914.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.4454141616821286,
|
|
"epoch": 1.8010059393225961,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004682209782099353,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.13994815796613694,
|
|
"num_tokens": 36415022.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.492913055419922,
|
|
"epoch": 1.8015410134303602,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046820138548025634,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.144903202354908,
|
|
"num_tokens": 36426155.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.520499753952026,
|
|
"epoch": 1.8020760875381239,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046818178717191464,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.1381929524242878,
|
|
"num_tokens": 36437345.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.520294523239135,
|
|
"epoch": 1.802611161645888,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004681621832854759,
|
|
"loss": 6.2415,
|
|
"mean_token_accuracy": 0.1451305240392685,
|
|
"num_tokens": 36448634.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.482553720474243,
|
|
"epoch": 1.8031462357536518,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046814257382150627,
|
|
"loss": 6.2023,
|
|
"mean_token_accuracy": 0.14824908673763276,
|
|
"num_tokens": 36458870.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.526421070098877,
|
|
"epoch": 1.8036813098614157,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00046812295878057193,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.1356567807495594,
|
|
"num_tokens": 36469865.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.506421089172363,
|
|
"epoch": 1.8042163839691798,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004681033381632393,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.13496703803539276,
|
|
"num_tokens": 36480502.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.568086290359497,
|
|
"epoch": 1.8047514580769437,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004680837119700749,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.13847601637244225,
|
|
"num_tokens": 36492356.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 6.469596433639526,
|
|
"epoch": 1.8052865321847076,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046806408020164553,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.13677831664681434,
|
|
"num_tokens": 36504659.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.4850420475006105,
|
|
"epoch": 1.8058216062924715,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046804444285851796,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.13537785932421684,
|
|
"num_tokens": 36516042.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.583554267883301,
|
|
"epoch": 1.8063566804002353,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046802479994125916,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.13417793661355973,
|
|
"num_tokens": 36527417.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.517843437194824,
|
|
"epoch": 1.8068917545079994,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004680051514504364,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.1450719028711319,
|
|
"num_tokens": 36538182.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.477873516082764,
|
|
"epoch": 1.8074268286157633,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004679854973866171,
|
|
"loss": 6.2986,
|
|
"mean_token_accuracy": 0.13775768205523492,
|
|
"num_tokens": 36549835.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.45180606842041,
|
|
"epoch": 1.8079619027235272,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046796583775036857,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14810781925916672,
|
|
"num_tokens": 36560238.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.533177089691162,
|
|
"epoch": 1.8084969768312913,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046794617254225865,
|
|
"loss": 6.2267,
|
|
"mean_token_accuracy": 0.14068657979369165,
|
|
"num_tokens": 36571267.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.52840747833252,
|
|
"epoch": 1.809032050939055,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004679265017628551,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.14016860574483872,
|
|
"num_tokens": 36582174.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.566719913482666,
|
|
"epoch": 1.809567125046819,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004679068254127259,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.1399499513208866,
|
|
"num_tokens": 36593054.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.543996334075928,
|
|
"epoch": 1.810102199154583,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046788714349243923,
|
|
"loss": 6.2411,
|
|
"mean_token_accuracy": 0.13865780755877494,
|
|
"num_tokens": 36603962.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.538334846496582,
|
|
"epoch": 1.8106372732623468,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004678674560025634,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.13803598582744597,
|
|
"num_tokens": 36616003.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.555250835418701,
|
|
"epoch": 1.811172347370111,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004678477629436669,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.1259820744395256,
|
|
"num_tokens": 36627189.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.563538408279419,
|
|
"epoch": 1.8117074214778746,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004678280643163184,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.1305183358490467,
|
|
"num_tokens": 36637756.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.52625207901001,
|
|
"epoch": 1.8122424955856387,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004678083601210865,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.14015371575951577,
|
|
"num_tokens": 36648946.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.581425952911377,
|
|
"epoch": 1.8127775696934025,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004677886503585404,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.13917845040559768,
|
|
"num_tokens": 36660184.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.549855661392212,
|
|
"epoch": 1.8133126438011664,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046776893502924904,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.13336536437273025,
|
|
"num_tokens": 36671346.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.584742641448974,
|
|
"epoch": 1.8138477179089305,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004677492141337818,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.13786211013793945,
|
|
"num_tokens": 36682917.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.547979497909546,
|
|
"epoch": 1.8143827920166942,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004677294876727081,
|
|
"loss": 6.305,
|
|
"mean_token_accuracy": 0.12805510684847832,
|
|
"num_tokens": 36693577.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.611744832992554,
|
|
"epoch": 1.8149178661244583,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004677097556465975,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.13698212802410126,
|
|
"num_tokens": 36704915.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.596394205093384,
|
|
"epoch": 1.8154529402322221,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046769001805601983,
|
|
"loss": 6.3643,
|
|
"mean_token_accuracy": 0.12665193229913713,
|
|
"num_tokens": 36716086.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.468046569824219,
|
|
"epoch": 1.815988014339986,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046767027490154494,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.13091371804475785,
|
|
"num_tokens": 36726110.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.549561405181885,
|
|
"epoch": 1.8165230884477501,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046765052618374296,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.1403437852859497,
|
|
"num_tokens": 36735846.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.515966844558716,
|
|
"epoch": 1.8170581625555138,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000467630771903184,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.1386712908744812,
|
|
"num_tokens": 36746851.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.525477933883667,
|
|
"epoch": 1.8175932366632779,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004676110120604387,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.13791928589344024,
|
|
"num_tokens": 36758032.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.572210121154785,
|
|
"epoch": 1.8181283107710418,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004675912466560775,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.14123788774013518,
|
|
"num_tokens": 36768939.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.577953958511353,
|
|
"epoch": 1.8186633848788056,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00046757147569067106,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13176384195685387,
|
|
"num_tokens": 36780338.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.507962799072265,
|
|
"epoch": 1.8191984589865697,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004675516991647903,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.13604221120476723,
|
|
"num_tokens": 36791384.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.4729632377624515,
|
|
"epoch": 1.8197335330943336,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046753191707900636,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.1321197956800461,
|
|
"num_tokens": 36802460.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.536910820007324,
|
|
"epoch": 1.8202686072020975,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046751212943389026,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.13371748030185698,
|
|
"num_tokens": 36813599.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.563910818099975,
|
|
"epoch": 1.8208036813098614,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004674923362300135,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.1385357163846493,
|
|
"num_tokens": 36823100.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.547238874435425,
|
|
"epoch": 1.8213387554176252,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046747253746794767,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13121092841029167,
|
|
"num_tokens": 36834245.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.488923406600952,
|
|
"epoch": 1.8218738295253893,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046745273314826425,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.1463228791952133,
|
|
"num_tokens": 36844126.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.494448804855347,
|
|
"epoch": 1.8224089036331532,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004674329232715353,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.14492320418357849,
|
|
"num_tokens": 36855451.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.573440742492676,
|
|
"epoch": 1.822943977740917,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004674131078383327,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.13452650755643844,
|
|
"num_tokens": 36864994.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.537502956390381,
|
|
"epoch": 1.8234790518486812,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004673932868492286,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.13883368894457818,
|
|
"num_tokens": 36875131.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.553777265548706,
|
|
"epoch": 1.8240141259564449,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046737346030479546,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.13633736670017244,
|
|
"num_tokens": 36884789.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.493189573287964,
|
|
"epoch": 1.824549200064209,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046735362820560564,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.13749801069498063,
|
|
"num_tokens": 36895199.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.533320331573487,
|
|
"epoch": 1.8250842741719728,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004673337905522318,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.13339270278811455,
|
|
"num_tokens": 36906495.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.4933160781860355,
|
|
"epoch": 1.8256193482797367,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046731394734524686,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.13503750115633012,
|
|
"num_tokens": 36916907.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.482892751693726,
|
|
"epoch": 1.8261544223875008,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046729409858522363,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.13926137164235114,
|
|
"num_tokens": 36927872.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.506586217880249,
|
|
"epoch": 1.8266894964952645,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004672742442727354,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.13534507304430007,
|
|
"num_tokens": 36938575.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.421038293838501,
|
|
"epoch": 1.8272245706030286,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046725438440835536,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.14953663647174836,
|
|
"num_tokens": 36949179.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.481749391555786,
|
|
"epoch": 1.8277596447107924,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.000467234518992657,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.1452023506164551,
|
|
"num_tokens": 36959164.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.567118787765503,
|
|
"epoch": 1.8282947188185563,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046721464802621383,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.13393226340413095,
|
|
"num_tokens": 36969091.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.562323141098022,
|
|
"epoch": 1.8288297929263204,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00046719477150959984,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13492230623960494,
|
|
"num_tokens": 36980481.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.547414779663086,
|
|
"epoch": 1.829364867034084,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00046717488944338873,
|
|
"loss": 6.2198,
|
|
"mean_token_accuracy": 0.13818060755729675,
|
|
"num_tokens": 36991349.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.537697601318359,
|
|
"epoch": 1.8298999411418482,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046715500182815473,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.13604205325245858,
|
|
"num_tokens": 37002803.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.5742217063903805,
|
|
"epoch": 1.830435015249612,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046713510866447204,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.13930715918540953,
|
|
"num_tokens": 37013578.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.480613660812378,
|
|
"epoch": 1.830970089357376,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004671152099529152,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.14176603630185128,
|
|
"num_tokens": 37024012.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.431010293960571,
|
|
"epoch": 1.83150516346514,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046709530569405855,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.1426972985267639,
|
|
"num_tokens": 37034149.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.464472866058349,
|
|
"epoch": 1.8320402375729037,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004670753958884769,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14506796300411223,
|
|
"num_tokens": 37045669.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.518822431564331,
|
|
"epoch": 1.8325753116806678,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046705548053674524,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.13655512034893036,
|
|
"num_tokens": 37056611.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.462148952484131,
|
|
"epoch": 1.8331103857884317,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046703555963943855,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.13259709179401397,
|
|
"num_tokens": 37067387.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.603019952774048,
|
|
"epoch": 1.8336454598961955,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046701563319713214,
|
|
"loss": 6.3093,
|
|
"mean_token_accuracy": 0.1327134758234024,
|
|
"num_tokens": 37078151.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.576609134674072,
|
|
"epoch": 1.8341805340039596,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046699570121040126,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.13562018275260926,
|
|
"num_tokens": 37088219.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.467413425445557,
|
|
"epoch": 1.8347156081117235,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004669757636798215,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.14191140681505204,
|
|
"num_tokens": 37098769.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.534985876083374,
|
|
"epoch": 1.8352506822194874,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004669558206059684,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.1294104613363743,
|
|
"num_tokens": 37110716.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.538275527954101,
|
|
"epoch": 1.8357857563272513,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004669358719894181,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.13603334054350852,
|
|
"num_tokens": 37122785.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.480508327484131,
|
|
"epoch": 1.8363208304350152,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004669159178307465,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.13679319992661476,
|
|
"num_tokens": 37133308.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.407593870162964,
|
|
"epoch": 1.8368559045427792,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004668959581305296,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.14222812801599502,
|
|
"num_tokens": 37143916.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.46957540512085,
|
|
"epoch": 1.8373909786505431,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046687599288934394,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.13823763206601142,
|
|
"num_tokens": 37154335.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.529861164093018,
|
|
"epoch": 1.837926052758307,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000466856022107766,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.1369415447115898,
|
|
"num_tokens": 37164116.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.50433087348938,
|
|
"epoch": 1.838461126866071,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046683604578637235,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.13340672180056573,
|
|
"num_tokens": 37175407.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.446762371063232,
|
|
"epoch": 1.8389962009738348,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046681606392573975,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.13607601448893547,
|
|
"num_tokens": 37185339.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.572753381729126,
|
|
"epoch": 1.8395312750815989,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004667960765264454,
|
|
"loss": 6.2672,
|
|
"mean_token_accuracy": 0.1362226776778698,
|
|
"num_tokens": 37195145.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.537802410125733,
|
|
"epoch": 1.8400663491893627,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004667760835890662,
|
|
"loss": 6.2779,
|
|
"mean_token_accuracy": 0.13509466499090195,
|
|
"num_tokens": 37206454.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.481271600723266,
|
|
"epoch": 1.8406014232971266,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046675608511417957,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.14024367779493332,
|
|
"num_tokens": 37216646.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.436294937133789,
|
|
"epoch": 1.8411364974048907,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046673608110236293,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.14751357436180115,
|
|
"num_tokens": 37227368.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.5536376476287845,
|
|
"epoch": 1.8416715715126544,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004667160715541939,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.13471471667289733,
|
|
"num_tokens": 37238150.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.509008359909058,
|
|
"epoch": 1.8422066456204185,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046669605647025014,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.13703424036502837,
|
|
"num_tokens": 37249534.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.5630042552948,
|
|
"epoch": 1.8427417197281823,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004666760358511098,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1386088714003563,
|
|
"num_tokens": 37260633.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.573452997207641,
|
|
"epoch": 1.8432767938359462,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046665600969735086,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.13207167088985444,
|
|
"num_tokens": 37271978.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.4870954036712645,
|
|
"epoch": 1.8438118679437103,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004666359780095515,
|
|
"loss": 6.1157,
|
|
"mean_token_accuracy": 0.14051857218146324,
|
|
"num_tokens": 37284130.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.54051194190979,
|
|
"epoch": 1.844346942051474,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004666159407882902,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.1303947575390339,
|
|
"num_tokens": 37295648.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.5121325016021725,
|
|
"epoch": 1.844882016159238,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004665958980341456,
|
|
"loss": 6.258,
|
|
"mean_token_accuracy": 0.13691130727529527,
|
|
"num_tokens": 37306715.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.534123659133911,
|
|
"epoch": 1.845417090267002,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046657584974769636,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.13898625373840331,
|
|
"num_tokens": 37317605.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.527424573898315,
|
|
"epoch": 1.8459521643747658,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004665557959295213,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.14265326410531998,
|
|
"num_tokens": 37328898.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.477344179153443,
|
|
"epoch": 1.84648723848253,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046653573658019963,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.1402975931763649,
|
|
"num_tokens": 37340108.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.543744611740112,
|
|
"epoch": 1.8470223125902936,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046651567170031053,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.13802868351340294,
|
|
"num_tokens": 37351773.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.494388151168823,
|
|
"epoch": 1.8475573866980577,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004664956012904332,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.13731587156653405,
|
|
"num_tokens": 37362748.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.510460567474365,
|
|
"epoch": 1.8480924608058216,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004664755253511474,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.13541723787784576,
|
|
"num_tokens": 37373487.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.5544881343841555,
|
|
"epoch": 1.8486275349135854,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004664554438830326,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.13703005909919738,
|
|
"num_tokens": 37383302.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.565484619140625,
|
|
"epoch": 1.8491626090213495,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004664353568866689,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.13908227831125258,
|
|
"num_tokens": 37393085.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.562853622436523,
|
|
"epoch": 1.8496976831291134,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000466415264362636,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.13739827275276184,
|
|
"num_tokens": 37403774.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.544837522506714,
|
|
"epoch": 1.8502327572368773,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046639516631151435,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.14629105776548385,
|
|
"num_tokens": 37414356.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.481632375717163,
|
|
"epoch": 1.8507678313446412,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00046637506273388416,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.1359451398253441,
|
|
"num_tokens": 37426381.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.522068500518799,
|
|
"epoch": 1.851302905452405,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046635495363032595,
|
|
"loss": 6.2128,
|
|
"mean_token_accuracy": 0.13729588389396669,
|
|
"num_tokens": 37436259.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.532771444320678,
|
|
"epoch": 1.8518379795601692,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00046633483900142026,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.1430345170199871,
|
|
"num_tokens": 37447498.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.483018445968628,
|
|
"epoch": 1.852373053667933,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000466314718847748,
|
|
"loss": 6.1869,
|
|
"mean_token_accuracy": 0.14144012928009034,
|
|
"num_tokens": 37457323.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.470933246612549,
|
|
"epoch": 1.852908127775697,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004662945931698901,
|
|
"loss": 6.2246,
|
|
"mean_token_accuracy": 0.1384797491133213,
|
|
"num_tokens": 37468121.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.515081596374512,
|
|
"epoch": 1.853443201883461,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00046627446196842784,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.1317722588777542,
|
|
"num_tokens": 37479205.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.556810903549194,
|
|
"epoch": 1.8539782759912247,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004662543252439422,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.13010217621922493,
|
|
"num_tokens": 37491015.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.579596424102784,
|
|
"epoch": 1.8545133500989888,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046623418299701494,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.13135558143258094,
|
|
"num_tokens": 37503078.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.5604668140411375,
|
|
"epoch": 1.8550484242067526,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004662140352282274,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.1412036180496216,
|
|
"num_tokens": 37514623.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.501449155807495,
|
|
"epoch": 1.8555834983145165,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046619388193816155,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.13932041376829146,
|
|
"num_tokens": 37525618.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.5468672752380375,
|
|
"epoch": 1.8561185724222806,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046617372312739917,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.14140139073133468,
|
|
"num_tokens": 37536023.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.581799411773682,
|
|
"epoch": 1.8566536465300443,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004661535587965224,
|
|
"loss": 6.26,
|
|
"mean_token_accuracy": 0.1331052377820015,
|
|
"num_tokens": 37545886.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.489939403533936,
|
|
"epoch": 1.8571887206378084,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046613338894611347,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.13516911789774894,
|
|
"num_tokens": 37557587.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.430360794067383,
|
|
"epoch": 1.8577237947455723,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004661132135767548,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.15580250471830367,
|
|
"num_tokens": 37569379.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.574359893798828,
|
|
"epoch": 1.8582588688533361,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000466093032689029,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13142267763614654,
|
|
"num_tokens": 37580478.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.483245992660523,
|
|
"epoch": 1.8587939429611002,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004660728462835187,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.14082368835806847,
|
|
"num_tokens": 37591506.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.4595136642456055,
|
|
"epoch": 1.8593290170688639,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004660526543608068,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.15273035317659378,
|
|
"num_tokens": 37602074.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.5289915084838865,
|
|
"epoch": 1.859864091176628,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004660324569214763,
|
|
"loss": 6.2628,
|
|
"mean_token_accuracy": 0.1343717895448208,
|
|
"num_tokens": 37612180.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.513068914413452,
|
|
"epoch": 1.8603991652843919,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004660122539661106,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.14054446592926978,
|
|
"num_tokens": 37622588.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.5763421058654785,
|
|
"epoch": 1.8609342393921557,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004659920454952928,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.14042455777525903,
|
|
"num_tokens": 37634323.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.562207317352295,
|
|
"epoch": 1.8614693134999198,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004659718315096065,
|
|
"loss": 6.2767,
|
|
"mean_token_accuracy": 0.13324531316757202,
|
|
"num_tokens": 37645816.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.585940647125244,
|
|
"epoch": 1.8620043876076835,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00046595161200963545,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.13371996730566024,
|
|
"num_tokens": 37656143.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.513905477523804,
|
|
"epoch": 1.8625394617154476,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00046593138699596343,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.13611202463507652,
|
|
"num_tokens": 37665959.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.486093330383301,
|
|
"epoch": 1.8630745358232115,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00046591115646917443,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13548298478126525,
|
|
"num_tokens": 37677176.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.472007322311401,
|
|
"epoch": 1.8636096099309754,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004658909204298526,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.14066635966300964,
|
|
"num_tokens": 37687740.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.482980394363404,
|
|
"epoch": 1.8641446840387395,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004658706788785823,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.14265646263957024,
|
|
"num_tokens": 37698536.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.552716970443726,
|
|
"epoch": 1.8646797581465033,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046585043181594793,
|
|
"loss": 6.2199,
|
|
"mean_token_accuracy": 0.14157683700323104,
|
|
"num_tokens": 37708795.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.550864553451538,
|
|
"epoch": 1.8652148322542672,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046583017924253426,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.14017075598239898,
|
|
"num_tokens": 37719136.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.603561115264893,
|
|
"epoch": 1.8657499063620313,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004658099211589259,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.13327914327383042,
|
|
"num_tokens": 37730513.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.459116220474243,
|
|
"epoch": 1.866284980469795,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.00046578965756570787,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.13692908883094787,
|
|
"num_tokens": 37741811.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.429191589355469,
|
|
"epoch": 1.866820054577559,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046576938846346527,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.14636265933513642,
|
|
"num_tokens": 37752213.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.444896173477173,
|
|
"epoch": 1.867355128685323,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00046574911385278343,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.15159211903810502,
|
|
"num_tokens": 37763253.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.566773557662964,
|
|
"epoch": 1.8678902027930868,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046572883373424776,
|
|
"loss": 6.2701,
|
|
"mean_token_accuracy": 0.13228057101368904,
|
|
"num_tokens": 37775087.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.56617431640625,
|
|
"epoch": 1.868425276900851,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00046570854810844373,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.13026925027370453,
|
|
"num_tokens": 37786119.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.5158192157745365,
|
|
"epoch": 1.8689603510086146,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00046568825697595724,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.13482827097177505,
|
|
"num_tokens": 37797482.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.523220825195312,
|
|
"epoch": 1.8694954251163787,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004656679603373741,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.13488890826702118,
|
|
"num_tokens": 37808067.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.5920967102050785,
|
|
"epoch": 1.8700304992241426,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004656476581932804,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.1309550918638706,
|
|
"num_tokens": 37819762.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.509218740463257,
|
|
"epoch": 1.8705655733319064,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004656273505442624,
|
|
"loss": 6.2132,
|
|
"mean_token_accuracy": 0.14369545131921768,
|
|
"num_tokens": 37829510.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.510902166366577,
|
|
"epoch": 1.8711006474396705,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00046560703739090633,
|
|
"loss": 6.283,
|
|
"mean_token_accuracy": 0.1339593842625618,
|
|
"num_tokens": 37839431.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.596603298187256,
|
|
"epoch": 1.8716357215474342,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046558671873379886,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.1272880144417286,
|
|
"num_tokens": 37850531.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.636654281616211,
|
|
"epoch": 1.8721707956551983,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004655663945735268,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.12858284413814544,
|
|
"num_tokens": 37861964.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.4125974655151365,
|
|
"epoch": 1.8727058697629622,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004655460649106768,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15219689756631852,
|
|
"num_tokens": 37873598.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.521950435638428,
|
|
"epoch": 1.873240943870726,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046552572974583597,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.13302481919527054,
|
|
"num_tokens": 37884643.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.507148408889771,
|
|
"epoch": 1.8737760179784901,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004655053890795914,
|
|
"loss": 6.2672,
|
|
"mean_token_accuracy": 0.13397427871823311,
|
|
"num_tokens": 37896566.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.59088625907898,
|
|
"epoch": 1.8743110920862538,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00046548504291253054,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.13231249898672104,
|
|
"num_tokens": 37907424.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.588667011260986,
|
|
"epoch": 1.874846166194018,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004654646912452408,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.14179185181856155,
|
|
"num_tokens": 37917318.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.510469579696656,
|
|
"epoch": 1.8753812403017818,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004654443340783099,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.1401626721024513,
|
|
"num_tokens": 37928521.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.499540185928344,
|
|
"epoch": 1.8759163144095456,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046542397141232554,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.1372986279428005,
|
|
"num_tokens": 37939930.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.504684114456177,
|
|
"epoch": 1.8764513885173097,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004654036032478759,
|
|
"loss": 6.1869,
|
|
"mean_token_accuracy": 0.14108899012207984,
|
|
"num_tokens": 37949690.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.546181392669678,
|
|
"epoch": 1.8769864626250736,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00046538322958554885,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.14192006289958953,
|
|
"num_tokens": 37962162.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.594173574447632,
|
|
"epoch": 1.8775215367328375,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004653628504259329,
|
|
"loss": 6.2469,
|
|
"mean_token_accuracy": 0.13679970055818558,
|
|
"num_tokens": 37972707.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.458856296539307,
|
|
"epoch": 1.8780566108406014,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046534246576961633,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.1458908274769783,
|
|
"num_tokens": 37983101.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.422877454757691,
|
|
"epoch": 1.8785916849483653,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046532207561718775,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.14392440170049667,
|
|
"num_tokens": 37994025.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.521886825561523,
|
|
"epoch": 1.8791267590561294,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046530167996923613,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.13209235221147536,
|
|
"num_tokens": 38004761.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.573818874359131,
|
|
"epoch": 1.8796618331638932,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004652812788263501,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13844591975212098,
|
|
"num_tokens": 38015129.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.533925724029541,
|
|
"epoch": 1.8801969072716571,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046526087218911894,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.14329466223716736,
|
|
"num_tokens": 38025501.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.5236128807067875,
|
|
"epoch": 1.8807319813794212,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046524046005813185,
|
|
"loss": 6.2105,
|
|
"mean_token_accuracy": 0.13993176072835922,
|
|
"num_tokens": 38034912.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.475555276870727,
|
|
"epoch": 1.8812670554871849,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004652200424339782,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.140637881308794,
|
|
"num_tokens": 38045417.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.520765924453736,
|
|
"epoch": 1.881802129594949,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004651996193172475,
|
|
"loss": 6.2945,
|
|
"mean_token_accuracy": 0.1352642834186554,
|
|
"num_tokens": 38057033.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.551823234558105,
|
|
"epoch": 1.8823372037027128,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004651791907085296,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.13857173919677734,
|
|
"num_tokens": 38067804.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.541230058670044,
|
|
"epoch": 1.8828722778104767,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004651587566084143,
|
|
"loss": 6.2188,
|
|
"mean_token_accuracy": 0.1486022040247917,
|
|
"num_tokens": 38079246.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.541295862197876,
|
|
"epoch": 1.8834073519182408,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046513831701749155,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.13094632104039192,
|
|
"num_tokens": 38090628.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.515250587463379,
|
|
"epoch": 1.8839424260260045,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046511787193635165,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.14270028993487358,
|
|
"num_tokens": 38100848.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.606397533416748,
|
|
"epoch": 1.8844775001337686,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046509742136558493,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.1411973714828491,
|
|
"num_tokens": 38110732.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.4958351135253904,
|
|
"epoch": 1.8850125742415325,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00046507696530578185,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.14429498165845872,
|
|
"num_tokens": 38121002.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.504161643981933,
|
|
"epoch": 1.8855476483492963,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004650565037575331,
|
|
"loss": 6.2381,
|
|
"mean_token_accuracy": 0.1369054652750492,
|
|
"num_tokens": 38132294.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.4798229217529295,
|
|
"epoch": 1.8860827224570604,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046503603672142955,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.1413409121334553,
|
|
"num_tokens": 38142962.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.5535815238952635,
|
|
"epoch": 1.886617796564824,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004650155641980621,
|
|
"loss": 6.262,
|
|
"mean_token_accuracy": 0.14034836292266845,
|
|
"num_tokens": 38153737.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.567475128173828,
|
|
"epoch": 1.8871528706725882,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046499508618802195,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.13480818271636963,
|
|
"num_tokens": 38163897.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.487664747238159,
|
|
"epoch": 1.887687944780352,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004649746026919004,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.14665645807981492,
|
|
"num_tokens": 38175123.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.484235763549805,
|
|
"epoch": 1.888223018888116,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046495411371028886,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.14219552129507065,
|
|
"num_tokens": 38186100.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.559158420562744,
|
|
"epoch": 1.88875809299588,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046493361924377903,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.14047744050621985,
|
|
"num_tokens": 38196385.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.4783586978912355,
|
|
"epoch": 1.8892931671036437,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004649131192929626,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.13876958936452866,
|
|
"num_tokens": 38207260.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.45147476196289,
|
|
"epoch": 1.8898282412114078,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004648926138584315,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.14660956487059593,
|
|
"num_tokens": 38217537.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.543872261047364,
|
|
"epoch": 1.8903633153191717,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00046487210294077794,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.13700347542762756,
|
|
"num_tokens": 38228956.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.471927785873413,
|
|
"epoch": 1.8908983894269356,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046485158654059405,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14353640973567963,
|
|
"num_tokens": 38240236.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.585081481933594,
|
|
"epoch": 1.8914334635346997,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004648310646584723,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13636186644434928,
|
|
"num_tokens": 38251739.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.48091344833374,
|
|
"epoch": 1.8919685376424635,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00046481053729500516,
|
|
"loss": 6.2058,
|
|
"mean_token_accuracy": 0.1312205635011196,
|
|
"num_tokens": 38262090.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.503962993621826,
|
|
"epoch": 1.8925036117502274,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004647900044507855,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.1413418248295784,
|
|
"num_tokens": 38272770.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.51068148612976,
|
|
"epoch": 1.8930386858579913,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004647694661264061,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.1368080921471119,
|
|
"num_tokens": 38283449.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.534865188598633,
|
|
"epoch": 1.8935737599657552,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046474892232246,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.13847722858190536,
|
|
"num_tokens": 38293831.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.489880561828613,
|
|
"epoch": 1.8941088340735193,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00046472837303954053,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.13979624956846237,
|
|
"num_tokens": 38304782.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.508448696136474,
|
|
"epoch": 1.8946439081812831,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046470781827824087,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.14288853406906127,
|
|
"num_tokens": 38316547.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.580143833160401,
|
|
"epoch": 1.895178982289047,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046468725803915464,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.13468163907527925,
|
|
"num_tokens": 38329488.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.461695432662964,
|
|
"epoch": 1.8957140563968111,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046466669232287543,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.1440846249461174,
|
|
"num_tokens": 38341290.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.52875862121582,
|
|
"epoch": 1.8962491305045748,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004646461211299973,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.13937623724341391,
|
|
"num_tokens": 38352445.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.528347730636597,
|
|
"epoch": 1.8967842046123389,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004646255444611139,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.1415594771504402,
|
|
"num_tokens": 38363825.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.49668550491333,
|
|
"epoch": 1.8973192787201028,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046460496231681957,
|
|
"loss": 6.31,
|
|
"mean_token_accuracy": 0.13838377743959426,
|
|
"num_tokens": 38375454.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.4484857559204105,
|
|
"epoch": 1.8978543528278666,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046458437469770866,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.1398676410317421,
|
|
"num_tokens": 38385938.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.540100574493408,
|
|
"epoch": 1.8983894269356307,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046456378160437555,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.14353546053171157,
|
|
"num_tokens": 38396143.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.488660621643066,
|
|
"epoch": 1.8989245010433944,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004645431830374149,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.12918649911880492,
|
|
"num_tokens": 38407445.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.5336669921875,
|
|
"epoch": 1.8994595751511585,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046452257899742144,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.12962775230407714,
|
|
"num_tokens": 38418438.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.467654991149902,
|
|
"epoch": 1.8999946492589224,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046450196948499015,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.13833793625235558,
|
|
"num_tokens": 38428821.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.498792219161987,
|
|
"epoch": 1.9005297233666862,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004644813545007161,
|
|
"loss": 6.1544,
|
|
"mean_token_accuracy": 0.13901732116937637,
|
|
"num_tokens": 38439560.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.54771318435669,
|
|
"epoch": 1.9010647974744503,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004644607340451946,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.1394535258412361,
|
|
"num_tokens": 38449724.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.517421054840088,
|
|
"epoch": 1.901599871582214,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046444010811902105,
|
|
"loss": 6.1717,
|
|
"mean_token_accuracy": 0.14054683744907379,
|
|
"num_tokens": 38459833.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.449574708938599,
|
|
"epoch": 1.902134945689978,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046441947672279095,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.14699629992246627,
|
|
"num_tokens": 38470682.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.484740591049194,
|
|
"epoch": 1.902670019797742,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004643988398571001,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.13642918542027474,
|
|
"num_tokens": 38481362.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.52804388999939,
|
|
"epoch": 1.9032050939055059,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004643781975225444,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.14055032059550285,
|
|
"num_tokens": 38492941.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.583075475692749,
|
|
"epoch": 1.90374016801327,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046435754971971976,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.1341730184853077,
|
|
"num_tokens": 38503823.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.473573112487793,
|
|
"epoch": 1.9042752421210336,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046433689644922256,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.14910909831523894,
|
|
"num_tokens": 38514482.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.472933340072632,
|
|
"epoch": 1.9048103162287977,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046431623771164897,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.13971884027123452,
|
|
"num_tokens": 38525580.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.449027681350708,
|
|
"epoch": 1.9053453903365616,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004642955735075958,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.1396370619535446,
|
|
"num_tokens": 38537025.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.487132024765015,
|
|
"epoch": 1.9058804644443255,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046427490383765943,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.14065134525299072,
|
|
"num_tokens": 38548974.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.4658825397491455,
|
|
"epoch": 1.9064155385520896,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004642542287024368,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.14220650643110275,
|
|
"num_tokens": 38559971.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.4972062587738035,
|
|
"epoch": 1.9069506126598534,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000464233548102525,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.13903797119855882,
|
|
"num_tokens": 38570326.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.4395452499389645,
|
|
"epoch": 1.9074856867676173,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000464212862038521,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.1364986389875412,
|
|
"num_tokens": 38580799.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.44638843536377,
|
|
"epoch": 1.9080207608753812,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046419217051102223,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.13144152835011483,
|
|
"num_tokens": 38591136.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.521512222290039,
|
|
"epoch": 1.908555834983145,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004641714735206261,
|
|
"loss": 6.184,
|
|
"mean_token_accuracy": 0.14119268357753753,
|
|
"num_tokens": 38602600.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.515765047073364,
|
|
"epoch": 1.9090909090909092,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046415077106793024,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.14135203510522842,
|
|
"num_tokens": 38612641.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.525089740753174,
|
|
"epoch": 1.909625983198673,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004641300631535325,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.14011745378375054,
|
|
"num_tokens": 38622873.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.479873371124268,
|
|
"epoch": 1.910161057306437,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004641093497780307,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.14634738862514496,
|
|
"num_tokens": 38633523.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.488259887695312,
|
|
"epoch": 1.910696131414201,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004640886309420231,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.1308392196893692,
|
|
"num_tokens": 38645635.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.5185023784637455,
|
|
"epoch": 1.9112312055219647,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004640679066461078,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.1497434303164482,
|
|
"num_tokens": 38656293.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.5067955493927006,
|
|
"epoch": 1.9117662796297288,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004640471768908832,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.13123812302947044,
|
|
"num_tokens": 38667307.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.555864238739014,
|
|
"epoch": 1.9123013537374927,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004640264416769481,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.13502105697989464,
|
|
"num_tokens": 38677775.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.471245193481446,
|
|
"epoch": 1.9128364278452565,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00046400570100490086,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.13582777678966523,
|
|
"num_tokens": 38688652.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.500534534454346,
|
|
"epoch": 1.9133715019530206,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00046398495487534066,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.13551617562770843,
|
|
"num_tokens": 38698694.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.506363296508789,
|
|
"epoch": 1.9139065760607843,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004639642032888664,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.136919304728508,
|
|
"num_tokens": 38709864.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.50716872215271,
|
|
"epoch": 1.9144416501685484,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004639434462460774,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.13497220128774642,
|
|
"num_tokens": 38721034.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 6.568297719955444,
|
|
"epoch": 1.9149767242763123,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00046392268374757285,
|
|
"loss": 6.2328,
|
|
"mean_token_accuracy": 0.13604136258363725,
|
|
"num_tokens": 38731874.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.487967205047608,
|
|
"epoch": 1.9155117983840761,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004639019157939524,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.14495863467454911,
|
|
"num_tokens": 38742447.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.484689235687256,
|
|
"epoch": 1.9160468724918402,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004638811423858157,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.13880375921726226,
|
|
"num_tokens": 38754117.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.554324913024902,
|
|
"epoch": 1.916581946599604,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046386036352376255,
|
|
"loss": 6.2277,
|
|
"mean_token_accuracy": 0.131800340116024,
|
|
"num_tokens": 38765057.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.493456125259399,
|
|
"epoch": 1.917117020707368,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046383957920839285,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.14344696775078775,
|
|
"num_tokens": 38775938.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.426898050308227,
|
|
"epoch": 1.9176520948151319,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046381878944030697,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.1440959244966507,
|
|
"num_tokens": 38787013.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.486614990234375,
|
|
"epoch": 1.9181871689228958,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.000463797994220105,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.14382546991109849,
|
|
"num_tokens": 38798412.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.483612489700318,
|
|
"epoch": 1.9187222430306599,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046377719354838756,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.13215523809194565,
|
|
"num_tokens": 38809983.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.530688667297364,
|
|
"epoch": 1.9192573171384235,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046375638742575506,
|
|
"loss": 6.2353,
|
|
"mean_token_accuracy": 0.1396634139120579,
|
|
"num_tokens": 38820418.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.560414886474609,
|
|
"epoch": 1.9197923912461876,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004637355758528085,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.14094739705324172,
|
|
"num_tokens": 38831482.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.572238254547119,
|
|
"epoch": 1.9203274653539515,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004637147588301486,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.13170821741223335,
|
|
"num_tokens": 38842110.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.451564836502075,
|
|
"epoch": 1.9208625394617154,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046369393635837657,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.13936901614069938,
|
|
"num_tokens": 38852861.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.468238449096679,
|
|
"epoch": 1.9213976135694795,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00046367310843809374,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.13597493693232537,
|
|
"num_tokens": 38864067.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.567491865158081,
|
|
"epoch": 1.9219326876772433,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046365227506990137,
|
|
"loss": 6.2192,
|
|
"mean_token_accuracy": 0.1376200519502163,
|
|
"num_tokens": 38875363.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.594467115402222,
|
|
"epoch": 1.9224677617850072,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004636314362544011,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.1406591974198818,
|
|
"num_tokens": 38886414.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.539594984054565,
|
|
"epoch": 1.923002835892771,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046361059199219457,
|
|
"loss": 6.297,
|
|
"mean_token_accuracy": 0.13197313323616983,
|
|
"num_tokens": 38897708.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.451222896575928,
|
|
"epoch": 1.923537910000535,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004635897422838837,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14442215859889984,
|
|
"num_tokens": 38908683.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.420654535293579,
|
|
"epoch": 1.924072984108299,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046356888713007055,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.14991554766893386,
|
|
"num_tokens": 38919279.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.555045938491821,
|
|
"epoch": 1.924608058216063,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046354802653135723,
|
|
"loss": 6.2259,
|
|
"mean_token_accuracy": 0.1369065135717392,
|
|
"num_tokens": 38929353.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.5306110858917235,
|
|
"epoch": 1.9251431323238268,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004635271604883462,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.14035843312740326,
|
|
"num_tokens": 38939296.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.471765947341919,
|
|
"epoch": 1.925678206431591,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046350628900163987,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.13961842954158782,
|
|
"num_tokens": 38950149.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.5483925342559814,
|
|
"epoch": 1.9262132805393546,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000463485412071841,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.13433675169944764,
|
|
"num_tokens": 38961052.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.9262132805393546,
|
|
"eval_entropy": 6.365103536153418,
|
|
"eval_loss": 6.311902046203613,
|
|
"eval_mean_token_accuracy": 0.14091309935652785,
|
|
"eval_num_tokens": 38961052.0,
|
|
"eval_runtime": 22.5469,
|
|
"eval_samples_per_second": 1316.325,
|
|
"eval_steps_per_second": 164.546,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 6.537387180328369,
|
|
"epoch": 1.9267483546471187,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046346452969955214,
|
|
"loss": 6.2505,
|
|
"mean_token_accuracy": 0.13952741846442224,
|
|
"num_tokens": 38972344.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 6.534369659423828,
|
|
"epoch": 1.9272834287548826,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004634436418853767,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.13502275794744492,
|
|
"num_tokens": 38982877.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 6.489065361022949,
|
|
"epoch": 1.9278185028626464,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046342274862991745,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.13976141065359116,
|
|
"num_tokens": 38994322.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 6.48278956413269,
|
|
"epoch": 1.9283535769704105,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046340184993377793,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.14276184588670732,
|
|
"num_tokens": 39003447.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 6.493710613250732,
|
|
"epoch": 1.9288886510781742,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046338094579756136,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.13028390035033227,
|
|
"num_tokens": 39013760.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 6.380214357376099,
|
|
"epoch": 1.9294237251859383,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046336003622187143,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15164145305752755,
|
|
"num_tokens": 39025559.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 6.507640695571899,
|
|
"epoch": 1.9299587992937022,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000463339121207312,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.1387665130198002,
|
|
"num_tokens": 39036004.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 6.50057692527771,
|
|
"epoch": 1.930493873401466,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004633182007544868,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.1374046929180622,
|
|
"num_tokens": 39047251.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 6.521696710586548,
|
|
"epoch": 1.9310289475092302,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046329727486400015,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.13776894733309747,
|
|
"num_tokens": 39057255.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 6.5461184024810795,
|
|
"epoch": 1.9315640216169938,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004632763435364561,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.1345633938908577,
|
|
"num_tokens": 39068186.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 6.460474252700806,
|
|
"epoch": 1.932099095724758,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046325540677245907,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.14090655818581582,
|
|
"num_tokens": 39079173.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 6.509998750686646,
|
|
"epoch": 1.9326341698325218,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00046323446457261365,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.13899825662374496,
|
|
"num_tokens": 39089939.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 6.483740901947021,
|
|
"epoch": 1.9331692439402857,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004632135169375245,
|
|
"loss": 6.2411,
|
|
"mean_token_accuracy": 0.1368535950779915,
|
|
"num_tokens": 39100464.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 6.590921926498413,
|
|
"epoch": 1.9337043180480498,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004631925638677965,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.1361953742802143,
|
|
"num_tokens": 39111161.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 6.5673949241638185,
|
|
"epoch": 1.9342393921558134,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046317160536403463,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14538534879684448,
|
|
"num_tokens": 39122469.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 6.501009321212768,
|
|
"epoch": 1.9347744662635775,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046315064142684416,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.1420877143740654,
|
|
"num_tokens": 39131871.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 6.536379814147949,
|
|
"epoch": 1.9353095403713414,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004631296720568304,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.13578182831406593,
|
|
"num_tokens": 39143061.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 6.519476127624512,
|
|
"epoch": 1.9358446144791053,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004631086972545987,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.14594390690326692,
|
|
"num_tokens": 39152452.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 6.481864023208618,
|
|
"epoch": 1.9363796885868694,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004630877170207548,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.14349544048309326,
|
|
"num_tokens": 39163196.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 6.444577312469482,
|
|
"epoch": 1.9369147626946333,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004630667313559045,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.13424062207341195,
|
|
"num_tokens": 39173958.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 6.509752082824707,
|
|
"epoch": 1.9374498368023971,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046304574026065376,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.14818471521139145,
|
|
"num_tokens": 39184483.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 6.464862442016601,
|
|
"epoch": 1.937984910910161,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004630247437356087,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.13587528467178345,
|
|
"num_tokens": 39196500.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 6.581671142578125,
|
|
"epoch": 1.9385199850179249,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046300374178137566,
|
|
"loss": 6.2811,
|
|
"mean_token_accuracy": 0.13231036737561225,
|
|
"num_tokens": 39207492.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 6.606667470932007,
|
|
"epoch": 1.939055059125689,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004629827343985609,
|
|
"loss": 6.2132,
|
|
"mean_token_accuracy": 0.1399967424571514,
|
|
"num_tokens": 39218204.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 6.5478047847747805,
|
|
"epoch": 1.9395901332334529,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046296172158777116,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.13208532631397246,
|
|
"num_tokens": 39229646.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 6.482489490509034,
|
|
"epoch": 1.9401252073412167,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004629407033496131,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.1369784414768219,
|
|
"num_tokens": 39240151.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 6.533039617538452,
|
|
"epoch": 1.9406602814489808,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004629196796846936,
|
|
"loss": 6.2495,
|
|
"mean_token_accuracy": 0.14209898710250854,
|
|
"num_tokens": 39251571.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 6.579952049255371,
|
|
"epoch": 1.9411953555567445,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00046289865059361983,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.13832592815160752,
|
|
"num_tokens": 39262937.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 6.596141672134399,
|
|
"epoch": 1.9417304296645086,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046287761607699887,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.1336644783616066,
|
|
"num_tokens": 39274354.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 6.532996129989624,
|
|
"epoch": 1.9422655037722725,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004628565761354382,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.1417832262814045,
|
|
"num_tokens": 39284314.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 6.474736070632934,
|
|
"epoch": 1.9428005778800364,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046283553076954527,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.13891778364777566,
|
|
"num_tokens": 39295516.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 6.522478151321411,
|
|
"epoch": 1.9433356519878004,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004628144799799277,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.13308093473315238,
|
|
"num_tokens": 39307221.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 6.490683937072754,
|
|
"epoch": 1.943870726095564,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004627934237671935,
|
|
"loss": 6.2232,
|
|
"mean_token_accuracy": 0.13667370676994323,
|
|
"num_tokens": 39318448.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 6.452537965774536,
|
|
"epoch": 1.9444058002033282,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046277236213195064,
|
|
"loss": 6.134,
|
|
"mean_token_accuracy": 0.14521567970514299,
|
|
"num_tokens": 39329384.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 6.541502904891968,
|
|
"epoch": 1.944940874311092,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046275129507480705,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.1390232525765896,
|
|
"num_tokens": 39340342.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 6.410711622238159,
|
|
"epoch": 1.945475948418856,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004627302225963713,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14687473252415656,
|
|
"num_tokens": 39350825.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 6.579923677444458,
|
|
"epoch": 1.94601102252662,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046270914469725174,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.1316472865641117,
|
|
"num_tokens": 39361986.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 6.550302743911743,
|
|
"epoch": 1.9465460966343837,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046268806137805704,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.13814951479434967,
|
|
"num_tokens": 39372440.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 6.4940667152404785,
|
|
"epoch": 1.9470811707421478,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004626669726393958,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.15121543034911156,
|
|
"num_tokens": 39383455.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 6.449176502227783,
|
|
"epoch": 1.9476162448499117,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004626458784818772,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.137010395526886,
|
|
"num_tokens": 39393511.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 6.5185973167419435,
|
|
"epoch": 1.9481513189576756,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046262477890611026,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.14350884780287743,
|
|
"num_tokens": 39404049.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 6.524765062332153,
|
|
"epoch": 1.9486863930654397,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046260367391270414,
|
|
"loss": 6.2084,
|
|
"mean_token_accuracy": 0.14273274093866348,
|
|
"num_tokens": 39414771.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 6.455693674087525,
|
|
"epoch": 1.9492214671732033,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046258256350226835,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.14329796582460402,
|
|
"num_tokens": 39424869.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 6.48890872001648,
|
|
"epoch": 1.9497565412809674,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004625614476754123,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.1388202503323555,
|
|
"num_tokens": 39435442.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 6.534210252761841,
|
|
"epoch": 1.9502916153887313,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046254032643274596,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14215890243649482,
|
|
"num_tokens": 39446704.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 6.4775608539581295,
|
|
"epoch": 1.9508266894964952,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046251919977487887,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.14251686334609986,
|
|
"num_tokens": 39458079.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 6.534129285812378,
|
|
"epoch": 1.9513617636042593,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046249806770242135,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.14502133950591087,
|
|
"num_tokens": 39469867.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 6.503177642822266,
|
|
"epoch": 1.9518968377120232,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004624769302159834,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.13654508143663407,
|
|
"num_tokens": 39481138.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 6.478667306900024,
|
|
"epoch": 1.952431911819787,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004624557873161755,
|
|
"loss": 6.1549,
|
|
"mean_token_accuracy": 0.1422030508518219,
|
|
"num_tokens": 39492066.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 6.619949913024902,
|
|
"epoch": 1.952966985927551,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004624346390036081,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.1362333133816719,
|
|
"num_tokens": 39502576.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 6.516488552093506,
|
|
"epoch": 1.9535020600353148,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004624134852788918,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.1413075566291809,
|
|
"num_tokens": 39513373.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 6.49299464225769,
|
|
"epoch": 1.954037134143079,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004623923261426374,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.13643113598227502,
|
|
"num_tokens": 39523970.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 6.487503910064698,
|
|
"epoch": 1.9545722082508428,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000462371161595456,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.14029355868697166,
|
|
"num_tokens": 39533893.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 6.499411344528198,
|
|
"epoch": 1.9551072823586066,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004623499916379586,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.13367502987384797,
|
|
"num_tokens": 39544276.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 6.508891677856445,
|
|
"epoch": 1.9556423564663707,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004623288162707565,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.1446276016533375,
|
|
"num_tokens": 39554443.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 6.481840372085571,
|
|
"epoch": 1.9561774305741344,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046230763549446116,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.1417379431426525,
|
|
"num_tokens": 39564508.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 6.506319046020508,
|
|
"epoch": 1.9567125046818985,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004622864493096842,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.13477322906255723,
|
|
"num_tokens": 39574757.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 6.530301570892334,
|
|
"epoch": 1.9572475787896624,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046226525771703733,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.1320313483476639,
|
|
"num_tokens": 39585911.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 6.52979040145874,
|
|
"epoch": 1.9577826528974263,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004622440607171324,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.13540443405508995,
|
|
"num_tokens": 39597443.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 6.5429998397827145,
|
|
"epoch": 1.9583177270051904,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046222285831058155,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.13729900270700454,
|
|
"num_tokens": 39608693.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 6.489964962005615,
|
|
"epoch": 1.958852801112954,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000462201650497997,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.13809031397104263,
|
|
"num_tokens": 39620002.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 6.494258642196655,
|
|
"epoch": 1.9593878752207181,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046218043727999105,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.14171760454773902,
|
|
"num_tokens": 39629856.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 6.454374885559082,
|
|
"epoch": 1.959922949328482,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046215921865717637,
|
|
"loss": 6.1583,
|
|
"mean_token_accuracy": 0.1480446234345436,
|
|
"num_tokens": 39640418.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 6.585394716262817,
|
|
"epoch": 1.9604580234362459,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004621379946301655,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.13282811343669892,
|
|
"num_tokens": 39652871.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 6.538632917404175,
|
|
"epoch": 1.96099309754401,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004621167651995713,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.13859786316752434,
|
|
"num_tokens": 39663864.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 6.443591547012329,
|
|
"epoch": 1.9615281716517736,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004620955303660068,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.14592609256505967,
|
|
"num_tokens": 39675835.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 6.486690998077393,
|
|
"epoch": 1.9620632457595377,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046207429013008525,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.13817154094576836,
|
|
"num_tokens": 39686799.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 6.595781373977661,
|
|
"epoch": 1.9625983198673016,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046205304449241976,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.14235665500164033,
|
|
"num_tokens": 39697564.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 6.546803331375122,
|
|
"epoch": 1.9631333939750655,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004620317934536239,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.13921477496623993,
|
|
"num_tokens": 39708064.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 6.4622925281524655,
|
|
"epoch": 1.9636684680828296,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004620105370143112,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.14588503614068032,
|
|
"num_tokens": 39718076.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 6.4703590869903564,
|
|
"epoch": 1.9642035421905932,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004619892751750957,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.1371205635368824,
|
|
"num_tokens": 39729532.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 6.572897434234619,
|
|
"epoch": 1.9647386162983573,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046196800793659116,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.13921429961919785,
|
|
"num_tokens": 39740372.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 6.471987104415893,
|
|
"epoch": 1.9652736904061212,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004619467352994115,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.1459924139082432,
|
|
"num_tokens": 39751283.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 6.492894411087036,
|
|
"epoch": 1.965808764513885,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004619254572641712,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.1367352746427059,
|
|
"num_tokens": 39763295.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 6.497032403945923,
|
|
"epoch": 1.9663438386216492,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046190417383148465,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.13938141465187073,
|
|
"num_tokens": 39773849.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 6.40442214012146,
|
|
"epoch": 1.966878912729413,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004618828850019663,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.149911268055439,
|
|
"num_tokens": 39784366.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 6.481572771072388,
|
|
"epoch": 1.967413986837177,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046186159077623093,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.13839536607265474,
|
|
"num_tokens": 39794226.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 6.461075973510742,
|
|
"epoch": 1.9679490609449408,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004618402911548933,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.13925424218177795,
|
|
"num_tokens": 39805557.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 6.508315753936768,
|
|
"epoch": 1.9684841350527047,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004618189861385686,
|
|
"loss": 6.1437,
|
|
"mean_token_accuracy": 0.14520555585622788,
|
|
"num_tokens": 39816090.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 6.483796405792236,
|
|
"epoch": 1.9690192091604688,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004617976757278719,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.13241346776485444,
|
|
"num_tokens": 39826662.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 6.5719798564910885,
|
|
"epoch": 1.9695542832682327,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046177635992341855,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.1341266453266144,
|
|
"num_tokens": 39837805.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 6.577894020080566,
|
|
"epoch": 1.9700893573759966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004617550387258241,
|
|
"loss": 6.2255,
|
|
"mean_token_accuracy": 0.1321740508079529,
|
|
"num_tokens": 39848052.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 6.544881772994995,
|
|
"epoch": 1.9706244314837607,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004617337121357041,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.13785637766122819,
|
|
"num_tokens": 39859448.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 6.523015117645263,
|
|
"epoch": 1.9711595055915243,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004617123801536744,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.14234541207551957,
|
|
"num_tokens": 39870053.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 6.52815432548523,
|
|
"epoch": 1.9716945796992884,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000461691042780351,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.1351883016526699,
|
|
"num_tokens": 39881547.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 6.530121231079102,
|
|
"epoch": 1.9722296538070523,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00046166970001635,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.13887228742241858,
|
|
"num_tokens": 39892974.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 6.54822850227356,
|
|
"epoch": 1.9727647279148162,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046164835186228757,
|
|
"loss": 6.2269,
|
|
"mean_token_accuracy": 0.13992278203368186,
|
|
"num_tokens": 39904210.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 6.473427581787109,
|
|
"epoch": 1.9732998020225803,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046162699831878026,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.13897218704223632,
|
|
"num_tokens": 39915464.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 6.516928815841675,
|
|
"epoch": 1.973834876130344,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004616056393864446,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.13783070743083953,
|
|
"num_tokens": 39927117.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 6.590982913970947,
|
|
"epoch": 1.974369950238108,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004615842750658972,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.1418525017797947,
|
|
"num_tokens": 39937363.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 6.485547065734863,
|
|
"epoch": 1.974905024345872,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004615629053577552,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.14801151901483536,
|
|
"num_tokens": 39948934.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 6.463800287246704,
|
|
"epoch": 1.9754400984536358,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004615415302626355,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14127560183405877,
|
|
"num_tokens": 39959435.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 6.523458242416382,
|
|
"epoch": 1.9759751725613999,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046152014978115535,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.13477562740445137,
|
|
"num_tokens": 39969006.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 6.495766067504883,
|
|
"epoch": 1.9765102466691635,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000461498763913932,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.13650858923792838,
|
|
"num_tokens": 39979264.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 6.57129921913147,
|
|
"epoch": 1.9770453207769276,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046147737266158314,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.13355173617601396,
|
|
"num_tokens": 39989791.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 6.5301202774047855,
|
|
"epoch": 1.9775803948846915,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004614559760247263,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.13895142823457718,
|
|
"num_tokens": 39999591.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 6.482016563415527,
|
|
"epoch": 1.9781154689924554,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004614345740039794,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.13693781420588494,
|
|
"num_tokens": 40010811.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 6.539826583862305,
|
|
"epoch": 1.9786505431002195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046141316659996037,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.13596573919057847,
|
|
"num_tokens": 40022190.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 6.58152756690979,
|
|
"epoch": 1.9791856172079834,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046139175381328725,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.1355739116668701,
|
|
"num_tokens": 40033905.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 6.540552377700806,
|
|
"epoch": 1.9797206913157472,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004613703356445786,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.1378948912024498,
|
|
"num_tokens": 40044923.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 6.489380884170532,
|
|
"epoch": 1.9802557654235111,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004613489120944526,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.13925086632370948,
|
|
"num_tokens": 40054988.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 6.544102430343628,
|
|
"epoch": 1.980790839531275,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004613274831635279,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.13340204507112502,
|
|
"num_tokens": 40065565.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 6.505882740020752,
|
|
"epoch": 1.981325913639039,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046130604885242333,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.13562422543764113,
|
|
"num_tokens": 40076282.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 6.533380508422852,
|
|
"epoch": 1.981860987746803,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004612846091617578,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.14382676631212235,
|
|
"num_tokens": 40087546.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 6.54186487197876,
|
|
"epoch": 1.9823960618545668,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004612631640921504,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.13900343030691148,
|
|
"num_tokens": 40097937.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 6.532418060302734,
|
|
"epoch": 1.982931135962331,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046124171364422025,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.14462210536003112,
|
|
"num_tokens": 40108639.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 6.446396064758301,
|
|
"epoch": 1.9834662100700946,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004612202578185868,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.141569384932518,
|
|
"num_tokens": 40119533.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 6.538776922225952,
|
|
"epoch": 1.9840012841778587,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004611987966158695,
|
|
"loss": 6.2132,
|
|
"mean_token_accuracy": 0.1406353272497654,
|
|
"num_tokens": 40131176.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 6.565519237518311,
|
|
"epoch": 1.9845363582856226,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046117733003668825,
|
|
"loss": 6.2267,
|
|
"mean_token_accuracy": 0.1372864879667759,
|
|
"num_tokens": 40143293.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 6.5465416431427,
|
|
"epoch": 1.9850714323933865,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004611558580816628,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.13630439192056656,
|
|
"num_tokens": 40155312.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 6.527706098556519,
|
|
"epoch": 1.9856065065011506,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000461134380751413,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.13936087787151336,
|
|
"num_tokens": 40166261.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 6.438541650772095,
|
|
"epoch": 1.9861415806089142,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046111289804655906,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14726999700069426,
|
|
"num_tokens": 40176641.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 6.49216136932373,
|
|
"epoch": 1.9866766547166783,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004610914099677214,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.13794424757361412,
|
|
"num_tokens": 40187784.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 6.482954502105713,
|
|
"epoch": 1.9872117288244422,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004610699165155204,
|
|
"loss": 6.2356,
|
|
"mean_token_accuracy": 0.13208975419402122,
|
|
"num_tokens": 40198219.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 6.478134822845459,
|
|
"epoch": 1.987746802932206,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046104841769057677,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.1381744846701622,
|
|
"num_tokens": 40208589.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 6.554107809066773,
|
|
"epoch": 1.9882818770399702,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004610269134935112,
|
|
"loss": 6.1706,
|
|
"mean_token_accuracy": 0.1381148010492325,
|
|
"num_tokens": 40219587.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 6.517787742614746,
|
|
"epoch": 1.9888169511477338,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004610054039249446,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.13920636028051375,
|
|
"num_tokens": 40230681.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 6.395852994918823,
|
|
"epoch": 1.989352025255498,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046098388898549816,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.14935251027345658,
|
|
"num_tokens": 40241356.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 6.527567195892334,
|
|
"epoch": 1.9898870993632618,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046096236867579306,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.1399472773075104,
|
|
"num_tokens": 40251652.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 6.50946536064148,
|
|
"epoch": 1.9904221734710257,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046094084299645065,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.1382264256477356,
|
|
"num_tokens": 40262819.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 6.514907598495483,
|
|
"epoch": 1.9909572475787898,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046091931194809253,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.12972357571125032,
|
|
"num_tokens": 40274314.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 6.545491456985474,
|
|
"epoch": 1.9914923216865534,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004608977755313404,
|
|
"loss": 6.2355,
|
|
"mean_token_accuracy": 0.13660071194171905,
|
|
"num_tokens": 40284733.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 6.5072033405303955,
|
|
"epoch": 1.9920273957943175,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004608762337468162,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.14152269139885904,
|
|
"num_tokens": 40295484.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 6.4947264194488525,
|
|
"epoch": 1.9925624699020814,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004608546865951418,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.1392577826976776,
|
|
"num_tokens": 40305470.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 6.535963344573974,
|
|
"epoch": 1.9930975440098453,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046083313407693945,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.13385921120643615,
|
|
"num_tokens": 40316055.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 6.542084646224976,
|
|
"epoch": 1.9936326181176094,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004608115761928315,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.13841846957802773,
|
|
"num_tokens": 40326689.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 6.468710279464721,
|
|
"epoch": 1.9941676922253733,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046079001294344036,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.13841242641210555,
|
|
"num_tokens": 40338511.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 6.463043689727783,
|
|
"epoch": 1.9947027663331371,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004607684443293887,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.1357182554900646,
|
|
"num_tokens": 40350395.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 6.522072792053223,
|
|
"epoch": 1.995237840440901,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004607468703512993,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.14726056009531022,
|
|
"num_tokens": 40360166.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 6.487435245513916,
|
|
"epoch": 1.995772914548665,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046072529100979514,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.13381341472268105,
|
|
"num_tokens": 40370655.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 6.5325366973876955,
|
|
"epoch": 1.996307988656429,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004607037063054993,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.14127666875720024,
|
|
"num_tokens": 40381502.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 6.629591035842895,
|
|
"epoch": 1.9968430627641929,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000460682116239035,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.133098354190588,
|
|
"num_tokens": 40391815.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 6.489607810974121,
|
|
"epoch": 1.9973781368719568,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046066052081102576,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.1387154445052147,
|
|
"num_tokens": 40403306.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 6.465019464492798,
|
|
"epoch": 1.9979132109797209,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046063892002209505,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.14460196644067763,
|
|
"num_tokens": 40414210.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 6.4084409236907955,
|
|
"epoch": 1.9984482850874845,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004606173138728666,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.15017177313566207,
|
|
"num_tokens": 40424368.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 6.5114758014678955,
|
|
"epoch": 1.9989833591952486,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004605957023639643,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.13938649669289588,
|
|
"num_tokens": 40436252.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 6.547441864013672,
|
|
"epoch": 1.9995184333030125,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046057408549601223,
|
|
"loss": 6.2263,
|
|
"mean_token_accuracy": 0.14011163935065268,
|
|
"num_tokens": 40447256.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 6.536722554100884,
|
|
"epoch": 2.0,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004605524632696344,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.14446689767969978,
|
|
"num_tokens": 40456516.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 6.493961954116822,
|
|
"epoch": 2.000535074107764,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004605308356854553,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.14020592719316483,
|
|
"num_tokens": 40467563.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 6.507263660430908,
|
|
"epoch": 2.0010701482155278,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004605092027440994,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.1470101334154606,
|
|
"num_tokens": 40478202.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 6.548767995834351,
|
|
"epoch": 2.001605222323292,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004604875644461914,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.14174846112728118,
|
|
"num_tokens": 40489677.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 6.478121328353882,
|
|
"epoch": 2.0021402964310555,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046046592079235595,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.1418830409646034,
|
|
"num_tokens": 40500694.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 6.4401421546936035,
|
|
"epoch": 2.0026753705388196,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004604442717832181,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.14176031202077866,
|
|
"num_tokens": 40511539.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 6.450679159164428,
|
|
"epoch": 2.0032104446465837,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000460422617419403,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.13956640735268594,
|
|
"num_tokens": 40521906.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 6.537706279754639,
|
|
"epoch": 2.0037455187543474,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046040095770153594,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.13734177649021148,
|
|
"num_tokens": 40531454.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 6.561151552200317,
|
|
"epoch": 2.0042805928621115,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004603792926302422,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.13300508707761766,
|
|
"num_tokens": 40541497.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 6.520805358886719,
|
|
"epoch": 2.004815666969875,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004603576222061475,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.13687062859535218,
|
|
"num_tokens": 40552576.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 6.5069859504699705,
|
|
"epoch": 2.005350741077639,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004603359464298774,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.14298826977610588,
|
|
"num_tokens": 40562906.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 6.425133419036865,
|
|
"epoch": 2.0058858151854033,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046031426530205796,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.14545038118958473,
|
|
"num_tokens": 40574510.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 6.397230625152588,
|
|
"epoch": 2.006420889293167,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004602925788233152,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.15217705965042114,
|
|
"num_tokens": 40586170.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 6.505608367919922,
|
|
"epoch": 2.006955963400931,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046027088699427516,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.13655173256993294,
|
|
"num_tokens": 40597613.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 6.553638553619384,
|
|
"epoch": 2.007491037508695,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046024918981556434,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.14074890017509462,
|
|
"num_tokens": 40608366.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 6.4714373588562015,
|
|
"epoch": 2.008026111616459,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004602274872878092,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.14470703527331352,
|
|
"num_tokens": 40618616.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 6.363052845001221,
|
|
"epoch": 2.008561185724223,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00046020577941163635,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.14627309516072273,
|
|
"num_tokens": 40628342.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 6.451393365859985,
|
|
"epoch": 2.0090962598319866,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046018406618767273,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.13995684161782265,
|
|
"num_tokens": 40638644.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 6.468491172790527,
|
|
"epoch": 2.0096313339397507,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004601623476165451,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.14497480690479278,
|
|
"num_tokens": 40649945.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 6.54347071647644,
|
|
"epoch": 2.010166408047515,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046014062369888084,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.13651128634810447,
|
|
"num_tokens": 40660896.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 6.5255241870880125,
|
|
"epoch": 2.0107014821552784,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000460118894435307,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13748193979263307,
|
|
"num_tokens": 40672072.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 6.53931622505188,
|
|
"epoch": 2.0112365562630425,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004600971598264511,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.13760020434856415,
|
|
"num_tokens": 40682622.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 6.446117830276489,
|
|
"epoch": 2.011771630370806,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004600754198729407,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.1457574747502804,
|
|
"num_tokens": 40693127.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 6.473992538452149,
|
|
"epoch": 2.0123067044785703,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046005367457540366,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.13953919857740402,
|
|
"num_tokens": 40705009.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 6.550481081008911,
|
|
"epoch": 2.0128417785863344,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046003192393446763,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.14077396765351297,
|
|
"num_tokens": 40716498.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 6.533742380142212,
|
|
"epoch": 2.013376852694098,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004600101679507609,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.1455170065164566,
|
|
"num_tokens": 40727802.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 6.489166402816773,
|
|
"epoch": 2.013911926801862,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004599884066249115,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.14338200241327287,
|
|
"num_tokens": 40738866.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 6.498798942565918,
|
|
"epoch": 2.014447000909626,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004599666399575479,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.1386456497013569,
|
|
"num_tokens": 40750214.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 6.508102321624756,
|
|
"epoch": 2.01498207501739,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004599448679492986,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.14615290239453316,
|
|
"num_tokens": 40759830.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 6.476041603088379,
|
|
"epoch": 2.015517149125154,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004599230906007921,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.14038556143641473,
|
|
"num_tokens": 40770007.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 6.50742359161377,
|
|
"epoch": 2.0160522232329177,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004599013079126575,
|
|
"loss": 6.106,
|
|
"mean_token_accuracy": 0.13792717307806016,
|
|
"num_tokens": 40781495.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 6.555199909210205,
|
|
"epoch": 2.0165872973406818,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004598795198855235,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.14419957250356674,
|
|
"num_tokens": 40792875.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 6.514164209365845,
|
|
"epoch": 2.0171223714484454,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004598577265200193,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.13229865208268166,
|
|
"num_tokens": 40804484.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 6.460537672042847,
|
|
"epoch": 2.0176574455562095,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004598359278167744,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.13799827843904494,
|
|
"num_tokens": 40814692.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 6.4778059959411625,
|
|
"epoch": 2.0181925196639736,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045981412377641795,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.14357306510210038,
|
|
"num_tokens": 40825443.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 6.522529554367066,
|
|
"epoch": 2.0187275937717373,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045979231439957966,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.14059658572077752,
|
|
"num_tokens": 40836699.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 6.514246606826783,
|
|
"epoch": 2.0192626678795014,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004597704996868893,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.13985197693109513,
|
|
"num_tokens": 40846736.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 6.526371955871582,
|
|
"epoch": 2.019797741987265,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004597486796389766,
|
|
"loss": 6.2235,
|
|
"mean_token_accuracy": 0.1408810056746006,
|
|
"num_tokens": 40858362.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 6.4865038871765135,
|
|
"epoch": 2.020332816095029,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045972685425647186,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.14298768937587739,
|
|
"num_tokens": 40869346.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 6.561742973327637,
|
|
"epoch": 2.0208678902027932,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004597050235400051,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.1398242346942425,
|
|
"num_tokens": 40880003.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 6.561382007598877,
|
|
"epoch": 2.021402964310557,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045968318749020675,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.14093911722302438,
|
|
"num_tokens": 40891515.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 6.505699968338012,
|
|
"epoch": 2.021938038418321,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004596613461077073,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.14346395581960678,
|
|
"num_tokens": 40902024.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 6.468415212631226,
|
|
"epoch": 2.022473112526085,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00045963949939313754,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.14756014198064804,
|
|
"num_tokens": 40912160.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 6.537594604492187,
|
|
"epoch": 2.0230081866338487,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000459617647347128,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.13268757611513138,
|
|
"num_tokens": 40922516.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 6.5097065448760985,
|
|
"epoch": 2.023543260741613,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045959578997031,
|
|
"loss": 6.1772,
|
|
"mean_token_accuracy": 0.136392692476511,
|
|
"num_tokens": 40934148.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 6.559519243240357,
|
|
"epoch": 2.0240783348493765,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045957392726331443,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.14509733468294145,
|
|
"num_tokens": 40944409.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 6.488625955581665,
|
|
"epoch": 2.0246134089571406,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00045955205922677264,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.14190514534711837,
|
|
"num_tokens": 40955133.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 6.518922281265259,
|
|
"epoch": 2.0251484830649047,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004595301858613161,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.1429607316851616,
|
|
"num_tokens": 40965508.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 6.571975135803223,
|
|
"epoch": 2.0256835571726683,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004595083071675763,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.14501149132847785,
|
|
"num_tokens": 40975931.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 6.506203508377075,
|
|
"epoch": 2.0262186312804324,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045948642314618514,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.14204735904932023,
|
|
"num_tokens": 40985797.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 6.4477344989776615,
|
|
"epoch": 2.026753705388196,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004594645337977744,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.13660738468170167,
|
|
"num_tokens": 40996501.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 6.477477931976319,
|
|
"epoch": 2.02728877949596,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004594426391229762,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.1394515760242939,
|
|
"num_tokens": 41005970.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 6.501707649230957,
|
|
"epoch": 2.0278238536037243,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004594207391224227,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.14223191663622856,
|
|
"num_tokens": 41017208.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 6.586483001708984,
|
|
"epoch": 2.028358927711488,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045939883379674624,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.13285416290163993,
|
|
"num_tokens": 41028435.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 6.510217237472534,
|
|
"epoch": 2.028894001819252,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045937692314657936,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.14351291060447693,
|
|
"num_tokens": 41039256.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 6.439512014389038,
|
|
"epoch": 2.0294290759270157,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004593550071725548,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.1356598161160946,
|
|
"num_tokens": 41050527.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 6.497146797180176,
|
|
"epoch": 2.02996415003478,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045933308587530527,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.1396307997405529,
|
|
"num_tokens": 41062259.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 6.493076324462891,
|
|
"epoch": 2.030499224142544,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004593111592554638,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.1417892321944237,
|
|
"num_tokens": 41073011.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 6.4537712097167965,
|
|
"epoch": 2.0310342982503076,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004592892273136635,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.1453937515616417,
|
|
"num_tokens": 41083482.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 6.476549673080444,
|
|
"epoch": 2.0315693723580717,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00045926729005053764,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14689192473888396,
|
|
"num_tokens": 41094028.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 6.480548477172851,
|
|
"epoch": 2.0321044464658353,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004592453474667197,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.14326013177633284,
|
|
"num_tokens": 41106346.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 6.558454704284668,
|
|
"epoch": 2.0326395205735994,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004592233995628432,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.1450323536992073,
|
|
"num_tokens": 41116130.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 6.436607503890992,
|
|
"epoch": 2.0331745946813635,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000459201446339542,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.14622003808617592,
|
|
"num_tokens": 41127103.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 6.416644954681397,
|
|
"epoch": 2.033709668789127,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004591794877974499,
|
|
"loss": 6.1282,
|
|
"mean_token_accuracy": 0.13969530984759332,
|
|
"num_tokens": 41138258.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 6.532529830932617,
|
|
"epoch": 2.0342447428968913,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045915752393720094,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.1450706236064434,
|
|
"num_tokens": 41148859.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 6.496345806121826,
|
|
"epoch": 2.034779817004655,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00045913555475942937,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.1406131975352764,
|
|
"num_tokens": 41158614.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 6.461399221420288,
|
|
"epoch": 2.035314891112419,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004591135802647695,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.1487656131386757,
|
|
"num_tokens": 41170215.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 6.5223548412323,
|
|
"epoch": 2.035849965220183,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004590916004538559,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.14125470146536828,
|
|
"num_tokens": 41180784.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 6.528457736968994,
|
|
"epoch": 2.036385039327947,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045906961532732316,
|
|
"loss": 6.1562,
|
|
"mean_token_accuracy": 0.1360959529876709,
|
|
"num_tokens": 41191305.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 6.501538276672363,
|
|
"epoch": 2.036920113435711,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004590476248858062,
|
|
"loss": 6.1764,
|
|
"mean_token_accuracy": 0.14044924229383468,
|
|
"num_tokens": 41202388.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 6.460980367660523,
|
|
"epoch": 2.037455187543475,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004590256291299399,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.14525325298309327,
|
|
"num_tokens": 41212136.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 6.458244180679321,
|
|
"epoch": 2.0379902616512386,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00045900362806035945,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.1392577327787876,
|
|
"num_tokens": 41223390.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 6.487509679794312,
|
|
"epoch": 2.0385253357590027,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045898162167770006,
|
|
"loss": 6.193,
|
|
"mean_token_accuracy": 0.14385589063167573,
|
|
"num_tokens": 41234775.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 6.516320753097534,
|
|
"epoch": 2.0390604098667664,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004589596099825973,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.1417277753353119,
|
|
"num_tokens": 41245627.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 6.480148649215698,
|
|
"epoch": 2.0395954839745305,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00045893759297568654,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.1406472384929657,
|
|
"num_tokens": 41255441.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 6.369239854812622,
|
|
"epoch": 2.0401305580822946,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004589155706576036,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.1408141165971756,
|
|
"num_tokens": 41268686.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 6.583061981201172,
|
|
"epoch": 2.0406656321900583,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045889354302898445,
|
|
"loss": 6.214,
|
|
"mean_token_accuracy": 0.13442379906773566,
|
|
"num_tokens": 41279384.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 6.608145332336425,
|
|
"epoch": 2.0412007062978224,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004588715100904651,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.1354267381131649,
|
|
"num_tokens": 41289923.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 6.458296060562134,
|
|
"epoch": 2.041735780405586,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004588494718426818,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.14421897679567336,
|
|
"num_tokens": 41300486.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 6.401919412612915,
|
|
"epoch": 2.04227085451335,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004588274282862708,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.14360963180661201,
|
|
"num_tokens": 41310507.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 6.4948516368865965,
|
|
"epoch": 2.042805928621114,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00045880537942186855,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.1460525207221508,
|
|
"num_tokens": 41321284.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 6.479793310165405,
|
|
"epoch": 2.043341002728878,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004587833252501118,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.14869818538427354,
|
|
"num_tokens": 41332037.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 6.436644220352173,
|
|
"epoch": 2.043876076836642,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004587612657716374,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.1404256284236908,
|
|
"num_tokens": 41343480.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 6.514421033859253,
|
|
"epoch": 2.0444111509444056,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004587392009870824,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.13664307445287704,
|
|
"num_tokens": 41353656.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 6.488293075561524,
|
|
"epoch": 2.0449462250521697,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004587171308970836,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.14327220767736434,
|
|
"num_tokens": 41363640.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 6.492086029052734,
|
|
"epoch": 2.045481299159934,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045869505550227857,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.13604222983121872,
|
|
"num_tokens": 41374194.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 6.451062726974487,
|
|
"epoch": 2.0460163732676975,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004586729748033046,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.14803083389997482,
|
|
"num_tokens": 41384968.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 6.469352102279663,
|
|
"epoch": 2.0465514473754616,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00045865088880079924,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.14876729846000672,
|
|
"num_tokens": 41395117.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 6.5053938865661625,
|
|
"epoch": 2.0470865214832252,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004586287974954004,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.14110405296087264,
|
|
"num_tokens": 41406366.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 6.5320250511169435,
|
|
"epoch": 2.0476215955909893,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004586067008877457,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.1459088757634163,
|
|
"num_tokens": 41417388.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 6.4374086380004885,
|
|
"epoch": 2.0481566696987534,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004585845989784734,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.14255037009716034,
|
|
"num_tokens": 41428085.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 6.516263008117676,
|
|
"epoch": 2.048691743806517,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045856249176822155,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.134604249894619,
|
|
"num_tokens": 41439117.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 6.499457502365113,
|
|
"epoch": 2.049226817914281,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045854037925762857,
|
|
"loss": 6.1752,
|
|
"mean_token_accuracy": 0.1368185169994831,
|
|
"num_tokens": 41450042.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 6.46821665763855,
|
|
"epoch": 2.049761892022045,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045851826144733296,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.15025001615285874,
|
|
"num_tokens": 41460554.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 6.5151244640350345,
|
|
"epoch": 2.050296966129809,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00045849613833797326,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.14511755853891373,
|
|
"num_tokens": 41471403.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 6.462577676773071,
|
|
"epoch": 2.050832040237573,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045847400993018835,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.13789881393313408,
|
|
"num_tokens": 41482098.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 6.476891613006591,
|
|
"epoch": 2.0513671143453367,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00045845187622461724,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.14094822630286216,
|
|
"num_tokens": 41493126.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 6.570120620727539,
|
|
"epoch": 2.051902188453101,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000458429737221899,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13628095909953117,
|
|
"num_tokens": 41504242.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 6.4928771495819095,
|
|
"epoch": 2.052437262560865,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004584075929226728,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.14559295326471328,
|
|
"num_tokens": 41515368.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 6.474678325653076,
|
|
"epoch": 2.0529723366686286,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004583854433275782,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.1395520031452179,
|
|
"num_tokens": 41525939.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 6.467396020889282,
|
|
"epoch": 2.0535074107763926,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00045836328843725465,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14105122685432434,
|
|
"num_tokens": 41536505.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 6.464931392669678,
|
|
"epoch": 2.0540424848841563,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045834112825234193,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.14669242650270461,
|
|
"num_tokens": 41546293.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 6.471874475479126,
|
|
"epoch": 2.0545775589919204,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00045831896277347985,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.14656351059675216,
|
|
"num_tokens": 41556596.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 6.509445333480835,
|
|
"epoch": 2.0551126330996845,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004582967920013085,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.14745448306202888,
|
|
"num_tokens": 41566732.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 6.532517051696777,
|
|
"epoch": 2.055647707207448,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045827461593646806,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.13695996776223182,
|
|
"num_tokens": 41577777.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 6.489979219436646,
|
|
"epoch": 2.0561827813152123,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004582524345795989,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.14347779750823975,
|
|
"num_tokens": 41587978.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 6.4816924095153805,
|
|
"epoch": 2.056717855422976,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004582302479313413,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.14375540167093276,
|
|
"num_tokens": 41598977.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 6.502046680450439,
|
|
"epoch": 2.05725292953074,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004582080559923362,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.13674740493297577,
|
|
"num_tokens": 41609664.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 6.478590059280395,
|
|
"epoch": 2.057788003638504,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004581858587632241,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.13895293027162553,
|
|
"num_tokens": 41619427.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 6.472123718261718,
|
|
"epoch": 2.0583230777462678,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004581636562446461,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.1371616877615452,
|
|
"num_tokens": 41629551.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 6.447014617919922,
|
|
"epoch": 2.058858151854032,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004581414484372433,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.13804002851247787,
|
|
"num_tokens": 41640183.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 6.43388876914978,
|
|
"epoch": 2.0593932259617955,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004581192353416569,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.14709998071193695,
|
|
"num_tokens": 41651934.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 6.3898547172546385,
|
|
"epoch": 2.0599283000695596,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004580970169585283,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.16168030798435212,
|
|
"num_tokens": 41662418.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 6.408938789367676,
|
|
"epoch": 2.0604633741773237,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045807479328849906,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.14857290759682656,
|
|
"num_tokens": 41673419.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 6.431122779846191,
|
|
"epoch": 2.0609984482850874,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045805256433221087,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.1496027022600174,
|
|
"num_tokens": 41684132.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 6.518172025680542,
|
|
"epoch": 2.0615335223928515,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004580303300903056,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.1433491162955761,
|
|
"num_tokens": 41695051.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 6.5380795955657955,
|
|
"epoch": 2.062068596500615,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00045800809056342534,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14187479242682458,
|
|
"num_tokens": 41705986.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 6.489912509918213,
|
|
"epoch": 2.0626036706083792,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045798584575221213,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.13931995928287505,
|
|
"num_tokens": 41717082.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 6.504186391830444,
|
|
"epoch": 2.0631387447161433,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004579635956573084,
|
|
"loss": 6.1781,
|
|
"mean_token_accuracy": 0.1459621638059616,
|
|
"num_tokens": 41728783.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 6.49009895324707,
|
|
"epoch": 2.063673818823907,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00045794134027935646,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.14074748381972313,
|
|
"num_tokens": 41740452.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 6.5198619842529295,
|
|
"epoch": 2.064208892931671,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004579190796189991,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.1458289071917534,
|
|
"num_tokens": 41750966.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 6.50558614730835,
|
|
"epoch": 2.064743967039435,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000457896813676879,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.144083159416914,
|
|
"num_tokens": 41762174.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 6.455884265899658,
|
|
"epoch": 2.065279041147199,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045787454245363907,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.13619274497032166,
|
|
"num_tokens": 41773396.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 6.48363618850708,
|
|
"epoch": 2.065814115254963,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004578522659499225,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14194218069314957,
|
|
"num_tokens": 41783833.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 6.466428661346436,
|
|
"epoch": 2.0663491893627266,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045782998416637235,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.15198036134243012,
|
|
"num_tokens": 41795363.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 6.538760805130005,
|
|
"epoch": 2.0668842634704907,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004578076971036321,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.14131421819329262,
|
|
"num_tokens": 41807575.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 6.3735511302948,
|
|
"epoch": 2.067419337578255,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004577854047623454,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.14580662548542023,
|
|
"num_tokens": 41818496.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 6.499590063095093,
|
|
"epoch": 2.0679544116860185,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004577631071431557,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.14684664011001586,
|
|
"num_tokens": 41829106.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 6.45405125617981,
|
|
"epoch": 2.0684894857937826,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00045774080424670704,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.14979782924056054,
|
|
"num_tokens": 41838095.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 6.437284278869629,
|
|
"epoch": 2.069024559901546,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004577184960736433,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.1353687562048435,
|
|
"num_tokens": 41847980.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 6.553657579421997,
|
|
"epoch": 2.0695596340093103,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045769618262460864,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.1402767464518547,
|
|
"num_tokens": 41858625.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 6.507570505142212,
|
|
"epoch": 2.0700947081170744,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004576738639002475,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.13780880868434905,
|
|
"num_tokens": 41870939.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 6.5192183494567875,
|
|
"epoch": 2.070629782224838,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004576515399012041,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.140149012953043,
|
|
"num_tokens": 41882356.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 6.491689586639405,
|
|
"epoch": 2.071164856332602,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004576292106281231,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1387277662754059,
|
|
"num_tokens": 41892306.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 6.512281131744385,
|
|
"epoch": 2.071699930440366,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045760687608164933,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.13818393498659134,
|
|
"num_tokens": 41902450.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 6.48457088470459,
|
|
"epoch": 2.07223500454813,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004575845362624278,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.1443415492773056,
|
|
"num_tokens": 41913319.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 6.522418546676636,
|
|
"epoch": 2.072770078655894,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045756219117110337,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.14059045165777206,
|
|
"num_tokens": 41923598.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 6.542702007293701,
|
|
"epoch": 2.0733051527636577,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045753984080832127,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.1389916017651558,
|
|
"num_tokens": 41934482.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 6.51252179145813,
|
|
"epoch": 2.0738402268714218,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000457517485174727,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.13963203877210617,
|
|
"num_tokens": 41945994.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 6.4817948818206785,
|
|
"epoch": 2.0743753009791854,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045749512427096595,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.13679138645529748,
|
|
"num_tokens": 41956564.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 6.440240144729614,
|
|
"epoch": 2.0749103750869495,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045747275809768386,
|
|
"loss": 6.1358,
|
|
"mean_token_accuracy": 0.14567358940839767,
|
|
"num_tokens": 41966847.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 6.506151437759399,
|
|
"epoch": 2.0754454491947136,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004574503866555265,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.1337882809340954,
|
|
"num_tokens": 41977752.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 6.516854572296142,
|
|
"epoch": 2.0759805233024773,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045742800994513983,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.14443642646074295,
|
|
"num_tokens": 41987837.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 6.52735481262207,
|
|
"epoch": 2.0765155974102414,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00045740562796717005,
|
|
"loss": 6.152,
|
|
"mean_token_accuracy": 0.13824782595038415,
|
|
"num_tokens": 41997988.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 6.381102895736694,
|
|
"epoch": 2.077050671518005,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004573832407222634,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.14729070663452148,
|
|
"num_tokens": 42009643.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 6.475057315826416,
|
|
"epoch": 2.077585745625769,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004573608482110663,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.13999679908156396,
|
|
"num_tokens": 42019972.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 6.497097396850586,
|
|
"epoch": 2.0781208197335332,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045733845043422535,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.14451572746038438,
|
|
"num_tokens": 42030536.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 6.529263639450074,
|
|
"epoch": 2.078655893841297,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004573160473923872,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.1403690680861473,
|
|
"num_tokens": 42041217.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 6.36537127494812,
|
|
"epoch": 2.079190967949061,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004572936390861988,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.14835600107908248,
|
|
"num_tokens": 42051346.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 6.546513509750366,
|
|
"epoch": 2.0797260420568247,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004572712255163072,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.13938311040401458,
|
|
"num_tokens": 42062718.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 6.524495077133179,
|
|
"epoch": 2.0802611161645888,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004572488066833596,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.1377783089876175,
|
|
"num_tokens": 42073587.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 6.5476109981536865,
|
|
"epoch": 2.080796190272353,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045722638258800335,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14769052118062972,
|
|
"num_tokens": 42083763.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 6.429262590408325,
|
|
"epoch": 2.0813312643801165,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004572039532308858,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.14719380512833596,
|
|
"num_tokens": 42094062.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 6.463222217559815,
|
|
"epoch": 2.0818663384878806,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004571815186126549,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.13777271136641503,
|
|
"num_tokens": 42106136.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 6.483076667785644,
|
|
"epoch": 2.0824014125956447,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045715907873395805,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.13568266183137895,
|
|
"num_tokens": 42116309.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 6.462263345718384,
|
|
"epoch": 2.0829364867034084,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004571366335954435,
|
|
"loss": 6.1484,
|
|
"mean_token_accuracy": 0.14241429641842843,
|
|
"num_tokens": 42127747.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 6.429238605499267,
|
|
"epoch": 2.0834715608111725,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004571141831977592,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.15075682997703552,
|
|
"num_tokens": 42137992.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 6.457944917678833,
|
|
"epoch": 2.084006634918936,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004570917275415535,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.14265020191669464,
|
|
"num_tokens": 42148833.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 6.44670033454895,
|
|
"epoch": 2.0845417090267,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004570692666274747,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14300988093018532,
|
|
"num_tokens": 42159276.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 6.566137170791626,
|
|
"epoch": 2.0850767831344643,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004570468004561715,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.14038451686501502,
|
|
"num_tokens": 42171541.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 6.4842836380004885,
|
|
"epoch": 2.085611857242228,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045702432902829245,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.14726416394114494,
|
|
"num_tokens": 42182888.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 6.458319664001465,
|
|
"epoch": 2.086146931349992,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004570018523444865,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.152434304356575,
|
|
"num_tokens": 42193405.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 6.482660341262817,
|
|
"epoch": 2.0866820054577557,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045697937040540263,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.1448497325181961,
|
|
"num_tokens": 42203355.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 6.451343965530396,
|
|
"epoch": 2.08721707956552,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045695688321169,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.13565196245908737,
|
|
"num_tokens": 42213191.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 6.488658666610718,
|
|
"epoch": 2.087752153673284,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045693439076399797,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.13889316320419312,
|
|
"num_tokens": 42223357.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 6.521796703338623,
|
|
"epoch": 2.0882872277810476,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045691189306297595,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.14505178332328797,
|
|
"num_tokens": 42234917.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 6.564554977416992,
|
|
"epoch": 2.0888223018888117,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045688939010927353,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.1397237330675125,
|
|
"num_tokens": 42245977.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 6.475429058074951,
|
|
"epoch": 2.0893573759965753,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004568668819035406,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.1414799951016903,
|
|
"num_tokens": 42257523.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 6.570040369033814,
|
|
"epoch": 2.0898924501043394,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045684436844642694,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.14639808982610703,
|
|
"num_tokens": 42267727.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 6.544137954711914,
|
|
"epoch": 2.0904275242121035,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004568218497385828,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.1419399283826351,
|
|
"num_tokens": 42278201.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 6.477737379074097,
|
|
"epoch": 2.090962598319867,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004567993257806582,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.13735170289874077,
|
|
"num_tokens": 42288695.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 6.477229118347168,
|
|
"epoch": 2.0914976724276313,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004567767965733036,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.1436895728111267,
|
|
"num_tokens": 42299418.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 6.500970315933228,
|
|
"epoch": 2.092032746535395,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045675426211716963,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.14467365369200708,
|
|
"num_tokens": 42310901.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 6.553741312026977,
|
|
"epoch": 2.092567820643159,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004567317224129069,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.14897666946053506,
|
|
"num_tokens": 42320055.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 6.481790685653687,
|
|
"epoch": 2.093102894750923,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004567091774611661,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.13946203663945198,
|
|
"num_tokens": 42330393.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 6.40696496963501,
|
|
"epoch": 2.093637968858687,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045668662726259846,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.14474439173936843,
|
|
"num_tokens": 42341384.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 6.495103406906128,
|
|
"epoch": 2.094173042966451,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00045666407181785496,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.1518527738749981,
|
|
"num_tokens": 42352351.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 6.419457292556762,
|
|
"epoch": 2.094708117074215,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004566415111275869,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.14589630886912347,
|
|
"num_tokens": 42363912.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 6.458062553405762,
|
|
"epoch": 2.0952431911819787,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004566189451924457,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.14219927787780762,
|
|
"num_tokens": 42374638.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 6.441175651550293,
|
|
"epoch": 2.0957782652897428,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045659637401308296,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.15543012022972108,
|
|
"num_tokens": 42385976.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 6.469603681564331,
|
|
"epoch": 2.0963133393975064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004565737975901505,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.13748691454529763,
|
|
"num_tokens": 42395714.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 6.465291452407837,
|
|
"epoch": 2.0968484135052705,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004565512159243001,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.1491420179605484,
|
|
"num_tokens": 42406027.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 6.539014196395874,
|
|
"epoch": 2.0973834876130346,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004565286290161839,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.1383569948375225,
|
|
"num_tokens": 42417756.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 6.514355230331421,
|
|
"epoch": 2.0979185617207983,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045650603686645403,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13685153424739838,
|
|
"num_tokens": 42429321.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 6.424641132354736,
|
|
"epoch": 2.0984536358285624,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045648343947576284,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.15203089416027069,
|
|
"num_tokens": 42440003.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 6.523432636260987,
|
|
"epoch": 2.098988709936326,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004564608368447628,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.1436428375542164,
|
|
"num_tokens": 42450743.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 6.451916790008545,
|
|
"epoch": 2.09952378404409,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004564382289741067,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.13660894110798835,
|
|
"num_tokens": 42460885.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 6.415532541275025,
|
|
"epoch": 2.1000588581518542,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045641561586444706,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.14363902807235718,
|
|
"num_tokens": 42470854.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 6.425800848007202,
|
|
"epoch": 2.100593932259618,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00045639299751643714,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.13822885900735854,
|
|
"num_tokens": 42482392.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 6.537102174758911,
|
|
"epoch": 2.101129006367382,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045637037393072996,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.1353036232292652,
|
|
"num_tokens": 42494156.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 6.513655471801758,
|
|
"epoch": 2.1016640804751456,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004563477451079786,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.1431437224149704,
|
|
"num_tokens": 42505185.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 6.388147211074829,
|
|
"epoch": 2.1021991545829097,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045632511104883657,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.14328691661357879,
|
|
"num_tokens": 42516415.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 6.4794971466064455,
|
|
"epoch": 2.102734228690674,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004563024717539575,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.14822357147932053,
|
|
"num_tokens": 42526945.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 6.578627300262451,
|
|
"epoch": 2.1032693027984375,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045627982722399506,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.1379284031689167,
|
|
"num_tokens": 42537629.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 6.435596323013305,
|
|
"epoch": 2.1038043769062016,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00045625717745960306,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.1474095955491066,
|
|
"num_tokens": 42547952.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 6.432778358459473,
|
|
"epoch": 2.1043394510139652,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045623452246143547,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.1428218349814415,
|
|
"num_tokens": 42559026.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 6.5374414920806885,
|
|
"epoch": 2.1048745251217293,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004562118622301466,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.1409413531422615,
|
|
"num_tokens": 42570046.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 6.548043823242187,
|
|
"epoch": 2.1054095992294934,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004561891967663906,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.13744086623191834,
|
|
"num_tokens": 42580440.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 6.514630222320557,
|
|
"epoch": 2.105944673337257,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045616652607082203,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.13829393386840821,
|
|
"num_tokens": 42591872.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 6.445277261734009,
|
|
"epoch": 2.106479747445021,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004561438501440955,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.13981586173176766,
|
|
"num_tokens": 42602843.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 6.445372295379639,
|
|
"epoch": 2.107014821552785,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004561211689868657,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.14785133600234984,
|
|
"num_tokens": 42613476.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 6.4247962474823,
|
|
"epoch": 2.107549895660549,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045609848259978766,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.15796087831258773,
|
|
"num_tokens": 42624059.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 6.483630037307739,
|
|
"epoch": 2.108084969768313,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004560757909835164,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.14062246009707452,
|
|
"num_tokens": 42633980.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 6.498415565490722,
|
|
"epoch": 2.1086200438760767,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045605309413870697,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.13881975784897804,
|
|
"num_tokens": 42645504.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 6.537342214584351,
|
|
"epoch": 2.109155117983841,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004560303920660151,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.13537875711917877,
|
|
"num_tokens": 42655403.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 6.579575824737549,
|
|
"epoch": 2.1096901920916045,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045600768476609596,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.14258636981248857,
|
|
"num_tokens": 42666236.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 6.493932390213013,
|
|
"epoch": 2.1102252661993686,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045598497223960533,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.13089609593153,
|
|
"num_tokens": 42677365.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 6.489971113204956,
|
|
"epoch": 2.1107603403071327,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045596225448719913,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.1416928417980671,
|
|
"num_tokens": 42688518.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 6.501855516433716,
|
|
"epoch": 2.1112954144148963,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00045593953150953326,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.1406565338373184,
|
|
"num_tokens": 42699877.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 6.451576900482178,
|
|
"epoch": 2.1118304885226604,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004559168033072638,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.14994507431983947,
|
|
"num_tokens": 42710191.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 6.479924058914184,
|
|
"epoch": 2.1123655626304245,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045589406988104717,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.14160223454236984,
|
|
"num_tokens": 42720874.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 6.5164580821990965,
|
|
"epoch": 2.112900636738188,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004558713312315396,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.14363001137971879,
|
|
"num_tokens": 42731783.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 6.487932395935059,
|
|
"epoch": 2.1134357108459523,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004558485873593978,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.14117844849824907,
|
|
"num_tokens": 42741602.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 6.53803071975708,
|
|
"epoch": 2.113970784953716,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045582583826527835,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.14546334072947503,
|
|
"num_tokens": 42751249.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 6.469318437576294,
|
|
"epoch": 2.11450585906148,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004558030839498383,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.1475038781762123,
|
|
"num_tokens": 42762083.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 6.468356037139893,
|
|
"epoch": 2.115040933169244,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004557803244137347,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.16054053381085395,
|
|
"num_tokens": 42773443.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 6.450197792053222,
|
|
"epoch": 2.115576007277008,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004557575596576245,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.1410667136311531,
|
|
"num_tokens": 42784126.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 6.411456775665283,
|
|
"epoch": 2.116111081384772,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045573478968216526,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1495702773332596,
|
|
"num_tokens": 42795472.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 6.448283720016479,
|
|
"epoch": 2.1166461554925355,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045571201448801424,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.149944069981575,
|
|
"num_tokens": 42805279.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 6.497313356399536,
|
|
"epoch": 2.1171812296002996,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004556892340758293,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.14337343201041222,
|
|
"num_tokens": 42815680.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 6.541849040985108,
|
|
"epoch": 2.1177163037080637,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004556664484462681,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.13567657470703126,
|
|
"num_tokens": 42826724.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 6.561293220520019,
|
|
"epoch": 2.1182513778158274,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045564365759998856,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.13923074975609778,
|
|
"num_tokens": 42837875.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 6.4971517562866214,
|
|
"epoch": 2.1187864519235915,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004556208615376488,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.13982677981257438,
|
|
"num_tokens": 42848714.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 6.450415515899659,
|
|
"epoch": 2.119321526031355,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004555980602599071,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.14171442985534669,
|
|
"num_tokens": 42859764.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 6.411892223358154,
|
|
"epoch": 2.1198566001391193,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004555752537674217,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.1471356302499771,
|
|
"num_tokens": 42870346.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 6.4905595779418945,
|
|
"epoch": 2.1203916742468834,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004555524420608513,
|
|
"loss": 6.151,
|
|
"mean_token_accuracy": 0.14037445932626724,
|
|
"num_tokens": 42882706.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 6.459938287734985,
|
|
"epoch": 2.120926748354647,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045552962514085443,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.14691274538636206,
|
|
"num_tokens": 42893611.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 6.507153940200806,
|
|
"epoch": 2.121461822462411,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045550680300809003,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.1446467638015747,
|
|
"num_tokens": 42904034.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 6.4270158290863035,
|
|
"epoch": 2.1219968965701748,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045548397566321706,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.1386638194322586,
|
|
"num_tokens": 42915530.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 6.4584770679473875,
|
|
"epoch": 2.122531970677939,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004554611431068947,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.1420776851475239,
|
|
"num_tokens": 42926696.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 6.492058563232422,
|
|
"epoch": 2.123067044785703,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004554383053397822,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.1484109416604042,
|
|
"num_tokens": 42936985.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 6.484788322448731,
|
|
"epoch": 2.1236021188934666,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045541546236253896,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.14406656697392464,
|
|
"num_tokens": 42947996.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 6.438353872299194,
|
|
"epoch": 2.1241371930012307,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045539261417582456,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.1453639894723892,
|
|
"num_tokens": 42959669.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 6.403155374526977,
|
|
"epoch": 2.124672267108995,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045536976078029874,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.1479623094201088,
|
|
"num_tokens": 42969687.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 6.461460113525391,
|
|
"epoch": 2.1252073412167585,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004553469021766215,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.13120304346084594,
|
|
"num_tokens": 42980752.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 6.529850339889526,
|
|
"epoch": 2.1257424153245226,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045532403836545286,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.1411494120955467,
|
|
"num_tokens": 42991949.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 6.461529397964478,
|
|
"epoch": 2.1262774894322862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004553011693474528,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1494043216109276,
|
|
"num_tokens": 43002689.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 6.485022020339966,
|
|
"epoch": 2.1268125635400503,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004552782951232819,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.14168797582387924,
|
|
"num_tokens": 43012939.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 6.468227243423462,
|
|
"epoch": 2.1273476376478144,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00045525541569360053,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.14344905391335488,
|
|
"num_tokens": 43023887.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 6.423562860488891,
|
|
"epoch": 2.127882711755578,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004552325310590694,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.1459365077316761,
|
|
"num_tokens": 43034554.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 6.529317188262939,
|
|
"epoch": 2.128417785863342,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004552096412203492,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.14376000091433525,
|
|
"num_tokens": 43046322.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 6.50398736000061,
|
|
"epoch": 2.128952859971106,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000455186746178101,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.14861174970865249,
|
|
"num_tokens": 43055981.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 6.5121767044067385,
|
|
"epoch": 2.12948793407887,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045516384593298584,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.13824398666620255,
|
|
"num_tokens": 43067217.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 6.50492148399353,
|
|
"epoch": 2.130023008186634,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045514094048566486,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.1418042376637459,
|
|
"num_tokens": 43078312.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 6.346564769744873,
|
|
"epoch": 2.1305580822943977,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045511802983679955,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.15819320529699327,
|
|
"num_tokens": 43090210.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 6.455585718154907,
|
|
"epoch": 2.131093156402162,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004550951139870515,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.14370020031929015,
|
|
"num_tokens": 43101282.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 6.4974658489227295,
|
|
"epoch": 2.1316282305099254,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045507219293708227,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.13790655955672265,
|
|
"num_tokens": 43112856.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 6.454631757736206,
|
|
"epoch": 2.1321633046176895,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045504926668755384,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.15341846123337746,
|
|
"num_tokens": 43123898.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 6.5012664794921875,
|
|
"epoch": 2.1326983787254536,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004550263352391281,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.14729975908994675,
|
|
"num_tokens": 43134651.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 6.511061096191407,
|
|
"epoch": 2.1332334528332173,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004550033985924672,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14541507959365846,
|
|
"num_tokens": 43145385.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 6.495218086242676,
|
|
"epoch": 2.1337685269409814,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004549804567482335,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.1441176116466522,
|
|
"num_tokens": 43157356.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 6.519485569000244,
|
|
"epoch": 2.134303601048745,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045495750970708944,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.14577193707227706,
|
|
"num_tokens": 43168289.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 6.421923637390137,
|
|
"epoch": 2.134838675156509,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045493455746969746,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.14722421169281005,
|
|
"num_tokens": 43177796.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 6.441613817214966,
|
|
"epoch": 2.1353737492642733,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004549116000367205,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.1484612539410591,
|
|
"num_tokens": 43188846.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 6.508660173416137,
|
|
"epoch": 2.135908823372037,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00045488863740882133,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.1432749792933464,
|
|
"num_tokens": 43199852.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 6.499727439880371,
|
|
"epoch": 2.136443897479801,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045486566958666307,
|
|
"loss": 6.0877,
|
|
"mean_token_accuracy": 0.1441863916814327,
|
|
"num_tokens": 43210591.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 6.491096925735474,
|
|
"epoch": 2.136978971587565,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045484269657090887,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.14160085022449492,
|
|
"num_tokens": 43221760.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 6.468918561935425,
|
|
"epoch": 2.1375140456953288,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045481971836222205,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.1341404989361763,
|
|
"num_tokens": 43233693.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 6.487259244918823,
|
|
"epoch": 2.138049119803093,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045479673496126615,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.14123794063925743,
|
|
"num_tokens": 43244565.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 6.4275530815124515,
|
|
"epoch": 2.1385841939108565,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045477374636870485,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.1453502856194973,
|
|
"num_tokens": 43254913.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 6.498678398132324,
|
|
"epoch": 2.1391192680186206,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045475075258520175,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.14247939884662628,
|
|
"num_tokens": 43265525.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 6.471640920639038,
|
|
"epoch": 2.1396543421263843,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004547277536114211,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.13235984146595,
|
|
"num_tokens": 43276954.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 6.4997851848602295,
|
|
"epoch": 2.1401894162341484,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004547047494480267,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.1417925976216793,
|
|
"num_tokens": 43287491.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 6.481905317306518,
|
|
"epoch": 2.1407244903419125,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004546817400956829,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.1345571480691433,
|
|
"num_tokens": 43298341.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 6.405822467803955,
|
|
"epoch": 2.141259564449676,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045465872555505417,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.15132260620594024,
|
|
"num_tokens": 43309450.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 6.5346914768219,
|
|
"epoch": 2.1417946385574402,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000454635705826805,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.1373695246875286,
|
|
"num_tokens": 43320126.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 6.544931650161743,
|
|
"epoch": 2.1423297126652043,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004546126809116,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.13375122770667075,
|
|
"num_tokens": 43331347.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 6.47828688621521,
|
|
"epoch": 2.142864786772968,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004545896508101041,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.14316849485039712,
|
|
"num_tokens": 43341351.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 6.532412767410278,
|
|
"epoch": 2.143399860880732,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004545666155229823,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.14234084039926528,
|
|
"num_tokens": 43352471.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 6.519003868103027,
|
|
"epoch": 2.1439349349884957,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045454357505089965,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.14596754610538482,
|
|
"num_tokens": 43363041.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 6.442016220092773,
|
|
"epoch": 2.14447000909626,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004545205293945215,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.14105915054678916,
|
|
"num_tokens": 43375034.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 6.487355136871338,
|
|
"epoch": 2.145005083204024,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004544974785545134,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.13306314796209334,
|
|
"num_tokens": 43386110.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 6.515271520614624,
|
|
"epoch": 2.1455401573117876,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004544744225315407,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.14595941603183746,
|
|
"num_tokens": 43396150.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 6.488174629211426,
|
|
"epoch": 2.1460752314195517,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004544513613262693,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14052343890070915,
|
|
"num_tokens": 43407237.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 6.469608306884766,
|
|
"epoch": 2.1466103055273154,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004544282949393652,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.14775441437959672,
|
|
"num_tokens": 43417626.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 6.488646841049194,
|
|
"epoch": 2.1471453796350795,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004544052233714941,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.14532986730337144,
|
|
"num_tokens": 43427368.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 6.430359697341919,
|
|
"epoch": 2.1476804537428436,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00045438214662332245,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.1424453228712082,
|
|
"num_tokens": 43438159.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 6.4834716796875,
|
|
"epoch": 2.148215527850607,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045435906469551657,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.14322199895977974,
|
|
"num_tokens": 43447403.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 6.49311900138855,
|
|
"epoch": 2.1487506019583713,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045433597758874286,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.15143866688013077,
|
|
"num_tokens": 43457713.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 6.494896507263183,
|
|
"epoch": 2.149285676066135,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.000454312885303668,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.1441124878823757,
|
|
"num_tokens": 43468520.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 6.5642084121704105,
|
|
"epoch": 2.149820750173899,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045428978784095873,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.13654238730669022,
|
|
"num_tokens": 43480501.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 6.568170070648193,
|
|
"epoch": 2.150355824281663,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00045426668520128204,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.14247775599360465,
|
|
"num_tokens": 43491297.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 6.522011947631836,
|
|
"epoch": 2.150890898389427,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004542435773853051,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.14496304243803024,
|
|
"num_tokens": 43501212.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 6.419024419784546,
|
|
"epoch": 2.151425972497191,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000454220464393695,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.13840727582573892,
|
|
"num_tokens": 43511136.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 6.552536344528198,
|
|
"epoch": 2.1519610466049546,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004541973462271192,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.1390797473490238,
|
|
"num_tokens": 43522006.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 6.53021936416626,
|
|
"epoch": 2.1524961207127187,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004541742228862451,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.14211415946483613,
|
|
"num_tokens": 43532746.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 6.430755567550659,
|
|
"epoch": 2.1530311948204828,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045415109437174064,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.14374642074108124,
|
|
"num_tokens": 43543707.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 6.490007734298706,
|
|
"epoch": 2.1535662689282464,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045412796068427337,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.13703791201114654,
|
|
"num_tokens": 43555029.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 6.537265777587891,
|
|
"epoch": 2.1541013430360105,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045410482182451153,
|
|
"loss": 6.1713,
|
|
"mean_token_accuracy": 0.13964841812849044,
|
|
"num_tokens": 43565639.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 6.462145185470581,
|
|
"epoch": 2.1546364171437746,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045408167779312306,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1506087988615036,
|
|
"num_tokens": 43576333.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 6.521839714050293,
|
|
"epoch": 2.1551714912515383,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045405852859077626,
|
|
"loss": 6.113,
|
|
"mean_token_accuracy": 0.13899362310767174,
|
|
"num_tokens": 43587012.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 6.470482683181762,
|
|
"epoch": 2.1557065653593024,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045403537421813975,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.14818194955587388,
|
|
"num_tokens": 43597779.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 6.523967313766479,
|
|
"epoch": 2.156241639467066,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045401221467588184,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.1424321189522743,
|
|
"num_tokens": 43608631.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 6.515417098999023,
|
|
"epoch": 2.15677671357483,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004539890499646714,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.1509397327899933,
|
|
"num_tokens": 43620254.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 6.435489892959595,
|
|
"epoch": 2.1573117876825942,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004539658800851773,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.14455048590898514,
|
|
"num_tokens": 43630986.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 6.40526442527771,
|
|
"epoch": 2.157846861790358,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004539427050380686,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.13671587854623796,
|
|
"num_tokens": 43641260.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 6.499885511398316,
|
|
"epoch": 2.158381935898122,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00045391952482401444,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.14062789976596832,
|
|
"num_tokens": 43652093.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 6.51837124824524,
|
|
"epoch": 2.1589170100058857,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045389633944368406,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.14618946686387063,
|
|
"num_tokens": 43662799.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 6.461586856842041,
|
|
"epoch": 2.1594520841136498,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004538731488977471,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.14218505173921586,
|
|
"num_tokens": 43674198.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 6.459530305862427,
|
|
"epoch": 2.159987158221414,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004538499531868731,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14445096328854562,
|
|
"num_tokens": 43684841.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 6.54753041267395,
|
|
"epoch": 2.1605222323291775,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045382675231173174,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.1367589585483074,
|
|
"num_tokens": 43695903.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 6.533148527145386,
|
|
"epoch": 2.1610573064369416,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004538035462729931,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.14191216602921486,
|
|
"num_tokens": 43706740.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 6.493363237380981,
|
|
"epoch": 2.1615923805447053,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004537803350713273,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.14305991306900978,
|
|
"num_tokens": 43717124.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 6.43371696472168,
|
|
"epoch": 2.1621274546524694,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004537571187074043,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.14660966843366624,
|
|
"num_tokens": 43727346.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 6.550573539733887,
|
|
"epoch": 2.1626625287602335,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045373389718189464,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1285846747457981,
|
|
"num_tokens": 43738297.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 6.51973147392273,
|
|
"epoch": 2.163197602867997,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004537106704954689,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14054710939526557,
|
|
"num_tokens": 43749543.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 6.507083559036255,
|
|
"epoch": 2.163732676975761,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00045368743864879755,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.14513924196362496,
|
|
"num_tokens": 43760324.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 6.542077159881591,
|
|
"epoch": 2.164267751083525,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045366420164255156,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.13762131631374358,
|
|
"num_tokens": 43770391.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 6.423087930679321,
|
|
"epoch": 2.164802825191289,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004536409594774019,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.13530075773596764,
|
|
"num_tokens": 43781516.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 6.377832555770874,
|
|
"epoch": 2.165337899299053,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045361771215401953,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.14707974418997766,
|
|
"num_tokens": 43794152.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 6.518850564956665,
|
|
"epoch": 2.1658729734068167,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00045359445967307595,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.14454821422696112,
|
|
"num_tokens": 43805712.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 6.557677412033081,
|
|
"epoch": 2.166408047514581,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004535712020352423,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.1400250017642975,
|
|
"num_tokens": 43816985.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 6.487140893936157,
|
|
"epoch": 2.166943121622345,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004535479392411904,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.14423147365450859,
|
|
"num_tokens": 43828048.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 6.512788724899292,
|
|
"epoch": 2.1674781957301086,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045352467129159183,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.1426374226808548,
|
|
"num_tokens": 43838507.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 6.404138040542603,
|
|
"epoch": 2.1680132698378727,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045350139818711846,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.14408638179302216,
|
|
"num_tokens": 43849328.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 6.454526615142822,
|
|
"epoch": 2.1685483439456363,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004534781199284423,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.14136345461010932,
|
|
"num_tokens": 43860311.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 6.540534973144531,
|
|
"epoch": 2.1690834180534004,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004534548365162354,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.14096086621284484,
|
|
"num_tokens": 43871167.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 6.461973047256469,
|
|
"epoch": 2.169618492161164,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00045343154795117024,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.14626741260290146,
|
|
"num_tokens": 43882332.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 6.528645181655884,
|
|
"epoch": 2.170153566268928,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004534082542339192,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.14352528899908065,
|
|
"num_tokens": 43892971.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 6.464555978775024,
|
|
"epoch": 2.1706886403766923,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045338495536515497,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.14322419315576554,
|
|
"num_tokens": 43904305.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 6.3747905731201175,
|
|
"epoch": 2.171223714484456,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004533616513455502,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.14520493596792222,
|
|
"num_tokens": 43914431.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 6.445853567123413,
|
|
"epoch": 2.17175878859222,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045333834217577775,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.14553093761205674,
|
|
"num_tokens": 43925350.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 6.422257614135742,
|
|
"epoch": 2.172293862699984,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00045331502785651075,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.1409260854125023,
|
|
"num_tokens": 43936194.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 6.531687641143799,
|
|
"epoch": 2.172828936807748,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004532917083884224,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.1401752181351185,
|
|
"num_tokens": 43946692.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 6.509691047668457,
|
|
"epoch": 2.173364010915512,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000453268383772186,
|
|
"loss": 6.106,
|
|
"mean_token_accuracy": 0.14296674653887748,
|
|
"num_tokens": 43957493.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 6.503253221511841,
|
|
"epoch": 2.1738990850232756,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045324505400847506,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.14070744961500167,
|
|
"num_tokens": 43970203.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 6.489485073089599,
|
|
"epoch": 2.1744341591310397,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045322171909796327,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.1403039015829563,
|
|
"num_tokens": 43980778.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 6.466435480117798,
|
|
"epoch": 2.1749692332388038,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045319837904132435,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.14622555673122406,
|
|
"num_tokens": 43992239.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 6.502254819869995,
|
|
"epoch": 2.1755043073465674,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004531750338392323,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.1422283098101616,
|
|
"num_tokens": 44001882.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 6.442241382598877,
|
|
"epoch": 2.1760393814543315,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004531516834923611,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.14044273942708968,
|
|
"num_tokens": 44013192.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 6.558344841003418,
|
|
"epoch": 2.176574455562095,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004531283280013852,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.13786421865224838,
|
|
"num_tokens": 44023072.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 6.533612155914307,
|
|
"epoch": 2.1771095296698593,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045310496736697875,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.13985364958643914,
|
|
"num_tokens": 44034238.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 6.473046875,
|
|
"epoch": 2.1776446037776234,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045308160158981646,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14215909615159034,
|
|
"num_tokens": 44044392.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 6.464304065704345,
|
|
"epoch": 2.178179677885387,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000453058230670573,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.14172023087739943,
|
|
"num_tokens": 44056129.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 6.444278764724731,
|
|
"epoch": 2.178714751993151,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045303485460992303,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.15108377784490584,
|
|
"num_tokens": 44067600.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 6.47888035774231,
|
|
"epoch": 2.1792498261009148,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045301147340854177,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.1531740114092827,
|
|
"num_tokens": 44077373.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 6.477386331558227,
|
|
"epoch": 2.179784900208679,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045298808706710416,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.14295275062322615,
|
|
"num_tokens": 44087422.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 6.520819902420044,
|
|
"epoch": 2.180319974316443,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045296469558628555,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.14255437552928923,
|
|
"num_tokens": 44098524.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 6.4786275863647464,
|
|
"epoch": 2.1808550484242066,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045294129896676134,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.15057651251554488,
|
|
"num_tokens": 44108340.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 6.45948371887207,
|
|
"epoch": 2.1813901225319707,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004529178972092071,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.1359841264784336,
|
|
"num_tokens": 44118985.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 6.517501878738403,
|
|
"epoch": 2.1819251966397344,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045289449031429873,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.143955484777689,
|
|
"num_tokens": 44129126.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 6.526478576660156,
|
|
"epoch": 2.1824602707474985,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045287107828271184,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.14495654180645942,
|
|
"num_tokens": 44139731.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 6.479117488861084,
|
|
"epoch": 2.1829953448552626,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004528476611151226,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14143309295177459,
|
|
"num_tokens": 44149924.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 6.470751094818115,
|
|
"epoch": 2.1835304189630262,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004528242388122071,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.13908825367689132,
|
|
"num_tokens": 44161155.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 6.491450452804566,
|
|
"epoch": 2.1840654930707903,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004528008113746417,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.14211047291755677,
|
|
"num_tokens": 44171563.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 6.446858167648315,
|
|
"epoch": 2.1846005671785544,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045277737880310284,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.1416269823908806,
|
|
"num_tokens": 44182719.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 6.42777271270752,
|
|
"epoch": 2.185135641286318,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045275394109826715,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.14696394503116608,
|
|
"num_tokens": 44192214.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 6.430699396133423,
|
|
"epoch": 2.185670715394082,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045273049826081145,
|
|
"loss": 6.1169,
|
|
"mean_token_accuracy": 0.14169675558805467,
|
|
"num_tokens": 44204074.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 6.55955171585083,
|
|
"epoch": 2.186205789501846,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004527070502914125,
|
|
"loss": 6.251,
|
|
"mean_token_accuracy": 0.13508173003792762,
|
|
"num_tokens": 44214402.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 6.564619398117065,
|
|
"epoch": 2.18674086360961,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004526835971907475,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.1409166358411312,
|
|
"num_tokens": 44224479.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 6.47654242515564,
|
|
"epoch": 2.187275937717374,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00045266013895949356,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.141594035923481,
|
|
"num_tokens": 44234069.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 6.449040937423706,
|
|
"epoch": 2.1878110118251377,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004526366755983281,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.13885367885231972,
|
|
"num_tokens": 44244978.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 6.489460229873657,
|
|
"epoch": 2.188346085932902,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004526132071079286,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.14799125045537947,
|
|
"num_tokens": 44255657.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 6.473532009124756,
|
|
"epoch": 2.1888811600406655,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045258973348897267,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.1426821157336235,
|
|
"num_tokens": 44267370.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 6.413994073867798,
|
|
"epoch": 2.1894162341484296,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004525662547421382,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.14376394227147102,
|
|
"num_tokens": 44277855.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 6.494499588012696,
|
|
"epoch": 2.1899513082561937,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000452542770868103,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.14557158648967744,
|
|
"num_tokens": 44288233.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 6.45966534614563,
|
|
"epoch": 2.1904863823639573,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045251928186754533,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.15051595345139504,
|
|
"num_tokens": 44298054.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 6.490744018554688,
|
|
"epoch": 2.1910214564717214,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004524957877411432,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.14246877953410148,
|
|
"num_tokens": 44309435.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 6.545108270645142,
|
|
"epoch": 2.191556530579485,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004524722884895753,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.14126525223255157,
|
|
"num_tokens": 44320502.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 6.411724042892456,
|
|
"epoch": 2.192091604687249,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045244878411352,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.15645946338772773,
|
|
"num_tokens": 44330911.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 6.504664468765259,
|
|
"epoch": 2.1926266787950133,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004524252746136559,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.13888708055019378,
|
|
"num_tokens": 44342159.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 6.480413436889648,
|
|
"epoch": 2.193161752902777,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045240175999066194,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.14757447615265845,
|
|
"num_tokens": 44352293.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 6.483118009567261,
|
|
"epoch": 2.193696827010541,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045237824024521714,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.14210179299116135,
|
|
"num_tokens": 44362321.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 6.492488813400269,
|
|
"epoch": 2.1942319011183047,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004523547153780005,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.14138875603675843,
|
|
"num_tokens": 44372682.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 6.498578691482544,
|
|
"epoch": 2.194766975226069,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004523311853896915,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.14599357843399047,
|
|
"num_tokens": 44383482.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 6.35706672668457,
|
|
"epoch": 2.195302049333833,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00045230765028096925,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.16601943522691726,
|
|
"num_tokens": 44395333.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 6.501402091979981,
|
|
"epoch": 2.1958371234415965,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045228411005251366,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.1356913849711418,
|
|
"num_tokens": 44406210.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 6.562849664688111,
|
|
"epoch": 2.1963721975493606,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004522605647050043,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.13747389018535613,
|
|
"num_tokens": 44415834.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 6.608779859542847,
|
|
"epoch": 2.1969072716571247,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045223701423912103,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.13901744186878204,
|
|
"num_tokens": 44427902.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 6.484367179870605,
|
|
"epoch": 2.1974423457648884,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00045221345865554386,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.15032985359430312,
|
|
"num_tokens": 44437406.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 6.450162410736084,
|
|
"epoch": 2.1979774198726525,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045218989795495294,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.1465378113090992,
|
|
"num_tokens": 44446889.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 6.4537286281585695,
|
|
"epoch": 2.198512493980416,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045216633213802866,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.13990189880132675,
|
|
"num_tokens": 44457132.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 6.475618886947632,
|
|
"epoch": 2.1990475680881802,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045214276120545137,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.13710540011525155,
|
|
"num_tokens": 44468006.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 6.533304738998413,
|
|
"epoch": 2.199582642195944,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004521191851579019,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.14562759175896645,
|
|
"num_tokens": 44478650.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 6.467861270904541,
|
|
"epoch": 2.200117716303708,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004520956039960607,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.1399306148290634,
|
|
"num_tokens": 44489842.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 6.47445764541626,
|
|
"epoch": 2.200652790411472,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045207201772060887,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1480284184217453,
|
|
"num_tokens": 44500444.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 6.4193922996521,
|
|
"epoch": 2.2011878645192358,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004520484263322274,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.14889391362667084,
|
|
"num_tokens": 44510711.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 6.450742149353028,
|
|
"epoch": 2.201722938627,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004520248298315975,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.1452381893992424,
|
|
"num_tokens": 44522343.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 6.44204044342041,
|
|
"epoch": 2.202258012734764,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045200122821940057,
|
|
"loss": 6.1594,
|
|
"mean_token_accuracy": 0.14006644934415818,
|
|
"num_tokens": 44533218.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 6.564455604553222,
|
|
"epoch": 2.2027930868425276,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045197762149631795,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.14281179010868073,
|
|
"num_tokens": 44543406.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 6.556970834732056,
|
|
"epoch": 2.2033281609502917,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045195400966303146,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.14433204755187035,
|
|
"num_tokens": 44555329.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 6.536537981033325,
|
|
"epoch": 2.2038632350580554,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004519303927202228,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.14017735421657562,
|
|
"num_tokens": 44565191.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 6.483732080459594,
|
|
"epoch": 2.2043983091658195,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045190677066857384,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.15376509577035904,
|
|
"num_tokens": 44576374.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 6.444904947280884,
|
|
"epoch": 2.2049333832735836,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004518831435087668,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.1488921172916889,
|
|
"num_tokens": 44586533.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 6.376462459564209,
|
|
"epoch": 2.2054684573813472,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004518595112414838,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.1550952360033989,
|
|
"num_tokens": 44596753.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 6.551543855667115,
|
|
"epoch": 2.2060035314891113,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004518358738674073,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.13503544703125953,
|
|
"num_tokens": 44607632.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 6.549866008758545,
|
|
"epoch": 2.206538605596875,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004518122313872198,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.13973730579018592,
|
|
"num_tokens": 44618786.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 6.450780916213989,
|
|
"epoch": 2.207073679704639,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045178858380160396,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.14023820906877518,
|
|
"num_tokens": 44628760.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 6.489461898803711,
|
|
"epoch": 2.207608753812403,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004517649311112426,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.14050846993923188,
|
|
"num_tokens": 44641206.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 6.535753488540649,
|
|
"epoch": 2.208143827920167,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004517412733168187,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.14522838592529297,
|
|
"num_tokens": 44651923.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 6.481085777282715,
|
|
"epoch": 2.208678902027931,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045171761041901533,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.1438140444457531,
|
|
"num_tokens": 44662375.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 6.353289842605591,
|
|
"epoch": 2.2092139761356946,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004516939424185158,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.15177821815013887,
|
|
"num_tokens": 44673201.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 6.4304039001464846,
|
|
"epoch": 2.2097490502434587,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004516702693160035,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.1409784272313118,
|
|
"num_tokens": 44684300.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 6.530240869522094,
|
|
"epoch": 2.210284124351223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004516465911121621,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.1425748884677887,
|
|
"num_tokens": 44694603.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 6.508754730224609,
|
|
"epoch": 2.2108191984589864,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004516229078076751,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.1477656126022339,
|
|
"num_tokens": 44704461.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 6.505958843231201,
|
|
"epoch": 2.2113542725667505,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004515992194032265,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.14030279144644736,
|
|
"num_tokens": 44715784.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 6.4570409774780275,
|
|
"epoch": 2.211889346674514,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045157552589950023,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1499457612633705,
|
|
"num_tokens": 44726025.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 6.408047342300415,
|
|
"epoch": 2.2124244207822783,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004515518272971805,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1566786177456379,
|
|
"num_tokens": 44736602.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 6.5007734298706055,
|
|
"epoch": 2.2129594948900424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004515281235969515,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.13739494383335113,
|
|
"num_tokens": 44746260.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 6.449839973449707,
|
|
"epoch": 2.213494568997806,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004515044147994978,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.1467547632753849,
|
|
"num_tokens": 44756894.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 6.483930683135986,
|
|
"epoch": 2.21402964310557,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004514807009055039,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.1407784640789032,
|
|
"num_tokens": 44768483.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 6.454762411117554,
|
|
"epoch": 2.2145647172133343,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045145698191565456,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1482870250940323,
|
|
"num_tokens": 44778843.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 6.458995056152344,
|
|
"epoch": 2.215099791321098,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045143325783063466,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.14676833376288415,
|
|
"num_tokens": 44788659.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 6.466281938552856,
|
|
"epoch": 2.215634865428862,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004514095286511293,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.14670583754777908,
|
|
"num_tokens": 44799730.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 6.432733345031738,
|
|
"epoch": 2.2161699395366257,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004513857943778235,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.1518693208694458,
|
|
"num_tokens": 44811679.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 6.483310317993164,
|
|
"epoch": 2.2167050136443898,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004513620550114027,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.1437581568956375,
|
|
"num_tokens": 44821996.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 6.5152074813842775,
|
|
"epoch": 2.217240087752154,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045133831055255234,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.14024235755205156,
|
|
"num_tokens": 44833713.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 6.488360595703125,
|
|
"epoch": 2.2177751618599175,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004513145610019581,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.1454211637377739,
|
|
"num_tokens": 44844751.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 6.4918300151824955,
|
|
"epoch": 2.2183102359676816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045129080636030554,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.13638500720262528,
|
|
"num_tokens": 44856089.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 6.480890226364136,
|
|
"epoch": 2.2188453100754453,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004512670466282808,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.14371456801891327,
|
|
"num_tokens": 44867313.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 6.519718313217163,
|
|
"epoch": 2.2193803841832094,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045124328180656993,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.1397297464311123,
|
|
"num_tokens": 44878430.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 6.489490127563476,
|
|
"epoch": 2.2199154582909735,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045121951189585897,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.14514275640249252,
|
|
"num_tokens": 44888746.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 6.483740425109863,
|
|
"epoch": 2.220450532398737,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00045119573689683445,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.13851530104875565,
|
|
"num_tokens": 44899412.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 6.474801683425904,
|
|
"epoch": 2.2209856065065012,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045117195681018273,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.14496598690748214,
|
|
"num_tokens": 44910362.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 6.451879596710205,
|
|
"epoch": 2.221520680614265,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004511481716365905,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14089406579732894,
|
|
"num_tokens": 44920552.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 6.464407587051392,
|
|
"epoch": 2.222055754722029,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004511243813767446,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.13718210086226462,
|
|
"num_tokens": 44932090.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 6.502533960342407,
|
|
"epoch": 2.222590828829793,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000451100586031332,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.1424417018890381,
|
|
"num_tokens": 44944122.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 6.524023962020874,
|
|
"epoch": 2.2231259029375567,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045107678560103953,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.14315226897597313,
|
|
"num_tokens": 44955104.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 6.473584270477295,
|
|
"epoch": 2.223660977045321,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045105298008655485,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.14250846058130265,
|
|
"num_tokens": 44965495.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 6.4412439346313475,
|
|
"epoch": 2.2241960511530845,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045102916948856493,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.13755118027329444,
|
|
"num_tokens": 44976627.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 6.515741062164307,
|
|
"epoch": 2.2247311252608486,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004510053538077576,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.13910733982920648,
|
|
"num_tokens": 44987955.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 6.549260854721069,
|
|
"epoch": 2.2252661993686127,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004509815330448203,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.14129999950528144,
|
|
"num_tokens": 44998124.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 6.513506078720093,
|
|
"epoch": 2.2258012734763764,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000450957707200441,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.13884468376636505,
|
|
"num_tokens": 45007881.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 6.476696252822876,
|
|
"epoch": 2.2263363475841405,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004509338762753076,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.15047593265771866,
|
|
"num_tokens": 45018994.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 6.48284068107605,
|
|
"epoch": 2.2268714216919046,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004509100402701083,
|
|
"loss": 6.1856,
|
|
"mean_token_accuracy": 0.14077048227190972,
|
|
"num_tokens": 45030109.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 6.394616651535034,
|
|
"epoch": 2.227406495799668,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045088619918553136,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.15419016480445863,
|
|
"num_tokens": 45039872.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 6.5200457096099855,
|
|
"epoch": 2.2279415699074323,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004508623530222651,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.15519756972789764,
|
|
"num_tokens": 45049216.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 6.387506532669067,
|
|
"epoch": 2.228476644015196,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045083850178099805,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.15361984074115753,
|
|
"num_tokens": 45059191.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 6.400663280487061,
|
|
"epoch": 2.22901171812296,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000450814645462419,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.14758966714143754,
|
|
"num_tokens": 45069212.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 6.452826261520386,
|
|
"epoch": 2.229546792230724,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045079078406721676,
|
|
"loss": 6.0877,
|
|
"mean_token_accuracy": 0.14639023467898368,
|
|
"num_tokens": 45080248.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 6.441942977905273,
|
|
"epoch": 2.230081866338488,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045076691759608035,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.14331901520490647,
|
|
"num_tokens": 45091315.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 6.432116222381592,
|
|
"epoch": 2.230616940446252,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045074304604969886,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.14278898015618324,
|
|
"num_tokens": 45102674.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 6.445503377914429,
|
|
"epoch": 2.2311520145540156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045071916942876163,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.14575490057468415,
|
|
"num_tokens": 45113171.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 6.473908710479736,
|
|
"epoch": 2.2316870886617797,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004506952877339581,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.1474693901836872,
|
|
"num_tokens": 45122912.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 6.509590673446655,
|
|
"epoch": 2.2322221627695438,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004506714009659778,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.14192293658852578,
|
|
"num_tokens": 45133839.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 6.463809442520142,
|
|
"epoch": 2.2327572368773074,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004506475091255105,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.14849280714988708,
|
|
"num_tokens": 45144914.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 6.458927726745605,
|
|
"epoch": 2.2332923109850715,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000450623612213246,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.14825727343559264,
|
|
"num_tokens": 45155194.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 6.455564641952515,
|
|
"epoch": 2.233827385092835,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045059971022987446,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.13915288597345352,
|
|
"num_tokens": 45166771.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 6.472472715377807,
|
|
"epoch": 2.2343624592005993,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045057580317608585,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.14202259555459024,
|
|
"num_tokens": 45177236.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 6.467026233673096,
|
|
"epoch": 2.2348975333083634,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045055189105257064,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.1369931496679783,
|
|
"num_tokens": 45187382.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 6.4739213466644285,
|
|
"epoch": 2.235432607416127,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045052797386001936,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14757725447416306,
|
|
"num_tokens": 45197287.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 6.542567539215088,
|
|
"epoch": 2.235967681523891,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004505040515991224,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.14881971925497056,
|
|
"num_tokens": 45208737.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 6.474895811080932,
|
|
"epoch": 2.236502755631655,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045048012427057057,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.13522807210683824,
|
|
"num_tokens": 45219586.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 6.533901405334473,
|
|
"epoch": 2.237037829739419,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004504561918750549,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.13439816907048224,
|
|
"num_tokens": 45230730.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 6.512403869628907,
|
|
"epoch": 2.237572903847183,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004504322544132663,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.156698514521122,
|
|
"num_tokens": 45241330.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 6.397086954116821,
|
|
"epoch": 2.2381079779549466,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000450408311885896,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.14560230374336242,
|
|
"num_tokens": 45251439.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 6.404899740219117,
|
|
"epoch": 2.2386430520627107,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045038436429363537,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.14653594940900802,
|
|
"num_tokens": 45262078.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 6.538563394546509,
|
|
"epoch": 2.2391781261704744,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045036041163717586,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.14452334865927696,
|
|
"num_tokens": 45272466.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 6.489725923538208,
|
|
"epoch": 2.2397132002782385,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004503364539172091,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.14924193769693375,
|
|
"num_tokens": 45281830.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 6.410014581680298,
|
|
"epoch": 2.2402482743860026,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004503124911344268,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.1358873277902603,
|
|
"num_tokens": 45293026.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 6.527070951461792,
|
|
"epoch": 2.2407833484937663,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045028852328952106,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.14645038545131683,
|
|
"num_tokens": 45303532.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 6.393893194198609,
|
|
"epoch": 2.2413184226015304,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004502645503831838,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.155904184281826,
|
|
"num_tokens": 45314448.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 6.44235200881958,
|
|
"epoch": 2.241853496709294,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045024057241610727,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.13548970520496367,
|
|
"num_tokens": 45323194.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 6.47519154548645,
|
|
"epoch": 2.242388570817058,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004502165893889839,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.16086768731474876,
|
|
"num_tokens": 45333464.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 6.43692307472229,
|
|
"epoch": 2.242923644924822,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004501926013025061,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.14124525263905524,
|
|
"num_tokens": 45344364.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 6.488691997528076,
|
|
"epoch": 2.243458719032586,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045016860815736646,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.1473349779844284,
|
|
"num_tokens": 45355202.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 6.460700845718383,
|
|
"epoch": 2.24399379314035,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004501446099542579,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.1478226363658905,
|
|
"num_tokens": 45365696.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 6.4001140117645265,
|
|
"epoch": 2.244528867248114,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004501206066938734,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.15158791840076447,
|
|
"num_tokens": 45376609.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 6.508848190307617,
|
|
"epoch": 2.2450639413558777,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045009659837690606,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.1312944307923317,
|
|
"num_tokens": 45386158.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 6.593734455108643,
|
|
"epoch": 2.245599015463642,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000450072585004049,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.14177413135766984,
|
|
"num_tokens": 45396824.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 6.512286615371704,
|
|
"epoch": 2.2461340895714055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004500485665759955,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.1438503846526146,
|
|
"num_tokens": 45407219.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 6.457460355758667,
|
|
"epoch": 2.2466691636791696,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004500245430934394,
|
|
"loss": 6.1737,
|
|
"mean_token_accuracy": 0.13699991330504419,
|
|
"num_tokens": 45418572.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 6.435413551330567,
|
|
"epoch": 2.2472042377869337,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045000051455707413,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.14574682861566543,
|
|
"num_tokens": 45429643.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.2472042377869337,
|
|
"eval_entropy": 6.317055676889548,
|
|
"eval_loss": 6.256918907165527,
|
|
"eval_mean_token_accuracy": 0.1449485192102985,
|
|
"eval_num_tokens": 45429643.0,
|
|
"eval_runtime": 22.62,
|
|
"eval_samples_per_second": 1312.069,
|
|
"eval_steps_per_second": 164.014,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 6.494276714324951,
|
|
"epoch": 2.2477393118946973,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004499764809675937,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14799585938453674,
|
|
"num_tokens": 45440183.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 6.423533725738525,
|
|
"epoch": 2.2482743860024614,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004499524423256918,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.14049314931035042,
|
|
"num_tokens": 45451252.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 6.446270084381103,
|
|
"epoch": 2.248809460110225,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044992839863206284,
|
|
"loss": 6.1529,
|
|
"mean_token_accuracy": 0.14202596694231034,
|
|
"num_tokens": 45462336.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 6.494549989700317,
|
|
"epoch": 2.249344534217989,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044990434988740095,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.14548687189817427,
|
|
"num_tokens": 45472526.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 6.534965944290161,
|
|
"epoch": 2.2498796083257533,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004498802960924005,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.1365474358201027,
|
|
"num_tokens": 45483281.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 6.523278141021729,
|
|
"epoch": 2.250414682433517,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004498562372477561,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.14712547808885573,
|
|
"num_tokens": 45494258.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 6.462643814086914,
|
|
"epoch": 2.250949756541281,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004498321733541624,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.14377980679273605,
|
|
"num_tokens": 45504233.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 6.43720498085022,
|
|
"epoch": 2.2514848306490447,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00044980810441231424,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.14584841281175615,
|
|
"num_tokens": 45513902.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 6.470683479309082,
|
|
"epoch": 2.252019904756809,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004497840304229066,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.14411644488573075,
|
|
"num_tokens": 45524111.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 6.498909044265747,
|
|
"epoch": 2.252554978864573,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044975995138663466,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.14330133497714997,
|
|
"num_tokens": 45534816.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 6.501578044891358,
|
|
"epoch": 2.2530900529723366,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044973586730419373,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.15145739763975144,
|
|
"num_tokens": 45546012.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 6.460418462753296,
|
|
"epoch": 2.2536251270801007,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004497117781762792,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14586476534605025,
|
|
"num_tokens": 45555402.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 6.412470436096191,
|
|
"epoch": 2.2541602011878643,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004496876840035866,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.14630192518234253,
|
|
"num_tokens": 45565537.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 6.4964922904968265,
|
|
"epoch": 2.2546952752956284,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044966358478681163,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.14896186143159867,
|
|
"num_tokens": 45576449.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 6.588002252578735,
|
|
"epoch": 2.2552303494033925,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004496394805266502,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.13857141211628915,
|
|
"num_tokens": 45586477.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 6.426201105117798,
|
|
"epoch": 2.255765423511156,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044961537122379844,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.1415586143732071,
|
|
"num_tokens": 45597279.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 6.510368394851684,
|
|
"epoch": 2.2563004976189203,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004495912568789522,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.13857755735516547,
|
|
"num_tokens": 45608216.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 6.460128498077393,
|
|
"epoch": 2.2568355717266844,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00044956713749280805,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.14786242842674255,
|
|
"num_tokens": 45620665.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 6.492896175384521,
|
|
"epoch": 2.257370645834448,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044954301306606234,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.14504493921995162,
|
|
"num_tokens": 45631635.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 6.3591552734375,
|
|
"epoch": 2.257905719942212,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044951888359941156,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.1540983110666275,
|
|
"num_tokens": 45642507.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 6.44664888381958,
|
|
"epoch": 2.2584407940499758,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044949474909355264,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.14081369936466218,
|
|
"num_tokens": 45653123.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 6.526295232772827,
|
|
"epoch": 2.25897586815774,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00044947060954918233,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.14571473002433777,
|
|
"num_tokens": 45663228.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 6.507929992675781,
|
|
"epoch": 2.2595109422655035,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004494464649669976,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.1444193385541439,
|
|
"num_tokens": 45673389.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 6.452843856811524,
|
|
"epoch": 2.2600460163732676,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044942231534769587,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.14502233862876893,
|
|
"num_tokens": 45684803.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 6.4407342910766605,
|
|
"epoch": 2.2605810904810317,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044939816069197415,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.14629731476306915,
|
|
"num_tokens": 45695164.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 6.530598545074463,
|
|
"epoch": 2.2611161645887954,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044937400100053017,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.14665451049804687,
|
|
"num_tokens": 45706169.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 6.569778633117676,
|
|
"epoch": 2.2616512386965595,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004493498362740613,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.13544171154499055,
|
|
"num_tokens": 45717299.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 6.448068857192993,
|
|
"epoch": 2.2621863128043236,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00044932566651326546,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.14793309047818184,
|
|
"num_tokens": 45728815.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 6.507202816009522,
|
|
"epoch": 2.2627213869120872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004493014917188405,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.13971466943621635,
|
|
"num_tokens": 45740293.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 6.530271005630493,
|
|
"epoch": 2.2632564610198513,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00044927731189148447,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14648326188325883,
|
|
"num_tokens": 45751243.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 6.39956750869751,
|
|
"epoch": 2.263791535127615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044925312703189546,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.1459802970290184,
|
|
"num_tokens": 45762477.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 6.4832066059112545,
|
|
"epoch": 2.264326609235379,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000449228937140772,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.14622026681900024,
|
|
"num_tokens": 45772929.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 6.514123630523682,
|
|
"epoch": 2.264861683343143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044920474221881243,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.14877657741308212,
|
|
"num_tokens": 45782999.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 6.420357942581177,
|
|
"epoch": 2.265396757450907,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044918054226671545,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.15075411200523375,
|
|
"num_tokens": 45793020.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 6.476064825057984,
|
|
"epoch": 2.265931831558671,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044915633728517975,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.15408962965011597,
|
|
"num_tokens": 45803020.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 6.486395454406738,
|
|
"epoch": 2.2664669056664346,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004491321272749042,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.14978941082954406,
|
|
"num_tokens": 45812700.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 6.529626274108887,
|
|
"epoch": 2.2670019797741987,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044910791223658805,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.13963496387004853,
|
|
"num_tokens": 45823097.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 6.494238567352295,
|
|
"epoch": 2.267537053881963,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.00044908369217093035,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.14395482316613198,
|
|
"num_tokens": 45832935.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 6.492327690124512,
|
|
"epoch": 2.2680721279897265,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00044905946707863057,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.13675348609685897,
|
|
"num_tokens": 45844296.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 6.514334344863892,
|
|
"epoch": 2.2686072020974906,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004490352369603881,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14247518181800842,
|
|
"num_tokens": 45854942.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 6.535731410980224,
|
|
"epoch": 2.2691422762052547,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044901100181690256,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.14441046714782715,
|
|
"num_tokens": 45866427.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 6.499472713470459,
|
|
"epoch": 2.2696773503130183,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044898676164887387,
|
|
"loss": 6.1453,
|
|
"mean_token_accuracy": 0.14784806817770005,
|
|
"num_tokens": 45877955.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 6.450230550765991,
|
|
"epoch": 2.2702124244207824,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044896251645700185,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.15432262271642685,
|
|
"num_tokens": 45888668.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 6.416332054138183,
|
|
"epoch": 2.270747498528546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004489382662419866,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.1441604271531105,
|
|
"num_tokens": 45898819.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 6.430312633514404,
|
|
"epoch": 2.27128257263631,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004489140110045283,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.1442831501364708,
|
|
"num_tokens": 45909390.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 6.480388879776001,
|
|
"epoch": 2.271817646744074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004488897507453275,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.14615595564246178,
|
|
"num_tokens": 45919697.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 6.538076448440552,
|
|
"epoch": 2.272352720851838,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044886548546508453,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.1460796669125557,
|
|
"num_tokens": 45929458.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 6.38146276473999,
|
|
"epoch": 2.272887794959602,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004488412151645001,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.14515896439552306,
|
|
"num_tokens": 45939373.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 6.384886407852173,
|
|
"epoch": 2.2734228690673657,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044881693984427504,
|
|
"loss": 6.1016,
|
|
"mean_token_accuracy": 0.14431605264544486,
|
|
"num_tokens": 45949954.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 6.547086715698242,
|
|
"epoch": 2.27395794317513,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004487926595051102,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.1462262287735939,
|
|
"num_tokens": 45960147.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 6.472574758529663,
|
|
"epoch": 2.274493017282894,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004487683741477068,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.14728278070688247,
|
|
"num_tokens": 45970718.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 6.425560331344604,
|
|
"epoch": 2.2750280913906575,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000448744083772766,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.1458531104028225,
|
|
"num_tokens": 45981631.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 6.528663396835327,
|
|
"epoch": 2.2755631654984216,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00044871978838098917,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.13858664259314538,
|
|
"num_tokens": 45992295.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 6.566414642333984,
|
|
"epoch": 2.2760982396061853,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004486954879730778,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.1391966737806797,
|
|
"num_tokens": 46002222.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 6.421219158172607,
|
|
"epoch": 2.2766333137139494,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004486711825497337,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.1610435277223587,
|
|
"num_tokens": 46012393.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 6.427218294143676,
|
|
"epoch": 2.2771683878217135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044864687211165863,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.14419070109725,
|
|
"num_tokens": 46022095.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 6.464762258529663,
|
|
"epoch": 2.277703461929477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044862255665955447,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.14105332791805267,
|
|
"num_tokens": 46032973.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 6.492861986160278,
|
|
"epoch": 2.2782385360372412,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004485982361941234,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.1447777658700943,
|
|
"num_tokens": 46043430.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 6.460416078567505,
|
|
"epoch": 2.278773610145005,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004485739107160677,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.1445997916162014,
|
|
"num_tokens": 46054580.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 6.481352138519287,
|
|
"epoch": 2.279308684252769,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044854958022608974,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14967705085873603,
|
|
"num_tokens": 46064898.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 6.406143474578857,
|
|
"epoch": 2.279843758360533,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00044852524472489196,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.14774246960878373,
|
|
"num_tokens": 46075985.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 6.512715768814087,
|
|
"epoch": 2.2803788324682968,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004485009042131771,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.13976200819015502,
|
|
"num_tokens": 46087544.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 6.571082544326782,
|
|
"epoch": 2.280913906576061,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044847655869164813,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.13850533664226533,
|
|
"num_tokens": 46097613.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 6.423566579818726,
|
|
"epoch": 2.281448980683825,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004484522081610078,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.15793740898370742,
|
|
"num_tokens": 46107728.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 6.400497674942017,
|
|
"epoch": 2.2819840547915886,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044842785262195936,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.14456717669963837,
|
|
"num_tokens": 46118309.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 6.467321157455444,
|
|
"epoch": 2.2825191288993527,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00044840349207520604,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.1494164675474167,
|
|
"num_tokens": 46128425.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 6.545786046981812,
|
|
"epoch": 2.2830542030071164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004483791265214513,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.13865891844034195,
|
|
"num_tokens": 46139506.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 6.482575273513794,
|
|
"epoch": 2.2835892771148805,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044835475596139855,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.1408474177122116,
|
|
"num_tokens": 46151226.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 6.514735078811645,
|
|
"epoch": 2.284124351222644,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004483303803957516,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.14154839813709258,
|
|
"num_tokens": 46162749.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 6.514428520202637,
|
|
"epoch": 2.2846594253304082,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004483059998252144,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.14344518333673478,
|
|
"num_tokens": 46174802.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 6.512063503265381,
|
|
"epoch": 2.2851944994381723,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00044828161425049067,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.1469471648335457,
|
|
"num_tokens": 46185579.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 6.490062093734741,
|
|
"epoch": 2.285729573545936,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044825722367228477,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.1354774422943592,
|
|
"num_tokens": 46196399.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 6.4843651294708256,
|
|
"epoch": 2.2862646476537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044823282809130084,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.1408316098153591,
|
|
"num_tokens": 46206931.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 6.480353307723999,
|
|
"epoch": 2.286799721761464,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044820842750824334,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.14742770195007324,
|
|
"num_tokens": 46217327.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 6.464926624298096,
|
|
"epoch": 2.287334795869228,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044818402192381684,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14369666427373887,
|
|
"num_tokens": 46227981.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 6.46083517074585,
|
|
"epoch": 2.287869869976992,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044815961133872606,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.1374279096722603,
|
|
"num_tokens": 46238500.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 6.423061943054199,
|
|
"epoch": 2.2884049440847556,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044813519575367586,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.15272779762744904,
|
|
"num_tokens": 46249530.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 6.463318729400635,
|
|
"epoch": 2.2889400181925197,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004481107751693711,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.14625746756792068,
|
|
"num_tokens": 46260272.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 6.405825805664063,
|
|
"epoch": 2.2894750923002833,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004480863495865171,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.14429645165801047,
|
|
"num_tokens": 46271805.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 6.4480000019073485,
|
|
"epoch": 2.2900101664080474,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004480619190058191,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.146460422873497,
|
|
"num_tokens": 46282211.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 6.375118398666382,
|
|
"epoch": 2.2905452405158115,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044803748342798247,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.14773557037115098,
|
|
"num_tokens": 46292287.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 6.414663934707642,
|
|
"epoch": 2.291080314623575,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044801304285371286,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.14005930796265603,
|
|
"num_tokens": 46302978.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 6.48315954208374,
|
|
"epoch": 2.2916153887313393,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004479885972837159,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.1436718448996544,
|
|
"num_tokens": 46313958.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 6.573699235916138,
|
|
"epoch": 2.2921504628391034,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004479641467186975,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.13935375362634658,
|
|
"num_tokens": 46325262.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 6.473975706100464,
|
|
"epoch": 2.292685536946867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044793969115936375,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.14281628876924515,
|
|
"num_tokens": 46336773.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 6.408493328094482,
|
|
"epoch": 2.293220611054631,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004479152306064207,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.1484253726899624,
|
|
"num_tokens": 46346616.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 6.433761548995972,
|
|
"epoch": 2.293755685162395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004478907650605745,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.14191639199852943,
|
|
"num_tokens": 46358564.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 6.500779056549073,
|
|
"epoch": 2.294290759270159,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044786629452253196,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.1546463519334793,
|
|
"num_tokens": 46369207.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 6.500661611557007,
|
|
"epoch": 2.294825833377923,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004478418189929994,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.1481148973107338,
|
|
"num_tokens": 46379382.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 6.394848299026489,
|
|
"epoch": 2.2953609074856867,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044781733847268357,
|
|
"loss": 6.2088,
|
|
"mean_token_accuracy": 0.13839469999074935,
|
|
"num_tokens": 46390738.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 6.445329666137695,
|
|
"epoch": 2.2958959815934508,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044779285296229137,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.15295333862304689,
|
|
"num_tokens": 46401740.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 6.529813671112061,
|
|
"epoch": 2.2964310557012144,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044776836246252985,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.14564138129353524,
|
|
"num_tokens": 46412009.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 6.511179065704345,
|
|
"epoch": 2.2969661298089785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004477438669741061,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.14272557497024535,
|
|
"num_tokens": 46422550.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 6.48570294380188,
|
|
"epoch": 2.2975012039167426,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004477193664977275,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.142554097622633,
|
|
"num_tokens": 46432797.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 6.362465810775757,
|
|
"epoch": 2.2980362780245063,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004476948610341015,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.15197512730956078,
|
|
"num_tokens": 46444638.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 6.499190998077393,
|
|
"epoch": 2.2985713521322704,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044767035058393564,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.14615911543369292,
|
|
"num_tokens": 46455404.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 6.454323482513428,
|
|
"epoch": 2.2991064262400345,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044764583514793766,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.14273363053798677,
|
|
"num_tokens": 46466821.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 6.49699592590332,
|
|
"epoch": 2.299641500347798,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004476213147268154,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1443875789642334,
|
|
"num_tokens": 46477222.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 6.466975498199463,
|
|
"epoch": 2.3001765744555622,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044759678932127693,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.1496296063065529,
|
|
"num_tokens": 46488596.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 6.467964744567871,
|
|
"epoch": 2.300711648563326,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044757225893203047,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.13738736882805824,
|
|
"num_tokens": 46499799.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 6.530542659759521,
|
|
"epoch": 2.30124672267109,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004475477235597843,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.1487916424870491,
|
|
"num_tokens": 46511077.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 6.540336608886719,
|
|
"epoch": 2.3017817967788536,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004475231832052469,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.13712119460105895,
|
|
"num_tokens": 46523517.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 6.44324221611023,
|
|
"epoch": 2.3023168708866177,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004474986378691267,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.1514226734638214,
|
|
"num_tokens": 46533198.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 6.458317995071411,
|
|
"epoch": 2.302851944994382,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044747408755213265,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.1400451898574829,
|
|
"num_tokens": 46544659.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 6.464485597610474,
|
|
"epoch": 2.3033870191021455,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044744953225497354,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.13881469368934632,
|
|
"num_tokens": 46555897.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 6.473492383956909,
|
|
"epoch": 2.3039220932099096,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044742497197835845,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.1433671548962593,
|
|
"num_tokens": 46565695.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 6.486868143081665,
|
|
"epoch": 2.3044571673176737,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004474004067229965,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.13898584991693497,
|
|
"num_tokens": 46576620.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 6.560863399505616,
|
|
"epoch": 2.3049922414254373,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000447375836489597,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.13523969948291778,
|
|
"num_tokens": 46588264.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 6.492392110824585,
|
|
"epoch": 2.3055273155332014,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00044735126127886944,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.1459447041153908,
|
|
"num_tokens": 46600180.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 6.416586303710938,
|
|
"epoch": 2.306062389640965,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004473266810915235,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.14974152147769929,
|
|
"num_tokens": 46610391.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 6.444928407669067,
|
|
"epoch": 2.306597463748729,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004473020959282688,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.14088292866945268,
|
|
"num_tokens": 46622955.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 6.541250991821289,
|
|
"epoch": 2.3071325378564933,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044727750578981535,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14749521464109422,
|
|
"num_tokens": 46632361.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 6.483514499664307,
|
|
"epoch": 2.307667611964257,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004472529106768731,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14300166070461273,
|
|
"num_tokens": 46642693.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 6.432924032211304,
|
|
"epoch": 2.308202686072021,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004472283105901522,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.1453826680779457,
|
|
"num_tokens": 46653251.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 6.4843464374542235,
|
|
"epoch": 2.3087377601797847,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004472037055303631,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.13390331342816353,
|
|
"num_tokens": 46664751.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 6.408978414535523,
|
|
"epoch": 2.309272834287549,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004471790954982162,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.13748776018619538,
|
|
"num_tokens": 46676825.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 6.457317972183228,
|
|
"epoch": 2.309807908395313,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004471544804944221,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.15056889727711678,
|
|
"num_tokens": 46687202.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 6.474427318572998,
|
|
"epoch": 2.3103429825030766,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004471298605196916,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.14413033798336983,
|
|
"num_tokens": 46697687.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 6.399207735061646,
|
|
"epoch": 2.3108780566108407,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00044710523557473544,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.14721462577581407,
|
|
"num_tokens": 46709088.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 6.450528955459594,
|
|
"epoch": 2.3114131307186048,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044708060566026487,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.1441744640469551,
|
|
"num_tokens": 46721675.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 6.5083414077758786,
|
|
"epoch": 2.3119482048263684,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000447055970776991,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.14367825761437417,
|
|
"num_tokens": 46731854.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 6.498157739639282,
|
|
"epoch": 2.3124832789341325,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044703133092562514,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.1401453897356987,
|
|
"num_tokens": 46742815.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 6.444508695602417,
|
|
"epoch": 2.313018353041896,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00044700668610687884,
|
|
"loss": 6.1099,
|
|
"mean_token_accuracy": 0.1517878845334053,
|
|
"num_tokens": 46753012.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 6.400829458236695,
|
|
"epoch": 2.3135534271496603,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044698203632146353,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.14552355259656907,
|
|
"num_tokens": 46763701.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 6.538299131393432,
|
|
"epoch": 2.314088501257424,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004469573815700911,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.13725191131234168,
|
|
"num_tokens": 46775407.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 6.443868112564087,
|
|
"epoch": 2.314623575365188,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00044693272185347357,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1495553120970726,
|
|
"num_tokens": 46786282.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 6.434365463256836,
|
|
"epoch": 2.315158649472952,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004469080571723228,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14069043099880219,
|
|
"num_tokens": 46796768.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 6.460161018371582,
|
|
"epoch": 2.315693723580716,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00044688338752735095,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.1459738865494728,
|
|
"num_tokens": 46806538.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 6.436695194244384,
|
|
"epoch": 2.31622879768848,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004468587129192705,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.15677194446325302,
|
|
"num_tokens": 46816692.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 6.412927484512329,
|
|
"epoch": 2.316763871796244,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00044683403334879384,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.14876748770475387,
|
|
"num_tokens": 46827551.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 6.446659421920776,
|
|
"epoch": 2.3172989459040076,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004468093488166337,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.13067039772868155,
|
|
"num_tokens": 46840168.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 6.497695875167847,
|
|
"epoch": 2.3178340200117717,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044678465932350273,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1501982994377613,
|
|
"num_tokens": 46851086.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 6.443648338317871,
|
|
"epoch": 2.3183690941195354,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044675996487011373,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15467752665281295,
|
|
"num_tokens": 46861830.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 6.460092782974243,
|
|
"epoch": 2.3189041682272995,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00044673526545718,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.15216980874538422,
|
|
"num_tokens": 46871348.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 6.397512769699096,
|
|
"epoch": 2.3194392423350636,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004467105610854146,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.1430137500166893,
|
|
"num_tokens": 46882737.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 6.517483139038086,
|
|
"epoch": 2.3199743164428273,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044668585175553085,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.13247976154088975,
|
|
"num_tokens": 46893616.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 6.594755077362061,
|
|
"epoch": 2.3205093905505914,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004466611374682423,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.14227721691131592,
|
|
"num_tokens": 46904546.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 6.500962781906128,
|
|
"epoch": 2.321044464658355,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044663641822426244,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.1464128315448761,
|
|
"num_tokens": 46915513.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 6.531744813919067,
|
|
"epoch": 2.321579538766119,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044661169402430517,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14340778365731238,
|
|
"num_tokens": 46925535.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 6.402699422836304,
|
|
"epoch": 2.322114612873883,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00044658696486908443,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.14523040503263474,
|
|
"num_tokens": 46936222.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 6.4080376625061035,
|
|
"epoch": 2.322649686981647,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004465622307593141,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.15628817230463027,
|
|
"num_tokens": 46946855.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 6.500241661071778,
|
|
"epoch": 2.323184761089411,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044653749169570845,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.1438905455172062,
|
|
"num_tokens": 46958246.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 6.426049470901489,
|
|
"epoch": 2.3237198351971746,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00044651274767898186,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.15005214810371398,
|
|
"num_tokens": 46969237.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 6.497728538513184,
|
|
"epoch": 2.3242549093049387,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004464879987098488,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.145807583630085,
|
|
"num_tokens": 46979897.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 6.512001848220825,
|
|
"epoch": 2.324789983412703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004464632447890238,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1542833387851715,
|
|
"num_tokens": 46989833.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 6.40179762840271,
|
|
"epoch": 2.3253250575204665,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044643848591722183,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.15154348015785218,
|
|
"num_tokens": 46999822.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 6.415911293029785,
|
|
"epoch": 2.3258601316282306,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044641372209515764,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.15227730497717856,
|
|
"num_tokens": 47010176.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 6.408161258697509,
|
|
"epoch": 2.3263952057359942,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004463889533235462,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.149746111035347,
|
|
"num_tokens": 47020184.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 6.489200210571289,
|
|
"epoch": 2.3269302798437583,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044636417960310294,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.14212247133255004,
|
|
"num_tokens": 47032066.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 6.504646682739258,
|
|
"epoch": 2.3274653539515224,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004463394009345431,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.13769288137555122,
|
|
"num_tokens": 47043571.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 6.5607038021087645,
|
|
"epoch": 2.328000428059286,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00044631461731858195,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14365242198109626,
|
|
"num_tokens": 47053813.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 6.518549680709839,
|
|
"epoch": 2.32853550216705,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044628982875593546,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.14682541340589522,
|
|
"num_tokens": 47063671.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 6.3841774463653564,
|
|
"epoch": 2.3290705762748143,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044626503524731917,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.15007409751415252,
|
|
"num_tokens": 47073537.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 6.404321336746216,
|
|
"epoch": 2.329605650382578,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004462402367934491,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.14446128010749817,
|
|
"num_tokens": 47084272.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 6.508105659484864,
|
|
"epoch": 2.330140724490342,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004462154333950412,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.13968442976474763,
|
|
"num_tokens": 47095198.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 6.586350345611573,
|
|
"epoch": 2.3306757985981057,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004461906250528117,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.13975676000118256,
|
|
"num_tokens": 47106540.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 6.496125936508179,
|
|
"epoch": 2.33121087270587,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000446165811767477,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.15234325900673867,
|
|
"num_tokens": 47117301.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 6.421975374221802,
|
|
"epoch": 2.3317459468136335,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004461409935397536,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.1442764952778816,
|
|
"num_tokens": 47127058.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 6.451207876205444,
|
|
"epoch": 2.3322810209213976,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044611617037035794,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.1451098144054413,
|
|
"num_tokens": 47137182.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 6.502760410308838,
|
|
"epoch": 2.3328160950291617,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000446091342260007,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.1408575102686882,
|
|
"num_tokens": 47148591.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 6.490858745574951,
|
|
"epoch": 2.3333511691369253,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044606650920941753,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.14580915346741677,
|
|
"num_tokens": 47159014.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 6.452058935165406,
|
|
"epoch": 2.3338862432446894,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004460416712193067,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.14342996776103972,
|
|
"num_tokens": 47168760.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 6.425150775909424,
|
|
"epoch": 2.3344213173524535,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004460168282903916,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.146635565161705,
|
|
"num_tokens": 47180902.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 6.415819263458252,
|
|
"epoch": 2.334956391460217,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044599198042338963,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.15336752980947493,
|
|
"num_tokens": 47190458.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 6.486897945404053,
|
|
"epoch": 2.3354914655679813,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00044596712761901824,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14041486904025077,
|
|
"num_tokens": 47201099.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 6.4499674320220945,
|
|
"epoch": 2.336026539675745,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004459422698779951,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.15117376744747163,
|
|
"num_tokens": 47211284.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 6.471955585479736,
|
|
"epoch": 2.336561613783509,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004459174072010379,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.140228820592165,
|
|
"num_tokens": 47222875.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 6.461224126815796,
|
|
"epoch": 2.337096687891273,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004458925395888646,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.13779575526714324,
|
|
"num_tokens": 47234238.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 6.491030359268189,
|
|
"epoch": 2.3376317619990368,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044586766704219326,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.14399240165948868,
|
|
"num_tokens": 47244634.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 6.505905437469482,
|
|
"epoch": 2.338166836106801,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000445842789561742,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.1389889657497406,
|
|
"num_tokens": 47256538.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 6.419703626632691,
|
|
"epoch": 2.3387019102145645,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004458179071482292,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.15503145307302474,
|
|
"num_tokens": 47266373.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 6.44592866897583,
|
|
"epoch": 2.3392369843223286,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044579301980237333,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.1415998123586178,
|
|
"num_tokens": 47276441.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 6.475642395019531,
|
|
"epoch": 2.3397720584300927,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004457681275248931,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.14419428408145904,
|
|
"num_tokens": 47287299.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 6.433586645126343,
|
|
"epoch": 2.3403071325378564,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044574323031650715,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.1488127738237381,
|
|
"num_tokens": 47298007.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 6.395630836486816,
|
|
"epoch": 2.3408422066456205,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004457183281779343,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.15820934772491455,
|
|
"num_tokens": 47309729.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 6.472767734527588,
|
|
"epoch": 2.3413772807533846,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044569342110989385,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.14362915158271788,
|
|
"num_tokens": 47319050.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 6.502427625656128,
|
|
"epoch": 2.3419123548611482,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004456685091131048,
|
|
"loss": 6.2318,
|
|
"mean_token_accuracy": 0.14244758933782578,
|
|
"num_tokens": 47330365.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 6.565773963928223,
|
|
"epoch": 2.3424474289689123,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00044564359218828654,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.14507446810603142,
|
|
"num_tokens": 47341225.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 6.466375350952148,
|
|
"epoch": 2.342982503076676,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044561867033615854,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.1484555646777153,
|
|
"num_tokens": 47352996.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 6.36544280052185,
|
|
"epoch": 2.34351757718444,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004455937435574404,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.14715228229761124,
|
|
"num_tokens": 47363577.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 6.528714418411255,
|
|
"epoch": 2.3440526512922037,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044556881185285185,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.1366798348724842,
|
|
"num_tokens": 47374389.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 6.43365478515625,
|
|
"epoch": 2.344587725399968,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044554387522311286,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.14907207265496253,
|
|
"num_tokens": 47385624.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 6.469548654556275,
|
|
"epoch": 2.345122799507732,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004455189336689435,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.14058734253048896,
|
|
"num_tokens": 47396611.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 6.524194955825806,
|
|
"epoch": 2.3456578736154956,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044549398719106374,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.14465692192316054,
|
|
"num_tokens": 47406693.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 6.439492654800415,
|
|
"epoch": 2.3461929477232597,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004454690357901942,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.14539337754249573,
|
|
"num_tokens": 47417528.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 6.4850907802581785,
|
|
"epoch": 2.346728021831024,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004454440794670552,
|
|
"loss": 6.1811,
|
|
"mean_token_accuracy": 0.14375433847308158,
|
|
"num_tokens": 47430032.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 6.543843221664429,
|
|
"epoch": 2.3472630959387875,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.00044541911822236724,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.14003921672701836,
|
|
"num_tokens": 47441002.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 6.503658056259155,
|
|
"epoch": 2.3477981700465516,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004453941520568513,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.15220372527837753,
|
|
"num_tokens": 47451716.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 6.424562406539917,
|
|
"epoch": 2.348333244154315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004453691809712281,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.14600750505924226,
|
|
"num_tokens": 47463039.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 6.391051959991455,
|
|
"epoch": 2.3488683182620793,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00044534420496621877,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.1518831267952919,
|
|
"num_tokens": 47473836.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 6.487048387527466,
|
|
"epoch": 2.3494033923698434,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044531922404254445,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.14269979447126388,
|
|
"num_tokens": 47485103.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 6.413436937332153,
|
|
"epoch": 2.349938466477607,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004452942382009265,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.15239893049001693,
|
|
"num_tokens": 47495509.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 6.4652406692504885,
|
|
"epoch": 2.350473540585371,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004452692474420863,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.14660671055316926,
|
|
"num_tokens": 47506062.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 6.419542264938355,
|
|
"epoch": 2.351008614693135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004452442517667455,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.1540869191288948,
|
|
"num_tokens": 47515632.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 6.395643329620361,
|
|
"epoch": 2.351543688800899,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004452192511756259,
|
|
"loss": 6.0084,
|
|
"mean_token_accuracy": 0.15169961005449295,
|
|
"num_tokens": 47525412.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 6.454103708267212,
|
|
"epoch": 2.352078762908663,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044519424566944935,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.14625447019934654,
|
|
"num_tokens": 47536094.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 6.431142520904541,
|
|
"epoch": 2.3526138370164267,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044516923524893777,
|
|
"loss": 6.036,
|
|
"mean_token_accuracy": 0.14398616775870324,
|
|
"num_tokens": 47546893.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 6.47427191734314,
|
|
"epoch": 2.353148911124191,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044514421991481354,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.14828135967254638,
|
|
"num_tokens": 47557117.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 6.466085052490234,
|
|
"epoch": 2.3536839852319544,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044511919966779885,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.14336677640676498,
|
|
"num_tokens": 47567878.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 6.446047401428222,
|
|
"epoch": 2.3542190593397185,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044509417450861615,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.13893141895532607,
|
|
"num_tokens": 47578185.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 6.540997695922852,
|
|
"epoch": 2.3547541334474826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004450691444379881,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.13426421955227852,
|
|
"num_tokens": 47590042.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 6.527778577804566,
|
|
"epoch": 2.3552892075552463,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044504410945663735,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.14576566070318223,
|
|
"num_tokens": 47601225.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 6.457901096343994,
|
|
"epoch": 2.3558242816630104,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044501906956528686,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.14177038371562958,
|
|
"num_tokens": 47612596.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 6.5307739734649655,
|
|
"epoch": 2.356359355770774,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004449940247646596,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.1433061607182026,
|
|
"num_tokens": 47623156.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 6.4633606433868405,
|
|
"epoch": 2.356894429878538,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044496897505547886,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.1438271701335907,
|
|
"num_tokens": 47633743.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 6.459659194946289,
|
|
"epoch": 2.3574295039863022,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004449439204384677,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.14252169132232667,
|
|
"num_tokens": 47643914.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 6.487078237533569,
|
|
"epoch": 2.357964578094066,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044491886091434983,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.1452212765812874,
|
|
"num_tokens": 47655187.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 6.503546190261841,
|
|
"epoch": 2.35849965220183,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004448937964838487,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.1437824249267578,
|
|
"num_tokens": 47667193.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 6.48775954246521,
|
|
"epoch": 2.359034726309594,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004448687271476881,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.14331882148981095,
|
|
"num_tokens": 47678116.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 6.495173025131225,
|
|
"epoch": 2.3595698004173578,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004448436529065918,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14533022344112395,
|
|
"num_tokens": 47689883.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 6.4617774963378904,
|
|
"epoch": 2.360104874525122,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004448185737612839,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.14905785024166107,
|
|
"num_tokens": 47699939.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 6.398660135269165,
|
|
"epoch": 2.3606399486328855,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044479348971248863,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.15168716311454772,
|
|
"num_tokens": 47710477.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 6.475105714797974,
|
|
"epoch": 2.3611750227406496,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004447684007609301,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.1445338323712349,
|
|
"num_tokens": 47720548.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 6.490202283859253,
|
|
"epoch": 2.3617100968484133,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044474330690733293,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.13948655053973197,
|
|
"num_tokens": 47732135.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 6.475314044952393,
|
|
"epoch": 2.3622451709561774,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004447182081524216,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.14495120644569398,
|
|
"num_tokens": 47742934.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 6.464633131027222,
|
|
"epoch": 2.3627802450639415,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044469310449692085,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14303620159626007,
|
|
"num_tokens": 47754586.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 6.516017961502075,
|
|
"epoch": 2.363315319171705,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044466799594155556,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.14106715619564056,
|
|
"num_tokens": 47765564.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 6.422468996047973,
|
|
"epoch": 2.363850393279469,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044464288248705075,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.14668594747781755,
|
|
"num_tokens": 47776191.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 6.520417404174805,
|
|
"epoch": 2.3643854673872333,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044461776413413153,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.1369754120707512,
|
|
"num_tokens": 47787193.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 6.5552184104919435,
|
|
"epoch": 2.364920541494997,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004445926408835232,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.1368870861828327,
|
|
"num_tokens": 47798576.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 6.376204156875611,
|
|
"epoch": 2.365455615602761,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004445675127359511,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.15470883771777152,
|
|
"num_tokens": 47809519.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 6.43874716758728,
|
|
"epoch": 2.3659906897105247,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000444542379692141,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.14309703782200814,
|
|
"num_tokens": 47820618.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 6.512845277786255,
|
|
"epoch": 2.366525763818289,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004445172417528186,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.14340648651123047,
|
|
"num_tokens": 47831756.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 6.501999855041504,
|
|
"epoch": 2.367060837926053,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044449209891870954,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.14158237874507903,
|
|
"num_tokens": 47841974.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 6.406654500961304,
|
|
"epoch": 2.3675959120338166,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044446695119053993,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.14741935357451438,
|
|
"num_tokens": 47852194.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 6.502700996398926,
|
|
"epoch": 2.3681309861415807,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000444441798569036,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.13913919031620026,
|
|
"num_tokens": 47863921.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 6.600926637649536,
|
|
"epoch": 2.3686660602493443,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044441664105492393,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.134506893157959,
|
|
"num_tokens": 47875520.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 6.531594085693359,
|
|
"epoch": 2.3692011343571084,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004443914786489301,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.14973307251930237,
|
|
"num_tokens": 47886047.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 6.3686503887176515,
|
|
"epoch": 2.3697362084648725,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044436631135178113,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.1579115778207779,
|
|
"num_tokens": 47896449.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 6.516362524032592,
|
|
"epoch": 2.370271282572636,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00044434113916420377,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.14160350561141968,
|
|
"num_tokens": 47908613.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 6.55473747253418,
|
|
"epoch": 2.3708063566804003,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044431596208692475,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.13570541143417358,
|
|
"num_tokens": 47919474.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 6.4521135807037355,
|
|
"epoch": 2.3713414307881644,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004442907801206712,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.14394913166761397,
|
|
"num_tokens": 47930929.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 6.437365913391114,
|
|
"epoch": 2.371876504895928,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044426559326617013,
|
|
"loss": 6.0503,
|
|
"mean_token_accuracy": 0.15559595823287964,
|
|
"num_tokens": 47942050.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 6.528932189941406,
|
|
"epoch": 2.372411579003692,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004442404015241488,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14278719425201417,
|
|
"num_tokens": 47953162.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 6.536012268066406,
|
|
"epoch": 2.372946653111456,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044421520489533467,
|
|
"loss": 6.1213,
|
|
"mean_token_accuracy": 0.1446191668510437,
|
|
"num_tokens": 47963140.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 6.445658540725708,
|
|
"epoch": 2.37348172721922,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00044419000338045527,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.14523965716362,
|
|
"num_tokens": 47975622.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 6.5038165092468265,
|
|
"epoch": 2.3740168013269836,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004441647969802383,
|
|
"loss": 6.1218,
|
|
"mean_token_accuracy": 0.13845564275979996,
|
|
"num_tokens": 47986450.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 6.540388774871826,
|
|
"epoch": 2.3745518754347477,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004441395856954117,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.1351679116487503,
|
|
"num_tokens": 47997441.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 6.459717512130737,
|
|
"epoch": 2.3750869495425118,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00044411436952670325,
|
|
"loss": 6.0997,
|
|
"mean_token_accuracy": 0.13807225227355957,
|
|
"num_tokens": 48008995.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 6.522867441177368,
|
|
"epoch": 2.3756220236502754,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044408914847484103,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.14891570806503296,
|
|
"num_tokens": 48019975.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 6.538968658447265,
|
|
"epoch": 2.3761570977580395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004440639225405536,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14091890752315522,
|
|
"num_tokens": 48031278.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 6.399729013442993,
|
|
"epoch": 2.3766921718658036,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000444038691724569,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.14269933402538298,
|
|
"num_tokens": 48042050.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 6.337248373031616,
|
|
"epoch": 2.3772272459735673,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044401345602761605,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.15868725776672363,
|
|
"num_tokens": 48052833.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 6.39757809638977,
|
|
"epoch": 2.3777623200813314,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044398821545042327,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.14557988718152046,
|
|
"num_tokens": 48063425.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 6.440204334259033,
|
|
"epoch": 2.378297394189095,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044396296999371946,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.14883712083101272,
|
|
"num_tokens": 48074941.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 6.4019585132598875,
|
|
"epoch": 2.378832468296859,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00044393771965823376,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.1523391529917717,
|
|
"num_tokens": 48085224.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 6.446329784393311,
|
|
"epoch": 2.3793675424046232,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000443912464444695,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.1432347536087036,
|
|
"num_tokens": 48096509.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 6.423505973815918,
|
|
"epoch": 2.379902616512387,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004438872043538327,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.14209741950035096,
|
|
"num_tokens": 48106839.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 6.512378549575805,
|
|
"epoch": 2.380437690620151,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000443861939386376,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.1461554616689682,
|
|
"num_tokens": 48118209.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 6.45034556388855,
|
|
"epoch": 2.3809727647279146,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004438366695430546,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.14676560685038567,
|
|
"num_tokens": 48128651.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 6.477226495742798,
|
|
"epoch": 2.3815078388356787,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00044381139482459805,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.14449237436056137,
|
|
"num_tokens": 48139612.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 6.503661060333252,
|
|
"epoch": 2.382042912943443,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044378611523173615,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.15411824882030487,
|
|
"num_tokens": 48150557.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 6.4357953548431395,
|
|
"epoch": 2.3825779870512065,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004437608307651989,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.1511611297726631,
|
|
"num_tokens": 48160784.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 6.403134393692016,
|
|
"epoch": 2.3831130611589706,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004437355414257165,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.14343835189938545,
|
|
"num_tokens": 48171075.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 6.475181961059571,
|
|
"epoch": 2.3836481352667347,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044371024721401894,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.13750439882278442,
|
|
"num_tokens": 48182713.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 6.499227380752563,
|
|
"epoch": 2.3841832093744983,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004436849481308367,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.15116696134209634,
|
|
"num_tokens": 48194198.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 6.431978607177735,
|
|
"epoch": 2.3847182834822624,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00044365964417690035,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.1466377079486847,
|
|
"num_tokens": 48205650.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 6.378844785690307,
|
|
"epoch": 2.385253357590026,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004436343353529404,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.14801887273788453,
|
|
"num_tokens": 48216335.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 6.4176350116729735,
|
|
"epoch": 2.38578843169779,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044360902165968774,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.14309422820806503,
|
|
"num_tokens": 48227206.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 6.446830129623413,
|
|
"epoch": 2.386323505805554,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004435837030978733,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.14635014533996582,
|
|
"num_tokens": 48237948.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 6.4844279289245605,
|
|
"epoch": 2.386858579913318,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004435583796682281,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.1542416825890541,
|
|
"num_tokens": 48250086.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 6.506739091873169,
|
|
"epoch": 2.387393654021082,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004435330513714834,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.14743863493204118,
|
|
"num_tokens": 48261004.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 6.426657199859619,
|
|
"epoch": 2.3879287281288457,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004435077182083705,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.14860199987888337,
|
|
"num_tokens": 48271314.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 6.372504711151123,
|
|
"epoch": 2.38846380223661,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044348238017962095,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.14628194123506547,
|
|
"num_tokens": 48281899.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 6.41559100151062,
|
|
"epoch": 2.388998876344374,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004434570372859663,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.14575926586985588,
|
|
"num_tokens": 48292925.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 6.5548206806182865,
|
|
"epoch": 2.3895339504521376,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004434316895281384,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.14652915820479392,
|
|
"num_tokens": 48303138.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 6.401421737670899,
|
|
"epoch": 2.3900690245599017,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004434063369068691,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.1548761323094368,
|
|
"num_tokens": 48313586.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 6.36795334815979,
|
|
"epoch": 2.3906040986676653,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00044338097942289045,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.1530877858400345,
|
|
"num_tokens": 48324756.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 6.460367870330811,
|
|
"epoch": 2.3911391727754294,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004433556170769348,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.13945283815264703,
|
|
"num_tokens": 48336012.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 6.510640048980713,
|
|
"epoch": 2.391674246883193,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004433302498697343,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.1377773813903332,
|
|
"num_tokens": 48348923.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 6.460583829879761,
|
|
"epoch": 2.392209320990957,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044330487780202144,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.16482816487550736,
|
|
"num_tokens": 48359708.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 6.432282495498657,
|
|
"epoch": 2.3927443950987213,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00044327950087452895,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1476660691201687,
|
|
"num_tokens": 48370497.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 6.411420297622681,
|
|
"epoch": 2.393279469206485,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004432541190879895,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14257829636335373,
|
|
"num_tokens": 48381020.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 6.464663314819336,
|
|
"epoch": 2.393814543314249,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044322873244313603,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14460955560207367,
|
|
"num_tokens": 48391696.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 6.423829746246338,
|
|
"epoch": 2.394349617422013,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00044320334094070154,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.1458517111837864,
|
|
"num_tokens": 48402403.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 6.4090986251831055,
|
|
"epoch": 2.394884691529777,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004431779445814192,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.15605130344629287,
|
|
"num_tokens": 48413579.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 6.525593090057373,
|
|
"epoch": 2.395419765637541,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044315254336602236,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.14264504760503768,
|
|
"num_tokens": 48423814.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 6.512730932235717,
|
|
"epoch": 2.3959548397453045,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00044312713729524443,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.14166969284415246,
|
|
"num_tokens": 48433937.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 6.485862922668457,
|
|
"epoch": 2.3964899138530686,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00044310172636981905,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.14675567895174027,
|
|
"num_tokens": 48444397.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 6.440472602844238,
|
|
"epoch": 2.3970249879608327,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004430763105904799,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.1553073525428772,
|
|
"num_tokens": 48454566.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 6.387523937225342,
|
|
"epoch": 2.3975600620685964,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000443050889957961,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.15581767559051513,
|
|
"num_tokens": 48465129.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 6.420242977142334,
|
|
"epoch": 2.3980951361763605,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044302546447299625,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.1484654039144516,
|
|
"num_tokens": 48475793.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 6.4296462059021,
|
|
"epoch": 2.398630210284124,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004430000341363198,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.1621704176068306,
|
|
"num_tokens": 48486543.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 6.501266527175903,
|
|
"epoch": 2.3991652843918883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004429745989486659,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.14941118508577347,
|
|
"num_tokens": 48498426.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 6.448358678817749,
|
|
"epoch": 2.3997003584996524,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004429491589107691,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.15213921815156936,
|
|
"num_tokens": 48508763.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 6.467694616317749,
|
|
"epoch": 2.400235432607416,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004429237140233639,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.14018561094999313,
|
|
"num_tokens": 48519112.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 6.507307338714599,
|
|
"epoch": 2.40077050671518,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004428982642871852,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.1463563159108162,
|
|
"num_tokens": 48530341.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 6.39431791305542,
|
|
"epoch": 2.401305580822944,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004428728097029676,
|
|
"loss": 6.0186,
|
|
"mean_token_accuracy": 0.15091662108898163,
|
|
"num_tokens": 48541962.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 6.493698930740356,
|
|
"epoch": 2.401840654930708,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00044284735027144624,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.1351309634745121,
|
|
"num_tokens": 48554206.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 6.404330825805664,
|
|
"epoch": 2.402375729038472,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004428218859933562,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.14448442980647086,
|
|
"num_tokens": 48563919.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 6.418425273895264,
|
|
"epoch": 2.4029108031462356,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044279641686943277,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.1504869654774666,
|
|
"num_tokens": 48575388.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 6.531083965301514,
|
|
"epoch": 2.4034458772539997,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044277094290041144,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.1469431161880493,
|
|
"num_tokens": 48587492.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 6.383284330368042,
|
|
"epoch": 2.4039809513617634,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044274546408702763,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.16313221529126168,
|
|
"num_tokens": 48598757.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 6.471029472351074,
|
|
"epoch": 2.4045160254695275,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00044271998043001723,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.1484705038368702,
|
|
"num_tokens": 48609912.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 6.4948567867279055,
|
|
"epoch": 2.4050510995772916,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004426944919301158,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.13821542486548424,
|
|
"num_tokens": 48621614.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 6.445605039596558,
|
|
"epoch": 2.4055861736850552,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044266899858805964,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.1508389189839363,
|
|
"num_tokens": 48632539.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 6.57605390548706,
|
|
"epoch": 2.4061212477928193,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044264350040458463,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.14077507331967354,
|
|
"num_tokens": 48644157.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 6.52549180984497,
|
|
"epoch": 2.4066563219005834,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00044261799738042713,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.146114069968462,
|
|
"num_tokens": 48654928.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 6.498835039138794,
|
|
"epoch": 2.407191396008347,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004425924895163235,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.15451390743255616,
|
|
"num_tokens": 48665183.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 6.45039701461792,
|
|
"epoch": 2.407726470116111,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044256697681301034,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.1531726285815239,
|
|
"num_tokens": 48675233.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 6.467570495605469,
|
|
"epoch": 2.408261544223875,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004425414592712242,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.14776048362255095,
|
|
"num_tokens": 48685881.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 6.476493644714355,
|
|
"epoch": 2.408796618331639,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044251593689170196,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.13813733235001563,
|
|
"num_tokens": 48696402.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 6.492434930801392,
|
|
"epoch": 2.409331692439403,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00044249040967518063,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14482902586460114,
|
|
"num_tokens": 48708041.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 6.511981630325318,
|
|
"epoch": 2.4098667665471667,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044246487762239717,
|
|
"loss": 6.0598,
|
|
"mean_token_accuracy": 0.14756403118371964,
|
|
"num_tokens": 48718836.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 6.456007957458496,
|
|
"epoch": 2.410401840654931,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000442439340734089,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.14885153025388717,
|
|
"num_tokens": 48729115.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 6.4136334419250485,
|
|
"epoch": 2.4109369147626944,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044241379901099334,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.1515069618821144,
|
|
"num_tokens": 48740037.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 6.437617921829224,
|
|
"epoch": 2.4114719888704585,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044238825245384775,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.1455809637904167,
|
|
"num_tokens": 48750894.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 6.481311511993408,
|
|
"epoch": 2.4120070629782226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004423627010633899,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.1552007332444191,
|
|
"num_tokens": 48761566.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 6.306411981582642,
|
|
"epoch": 2.4125421370859863,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044233714484035765,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.15204857736825944,
|
|
"num_tokens": 48772971.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 6.364185476303101,
|
|
"epoch": 2.4130772111937504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044231158378548873,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.14920533671975136,
|
|
"num_tokens": 48784548.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 6.321473407745361,
|
|
"epoch": 2.4136122853015145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004422860178995215,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.15894851684570313,
|
|
"num_tokens": 48795228.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 6.471438884735107,
|
|
"epoch": 2.414147359409278,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044226044718319383,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.14554901495575906,
|
|
"num_tokens": 48806497.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 6.473359823226929,
|
|
"epoch": 2.4146824335170423,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004422348716372444,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.14836304187774657,
|
|
"num_tokens": 48816402.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 6.509381818771362,
|
|
"epoch": 2.415217507624806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004422092912624115,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.14918296039104462,
|
|
"num_tokens": 48826151.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 6.412098503112793,
|
|
"epoch": 2.41575258173257,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044218370605943376,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.1476098269224167,
|
|
"num_tokens": 48836458.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 6.420450353622437,
|
|
"epoch": 2.4162876558403337,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044215811602905003,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14455177783966064,
|
|
"num_tokens": 48845863.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 6.479944658279419,
|
|
"epoch": 2.4168227299480978,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044213252117199914,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.14214532673358918,
|
|
"num_tokens": 48856453.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 6.492744493484497,
|
|
"epoch": 2.417357804055862,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044210692148902034,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.14207544103264808,
|
|
"num_tokens": 48867013.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 6.453858852386475,
|
|
"epoch": 2.4178928781636255,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004420813169808525,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.14191123098134995,
|
|
"num_tokens": 48876455.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 6.422561597824097,
|
|
"epoch": 2.4184279522713896,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004420557076482352,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.14265096932649612,
|
|
"num_tokens": 48888223.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 6.4624885559082035,
|
|
"epoch": 2.4189630263791537,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044203009349190784,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.14904020428657533,
|
|
"num_tokens": 48899287.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 6.471385812759399,
|
|
"epoch": 2.4194981004869174,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004420044745126099,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.1431280069053173,
|
|
"num_tokens": 48910740.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 6.415463924407959,
|
|
"epoch": 2.4200331745946815,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044197885071108127,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.14546657726168633,
|
|
"num_tokens": 48921925.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 6.477572059631347,
|
|
"epoch": 2.420568248702445,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004419532220880619,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.13765173256397248,
|
|
"num_tokens": 48933164.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 6.4573770523071286,
|
|
"epoch": 2.4211033228102092,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044192758864429157,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.14260666817426682,
|
|
"num_tokens": 48943285.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 6.4639030456542965,
|
|
"epoch": 2.421638396917973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004419019503805106,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.13802081048488618,
|
|
"num_tokens": 48952852.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 6.475673580169678,
|
|
"epoch": 2.422173471025737,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044187630729745924,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.1392153263092041,
|
|
"num_tokens": 48964339.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 6.548929643630982,
|
|
"epoch": 2.422708545133501,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00044185065939587805,
|
|
"loss": 6.0928,
|
|
"mean_token_accuracy": 0.14192020371556283,
|
|
"num_tokens": 48974754.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 6.529342985153198,
|
|
"epoch": 2.4232436192412647,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044182500667650746,
|
|
"loss": 6.1153,
|
|
"mean_token_accuracy": 0.15106630325317383,
|
|
"num_tokens": 48985596.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 6.482286691665649,
|
|
"epoch": 2.423778693349029,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004417993491400882,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.14724427387118338,
|
|
"num_tokens": 48997400.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 6.464413404464722,
|
|
"epoch": 2.424313767456793,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044177368678736126,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.14810301959514618,
|
|
"num_tokens": 49007525.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 6.40142855644226,
|
|
"epoch": 2.4248488415645566,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044174801961906744,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.146372439712286,
|
|
"num_tokens": 49018205.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 6.501100969314575,
|
|
"epoch": 2.4253839156723207,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044172234763594805,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.13930772989988327,
|
|
"num_tokens": 49028760.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 6.497635555267334,
|
|
"epoch": 2.4259189897800844,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004416966708387443,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14591245353221893,
|
|
"num_tokens": 49040734.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 6.443426513671875,
|
|
"epoch": 2.4264540638878485,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044167098922819764,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.1393363393843174,
|
|
"num_tokens": 49051474.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 6.413713979721069,
|
|
"epoch": 2.4269891379956126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044164530280504954,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.15655675828456878,
|
|
"num_tokens": 49061697.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 6.4234696388244625,
|
|
"epoch": 2.427524212103376,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00044161961157004176,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.15082429945468903,
|
|
"num_tokens": 49072124.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 6.489072465896607,
|
|
"epoch": 2.4280592862111403,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000441593915523916,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.14353536069393158,
|
|
"num_tokens": 49082653.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 6.54815263748169,
|
|
"epoch": 2.428594360318904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044156821466741447,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.1378464676439762,
|
|
"num_tokens": 49092481.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 6.503483247756958,
|
|
"epoch": 2.429129434426668,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004415425090012792,
|
|
"loss": 6.1721,
|
|
"mean_token_accuracy": 0.13664378374814987,
|
|
"num_tokens": 49103189.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 6.508397340774536,
|
|
"epoch": 2.429664508534432,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044151679852625226,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.14309491217136383,
|
|
"num_tokens": 49114071.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 6.520497989654541,
|
|
"epoch": 2.430199582642196,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004414910832430762,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.14919390380382538,
|
|
"num_tokens": 49125521.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 6.4971236228942875,
|
|
"epoch": 2.43073465674996,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004414653631524935,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.14214812368154525,
|
|
"num_tokens": 49136162.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 6.510256052017212,
|
|
"epoch": 2.431269730857724,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004414396382552468,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.1436297044157982,
|
|
"num_tokens": 49146127.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 6.46959342956543,
|
|
"epoch": 2.4318048049654877,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044141390855207904,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.15364223942160607,
|
|
"num_tokens": 49156619.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 6.415626573562622,
|
|
"epoch": 2.4323398790732518,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00044138817404373295,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.13829587697982787,
|
|
"num_tokens": 49168578.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 6.500268459320068,
|
|
"epoch": 2.4328749531810154,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004413624347309517,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.14751689434051513,
|
|
"num_tokens": 49178845.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 6.527559614181518,
|
|
"epoch": 2.4334100272887795,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044133669061447855,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.14516956731677055,
|
|
"num_tokens": 49189067.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 6.511234521865845,
|
|
"epoch": 2.433945101396543,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044131094169505694,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.13915981277823447,
|
|
"num_tokens": 49200368.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 6.445730495452881,
|
|
"epoch": 2.4344801755043073,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044128518797343014,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.146923066675663,
|
|
"num_tokens": 49211630.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 6.510638475418091,
|
|
"epoch": 2.4350152496120714,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000441259429450342,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.14221021831035613,
|
|
"num_tokens": 49223092.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 6.516750764846802,
|
|
"epoch": 2.435550323719835,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00044123366612653617,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.14769039750099183,
|
|
"num_tokens": 49233963.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 6.510983324050903,
|
|
"epoch": 2.436085397827599,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004412078980027565,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.14667008966207504,
|
|
"num_tokens": 49243834.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 6.3816369533538815,
|
|
"epoch": 2.4366204719353632,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004411821250797472,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.15285905301570893,
|
|
"num_tokens": 49254274.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 6.4198259830474855,
|
|
"epoch": 2.437155546043127,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004411563473582524,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.15313953161239624,
|
|
"num_tokens": 49264734.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 6.45964789390564,
|
|
"epoch": 2.437690620150891,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004411305648390163,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.14700526148080825,
|
|
"num_tokens": 49274708.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 6.428467702865601,
|
|
"epoch": 2.4382256942586547,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004411047775227836,
|
|
"loss": 6.095,
|
|
"mean_token_accuracy": 0.14973544627428054,
|
|
"num_tokens": 49286318.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 6.561038875579834,
|
|
"epoch": 2.4387607683664188,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044107898541029885,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.14294078052043915,
|
|
"num_tokens": 49296948.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 6.394412851333618,
|
|
"epoch": 2.439295842474183,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004410531885023066,
|
|
"loss": 6.0065,
|
|
"mean_token_accuracy": 0.1525759816169739,
|
|
"num_tokens": 49307060.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 6.4518519878387455,
|
|
"epoch": 2.4398309165819465,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00044102738679955195,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.1396223224699497,
|
|
"num_tokens": 49318449.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 6.4768232822418215,
|
|
"epoch": 2.4403659906897106,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004410015803027798,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.1476379208266735,
|
|
"num_tokens": 49329567.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 6.531068229675293,
|
|
"epoch": 2.4409010647974743,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00044097576901273535,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.1490224227309227,
|
|
"num_tokens": 49340854.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 6.511512708663941,
|
|
"epoch": 2.4414361389052384,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004409499529301639,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.1371899165213108,
|
|
"num_tokens": 49352749.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 6.520124387741089,
|
|
"epoch": 2.4419712130130025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004409241320558109,
|
|
"loss": 6.1539,
|
|
"mean_token_accuracy": 0.13934962078928947,
|
|
"num_tokens": 49364703.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 6.421018981933594,
|
|
"epoch": 2.442506287120766,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044089830639042183,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.14887553080916405,
|
|
"num_tokens": 49375873.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 6.493728590011597,
|
|
"epoch": 2.44304136122853,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044087247593474255,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14297319129109382,
|
|
"num_tokens": 49386578.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 6.490143918991089,
|
|
"epoch": 2.4435764353362943,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004408466406895188,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.14254355281591416,
|
|
"num_tokens": 49398394.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 6.415010547637939,
|
|
"epoch": 2.444111509444058,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004408208006554966,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.16062988042831422,
|
|
"num_tokens": 49408758.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 6.434513521194458,
|
|
"epoch": 2.444646583551822,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004407949558334221,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.14622282311320306,
|
|
"num_tokens": 49420447.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 6.488108825683594,
|
|
"epoch": 2.4451816576595857,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.00044076910622404153,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.14922792315483094,
|
|
"num_tokens": 49430246.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 6.4994512557983395,
|
|
"epoch": 2.44571673176735,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00044074325182810135,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.14986441880464554,
|
|
"num_tokens": 49441272.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 6.449289035797119,
|
|
"epoch": 2.4462518058751135,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044071739264634803,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.1379289485514164,
|
|
"num_tokens": 49452778.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 6.479628276824951,
|
|
"epoch": 2.4467868799828776,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004406915286795283,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.14443983361124993,
|
|
"num_tokens": 49463594.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 6.479138946533203,
|
|
"epoch": 2.4473219540906417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004406656599283889,
|
|
"loss": 6.1224,
|
|
"mean_token_accuracy": 0.14434010833501815,
|
|
"num_tokens": 49473649.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 6.4379212856292725,
|
|
"epoch": 2.4478570281984053,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004406397863936769,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.15006129294633866,
|
|
"num_tokens": 49485112.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 6.478448152542114,
|
|
"epoch": 2.4483921023061694,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004406139080761394,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.14289058968424798,
|
|
"num_tokens": 49495455.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 6.483002424240112,
|
|
"epoch": 2.4489271764139335,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004405880249765235,
|
|
"loss": 6.0915,
|
|
"mean_token_accuracy": 0.1443782240152359,
|
|
"num_tokens": 49506495.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 6.48294768333435,
|
|
"epoch": 2.449462250521697,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044056213709557667,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.14086200296878815,
|
|
"num_tokens": 49516384.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 6.451174259185791,
|
|
"epoch": 2.4499973246294613,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044053624443404646,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.15161909013986588,
|
|
"num_tokens": 49527972.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 6.448730897903443,
|
|
"epoch": 2.450532398737225,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004405103469926803,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.14860376343131065,
|
|
"num_tokens": 49540643.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 6.39932770729065,
|
|
"epoch": 2.451067472844989,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044048444477222626,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.1538733258843422,
|
|
"num_tokens": 49550968.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 6.416860103607178,
|
|
"epoch": 2.451602546952753,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004404585377734321,
|
|
"loss": 6.0506,
|
|
"mean_token_accuracy": 0.14601152762770653,
|
|
"num_tokens": 49562381.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 6.406810569763183,
|
|
"epoch": 2.452137621060517,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004404326259970459,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1447313718497753,
|
|
"num_tokens": 49573414.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 6.488003444671631,
|
|
"epoch": 2.452672695168281,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004404067094438159,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.1477361500263214,
|
|
"num_tokens": 49583772.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 6.478089761734009,
|
|
"epoch": 2.4532077692760446,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004403807881144903,
|
|
"loss": 6.1583,
|
|
"mean_token_accuracy": 0.13924882858991622,
|
|
"num_tokens": 49594751.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 6.426532173156739,
|
|
"epoch": 2.4537428433838087,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044035486200981786,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.14557305574417115,
|
|
"num_tokens": 49605048.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 6.513061380386352,
|
|
"epoch": 2.4542779174915728,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044032893113054683,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.14277911186218262,
|
|
"num_tokens": 49616582.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 6.532836675643921,
|
|
"epoch": 2.4548129915993364,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004403029954774263,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.14294343516230584,
|
|
"num_tokens": 49626974.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 6.45196304321289,
|
|
"epoch": 2.4553480657071005,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004402770550512049,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14586984887719154,
|
|
"num_tokens": 49637580.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 6.513627624511718,
|
|
"epoch": 2.455883139814864,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004402511098526318,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.1434204913675785,
|
|
"num_tokens": 49648543.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 6.502149057388306,
|
|
"epoch": 2.4564182139226283,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004402251598824561,
|
|
"loss": 6.1328,
|
|
"mean_token_accuracy": 0.14280304610729216,
|
|
"num_tokens": 49659057.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 6.410835123062133,
|
|
"epoch": 2.4569532880303924,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004401992051414272,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.14516770616173744,
|
|
"num_tokens": 49671226.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 6.475321960449219,
|
|
"epoch": 2.457488362138156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044017324563029435,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.14667897745966912,
|
|
"num_tokens": 49682063.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 6.423736429214477,
|
|
"epoch": 2.45802343624592,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004401472813498074,
|
|
"loss": 6.0617,
|
|
"mean_token_accuracy": 0.14960189312696456,
|
|
"num_tokens": 49693768.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 6.466357040405273,
|
|
"epoch": 2.458558510353684,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044012131230071575,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.1430794417858124,
|
|
"num_tokens": 49703807.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 6.444790935516357,
|
|
"epoch": 2.459093584461448,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004400953384837695,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.14478445202112197,
|
|
"num_tokens": 49714945.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 6.459289789199829,
|
|
"epoch": 2.459628658569212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004400693598997185,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.15960747748613358,
|
|
"num_tokens": 49727267.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 6.408087491989136,
|
|
"epoch": 2.4601637326769756,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044004337654931293,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.14450939372181892,
|
|
"num_tokens": 49738370.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 6.4737691402435305,
|
|
"epoch": 2.4606988067847397,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044001738843330306,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.14351325035095214,
|
|
"num_tokens": 49750113.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 6.486575174331665,
|
|
"epoch": 2.461233880892504,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043999139555243936,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.1371962085366249,
|
|
"num_tokens": 49761163.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 6.512165069580078,
|
|
"epoch": 2.4617689550002675,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004399653979074722,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.14443175718188286,
|
|
"num_tokens": 49771185.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 6.474620771408081,
|
|
"epoch": 2.4623040291080316,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00043993939549915245,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.14699120223522186,
|
|
"num_tokens": 49781202.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 6.435923099517822,
|
|
"epoch": 2.4628391032157952,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043991338832823074,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.14400503635406495,
|
|
"num_tokens": 49790971.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 6.422207832336426,
|
|
"epoch": 2.4633741773235593,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004398873763954582,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.14769563227891921,
|
|
"num_tokens": 49800942.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 6.405848407745362,
|
|
"epoch": 2.463909251431323,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043986135970158573,
|
|
"loss": 6.034,
|
|
"mean_token_accuracy": 0.1474476121366024,
|
|
"num_tokens": 49812043.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 6.365705394744873,
|
|
"epoch": 2.464444325539087,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043983533824736476,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15809634178876877,
|
|
"num_tokens": 49823045.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 6.503657388687134,
|
|
"epoch": 2.464979399646851,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004398093120335465,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.14928590059280394,
|
|
"num_tokens": 49833014.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 6.409166574478149,
|
|
"epoch": 2.465514473754615,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043978328106088254,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.14776428788900375,
|
|
"num_tokens": 49843171.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 6.3962408065795895,
|
|
"epoch": 2.466049547862379,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004397572453301246,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.15220305025577546,
|
|
"num_tokens": 49853772.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 6.457070207595825,
|
|
"epoch": 2.466584621970143,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043973120484202416,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.1467456340789795,
|
|
"num_tokens": 49865379.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 6.455566263198852,
|
|
"epoch": 2.4671196960779067,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043970515959733343,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.14159029349684715,
|
|
"num_tokens": 49876453.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 6.37555570602417,
|
|
"epoch": 2.467654770185671,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043967910959680435,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.15629979074001313,
|
|
"num_tokens": 49886675.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 6.398741769790649,
|
|
"epoch": 2.4681898442934345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004396530548411891,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14982084035873414,
|
|
"num_tokens": 49896946.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 6.462337923049927,
|
|
"epoch": 2.4687249184011986,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004396269953312401,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.1378537319600582,
|
|
"num_tokens": 49906989.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 6.367944669723511,
|
|
"epoch": 2.4692599925089627,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043960093106770964,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.15191028118133545,
|
|
"num_tokens": 49917861.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 6.400054168701172,
|
|
"epoch": 2.4697950666167263,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043957486205135047,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.14867668226361275,
|
|
"num_tokens": 49930529.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 6.440872430801392,
|
|
"epoch": 2.4703301407244904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004395487882829153,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.14804016947746276,
|
|
"num_tokens": 49943067.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 6.468083000183105,
|
|
"epoch": 2.470865214832254,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043952270976315707,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.14439067244529724,
|
|
"num_tokens": 49953648.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 6.509150695800781,
|
|
"epoch": 2.471400288940018,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043949662649282853,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.13846293613314628,
|
|
"num_tokens": 49963571.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 6.4821052074432375,
|
|
"epoch": 2.4719353630477823,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043947053847268313,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.15272858291864394,
|
|
"num_tokens": 49974627.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 6.520781564712524,
|
|
"epoch": 2.472470437155546,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000439444445703474,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.14583753868937493,
|
|
"num_tokens": 49986659.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 6.452333688735962,
|
|
"epoch": 2.47300551126331,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043941834818595464,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.150446055829525,
|
|
"num_tokens": 49997099.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 6.421077680587769,
|
|
"epoch": 2.473540585371074,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00043939224592087864,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.14522971212863922,
|
|
"num_tokens": 50008148.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 6.531986284255981,
|
|
"epoch": 2.474075659478838,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043936613890899955,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.1413787081837654,
|
|
"num_tokens": 50019335.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 6.427493143081665,
|
|
"epoch": 2.474610733586602,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004393400271510713,
|
|
"loss": 6.0461,
|
|
"mean_token_accuracy": 0.1487402305006981,
|
|
"num_tokens": 50029513.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 6.495285224914551,
|
|
"epoch": 2.4751458076943655,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043931391064784786,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.1396355152130127,
|
|
"num_tokens": 50039353.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 6.460680055618286,
|
|
"epoch": 2.4756808818021296,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043928778940008334,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.14789653718471527,
|
|
"num_tokens": 50050260.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 6.38835916519165,
|
|
"epoch": 2.4762159559098933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043926166340853203,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14648790806531906,
|
|
"num_tokens": 50061384.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 6.468059730529785,
|
|
"epoch": 2.4767510300176574,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004392355326739483,
|
|
"loss": 6.0317,
|
|
"mean_token_accuracy": 0.15342689007520677,
|
|
"num_tokens": 50071984.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 6.456266403198242,
|
|
"epoch": 2.4772861041254215,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043920939719708656,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.1549179270863533,
|
|
"num_tokens": 50083225.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 6.434696054458618,
|
|
"epoch": 2.477821178233185,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004391832569787016,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.15381431430578232,
|
|
"num_tokens": 50093240.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 6.423350858688354,
|
|
"epoch": 2.4783562523409493,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004391571120195481,
|
|
"loss": 6.0996,
|
|
"mean_token_accuracy": 0.14446234777569772,
|
|
"num_tokens": 50103870.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 6.4318469047546385,
|
|
"epoch": 2.4788913264487134,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004391309623203811,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.1447260245680809,
|
|
"num_tokens": 50115231.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 6.458612775802612,
|
|
"epoch": 2.479426400556477,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004391048078819556,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.14789726138114928,
|
|
"num_tokens": 50125592.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 6.370980739593506,
|
|
"epoch": 2.479961474664241,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004390786487050269,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.1512372836470604,
|
|
"num_tokens": 50136713.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 6.459298944473266,
|
|
"epoch": 2.4804965487720048,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004390524847903502,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.1442016489803791,
|
|
"num_tokens": 50148645.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 6.510531091690064,
|
|
"epoch": 2.481031622879769,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004390263161386811,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.1441599190235138,
|
|
"num_tokens": 50159973.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 6.476980257034302,
|
|
"epoch": 2.481566696987533,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00043900014275077517,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.14473516941070558,
|
|
"num_tokens": 50170591.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 6.434345006942749,
|
|
"epoch": 2.4821017710952966,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043897396462738817,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.15290300399065018,
|
|
"num_tokens": 50182414.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 6.4994419574737545,
|
|
"epoch": 2.4826368452030607,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004389477817692759,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.14065559729933738,
|
|
"num_tokens": 50192567.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 6.5225043296813965,
|
|
"epoch": 2.4831719193108244,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004389215941771946,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.14196338802576064,
|
|
"num_tokens": 50203142.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 6.466710758209229,
|
|
"epoch": 2.4837069934185885,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043889540185190024,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.13840990290045738,
|
|
"num_tokens": 50214854.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 6.476119756698608,
|
|
"epoch": 2.4842420675263526,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004388692047941492,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.13987003415822982,
|
|
"num_tokens": 50225999.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 6.5091104984283445,
|
|
"epoch": 2.4847771416341162,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004388430030046978,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.14605989456176757,
|
|
"num_tokens": 50236657.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 6.5166901588439945,
|
|
"epoch": 2.4853122157418803,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004388167964843029,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.1424080826342106,
|
|
"num_tokens": 50246457.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 6.46362681388855,
|
|
"epoch": 2.485847289849644,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004387905852337209,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.14413710832595825,
|
|
"num_tokens": 50257020.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 6.472870254516602,
|
|
"epoch": 2.486382363957408,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043876436925370873,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.15392645075917244,
|
|
"num_tokens": 50267173.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 6.422497415542603,
|
|
"epoch": 2.486917438065172,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004387381485450235,
|
|
"loss": 6.1328,
|
|
"mean_token_accuracy": 0.14750081449747085,
|
|
"num_tokens": 50278352.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 6.47580041885376,
|
|
"epoch": 2.487452512172936,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00043871192310842216,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.13669595420360564,
|
|
"num_tokens": 50290301.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 6.599526119232178,
|
|
"epoch": 2.4879875862807,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004386856929446621,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.136481686681509,
|
|
"num_tokens": 50301707.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 6.518272590637207,
|
|
"epoch": 2.4885226603884636,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004386594580545006,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14791110083460807,
|
|
"num_tokens": 50313334.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 6.407838249206543,
|
|
"epoch": 2.4890577344962277,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004386332184386953,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.14902055412530898,
|
|
"num_tokens": 50324228.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 6.375598478317261,
|
|
"epoch": 2.489592808603992,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043860697409800383,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.1506534829735756,
|
|
"num_tokens": 50335001.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 6.4696540355682375,
|
|
"epoch": 2.4901278827117554,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043858072503318393,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.1484534554183483,
|
|
"num_tokens": 50346415.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 6.425711917877197,
|
|
"epoch": 2.4906629568195195,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00043855447124499356,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14480747878551484,
|
|
"num_tokens": 50357625.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 6.439349508285522,
|
|
"epoch": 2.4911980309272836,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043852821273419087,
|
|
"loss": 6.0058,
|
|
"mean_token_accuracy": 0.1571085900068283,
|
|
"num_tokens": 50367672.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 6.428450393676758,
|
|
"epoch": 2.4917331050350473,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000438501949501534,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.1523447170853615,
|
|
"num_tokens": 50378220.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 6.446330785751343,
|
|
"epoch": 2.4922681791428114,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043847568154778134,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.15336769074201584,
|
|
"num_tokens": 50389517.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 6.468391418457031,
|
|
"epoch": 2.492803253250575,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004384494088736913,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.15114848762750627,
|
|
"num_tokens": 50401155.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 6.445683765411377,
|
|
"epoch": 2.493338327358339,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004384231314800226,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.14842903316020967,
|
|
"num_tokens": 50412609.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 6.494117212295532,
|
|
"epoch": 2.493873401466103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004383968493675339,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.14793714582920076,
|
|
"num_tokens": 50422665.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 6.494427299499511,
|
|
"epoch": 2.494408475573867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004383705625369841,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.1393368974328041,
|
|
"num_tokens": 50434012.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 6.470083379745484,
|
|
"epoch": 2.494943549681631,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004383442709891323,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.14519904255867006,
|
|
"num_tokens": 50444270.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 6.392035007476807,
|
|
"epoch": 2.4954786237893947,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043831797472473763,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.15484258234500886,
|
|
"num_tokens": 50455236.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 6.444661092758179,
|
|
"epoch": 2.4960136978971588,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004382916737445594,
|
|
"loss": 6.111,
|
|
"mean_token_accuracy": 0.1406653791666031,
|
|
"num_tokens": 50466431.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 6.523527050018311,
|
|
"epoch": 2.496548772004923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000438265368049357,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.13907749727368354,
|
|
"num_tokens": 50477211.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 6.5079161643981935,
|
|
"epoch": 2.4970838461126865,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043823905763989003,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.14193671345710754,
|
|
"num_tokens": 50488668.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 6.446755361557007,
|
|
"epoch": 2.4976189202204506,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043821274251691823,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.1504003033041954,
|
|
"num_tokens": 50498031.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 6.340474939346313,
|
|
"epoch": 2.4981539943282143,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043818642268120153,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.1462131343781948,
|
|
"num_tokens": 50508567.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 6.437395620346069,
|
|
"epoch": 2.4986890684359784,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00043816009813349964,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.15378950387239457,
|
|
"num_tokens": 50519057.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 6.538073492050171,
|
|
"epoch": 2.4992241425437425,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000438133768874573,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.1484562948346138,
|
|
"num_tokens": 50530572.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 6.47088360786438,
|
|
"epoch": 2.499759216651506,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043810743490518155,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.1463600903749466,
|
|
"num_tokens": 50541195.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 6.515494632720947,
|
|
"epoch": 2.5002942907592702,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043808109622608596,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.13623849898576737,
|
|
"num_tokens": 50552655.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 6.481916379928589,
|
|
"epoch": 2.500829364867034,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043805475283804657,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.14265030547976493,
|
|
"num_tokens": 50562848.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 6.439973831176758,
|
|
"epoch": 2.501364438974798,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004380284047418241,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.15172381699085236,
|
|
"num_tokens": 50572690.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 6.383023691177368,
|
|
"epoch": 2.501899513082562,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004380020519381794,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.15252356231212616,
|
|
"num_tokens": 50583826.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 6.334165954589844,
|
|
"epoch": 2.5024345871903257,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00043797569442787334,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.15069624707102774,
|
|
"num_tokens": 50595148.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 6.488463115692139,
|
|
"epoch": 2.50296966129809,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000437949332211667,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.1439678907394409,
|
|
"num_tokens": 50606568.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 6.571941328048706,
|
|
"epoch": 2.503504735405854,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043792296529032156,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.14040026888251306,
|
|
"num_tokens": 50618144.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 6.55412974357605,
|
|
"epoch": 2.5040398095136176,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004378965936645984,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.1514056220650673,
|
|
"num_tokens": 50629721.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 6.443898248672485,
|
|
"epoch": 2.5045748836213817,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043787021733525904,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.14666295945644378,
|
|
"num_tokens": 50640482.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 6.477694988250732,
|
|
"epoch": 2.5051099577291454,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000437843836303065,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.13883556723594664,
|
|
"num_tokens": 50652261.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 6.452952766418457,
|
|
"epoch": 2.5056450318369095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004378174505687781,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.15319164842367172,
|
|
"num_tokens": 50662397.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 6.410601568222046,
|
|
"epoch": 2.506180105944673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004377910601331601,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1474452570080757,
|
|
"num_tokens": 50673494.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 6.360077285766602,
|
|
"epoch": 2.506715180052437,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004377646649969733,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.15623431354761125,
|
|
"num_tokens": 50683963.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 6.472473907470703,
|
|
"epoch": 2.5072502541602013,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043773826516097945,
|
|
"loss": 6.0933,
|
|
"mean_token_accuracy": 0.14767294973134995,
|
|
"num_tokens": 50694449.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 6.5044702053070065,
|
|
"epoch": 2.507785328267965,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00043771186062594114,
|
|
"loss": 6.0732,
|
|
"mean_token_accuracy": 0.15112870782613755,
|
|
"num_tokens": 50705877.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 6.459271717071533,
|
|
"epoch": 2.508320402375729,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043768545139262076,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.14634856283664704,
|
|
"num_tokens": 50716581.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 6.450234508514404,
|
|
"epoch": 2.508855476483493,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004376590374617809,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.14191805496811866,
|
|
"num_tokens": 50727948.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 6.343714380264283,
|
|
"epoch": 2.509390550591257,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043763261883418396,
|
|
"loss": 5.9523,
|
|
"mean_token_accuracy": 0.1620820701122284,
|
|
"num_tokens": 50739189.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 6.4272877216339115,
|
|
"epoch": 2.509925624699021,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004376061955105932,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.15062596499919892,
|
|
"num_tokens": 50749439.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 6.463335657119751,
|
|
"epoch": 2.5104606988067846,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043757976749177137,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.14523911774158477,
|
|
"num_tokens": 50761463.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 6.491697835922241,
|
|
"epoch": 2.5109957729145487,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004375533347784816,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.1446097180247307,
|
|
"num_tokens": 50771359.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 6.476978874206543,
|
|
"epoch": 2.5115308470223123,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043752689737148705,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.14670259952545167,
|
|
"num_tokens": 50781669.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 6.47306456565857,
|
|
"epoch": 2.5120659211300764,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00043750045527155126,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.1475702315568924,
|
|
"num_tokens": 50792217.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 6.445755338668823,
|
|
"epoch": 2.5126009952378405,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004374740084794376,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.14298529252409936,
|
|
"num_tokens": 50805288.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 6.423535013198853,
|
|
"epoch": 2.513136069345604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004374475569959098,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.15176984742283822,
|
|
"num_tokens": 50815563.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 6.444725227355957,
|
|
"epoch": 2.5136711434533683,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004374211008217316,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.15303923562169075,
|
|
"num_tokens": 50826108.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 6.406829595565796,
|
|
"epoch": 2.5142062175611324,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043739463995766696,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.14996329694986343,
|
|
"num_tokens": 50837180.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 6.415341234207153,
|
|
"epoch": 2.514741291668896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004373681744044799,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.15418055057525634,
|
|
"num_tokens": 50847430.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 6.484678506851196,
|
|
"epoch": 2.51527636577666,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043734170416293467,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.14977000206708907,
|
|
"num_tokens": 50858100.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 6.495728826522827,
|
|
"epoch": 2.5158114398844242,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043731522923379554,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.1433524288237095,
|
|
"num_tokens": 50868549.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 6.487738037109375,
|
|
"epoch": 2.516346513992188,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004372887496178269,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.14577526077628136,
|
|
"num_tokens": 50879522.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 6.4393473148345945,
|
|
"epoch": 2.516881588099952,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004372622653157935,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.1456751585006714,
|
|
"num_tokens": 50891139.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 6.421893692016601,
|
|
"epoch": 2.5174166622077156,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004372357763284599,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.14199379533529283,
|
|
"num_tokens": 50901267.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 6.463366556167602,
|
|
"epoch": 2.5179517363154797,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004372092826565911,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.1521808072924614,
|
|
"num_tokens": 50912137.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 6.458667516708374,
|
|
"epoch": 2.5184868104232434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004371827843009521,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.1470927283167839,
|
|
"num_tokens": 50922724.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 6.46234164237976,
|
|
"epoch": 2.5190218845310075,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00043715628126230795,
|
|
"loss": 6.1108,
|
|
"mean_token_accuracy": 0.14309716820716858,
|
|
"num_tokens": 50934617.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 6.464339351654052,
|
|
"epoch": 2.5195569586387716,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004371297735414239,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.1441352665424347,
|
|
"num_tokens": 50945179.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 6.462499189376831,
|
|
"epoch": 2.5200920327465353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043710326113906555,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.15157264620065689,
|
|
"num_tokens": 50955383.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 6.5211022853851315,
|
|
"epoch": 2.5206271068542994,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004370767440559983,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.151044125854969,
|
|
"num_tokens": 50966107.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 6.396521520614624,
|
|
"epoch": 2.5211621809620635,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043705022229298775,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.16853859797120094,
|
|
"num_tokens": 50977042.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 6.415504598617554,
|
|
"epoch": 2.521697255069827,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004370236958507998,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.14767294153571128,
|
|
"num_tokens": 50986999.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 6.4797906398773195,
|
|
"epoch": 2.522232329177591,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004369971647302005,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.1419106476008892,
|
|
"num_tokens": 50997824.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 6.577082347869873,
|
|
"epoch": 2.522767403285355,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004369706289319558,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.14608432352542877,
|
|
"num_tokens": 51009001.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 6.476378059387207,
|
|
"epoch": 2.523302477393119,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043694408845683185,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.152521114051342,
|
|
"num_tokens": 51019222.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 6.480445861816406,
|
|
"epoch": 2.5238375515008826,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004369175433055952,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.1476146787405014,
|
|
"num_tokens": 51029473.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 6.471163082122803,
|
|
"epoch": 2.5243726256086467,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043689099347901227,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.14782582521438598,
|
|
"num_tokens": 51040667.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 6.379007577896118,
|
|
"epoch": 2.524907699716411,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00043686443897784954,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.15364776849746703,
|
|
"num_tokens": 51050386.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 6.458848714828491,
|
|
"epoch": 2.5254427738241745,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000436837879802874,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.14842621833086014,
|
|
"num_tokens": 51060752.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 6.440014266967774,
|
|
"epoch": 2.5259778479319386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043681131595485234,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.14779562056064605,
|
|
"num_tokens": 51072467.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 6.544898653030396,
|
|
"epoch": 2.5265129220397027,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004367847474345517,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.14447703212499619,
|
|
"num_tokens": 51083404.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 6.453373813629151,
|
|
"epoch": 2.5270479961474663,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043675817424273925,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.15299114361405372,
|
|
"num_tokens": 51094392.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 6.488115406036377,
|
|
"epoch": 2.5275830702552304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043673159638018215,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.14106457233428954,
|
|
"num_tokens": 51104706.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 6.490919971466065,
|
|
"epoch": 2.5281181443629945,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000436705013847648,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.14325982183218003,
|
|
"num_tokens": 51114881.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 6.531571578979492,
|
|
"epoch": 2.528653218470758,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004366784266459043,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.14374287724494933,
|
|
"num_tokens": 51125705.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 6.535162162780762,
|
|
"epoch": 2.5291882925785223,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043665183477571874,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.1407308377325535,
|
|
"num_tokens": 51136460.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 6.430759429931641,
|
|
"epoch": 2.529723366686286,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004366252382378592,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.1493188112974167,
|
|
"num_tokens": 51146206.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 6.424686098098755,
|
|
"epoch": 2.53025844079405,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004365986370330935,
|
|
"loss": 6.1766,
|
|
"mean_token_accuracy": 0.1391225829720497,
|
|
"num_tokens": 51156650.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 6.480143070220947,
|
|
"epoch": 2.5307935149018137,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043657203116218994,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.14662258252501487,
|
|
"num_tokens": 51168401.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 6.523509883880616,
|
|
"epoch": 2.531328589009578,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043654542062591674,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.1411995768547058,
|
|
"num_tokens": 51178571.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 6.503192996978759,
|
|
"epoch": 2.531863663117342,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043651880542504214,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.13608428239822387,
|
|
"num_tokens": 51189143.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 6.448965835571289,
|
|
"epoch": 2.5323987372251056,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043649218556033475,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.14627905040979386,
|
|
"num_tokens": 51200552.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 6.4708034038543705,
|
|
"epoch": 2.5329338113328697,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004364655610325632,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.14722600281238557,
|
|
"num_tokens": 51210493.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 6.445748710632325,
|
|
"epoch": 2.5334688854406338,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004364389318424962,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.14877480193972586,
|
|
"num_tokens": 51220535.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 6.439504957199096,
|
|
"epoch": 2.5340039595483974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043641229799090285,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.14188293144106864,
|
|
"num_tokens": 51232078.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 6.4832312107086185,
|
|
"epoch": 2.5345390336561615,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000436385659478552,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.15170127898454666,
|
|
"num_tokens": 51242750.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 6.575940847396851,
|
|
"epoch": 2.535074107763925,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043635901630621293,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.13975838497281073,
|
|
"num_tokens": 51254295.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 6.483678245544434,
|
|
"epoch": 2.5356091818716893,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043633236847465497,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.14603102207183838,
|
|
"num_tokens": 51265060.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 6.381811571121216,
|
|
"epoch": 2.536144255979453,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004363057159846475,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.14961035996675492,
|
|
"num_tokens": 51275623.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 6.393724012374878,
|
|
"epoch": 2.536679330087217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004362790588369602,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.15411610305309295,
|
|
"num_tokens": 51285830.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 6.456270313262939,
|
|
"epoch": 2.537214404194981,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004362523970323627,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.14590513259172438,
|
|
"num_tokens": 51297047.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 6.435363292694092,
|
|
"epoch": 2.5377494783027448,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00043622573057162484,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.14598360732197763,
|
|
"num_tokens": 51307254.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 6.454430150985718,
|
|
"epoch": 2.538284552410509,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004361990594555167,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.13499054610729216,
|
|
"num_tokens": 51317796.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 6.507284021377563,
|
|
"epoch": 2.538819626518273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043617238368480845,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14208370372653006,
|
|
"num_tokens": 51330172.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 6.527377986907959,
|
|
"epoch": 2.5393547006260366,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043614570326027015,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.15405570715665817,
|
|
"num_tokens": 51340844.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 6.481348705291748,
|
|
"epoch": 2.5398897747338007,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004361190181826724,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.1491836801171303,
|
|
"num_tokens": 51352078.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 6.4385000705719,
|
|
"epoch": 2.540424848841565,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043609232845278565,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.13707626909017562,
|
|
"num_tokens": 51364121.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 6.486933803558349,
|
|
"epoch": 2.5409599229493285,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004360656340713805,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.15508515536785125,
|
|
"num_tokens": 51375046.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 6.453219890594482,
|
|
"epoch": 2.541494997057092,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004360389350392278,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.14416414871811867,
|
|
"num_tokens": 51386363.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 6.3984826564788815,
|
|
"epoch": 2.5420300711648562,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043601223135709846,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.15675863921642302,
|
|
"num_tokens": 51398036.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 6.425463771820068,
|
|
"epoch": 2.5425651452726203,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004359855230257636,
|
|
"loss": 6.0867,
|
|
"mean_token_accuracy": 0.14525877088308334,
|
|
"num_tokens": 51408769.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 6.457871580123902,
|
|
"epoch": 2.543100219380384,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00043595881004599444,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.14525377601385117,
|
|
"num_tokens": 51420315.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 6.445687532424927,
|
|
"epoch": 2.543635293488148,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043593209241856216,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.15387475341558457,
|
|
"num_tokens": 51432283.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 6.468622398376465,
|
|
"epoch": 2.544170367595912,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043590537014423833,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.15372790396213531,
|
|
"num_tokens": 51443151.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 6.330078363418579,
|
|
"epoch": 2.544705441703676,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004358786432237946,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.14666105732321738,
|
|
"num_tokens": 51453964.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 6.450662469863891,
|
|
"epoch": 2.54524051581144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004358519116580026,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.15346280187368394,
|
|
"num_tokens": 51464236.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 6.363191318511963,
|
|
"epoch": 2.545775589919204,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004358251754476344,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.15527293980121612,
|
|
"num_tokens": 51474388.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 6.410833835601807,
|
|
"epoch": 2.5463106640269677,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004357984345934617,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.13957794830203057,
|
|
"num_tokens": 51485209.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 6.441276693344117,
|
|
"epoch": 2.546845738134732,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004357716890962568,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.15188122242689134,
|
|
"num_tokens": 51495993.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 6.450775861740112,
|
|
"epoch": 2.5473808122424955,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000435744938956792,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.1522235870361328,
|
|
"num_tokens": 51506282.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 6.4267974376678465,
|
|
"epoch": 2.5479158863502596,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043571818417583976,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.1420055314898491,
|
|
"num_tokens": 51517728.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 6.458556127548218,
|
|
"epoch": 2.548450960458023,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004356914247541724,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.15005556344985962,
|
|
"num_tokens": 51528769.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 6.454838466644287,
|
|
"epoch": 2.5489860345657873,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043566466069256283,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.14791302084922792,
|
|
"num_tokens": 51540148.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 6.476283884048462,
|
|
"epoch": 2.5495211086735514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004356378919917837,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.1498100385069847,
|
|
"num_tokens": 51550657.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 6.441194677352906,
|
|
"epoch": 2.550056182781315,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004356111186526081,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.15196770578622817,
|
|
"num_tokens": 51560399.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 6.414425039291382,
|
|
"epoch": 2.550591256889079,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043558434067580894,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.1447290763258934,
|
|
"num_tokens": 51571463.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 6.480480623245239,
|
|
"epoch": 2.5511263309968433,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043555755806215946,
|
|
"loss": 6.0227,
|
|
"mean_token_accuracy": 0.15467719733715057,
|
|
"num_tokens": 51583136.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 6.4993109703063965,
|
|
"epoch": 2.551661405104607,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043553077081243314,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.1417586736381054,
|
|
"num_tokens": 51594397.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 6.486432266235352,
|
|
"epoch": 2.552196479212371,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004355039789274034,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.1408970907330513,
|
|
"num_tokens": 51605788.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 6.497194528579712,
|
|
"epoch": 2.5527315533201347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004354771824078437,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.14397743716835976,
|
|
"num_tokens": 51615693.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 6.396121883392334,
|
|
"epoch": 2.553266627427899,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043545038125452793,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.15312101393938066,
|
|
"num_tokens": 51626607.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 6.424760103225708,
|
|
"epoch": 2.5538017015356624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043542357546823003,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1500844404101372,
|
|
"num_tokens": 51636905.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 6.450059413909912,
|
|
"epoch": 2.5543367756434265,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043539676504972393,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1490839898586273,
|
|
"num_tokens": 51648142.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 6.512945318222046,
|
|
"epoch": 2.5548718497511906,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004353699499997837,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.1372237868607044,
|
|
"num_tokens": 51659583.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 6.450292873382568,
|
|
"epoch": 2.5554069238589543,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004353431303191837,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.1443669892847538,
|
|
"num_tokens": 51670582.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 6.533113813400268,
|
|
"epoch": 2.5559419979667184,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043531630600869846,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.13966882973909378,
|
|
"num_tokens": 51680773.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 6.502314758300781,
|
|
"epoch": 2.5564770720744825,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004352894770691024,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.14475717693567275,
|
|
"num_tokens": 51690680.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 6.467441606521606,
|
|
"epoch": 2.557012146182246,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004352626435011701,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.14894639998674392,
|
|
"num_tokens": 51700910.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 6.467555284500122,
|
|
"epoch": 2.5575472202900102,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043523580530567654,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.14425421729683877,
|
|
"num_tokens": 51712331.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 6.374993991851807,
|
|
"epoch": 2.5580822943977743,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004352089624833966,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.1546017974615097,
|
|
"num_tokens": 51722805.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 6.422532653808593,
|
|
"epoch": 2.558617368505538,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043518211503510535,
|
|
"loss": 6.0655,
|
|
"mean_token_accuracy": 0.150536473095417,
|
|
"num_tokens": 51733909.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 6.460271120071411,
|
|
"epoch": 2.559152442613302,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043515526296157813,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.139005671441555,
|
|
"num_tokens": 51745062.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 6.463294887542725,
|
|
"epoch": 2.5596875167210658,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004351284062635901,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.14392079263925553,
|
|
"num_tokens": 51756235.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 6.4998626708984375,
|
|
"epoch": 2.56022259082883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000435101544941917,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.14673112258315085,
|
|
"num_tokens": 51765689.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 6.408583688735962,
|
|
"epoch": 2.5607576649365935,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004350746789973341,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.15023422092199326,
|
|
"num_tokens": 51777090.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 6.4311888217926025,
|
|
"epoch": 2.5612927390443576,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004350478084306174,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.14473380595445634,
|
|
"num_tokens": 51787360.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 6.3969158172607425,
|
|
"epoch": 2.5618278131521217,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004350209332425428,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.14888717755675315,
|
|
"num_tokens": 51799075.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 6.376031541824341,
|
|
"epoch": 2.5623628872598854,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043499405343388613,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.16880181729793547,
|
|
"num_tokens": 51810024.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 6.454634141921997,
|
|
"epoch": 2.5628979613676495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004349671690054238,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.14208773672580718,
|
|
"num_tokens": 51820710.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 6.4697834014892575,
|
|
"epoch": 2.5634330354754136,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043494027995793176,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.1473910927772522,
|
|
"num_tokens": 51831451.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 6.313320589065552,
|
|
"epoch": 2.5639681095831772,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004349133862921867,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.16042271703481675,
|
|
"num_tokens": 51841483.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 6.412751722335815,
|
|
"epoch": 2.5645031836909413,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043488648800896516,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.15336196273565292,
|
|
"num_tokens": 51852838.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 6.406958389282226,
|
|
"epoch": 2.565038257798705,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004348595851090436,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.14980074018239975,
|
|
"num_tokens": 51863851.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 6.432291507720947,
|
|
"epoch": 2.565573331906469,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00043483267759319907,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.15225662142038346,
|
|
"num_tokens": 51874380.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 6.49734263420105,
|
|
"epoch": 2.5661084060142327,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004348057654622084,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.15027616024017335,
|
|
"num_tokens": 51884594.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 6.482366228103638,
|
|
"epoch": 2.566643480121997,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004347788487168487,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.13969626873731614,
|
|
"num_tokens": 51897679.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 6.483441352844238,
|
|
"epoch": 2.567178554229761,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004347519273578972,
|
|
"loss": 6.2197,
|
|
"mean_token_accuracy": 0.13812159448862077,
|
|
"num_tokens": 51907501.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 6.465521383285522,
|
|
"epoch": 2.5677136283375246,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043472500138613124,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.14138805717229844,
|
|
"num_tokens": 51917732.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 6.463391351699829,
|
|
"epoch": 2.5682487024452887,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004346980708023284,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.1416984058916569,
|
|
"num_tokens": 51929038.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.5682487024452887,
|
|
"eval_entropy": 6.27463636732487,
|
|
"eval_loss": 6.196377277374268,
|
|
"eval_mean_token_accuracy": 0.149448194002577,
|
|
"eval_num_tokens": 51929038.0,
|
|
"eval_runtime": 22.6201,
|
|
"eval_samples_per_second": 1312.061,
|
|
"eval_steps_per_second": 164.013,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 6.516879844665527,
|
|
"epoch": 2.568783776553053,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004346711356072661,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.14101736843585969,
|
|
"num_tokens": 51939481.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 6.5593249797821045,
|
|
"epoch": 2.5693188506608164,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004346441958017222,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1444205828011036,
|
|
"num_tokens": 51951393.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 6.53387942314148,
|
|
"epoch": 2.5698539247685805,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004346172513864746,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.14086406603455542,
|
|
"num_tokens": 51962897.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 6.456385469436645,
|
|
"epoch": 2.5703889988763446,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043459030236230137,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.14337882846593858,
|
|
"num_tokens": 51974443.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 6.391973829269409,
|
|
"epoch": 2.5709240729841083,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004345633487299805,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.14847104549407958,
|
|
"num_tokens": 51985158.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 6.52832260131836,
|
|
"epoch": 2.571459147091872,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043453639049029035,
|
|
"loss": 6.2,
|
|
"mean_token_accuracy": 0.1380402758717537,
|
|
"num_tokens": 51994956.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 6.5086275100708,
|
|
"epoch": 2.571994221199636,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043450942764400937,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.15147302001714708,
|
|
"num_tokens": 52004922.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 6.386508321762085,
|
|
"epoch": 2.5725292953074,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004344824601919161,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.15597374141216278,
|
|
"num_tokens": 52014684.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 6.441916227340698,
|
|
"epoch": 2.573064369415164,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043445548813478914,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15587343275547028,
|
|
"num_tokens": 52025283.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 6.532823181152343,
|
|
"epoch": 2.573599443522928,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004344285114734074,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.1462143950164318,
|
|
"num_tokens": 52036513.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 6.517218828201294,
|
|
"epoch": 2.574134517630692,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043440153020854987,
|
|
"loss": 6.0316,
|
|
"mean_token_accuracy": 0.15213731974363326,
|
|
"num_tokens": 52047230.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 6.448276519775391,
|
|
"epoch": 2.5746695917384557,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004343745443409954,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.14763810187578202,
|
|
"num_tokens": 52058889.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 6.425657510757446,
|
|
"epoch": 2.5752046658462198,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043434755387152354,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.14771818220615388,
|
|
"num_tokens": 52068478.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 6.386288118362427,
|
|
"epoch": 2.575739739953984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004343205588009133,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.1480717495083809,
|
|
"num_tokens": 52079756.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 6.497709560394287,
|
|
"epoch": 2.5762748140617475,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043429355912994437,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.14538149759173394,
|
|
"num_tokens": 52090452.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 6.452464532852173,
|
|
"epoch": 2.5768098881695116,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004342665548593964,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14874869138002395,
|
|
"num_tokens": 52101134.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 6.4219461441040036,
|
|
"epoch": 2.5773449622772753,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004342395459900489,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.14652038589119912,
|
|
"num_tokens": 52111529.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 6.355379915237426,
|
|
"epoch": 2.5778800363850394,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043421253252268194,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.14850951135158538,
|
|
"num_tokens": 52122779.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 6.447815465927124,
|
|
"epoch": 2.578415110492803,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004341855144580754,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.1435435838997364,
|
|
"num_tokens": 52134140.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 6.467025518417358,
|
|
"epoch": 2.578950184600567,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043415849179700956,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.1435348868370056,
|
|
"num_tokens": 52146033.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 6.370548820495605,
|
|
"epoch": 2.5794852587083312,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004341314645402647,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.14471182450652123,
|
|
"num_tokens": 52157516.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 6.415873670578003,
|
|
"epoch": 2.580020332816095,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004341044326886211,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1526182025671005,
|
|
"num_tokens": 52167523.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 6.395650959014892,
|
|
"epoch": 2.580555406923859,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004340773962428593,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.15602321103215216,
|
|
"num_tokens": 52178235.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 6.370280075073242,
|
|
"epoch": 2.581090481031623,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043405035520376013,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.1569521740078926,
|
|
"num_tokens": 52188586.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 6.424892568588257,
|
|
"epoch": 2.5816255551393867,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004340233095721043,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.15124413520097732,
|
|
"num_tokens": 52199081.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 6.458188056945801,
|
|
"epoch": 2.582160629247151,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004339962593486727,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.14388948678970337,
|
|
"num_tokens": 52210324.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 6.4354267597198485,
|
|
"epoch": 2.5826957033549145,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043396920453424656,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.14596305638551713,
|
|
"num_tokens": 52221973.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 6.415314340591431,
|
|
"epoch": 2.5832307774626786,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00043394214512960683,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.1482434719800949,
|
|
"num_tokens": 52232560.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 6.429066514968872,
|
|
"epoch": 2.5837658515704423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004339150811355351,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.15345148146152496,
|
|
"num_tokens": 52243416.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 6.370793199539184,
|
|
"epoch": 2.5843009256782064,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004338880125528127,
|
|
"loss": 6.0729,
|
|
"mean_token_accuracy": 0.14965935051441193,
|
|
"num_tokens": 52254213.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 6.346394824981689,
|
|
"epoch": 2.5848359997859705,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043386093938222126,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.14227450117468834,
|
|
"num_tokens": 52265381.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 6.439273071289063,
|
|
"epoch": 2.585371073893734,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004338338616245425,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.15383731126785277,
|
|
"num_tokens": 52276407.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 6.47182822227478,
|
|
"epoch": 2.585906148001498,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00043380677928055834,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.14760112687945365,
|
|
"num_tokens": 52286484.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 6.447051572799682,
|
|
"epoch": 2.5864412221092623,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043377969235105075,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.1589368149638176,
|
|
"num_tokens": 52297674.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 6.466054677963257,
|
|
"epoch": 2.586976296217026,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004337526008368018,
|
|
"loss": 6.2,
|
|
"mean_token_accuracy": 0.13537324145436286,
|
|
"num_tokens": 52309100.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 6.463847732543945,
|
|
"epoch": 2.58751137032479,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004337255047385938,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.14427336156368256,
|
|
"num_tokens": 52320002.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 6.506901597976684,
|
|
"epoch": 2.588046444432554,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043369840405720923,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.1494366154074669,
|
|
"num_tokens": 52330073.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 6.470348787307739,
|
|
"epoch": 2.588581518540318,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043367129879343054,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.1489595964550972,
|
|
"num_tokens": 52340472.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 6.375665807723999,
|
|
"epoch": 2.589116592648082,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00043364418894804033,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.1446430616080761,
|
|
"num_tokens": 52350654.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 6.377849435806274,
|
|
"epoch": 2.5896516667558456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043361707452182146,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.1453050084412098,
|
|
"num_tokens": 52361412.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 6.456816053390503,
|
|
"epoch": 2.5901867408636097,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043358995551555693,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.15469790548086165,
|
|
"num_tokens": 52372030.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 6.451414012908936,
|
|
"epoch": 2.5907218149713733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043356283193002966,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14788893163204192,
|
|
"num_tokens": 52382965.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 6.400993394851684,
|
|
"epoch": 2.5912568890791374,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004335357037660229,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.16124625951051713,
|
|
"num_tokens": 52393959.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 6.459224557876587,
|
|
"epoch": 2.5917919631869015,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043350857102432,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14438671991229057,
|
|
"num_tokens": 52405142.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 6.456777429580688,
|
|
"epoch": 2.592327037294665,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004334814337057043,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.14303739219903946,
|
|
"num_tokens": 52415927.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 6.43075041770935,
|
|
"epoch": 2.5928621114024293,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043345429181095957,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.15044942498207092,
|
|
"num_tokens": 52426475.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 6.418110799789429,
|
|
"epoch": 2.5933971855101934,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043342714534086945,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1518814221024513,
|
|
"num_tokens": 52437239.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 6.429792833328247,
|
|
"epoch": 2.593932259617957,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004333999942962177,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.14043737947940826,
|
|
"num_tokens": 52447323.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 6.528575420379639,
|
|
"epoch": 2.594467333725721,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.00043337283867778836,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14742616713047027,
|
|
"num_tokens": 52458465.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 6.451436614990234,
|
|
"epoch": 2.595002407833485,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043334567848636563,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.14342329725623132,
|
|
"num_tokens": 52468809.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 6.460465335845948,
|
|
"epoch": 2.595537481941249,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043331851372273365,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.14166531935334206,
|
|
"num_tokens": 52479456.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 6.434340095520019,
|
|
"epoch": 2.5960725560490125,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043329134438767683,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.14960811734199525,
|
|
"num_tokens": 52490146.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 6.475519704818725,
|
|
"epoch": 2.5966076301567766,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004332641704819797,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.14168959707021714,
|
|
"num_tokens": 52499875.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 6.394170427322388,
|
|
"epoch": 2.5971427042645407,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043323699200642686,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.15287287384271622,
|
|
"num_tokens": 52510297.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 6.294159889221191,
|
|
"epoch": 2.5976777783723044,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004332098089618031,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.15982006639242172,
|
|
"num_tokens": 52523111.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 6.367207765579224,
|
|
"epoch": 2.5982128524800685,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043318262134889334,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.15884466767311095,
|
|
"num_tokens": 52534097.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 6.45570821762085,
|
|
"epoch": 2.5987479265878326,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004331554291684827,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.14977332353591918,
|
|
"num_tokens": 52544985.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 6.50822811126709,
|
|
"epoch": 2.5992830006955963,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004331282324213561,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.1470681443810463,
|
|
"num_tokens": 52555772.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 6.394162940979004,
|
|
"epoch": 2.5998180748033604,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004331010311082992,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.1432741865515709,
|
|
"num_tokens": 52566578.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 6.414872694015503,
|
|
"epoch": 2.6003531489111245,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00043307382523009717,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.13928197622299193,
|
|
"num_tokens": 52578551.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 6.473379039764405,
|
|
"epoch": 2.600888223018888,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004330466147875356,
|
|
"loss": 6.0349,
|
|
"mean_token_accuracy": 0.15189071148633956,
|
|
"num_tokens": 52589225.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 6.449392700195313,
|
|
"epoch": 2.6014232971266518,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043301939978140024,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.15292997807264327,
|
|
"num_tokens": 52599572.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 6.5235514640808105,
|
|
"epoch": 2.601958371234416,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043299218021247693,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.14887815117835998,
|
|
"num_tokens": 52610562.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 6.455296993255615,
|
|
"epoch": 2.60249344534218,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004329649560815517,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.14208897054195405,
|
|
"num_tokens": 52621078.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 6.351390933990478,
|
|
"epoch": 2.6030285194499436,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004329377273894104,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.15557428300380707,
|
|
"num_tokens": 52632336.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 6.331639194488526,
|
|
"epoch": 2.6035635935577077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004329104941368396,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.15507864207029343,
|
|
"num_tokens": 52643701.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 6.33278169631958,
|
|
"epoch": 2.604098667665472,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004328832563246254,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.16262860000133514,
|
|
"num_tokens": 52654052.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 6.350516843795776,
|
|
"epoch": 2.6046337417732355,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043285601395355426,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.1586562916636467,
|
|
"num_tokens": 52665033.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 6.429211378097534,
|
|
"epoch": 2.6051688158809996,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043282876702441296,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.14732210487127304,
|
|
"num_tokens": 52674726.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 6.438467884063721,
|
|
"epoch": 2.6057038899887637,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043280151553798824,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.15359852015972136,
|
|
"num_tokens": 52687221.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 6.471713638305664,
|
|
"epoch": 2.6062389640965273,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004327742594950669,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.14772944822907447,
|
|
"num_tokens": 52697902.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 6.433329105377197,
|
|
"epoch": 2.6067740382042914,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000432746998896436,
|
|
"loss": 6.0359,
|
|
"mean_token_accuracy": 0.1486979454755783,
|
|
"num_tokens": 52707845.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 6.360949325561523,
|
|
"epoch": 2.607309112312055,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004327197337428827,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.14805514216423035,
|
|
"num_tokens": 52719254.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 6.387172746658325,
|
|
"epoch": 2.607844186419819,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004326924640351942,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.14471611082553865,
|
|
"num_tokens": 52729765.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 6.455325651168823,
|
|
"epoch": 2.608379260527583,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043266518977415797,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.14488050118088722,
|
|
"num_tokens": 52740997.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 6.523528909683227,
|
|
"epoch": 2.608914334635347,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004326379109605615,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.14074205458164216,
|
|
"num_tokens": 52753107.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 6.374628067016602,
|
|
"epoch": 2.609449408743111,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004326106275951926,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.14371056407690047,
|
|
"num_tokens": 52765453.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 6.430091094970703,
|
|
"epoch": 2.6099844828508747,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004325833396788389,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.1492977872490883,
|
|
"num_tokens": 52776145.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 6.46644344329834,
|
|
"epoch": 2.610519556958639,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004325560472122884,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.1439564608037472,
|
|
"num_tokens": 52788404.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 6.458155012130737,
|
|
"epoch": 2.611054631066403,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004325287501963293,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.1481269381940365,
|
|
"num_tokens": 52800481.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 6.479500007629395,
|
|
"epoch": 2.6115897051741666,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004325014486317495,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.14577948302030563,
|
|
"num_tokens": 52811539.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 6.483169221878052,
|
|
"epoch": 2.6121247792819307,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004324741425193376,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.15455956906080245,
|
|
"num_tokens": 52822330.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 6.435340213775635,
|
|
"epoch": 2.6126598533896943,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000432446831859882,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.14749523997306824,
|
|
"num_tokens": 52832447.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 6.390778493881226,
|
|
"epoch": 2.6131949274974584,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004324195166541712,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15169788151979446,
|
|
"num_tokens": 52843089.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 6.512231492996216,
|
|
"epoch": 2.613730001605222,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000432392196902994,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.1472408302128315,
|
|
"num_tokens": 52854235.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 6.487987804412842,
|
|
"epoch": 2.614265075712986,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004323648726071392,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14550320953130721,
|
|
"num_tokens": 52864693.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 6.454853820800781,
|
|
"epoch": 2.6148001498207503,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043233754376739583,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.13794720098376273,
|
|
"num_tokens": 52876410.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 6.511990690231324,
|
|
"epoch": 2.615335223928514,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043231021038455297,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.14732400625944136,
|
|
"num_tokens": 52887416.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 6.457764339447022,
|
|
"epoch": 2.615870298036278,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00043228287245939995,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.14884536266326903,
|
|
"num_tokens": 52899191.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 6.423716735839844,
|
|
"epoch": 2.616405372144042,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000432255529992726,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.14540746733546256,
|
|
"num_tokens": 52910479.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 6.5056352615356445,
|
|
"epoch": 2.6169404462518058,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043222818298532074,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.14803672283887864,
|
|
"num_tokens": 52921121.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 6.44695553779602,
|
|
"epoch": 2.61747552035957,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00043220083143797385,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.13852541148662567,
|
|
"num_tokens": 52931604.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 6.373794031143189,
|
|
"epoch": 2.618010594467334,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000432173475351475,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.14527107030153275,
|
|
"num_tokens": 52942200.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 6.4063183784484865,
|
|
"epoch": 2.6185456685750976,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004321461147266141,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.14536070376634597,
|
|
"num_tokens": 52954350.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 6.480186939239502,
|
|
"epoch": 2.6190807426828617,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00043211874956418134,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.16361079066991807,
|
|
"num_tokens": 52965683.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 6.446354913711548,
|
|
"epoch": 2.6196158167906254,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004320913798649667,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.1539105162024498,
|
|
"num_tokens": 52975463.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 6.352461862564087,
|
|
"epoch": 2.6201508908983895,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004320640056297605,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.1458171598613262,
|
|
"num_tokens": 52986115.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 6.436176395416259,
|
|
"epoch": 2.620685965006153,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004320366268593532,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.1481872394680977,
|
|
"num_tokens": 52995770.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 6.432749843597412,
|
|
"epoch": 2.6212210391139172,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043200924355453544,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.14631206393241883,
|
|
"num_tokens": 53006490.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 6.402523422241211,
|
|
"epoch": 2.6217561132216813,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004319818557160978,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.156124509871006,
|
|
"num_tokens": 53016129.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 6.429434156417846,
|
|
"epoch": 2.622291187329445,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043195446334483116,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.147378371655941,
|
|
"num_tokens": 53026568.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 6.433309268951416,
|
|
"epoch": 2.622826261437209,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043192706644152646,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.15224088430404664,
|
|
"num_tokens": 53036488.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 6.49397087097168,
|
|
"epoch": 2.623361335544973,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004318996650069747,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.14693214744329453,
|
|
"num_tokens": 53047195.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 6.420006895065308,
|
|
"epoch": 2.623896409652737,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004318722590419672,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.13790112733840942,
|
|
"num_tokens": 53058602.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 6.481870889663696,
|
|
"epoch": 2.624431483760501,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004318448485472953,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.14528400152921678,
|
|
"num_tokens": 53070822.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 6.453919887542725,
|
|
"epoch": 2.6249665578682646,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00043181743352375035,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.14658737927675247,
|
|
"num_tokens": 53082166.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 6.479091215133667,
|
|
"epoch": 2.6255016319760287,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000431790013972124,
|
|
"loss": 6.2179,
|
|
"mean_token_accuracy": 0.143229378759861,
|
|
"num_tokens": 53093688.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 6.460739183425903,
|
|
"epoch": 2.6260367060837924,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004317625898932082,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.148956398665905,
|
|
"num_tokens": 53104793.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 6.434842872619629,
|
|
"epoch": 2.6265717801915565,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004317351612877946,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.14351183474063872,
|
|
"num_tokens": 53115835.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 6.37038779258728,
|
|
"epoch": 2.6271068542993206,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004317077281566751,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.15568140149116516,
|
|
"num_tokens": 53127153.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 6.372911405563355,
|
|
"epoch": 2.627641928407084,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043168029050064214,
|
|
"loss": 5.9788,
|
|
"mean_token_accuracy": 0.15299040228128433,
|
|
"num_tokens": 53137323.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 6.4208156108856205,
|
|
"epoch": 2.6281770025148483,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043165284832048773,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.14667749255895615,
|
|
"num_tokens": 53146858.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 6.425225877761841,
|
|
"epoch": 2.6287120766226124,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043162540161700434,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.14319248422980307,
|
|
"num_tokens": 53157225.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 6.424941825866699,
|
|
"epoch": 2.629247150730376,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043159795039098453,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.1474204957485199,
|
|
"num_tokens": 53167571.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 6.397244167327881,
|
|
"epoch": 2.62978222483814,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004315704946432209,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.15182553678750993,
|
|
"num_tokens": 53178562.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 6.476341485977173,
|
|
"epoch": 2.6303172989459043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043154303437450617,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.14258697107434273,
|
|
"num_tokens": 53188833.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 6.474404048919678,
|
|
"epoch": 2.630852373053668,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00043151556958563337,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.15322111696004867,
|
|
"num_tokens": 53199596.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 6.47436900138855,
|
|
"epoch": 2.6313874471614316,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004314881002773955,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.15083299130201339,
|
|
"num_tokens": 53209942.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 6.477980422973633,
|
|
"epoch": 2.6319225212691957,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004314606264505857,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.14410494416952133,
|
|
"num_tokens": 53221546.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 6.475403738021851,
|
|
"epoch": 2.63245759537696,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004314331481059973,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.1430260181427002,
|
|
"num_tokens": 53232343.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 6.409321403503418,
|
|
"epoch": 2.6329926694847234,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004314056652444237,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15831847935914994,
|
|
"num_tokens": 53242820.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 6.507085609436035,
|
|
"epoch": 2.6335277435924875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043137817786665863,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.14766844362020493,
|
|
"num_tokens": 53253503.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 6.508805513381958,
|
|
"epoch": 2.6340628177002516,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043135068597349545,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.15044575780630112,
|
|
"num_tokens": 53264160.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 6.446940660476685,
|
|
"epoch": 2.6345978918080153,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004313231895657283,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.1428944207727909,
|
|
"num_tokens": 53275002.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 6.383434438705445,
|
|
"epoch": 2.6351329659157794,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00043129568864415103,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.1554861694574356,
|
|
"num_tokens": 53284216.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 6.431263828277588,
|
|
"epoch": 2.6356680400235435,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00043126818320955766,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.1596357226371765,
|
|
"num_tokens": 53294277.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 6.410352087020874,
|
|
"epoch": 2.636203114131307,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004312406732627425,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.14713098406791686,
|
|
"num_tokens": 53304448.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 6.383740377426148,
|
|
"epoch": 2.6367381882390712,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043121315880449983,
|
|
"loss": 6.0372,
|
|
"mean_token_accuracy": 0.14834167659282685,
|
|
"num_tokens": 53315765.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 6.347890996932984,
|
|
"epoch": 2.637273262346835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043118563983562415,
|
|
"loss": 5.9345,
|
|
"mean_token_accuracy": 0.15982358157634735,
|
|
"num_tokens": 53326529.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 6.367116641998291,
|
|
"epoch": 2.637808336454599,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043115811635691006,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.15975846648216246,
|
|
"num_tokens": 53336132.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 6.383596181869507,
|
|
"epoch": 2.6383434105623627,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004311305883691524,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.15277714729309083,
|
|
"num_tokens": 53347284.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 6.443270826339722,
|
|
"epoch": 2.6388784846701268,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004311030558731458,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.15340566188097,
|
|
"num_tokens": 53357872.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 6.484456729888916,
|
|
"epoch": 2.639413558777891,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043107551886968545,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.14664531275629997,
|
|
"num_tokens": 53370311.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 6.413418436050415,
|
|
"epoch": 2.6399486328856545,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043104797735956643,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.16085440367460252,
|
|
"num_tokens": 53380320.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 6.411125373840332,
|
|
"epoch": 2.6404837069934186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000431020431343584,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.14206002801656722,
|
|
"num_tokens": 53391311.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 6.404000473022461,
|
|
"epoch": 2.6410187811011827,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004309928808225335,
|
|
"loss": 6.1327,
|
|
"mean_token_accuracy": 0.14414913654327394,
|
|
"num_tokens": 53402367.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 6.441148138046264,
|
|
"epoch": 2.6415538552089464,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004309653257972105,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.14555063843727112,
|
|
"num_tokens": 53414253.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 6.493502807617188,
|
|
"epoch": 2.6420889293167105,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043093776626841075,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.15417672991752623,
|
|
"num_tokens": 53425727.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 6.439263868331909,
|
|
"epoch": 2.6426240034244746,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043091020223692974,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.14718570187687874,
|
|
"num_tokens": 53435402.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 6.365416574478149,
|
|
"epoch": 2.643159077532238,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043088263370356364,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.1540623649954796,
|
|
"num_tokens": 53447421.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 6.426650619506836,
|
|
"epoch": 2.643694151640002,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004308550606691084,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.1605531767010689,
|
|
"num_tokens": 53458346.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 6.4874035835266115,
|
|
"epoch": 2.644229225747766,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004308274831343601,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.14778290167450905,
|
|
"num_tokens": 53469638.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 6.464153385162353,
|
|
"epoch": 2.64476429985553,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043079990110011525,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.1428764671087265,
|
|
"num_tokens": 53480645.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 6.435031175613403,
|
|
"epoch": 2.6452993739632937,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00043077231456717006,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.14761828482151032,
|
|
"num_tokens": 53491958.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 6.392915153503418,
|
|
"epoch": 2.645834448071058,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043074472353632124,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.14870360642671585,
|
|
"num_tokens": 53502183.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 6.404493141174316,
|
|
"epoch": 2.646369522178822,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004307171280083653,
|
|
"loss": 6.0169,
|
|
"mean_token_accuracy": 0.15042298138141633,
|
|
"num_tokens": 53513373.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 6.382497024536133,
|
|
"epoch": 2.6469045962865856,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004306895279840992,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.15482517778873445,
|
|
"num_tokens": 53523668.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 6.4751592636108395,
|
|
"epoch": 2.6474396703943497,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004306619234643199,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.1475205034017563,
|
|
"num_tokens": 53535642.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 6.268040752410888,
|
|
"epoch": 2.647974744502114,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00043063431444982447,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.16326033398509027,
|
|
"num_tokens": 53546192.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 6.401771163940429,
|
|
"epoch": 2.6485098186098774,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00043060670094141005,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.15051522105932236,
|
|
"num_tokens": 53557375.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 6.510762023925781,
|
|
"epoch": 2.6490448927176415,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043057908293987404,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.14500435888767244,
|
|
"num_tokens": 53568434.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 6.46000919342041,
|
|
"epoch": 2.649579966825405,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004305514604460138,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.1520714595913887,
|
|
"num_tokens": 53579095.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 6.420160961151123,
|
|
"epoch": 2.6501150409331693,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000430523833460627,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.14869655817747116,
|
|
"num_tokens": 53590082.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 6.45833101272583,
|
|
"epoch": 2.650650115040933,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043049620198451147,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.14549318552017212,
|
|
"num_tokens": 53600421.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 6.349174451828003,
|
|
"epoch": 2.651185189148697,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043046856601846483,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.16112893372774123,
|
|
"num_tokens": 53610994.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 6.464407253265381,
|
|
"epoch": 2.651720263256461,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043044092556328517,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.1479618787765503,
|
|
"num_tokens": 53622205.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 6.405384492874146,
|
|
"epoch": 2.652255337364225,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043041328061977073,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.15121926069259645,
|
|
"num_tokens": 53632440.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 6.376495122909546,
|
|
"epoch": 2.652790411471989,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043038563118871965,
|
|
"loss": 6.0356,
|
|
"mean_token_accuracy": 0.15253866016864776,
|
|
"num_tokens": 53642443.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 6.528036117553711,
|
|
"epoch": 2.653325485579753,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004303579772709303,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.1376488521695137,
|
|
"num_tokens": 53653671.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 6.458281230926514,
|
|
"epoch": 2.6538605596875167,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043033031886720107,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.15538475215435027,
|
|
"num_tokens": 53664874.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 6.434471368789673,
|
|
"epoch": 2.6543956337952808,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004303026559783309,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.14613264203071594,
|
|
"num_tokens": 53675623.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 6.422491359710693,
|
|
"epoch": 2.6549307079030444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004302749886051182,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.14470580369234085,
|
|
"num_tokens": 53685754.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 6.373309707641601,
|
|
"epoch": 2.6554657820108085,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004302473167483621,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.15031711682677268,
|
|
"num_tokens": 53696925.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 6.441711902618408,
|
|
"epoch": 2.656000856118572,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043021964040886154,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.15357198864221572,
|
|
"num_tokens": 53708046.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 6.334389972686767,
|
|
"epoch": 2.6565359302263363,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004301919595874156,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.1596555545926094,
|
|
"num_tokens": 53719179.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 6.404006052017212,
|
|
"epoch": 2.6570710043341004,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004301642742848237,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.1488211527466774,
|
|
"num_tokens": 53731523.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 6.4574353218078615,
|
|
"epoch": 2.657606078441864,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004301365845018853,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.13889062777161598,
|
|
"num_tokens": 53742072.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 6.485256576538086,
|
|
"epoch": 2.658141152549628,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004301088902393996,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.14621224775910377,
|
|
"num_tokens": 53754695.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 6.4294593811035154,
|
|
"epoch": 2.6586762266573922,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004300811914981666,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.1572926238179207,
|
|
"num_tokens": 53764587.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 6.477381372451783,
|
|
"epoch": 2.659211300765156,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000430053488278986,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.1446160852909088,
|
|
"num_tokens": 53775609.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 6.383706712722779,
|
|
"epoch": 2.65974637487292,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043002578058265776,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.14788891226053238,
|
|
"num_tokens": 53786495.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 6.42982931137085,
|
|
"epoch": 2.660281448980684,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004299980684099818,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.1474327877163887,
|
|
"num_tokens": 53797058.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 6.492137670516968,
|
|
"epoch": 2.6608165230884477,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042997035176175834,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.14735824167728423,
|
|
"num_tokens": 53808148.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 6.425716733932495,
|
|
"epoch": 2.661351597196212,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004299426306387879,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.16062136590480805,
|
|
"num_tokens": 53818375.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 6.464401626586914,
|
|
"epoch": 2.6618866713039755,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004299149050418707,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.14501127004623413,
|
|
"num_tokens": 53831273.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 6.367207431793213,
|
|
"epoch": 2.6624217454117396,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00042988717497180733,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.1531870424747467,
|
|
"num_tokens": 53842492.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 6.438853931427002,
|
|
"epoch": 2.6629568195195032,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042985944042939867,
|
|
"loss": 6.0598,
|
|
"mean_token_accuracy": 0.14983204305171965,
|
|
"num_tokens": 53853017.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 6.498943614959717,
|
|
"epoch": 2.6634918936272673,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042983170141544535,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.1471282422542572,
|
|
"num_tokens": 53863606.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 6.376990270614624,
|
|
"epoch": 2.6640269677350314,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004298039579307484,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.15422668308019638,
|
|
"num_tokens": 53874689.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 6.489285039901733,
|
|
"epoch": 2.664562041842795,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000429776209976109,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.15514324307441713,
|
|
"num_tokens": 53885247.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 6.432543611526489,
|
|
"epoch": 2.665097115950559,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004297484575523282,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.14705170542001725,
|
|
"num_tokens": 53896829.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 6.4299815654754635,
|
|
"epoch": 2.6656321900583233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042972070066020745,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.15523212403059006,
|
|
"num_tokens": 53907236.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 6.46129002571106,
|
|
"epoch": 2.666167264166087,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004296929393005482,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.147062748670578,
|
|
"num_tokens": 53918420.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 6.35111141204834,
|
|
"epoch": 2.666702338273851,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004296651734741521,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.15533339977264404,
|
|
"num_tokens": 53928949.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 6.429946231842041,
|
|
"epoch": 2.6672374123816147,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042963740318182085,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.1437372788786888,
|
|
"num_tokens": 53939332.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 6.449320459365845,
|
|
"epoch": 2.667772486489379,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004296096284243563,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.14638348892331124,
|
|
"num_tokens": 53950703.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 6.524592351913452,
|
|
"epoch": 2.6683075605971425,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004295818492025605,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.14144029915332795,
|
|
"num_tokens": 53964061.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 6.435032606124878,
|
|
"epoch": 2.6688426347049066,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004295540655172355,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.15345773547887803,
|
|
"num_tokens": 53974980.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 6.350369501113891,
|
|
"epoch": 2.6693777088126707,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295262773691835,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.15522173494100572,
|
|
"num_tokens": 53985437.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 6.410931539535523,
|
|
"epoch": 2.6699127829204343,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042949848475920706,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.14897070825099945,
|
|
"num_tokens": 53996952.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 6.481980085372925,
|
|
"epoch": 2.6704478570281984,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004294706876881085,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.15164224207401275,
|
|
"num_tokens": 54007727.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 6.351395225524902,
|
|
"epoch": 2.6709829311359625,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042944288615669055,
|
|
"loss": 5.9179,
|
|
"mean_token_accuracy": 0.16518451124429703,
|
|
"num_tokens": 54018275.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 6.390604639053345,
|
|
"epoch": 2.671518005243726,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042941508016575597,
|
|
"loss": 6.161,
|
|
"mean_token_accuracy": 0.14320803731679915,
|
|
"num_tokens": 54030376.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 6.420176219940186,
|
|
"epoch": 2.6720530793514903,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004293872697161077,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.14821335524320603,
|
|
"num_tokens": 54041487.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 6.461021041870117,
|
|
"epoch": 2.6725881534592544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042935945480854866,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.1632443353533745,
|
|
"num_tokens": 54051273.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 6.391329097747803,
|
|
"epoch": 2.673123227567018,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004293316354438821,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.15727767050266267,
|
|
"num_tokens": 54061910.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 6.446732759475708,
|
|
"epoch": 2.6736583016747817,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004293038116229112,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.14669544547796248,
|
|
"num_tokens": 54072980.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 6.392126369476318,
|
|
"epoch": 2.674193375782546,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004292759833464394,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.1577082723379135,
|
|
"num_tokens": 54083027.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 6.342571830749511,
|
|
"epoch": 2.67472844989031,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042924815061527033,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.14960994720458984,
|
|
"num_tokens": 54094068.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 6.419144201278686,
|
|
"epoch": 2.6752635239980735,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004292203134302076,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.15052372217178345,
|
|
"num_tokens": 54104683.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 6.448585128784179,
|
|
"epoch": 2.6757985981058376,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000429192471792055,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.14589312821626663,
|
|
"num_tokens": 54115357.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 6.480725955963135,
|
|
"epoch": 2.6763336722136017,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004291646257016163,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.14583337679505348,
|
|
"num_tokens": 54126410.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 6.371913909912109,
|
|
"epoch": 2.6768687463213654,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00042913677515969586,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.15447857975959778,
|
|
"num_tokens": 54137279.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 6.391150856018067,
|
|
"epoch": 2.6774038204291295,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004291089201670976,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.15128765851259232,
|
|
"num_tokens": 54146521.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 6.489438486099243,
|
|
"epoch": 2.6779388945368936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042908106072462595,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1405947297811508,
|
|
"num_tokens": 54157277.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 6.485062789916992,
|
|
"epoch": 2.6784739686446573,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004290531968330853,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.1452994555234909,
|
|
"num_tokens": 54168078.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 6.527255439758301,
|
|
"epoch": 2.6790090427524214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004290253284932803,
|
|
"loss": 6.1064,
|
|
"mean_token_accuracy": 0.1496105045080185,
|
|
"num_tokens": 54178567.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 6.407850360870361,
|
|
"epoch": 2.679544116860185,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004289974557060155,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.14675920233130454,
|
|
"num_tokens": 54189485.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 6.511658954620361,
|
|
"epoch": 2.680079190967949,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00042896957847209593,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.14646179378032684,
|
|
"num_tokens": 54199351.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 6.459256601333618,
|
|
"epoch": 2.6806142650757128,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004289416967923264,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.14572961181402205,
|
|
"num_tokens": 54209001.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 6.423435878753662,
|
|
"epoch": 2.681149339183477,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00042891381066751186,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.14531078115105628,
|
|
"num_tokens": 54219783.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 6.477549695968628,
|
|
"epoch": 2.681684413291241,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042888592009845776,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.1480795480310917,
|
|
"num_tokens": 54231337.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 6.467353487014771,
|
|
"epoch": 2.6822194873990046,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004288580250859694,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15658991187810897,
|
|
"num_tokens": 54241650.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 6.433385515213013,
|
|
"epoch": 2.6827545615067687,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004288301256308521,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.1416018508374691,
|
|
"num_tokens": 54252223.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 6.455324649810791,
|
|
"epoch": 2.683289635614533,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042880222173391155,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.15223479270935059,
|
|
"num_tokens": 54262469.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 6.428207540512085,
|
|
"epoch": 2.6838247097222965,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004287743133959535,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.14683943539857863,
|
|
"num_tokens": 54272885.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 6.396878862380982,
|
|
"epoch": 2.6843597838300606,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004287464006177837,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.14735295325517656,
|
|
"num_tokens": 54283327.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 6.414928197860718,
|
|
"epoch": 2.6848948579378242,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004287184834002082,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.15037444978952408,
|
|
"num_tokens": 54294761.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 6.527772426605225,
|
|
"epoch": 2.6854299320455883,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042869056174403303,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.1509876862168312,
|
|
"num_tokens": 54305205.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 6.475588035583496,
|
|
"epoch": 2.685965006153352,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004286626356500647,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.15058556497097014,
|
|
"num_tokens": 54315902.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 6.434620761871338,
|
|
"epoch": 2.686500080261116,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004286347051191091,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.15154436528682708,
|
|
"num_tokens": 54327345.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 6.479596376419067,
|
|
"epoch": 2.68703515436888,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004286067701519731,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.14832493662834167,
|
|
"num_tokens": 54337548.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 6.468802404403687,
|
|
"epoch": 2.687570228476644,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042857883074946324,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.1414439335465431,
|
|
"num_tokens": 54348384.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 6.47977991104126,
|
|
"epoch": 2.688105302584408,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004285508869123862,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.14674096405506135,
|
|
"num_tokens": 54358245.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 6.33971757888794,
|
|
"epoch": 2.688640376692172,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042852293864154885,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.14785065352916718,
|
|
"num_tokens": 54370421.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 6.456410455703735,
|
|
"epoch": 2.6891754507999357,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042849498593775827,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.15010035261511803,
|
|
"num_tokens": 54381368.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 6.464001274108886,
|
|
"epoch": 2.6897105249077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042846702880182147,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.1457326479256153,
|
|
"num_tokens": 54392226.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 6.420953226089478,
|
|
"epoch": 2.690245599015464,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004284390672345458,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.14454921185970307,
|
|
"num_tokens": 54402295.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 6.513278436660767,
|
|
"epoch": 2.6907806731232276,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004284111012367387,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.1444273203611374,
|
|
"num_tokens": 54413808.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 6.480533790588379,
|
|
"epoch": 2.6913157472309917,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042838313080920755,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.14802695363759993,
|
|
"num_tokens": 54425048.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 6.487511825561524,
|
|
"epoch": 2.6918508213387553,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042835515595276,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.14218694269657134,
|
|
"num_tokens": 54435908.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 6.376295328140259,
|
|
"epoch": 2.6923858954465194,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004283271766682039,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.15328938513994217,
|
|
"num_tokens": 54447594.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 6.357793855667114,
|
|
"epoch": 2.692920969554283,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004282991929563471,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.1499350219964981,
|
|
"num_tokens": 54458918.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 6.3818987846374515,
|
|
"epoch": 2.693456043662047,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004282712048179977,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.15822725892066955,
|
|
"num_tokens": 54469423.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 6.473826122283936,
|
|
"epoch": 2.6939911177698113,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004282432122539638,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.14685898870229722,
|
|
"num_tokens": 54481895.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 6.487961006164551,
|
|
"epoch": 2.694526191877575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042821521526505363,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.1499170407652855,
|
|
"num_tokens": 54492233.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 6.439240312576294,
|
|
"epoch": 2.695061265985339,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004281872138520757,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.15573531836271287,
|
|
"num_tokens": 54502366.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 6.343453073501587,
|
|
"epoch": 2.695596340093103,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00042815920801583845,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.15038024187088012,
|
|
"num_tokens": 54512565.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 6.405899429321289,
|
|
"epoch": 2.6961314142008668,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042813119775715066,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.15058374032378197,
|
|
"num_tokens": 54522999.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 6.421649551391601,
|
|
"epoch": 2.696666488308631,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00042810318307682095,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.14846908748149873,
|
|
"num_tokens": 54533776.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 6.406240320205688,
|
|
"epoch": 2.6972015624163945,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042807516397565845,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.14737222194671631,
|
|
"num_tokens": 54544972.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 6.41619553565979,
|
|
"epoch": 2.6977366365241586,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004280471404544721,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.14818297401070596,
|
|
"num_tokens": 54556034.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 6.489672470092773,
|
|
"epoch": 2.6982717106319223,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042801911251407095,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.15989175885915757,
|
|
"num_tokens": 54566662.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 6.464313793182373,
|
|
"epoch": 2.6988067847396864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004279910801552645,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.14871048629283906,
|
|
"num_tokens": 54578889.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 6.447121953964233,
|
|
"epoch": 2.6993418588474505,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004279630433788621,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.1456712655723095,
|
|
"num_tokens": 54590456.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 6.448766422271729,
|
|
"epoch": 2.699876932955214,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004279350021856734,
|
|
"loss": 6.107,
|
|
"mean_token_accuracy": 0.14201193749904634,
|
|
"num_tokens": 54602327.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 6.521866321563721,
|
|
"epoch": 2.7004120070629782,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042790695657650787,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.1502055585384369,
|
|
"num_tokens": 54612999.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 6.422251272201538,
|
|
"epoch": 2.7009470811707423,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042787890655217553,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.14514252096414565,
|
|
"num_tokens": 54624332.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 6.35856351852417,
|
|
"epoch": 2.701482155278506,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042785085211348624,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.15130027532577514,
|
|
"num_tokens": 54635679.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 6.424386024475098,
|
|
"epoch": 2.70201722938627,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042782279326125005,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.15152093768119812,
|
|
"num_tokens": 54646344.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 6.485493278503418,
|
|
"epoch": 2.702552303494034,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00042779472999627724,
|
|
"loss": 6.0933,
|
|
"mean_token_accuracy": 0.1456468641757965,
|
|
"num_tokens": 54657395.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 6.409106349945068,
|
|
"epoch": 2.703087377601798,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427766662319378,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.14813070893287658,
|
|
"num_tokens": 54668755.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 6.453620576858521,
|
|
"epoch": 2.7036224517095615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042773859023136285,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.14971143901348113,
|
|
"num_tokens": 54679170.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 6.405198049545288,
|
|
"epoch": 2.7041575258173256,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004277105137330424,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15056706219911575,
|
|
"num_tokens": 54688728.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 6.376384544372558,
|
|
"epoch": 2.7046925999250897,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042768243282522735,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15315230637788774,
|
|
"num_tokens": 54700236.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 6.428701400756836,
|
|
"epoch": 2.7052276740328534,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042765434750872847,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.15179484635591506,
|
|
"num_tokens": 54710586.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 6.43684573173523,
|
|
"epoch": 2.7057627481406175,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042762625778435676,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.15380548536777497,
|
|
"num_tokens": 54721159.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 6.433546876907348,
|
|
"epoch": 2.7062978222483816,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004275981636529233,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.15126713663339614,
|
|
"num_tokens": 54731593.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 6.4233095169067385,
|
|
"epoch": 2.706832896356145,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004275700651152393,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.15337316542863846,
|
|
"num_tokens": 54742890.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 6.359569358825683,
|
|
"epoch": 2.7073679704639093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042754196217211616,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.15261325538158416,
|
|
"num_tokens": 54753344.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 6.481750774383545,
|
|
"epoch": 2.7079030445716734,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042751385482436523,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14214920699596406,
|
|
"num_tokens": 54763157.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 6.480219459533691,
|
|
"epoch": 2.708438118679437,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042748574307279824,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.14984458982944487,
|
|
"num_tokens": 54772515.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 6.3885527610778805,
|
|
"epoch": 2.708973192787201,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004274576269182268,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.14940545037388803,
|
|
"num_tokens": 54783178.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 6.457936239242554,
|
|
"epoch": 2.709508266894965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004274295063614629,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.14772203788161278,
|
|
"num_tokens": 54794709.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 6.480543708801269,
|
|
"epoch": 2.710043341002729,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004274013814033184,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.15019096583127975,
|
|
"num_tokens": 54804821.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 6.459848165512085,
|
|
"epoch": 2.7105784151104926,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042737325204460523,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.1405377745628357,
|
|
"num_tokens": 54815291.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 6.268032884597778,
|
|
"epoch": 2.7111134892182567,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000427345118286136,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.16145387887954712,
|
|
"num_tokens": 54826891.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 6.441977500915527,
|
|
"epoch": 2.7116485633260208,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004273169801287228,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.14884840250015258,
|
|
"num_tokens": 54837545.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 6.501547765731812,
|
|
"epoch": 2.7121836374337844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042728883757317825,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.13928472399711608,
|
|
"num_tokens": 54848028.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 6.47163143157959,
|
|
"epoch": 2.7127187115415485,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042726069062031495,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14257197231054305,
|
|
"num_tokens": 54858679.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 6.447218370437622,
|
|
"epoch": 2.7132537856493126,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042723253927094565,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.15201518535614014,
|
|
"num_tokens": 54870892.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 6.411854791641235,
|
|
"epoch": 2.7137888597570763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000427204383525883,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.15155672430992126,
|
|
"num_tokens": 54881131.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 6.389288377761841,
|
|
"epoch": 2.7143239338648404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004271762233859403,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.1513580046594143,
|
|
"num_tokens": 54891532.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 6.3969708442687985,
|
|
"epoch": 2.714859007972604,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042714805885193046,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.15483452528715133,
|
|
"num_tokens": 54902945.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 6.416445636749268,
|
|
"epoch": 2.715394082080368,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042711988992466684,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.1438060313463211,
|
|
"num_tokens": 54913943.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 6.459086894989014,
|
|
"epoch": 2.715929156188132,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042709171660496275,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.15137378722429276,
|
|
"num_tokens": 54924241.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 6.42902946472168,
|
|
"epoch": 2.716464230295896,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004270635388936317,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.15176012068986894,
|
|
"num_tokens": 54934083.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 6.4336676597595215,
|
|
"epoch": 2.71699930440366,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042703535679148734,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.14425669983029366,
|
|
"num_tokens": 54944928.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 6.357444190979004,
|
|
"epoch": 2.7175343785114237,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042700717029934345,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.15729526579380035,
|
|
"num_tokens": 54955715.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 6.38131160736084,
|
|
"epoch": 2.7180694526191878,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004269789794180139,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14945384711027146,
|
|
"num_tokens": 54966149.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 6.423126935958862,
|
|
"epoch": 2.718604526726952,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00042695078414831263,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.14676564559340477,
|
|
"num_tokens": 54976854.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 6.480395746231079,
|
|
"epoch": 2.7191396008347155,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004269225844910538,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.14946893900632857,
|
|
"num_tokens": 54987377.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 6.4805260181427,
|
|
"epoch": 2.7196746749424796,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004268943804470518,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.14189084023237228,
|
|
"num_tokens": 54999488.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 6.543209362030029,
|
|
"epoch": 2.7202097490502437,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00042686617201712074,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.14102415665984153,
|
|
"num_tokens": 55011517.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 6.5075311183929445,
|
|
"epoch": 2.7207448231580074,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004268379592020754,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.14639490693807602,
|
|
"num_tokens": 55022133.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 6.380606174468994,
|
|
"epoch": 2.7212798972657715,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042680974200273036,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.14934568852186203,
|
|
"num_tokens": 55032684.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 6.466644954681397,
|
|
"epoch": 2.721814971373535,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004267815204199003,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.15035367980599404,
|
|
"num_tokens": 55042943.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 6.43906717300415,
|
|
"epoch": 2.722350045481299,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004267532944544002,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1449126720428467,
|
|
"num_tokens": 55053805.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 6.397273015975952,
|
|
"epoch": 2.722885119589063,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042672506410704495,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.14536254554986955,
|
|
"num_tokens": 55066611.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 6.443541193008423,
|
|
"epoch": 2.723420193696827,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004266968293786499,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.14655536636710167,
|
|
"num_tokens": 55077954.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 6.4696681022644045,
|
|
"epoch": 2.723955267804591,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004266685902700302,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.1491883784532547,
|
|
"num_tokens": 55090296.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 6.531213331222534,
|
|
"epoch": 2.7244903419123547,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004266403467820013,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14442493617534638,
|
|
"num_tokens": 55100664.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 6.411429309844971,
|
|
"epoch": 2.725025416020119,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004266120989153786,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15167819559574128,
|
|
"num_tokens": 55111094.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 6.498197746276856,
|
|
"epoch": 2.725560490127883,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042658384667097787,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14239726811647416,
|
|
"num_tokens": 55121877.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 6.418594217300415,
|
|
"epoch": 2.7260955642356466,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004265555900496149,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.15120193213224412,
|
|
"num_tokens": 55133087.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 6.427367448806763,
|
|
"epoch": 2.7266306383434107,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042652732905210555,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.14529965370893477,
|
|
"num_tokens": 55144257.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 6.439451503753662,
|
|
"epoch": 2.7271657124511743,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004264990636792659,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.15734648704528809,
|
|
"num_tokens": 55154389.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 6.373074102401733,
|
|
"epoch": 2.7277007865589384,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000426470793931912,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.1599299654364586,
|
|
"num_tokens": 55165734.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 6.29597053527832,
|
|
"epoch": 2.728235860666702,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004264425198108603,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15958747416734695,
|
|
"num_tokens": 55176448.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 6.41937141418457,
|
|
"epoch": 2.728770934774466,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042641424131692707,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.1583247035741806,
|
|
"num_tokens": 55187515.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 6.470597219467163,
|
|
"epoch": 2.7293060088822303,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004263859584509289,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.14412814304232596,
|
|
"num_tokens": 55199236.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 6.454286384582519,
|
|
"epoch": 2.729841082989994,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004263576712136825,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.15354201048612595,
|
|
"num_tokens": 55210151.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 6.429635143280029,
|
|
"epoch": 2.730376157097758,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042632937960600454,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.1496674232184887,
|
|
"num_tokens": 55221322.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 6.3394568920135494,
|
|
"epoch": 2.730911231205522,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042630108362871205,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.16026728898286818,
|
|
"num_tokens": 55231901.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 6.440993118286133,
|
|
"epoch": 2.731446305313286,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00042627278328262203,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.155671626329422,
|
|
"num_tokens": 55243154.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 6.435354852676392,
|
|
"epoch": 2.73198137942105,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042624447856855164,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.15432586893439293,
|
|
"num_tokens": 55253485.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 6.496493625640869,
|
|
"epoch": 2.732516453528814,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042621616948731816,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.14419427067041396,
|
|
"num_tokens": 55264936.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 6.424218559265137,
|
|
"epoch": 2.7330515276365777,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004261878560397391,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.15414737910032272,
|
|
"num_tokens": 55276138.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 6.428554201126099,
|
|
"epoch": 2.7335866017443413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042615953822663195,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.14704363346099852,
|
|
"num_tokens": 55287398.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 6.517673301696777,
|
|
"epoch": 2.7341216758521054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042613121604881426,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.14067264199256896,
|
|
"num_tokens": 55298806.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 6.450430774688721,
|
|
"epoch": 2.7346567499598695,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004261028895071041,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15255129635334014,
|
|
"num_tokens": 55309976.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 6.466075468063354,
|
|
"epoch": 2.735191824067633,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042607455860231916,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14783285185694695,
|
|
"num_tokens": 55320806.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 6.418241882324219,
|
|
"epoch": 2.7357268981753973,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004260462233352775,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.15122041404247283,
|
|
"num_tokens": 55332153.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 6.439561128616333,
|
|
"epoch": 2.7362619722831614,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042601788370679746,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.14657056778669358,
|
|
"num_tokens": 55343595.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 6.4276245594024655,
|
|
"epoch": 2.736797046390925,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042598953971769723,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.14435483440756797,
|
|
"num_tokens": 55353891.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 6.4939628601074215,
|
|
"epoch": 2.737332120498689,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004259611913687952,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.15009569823741914,
|
|
"num_tokens": 55364743.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 6.52032790184021,
|
|
"epoch": 2.7378671946064532,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042593283866091,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.14124570339918135,
|
|
"num_tokens": 55375122.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 6.426980447769165,
|
|
"epoch": 2.738402268714217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042590448159486035,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1450087994337082,
|
|
"num_tokens": 55387281.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 6.457336950302124,
|
|
"epoch": 2.738937342821981,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042587612017146496,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.14195430800318717,
|
|
"num_tokens": 55397859.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 6.44852499961853,
|
|
"epoch": 2.7394724169297446,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042584775439154276,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.15435815900564193,
|
|
"num_tokens": 55408169.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 6.361451578140259,
|
|
"epoch": 2.7400074910375087,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004258193842559129,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.14957543089985847,
|
|
"num_tokens": 55419342.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 6.3249797344207765,
|
|
"epoch": 2.7405425651452724,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004257910097653945,
|
|
"loss": 5.9535,
|
|
"mean_token_accuracy": 0.15536751300096513,
|
|
"num_tokens": 55430271.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 6.473565578460693,
|
|
"epoch": 2.7410776392530365,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004257626309208069,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.14854575842618942,
|
|
"num_tokens": 55441901.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 6.395791482925415,
|
|
"epoch": 2.7416127133608006,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004257342477229695,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.15168683230876923,
|
|
"num_tokens": 55451743.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 6.432854413986206,
|
|
"epoch": 2.7421477874685642,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00042570586017270196,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.15006721764802933,
|
|
"num_tokens": 55462805.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 6.389247465133667,
|
|
"epoch": 2.7426828615763283,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042567746827082377,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.1479640744626522,
|
|
"num_tokens": 55474277.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 6.4561385154724125,
|
|
"epoch": 2.7432179356840924,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004256490720181549,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.14657876044511794,
|
|
"num_tokens": 55485257.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 6.33825159072876,
|
|
"epoch": 2.743753009791856,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042562067141551523,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.15036061704158782,
|
|
"num_tokens": 55495835.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 6.489846181869507,
|
|
"epoch": 2.74428808389962,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042559226646372486,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.14170274659991264,
|
|
"num_tokens": 55506256.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 6.486428928375244,
|
|
"epoch": 2.744823158007384,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000425563857163604,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.15948477312922477,
|
|
"num_tokens": 55516821.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 6.4164635181427006,
|
|
"epoch": 2.745358232115148,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042553544351597286,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1425837606191635,
|
|
"num_tokens": 55527153.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 6.470670938491821,
|
|
"epoch": 2.7458933062229116,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042550702552165195,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.1411615192890167,
|
|
"num_tokens": 55538219.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 6.536293363571167,
|
|
"epoch": 2.7464283803306757,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042547860318146183,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.14561992436647414,
|
|
"num_tokens": 55548733.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 6.4749914646148685,
|
|
"epoch": 2.74696345443844,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042545017649622314,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.14953542426228522,
|
|
"num_tokens": 55559746.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 6.376782751083374,
|
|
"epoch": 2.7474985285462035,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004254217454667569,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.14929199293255807,
|
|
"num_tokens": 55570322.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 6.30539608001709,
|
|
"epoch": 2.7480336026539676,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004253933100938837,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.15574714094400405,
|
|
"num_tokens": 55580715.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 6.477630615234375,
|
|
"epoch": 2.7485686767617317,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004253648703784249,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.15008877217769623,
|
|
"num_tokens": 55591685.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 6.437804937362671,
|
|
"epoch": 2.7491037508694953,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004253364263212016,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.14492260217666625,
|
|
"num_tokens": 55602288.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 6.4257549285888675,
|
|
"epoch": 2.7496388249772594,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004253079779230352,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.14752286523580552,
|
|
"num_tokens": 55613011.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 6.3855335235595705,
|
|
"epoch": 2.7501738990850235,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004252795251847469,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.1493801310658455,
|
|
"num_tokens": 55623630.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 6.370765733718872,
|
|
"epoch": 2.750708973192787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042525106810715845,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.1563740164041519,
|
|
"num_tokens": 55634764.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 6.477820873260498,
|
|
"epoch": 2.7512440473005513,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042522260669109157,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.15210364609956742,
|
|
"num_tokens": 55645085.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 6.484300136566162,
|
|
"epoch": 2.751779121408315,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000425194140937368,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.1394964836537838,
|
|
"num_tokens": 55656249.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 6.4998280048370365,
|
|
"epoch": 2.752314195516079,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042516567084680977,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.1518393263220787,
|
|
"num_tokens": 55668138.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 6.4903425693511965,
|
|
"epoch": 2.7528492696238427,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004251371964202389,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.15156002789735795,
|
|
"num_tokens": 55678747.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 6.476528024673462,
|
|
"epoch": 2.753384343731607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004251087176584775,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.1491600140929222,
|
|
"num_tokens": 55690266.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 6.437159252166748,
|
|
"epoch": 2.753919417839371,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042508023456234805,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.1483944557607174,
|
|
"num_tokens": 55700229.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 6.423054265975952,
|
|
"epoch": 2.7544544919471345,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042505174713267286,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.14628783166408538,
|
|
"num_tokens": 55711564.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 6.439503717422485,
|
|
"epoch": 2.7549895660548986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004250232553702746,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.1559218168258667,
|
|
"num_tokens": 55722618.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 6.37799711227417,
|
|
"epoch": 2.7555246401626627,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004249947592759759,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.15584196150302887,
|
|
"num_tokens": 55732828.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 6.399539756774902,
|
|
"epoch": 2.7560597142704264,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004249662588505996,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.1494250327348709,
|
|
"num_tokens": 55742283.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 6.403476762771606,
|
|
"epoch": 2.7565947883781905,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042493775409496867,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.14976274520158767,
|
|
"num_tokens": 55752883.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 6.4517827987670895,
|
|
"epoch": 2.757129862485954,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004249092450099062,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.15013401955366135,
|
|
"num_tokens": 55762730.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 6.311103868484497,
|
|
"epoch": 2.7576649365937183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004248807315962353,
|
|
"loss": 5.9962,
|
|
"mean_token_accuracy": 0.1520252913236618,
|
|
"num_tokens": 55774068.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 6.432100439071656,
|
|
"epoch": 2.758200010701482,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004248522138547793,
|
|
"loss": 6.0689,
|
|
"mean_token_accuracy": 0.1418062664568424,
|
|
"num_tokens": 55784896.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 6.414865493774414,
|
|
"epoch": 2.758735084809246,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004248236917863617,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.15214278548955917,
|
|
"num_tokens": 55796186.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 6.412644672393799,
|
|
"epoch": 2.75927015891701,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042479516539180605,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.16199107319116593,
|
|
"num_tokens": 55806439.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 6.414120721817016,
|
|
"epoch": 2.7598052330247738,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000424766634671936,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.14124292209744455,
|
|
"num_tokens": 55817955.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 6.456507301330566,
|
|
"epoch": 2.760340307132538,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042473809962757553,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.14716726094484328,
|
|
"num_tokens": 55828876.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 6.43586106300354,
|
|
"epoch": 2.760875381240302,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004247095602595485,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.15277801603078842,
|
|
"num_tokens": 55839721.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 6.371204137802124,
|
|
"epoch": 2.7614104553480656,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004246810165686788,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.15058609694242478,
|
|
"num_tokens": 55850427.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 6.464559412002563,
|
|
"epoch": 2.7619455294558297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042465246855579093,
|
|
"loss": 6.0862,
|
|
"mean_token_accuracy": 0.14228805601596833,
|
|
"num_tokens": 55860245.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 6.446472454071045,
|
|
"epoch": 2.762480603563594,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042462391622170897,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1508305251598358,
|
|
"num_tokens": 55869957.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 6.4355621337890625,
|
|
"epoch": 2.7630156776713575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004245953595672575,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.1406472772359848,
|
|
"num_tokens": 55881159.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 6.6007133483886715,
|
|
"epoch": 2.7635507517791216,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000424566798593261,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.14426540583372116,
|
|
"num_tokens": 55891830.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 6.466911125183105,
|
|
"epoch": 2.7640858258868852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042453823330054427,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.14225400537252425,
|
|
"num_tokens": 55901904.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 6.364355087280273,
|
|
"epoch": 2.7646208999946493,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000424509663689932,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.14474194422364234,
|
|
"num_tokens": 55913808.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 6.415271329879761,
|
|
"epoch": 2.765155974102413,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004244810897622492,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.1504080578684807,
|
|
"num_tokens": 55924997.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 6.5113883972167965,
|
|
"epoch": 2.765691048210177,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000424452511518321,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.14324550479650497,
|
|
"num_tokens": 55935623.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 6.443820476531982,
|
|
"epoch": 2.766226122317941,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004244239289589724,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.1478296235203743,
|
|
"num_tokens": 55946733.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 6.423967504501343,
|
|
"epoch": 2.766761196425705,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000424395342085029,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.14689281582832336,
|
|
"num_tokens": 55956158.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 6.474572324752808,
|
|
"epoch": 2.767296270533469,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00042436675089731603,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.15330372601747513,
|
|
"num_tokens": 55966442.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 6.466239404678345,
|
|
"epoch": 2.767831344641233,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004243381553966591,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.14939797669649124,
|
|
"num_tokens": 55977314.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 6.385185813903808,
|
|
"epoch": 2.7683664187489967,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042430955558388396,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15223354548215867,
|
|
"num_tokens": 55987457.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 6.423221492767334,
|
|
"epoch": 2.768901492856761,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042428095145981634,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.1532500207424164,
|
|
"num_tokens": 55998319.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 6.392953205108642,
|
|
"epoch": 2.7694365669645244,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042425234302528224,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.15218333899974823,
|
|
"num_tokens": 56008654.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 6.441227436065674,
|
|
"epoch": 2.7699716410722885,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004242237302811077,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.14420871809124947,
|
|
"num_tokens": 56019793.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 6.475605630874634,
|
|
"epoch": 2.770506715180052,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000424195113228119,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1509287327528,
|
|
"num_tokens": 56031051.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 6.492498683929443,
|
|
"epoch": 2.7710417892878163,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004241664918671423,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.14654675051569938,
|
|
"num_tokens": 56041210.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 6.396188879013062,
|
|
"epoch": 2.7715768633955804,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000424137866199004,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.1532615229487419,
|
|
"num_tokens": 56051601.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 6.413284063339233,
|
|
"epoch": 2.772111937503344,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004241092362245309,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.15736669600009917,
|
|
"num_tokens": 56062669.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 6.384915113449097,
|
|
"epoch": 2.772647011611108,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042408060194454956,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14913412779569626,
|
|
"num_tokens": 56074414.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 6.438897609710693,
|
|
"epoch": 2.7731820857188723,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042405196335988676,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.14428338557481765,
|
|
"num_tokens": 56085428.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 6.469063854217529,
|
|
"epoch": 2.773717159826636,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042402332047136943,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.14452765062451361,
|
|
"num_tokens": 56097403.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 6.37754077911377,
|
|
"epoch": 2.7742522339344,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004239946732798247,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.15868452787399293,
|
|
"num_tokens": 56107781.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 6.314821100234985,
|
|
"epoch": 2.774787308042164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042396602178607973,
|
|
"loss": 5.9184,
|
|
"mean_token_accuracy": 0.16537774503231048,
|
|
"num_tokens": 56118698.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 6.4062371253967285,
|
|
"epoch": 2.7753223821499278,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004239373659909618,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.14684186428785323,
|
|
"num_tokens": 56128397.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 6.397486543655395,
|
|
"epoch": 2.7758574562576914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004239087058952984,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15191538780927658,
|
|
"num_tokens": 56138798.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 6.455853891372681,
|
|
"epoch": 2.7763925303654555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000423880041499917,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.16300947815179825,
|
|
"num_tokens": 56149936.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 6.455181455612182,
|
|
"epoch": 2.7769276044732196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004238513728056453,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.14964846074581145,
|
|
"num_tokens": 56161433.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 6.446481704711914,
|
|
"epoch": 2.7774626785809833,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042382269981331116,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.1433508016169071,
|
|
"num_tokens": 56172312.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 6.373271846771241,
|
|
"epoch": 2.7779977526887474,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042379402252374244,
|
|
"loss": 5.9855,
|
|
"mean_token_accuracy": 0.15436504632234574,
|
|
"num_tokens": 56183887.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 6.403153800964356,
|
|
"epoch": 2.7785328267965115,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042376534093776727,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.1564489260315895,
|
|
"num_tokens": 56194172.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 6.458992290496826,
|
|
"epoch": 2.779067900904275,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004237366550562137,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.14420275539159774,
|
|
"num_tokens": 56204569.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 6.441669607162476,
|
|
"epoch": 2.7796029750120392,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042370796487991013,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15280842930078506,
|
|
"num_tokens": 56215875.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 6.47059588432312,
|
|
"epoch": 2.7801380491198033,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042367927040968514,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.13782498762011527,
|
|
"num_tokens": 56227633.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 6.278856658935547,
|
|
"epoch": 2.780673123227567,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004236505716463669,
|
|
"loss": 5.9493,
|
|
"mean_token_accuracy": 0.15624210983514786,
|
|
"num_tokens": 56239420.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 6.404437065124512,
|
|
"epoch": 2.781208197335331,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004236218685907844,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.1480076566338539,
|
|
"num_tokens": 56250538.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 6.4202343940734865,
|
|
"epoch": 2.7817432714430947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004235931612437663,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.146730624884367,
|
|
"num_tokens": 56261423.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 6.429287576675415,
|
|
"epoch": 2.782278345550859,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004235644496061416,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.14426886811852455,
|
|
"num_tokens": 56272581.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 6.458887147903442,
|
|
"epoch": 2.7828134196586225,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004235357336787392,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.15403840988874434,
|
|
"num_tokens": 56283703.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 6.521402978897095,
|
|
"epoch": 2.7833484937663866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042350701346238853,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.14179784655570984,
|
|
"num_tokens": 56294657.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 6.421674919128418,
|
|
"epoch": 2.7838835678741507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004234782889579185,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.15186866819858552,
|
|
"num_tokens": 56305555.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 6.426959609985351,
|
|
"epoch": 2.7844186419819144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042344956016615885,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.1473462998867035,
|
|
"num_tokens": 56316716.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 6.432470464706421,
|
|
"epoch": 2.7849537160896785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004234208270879389,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14987516403198242,
|
|
"num_tokens": 56326582.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 6.447471284866333,
|
|
"epoch": 2.7854887901974426,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042339208972408865,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.15618169754743577,
|
|
"num_tokens": 56336687.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 6.364188575744629,
|
|
"epoch": 2.786023864305206,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004233633480754375,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.1612467125058174,
|
|
"num_tokens": 56347493.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 6.418560409545899,
|
|
"epoch": 2.7865589384129703,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042333460214281557,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.14950570613145828,
|
|
"num_tokens": 56359259.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 6.374906349182129,
|
|
"epoch": 2.787094012520734,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042330585192705284,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.14752267599105834,
|
|
"num_tokens": 56370502.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 6.369175243377685,
|
|
"epoch": 2.787629086628498,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042327709742897944,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.14704466462135315,
|
|
"num_tokens": 56381047.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 6.40776834487915,
|
|
"epoch": 2.7881641607362617,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042324833864942576,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.15330395549535752,
|
|
"num_tokens": 56392304.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 6.401726818084716,
|
|
"epoch": 2.788699234844026,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004232195755892221,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.16093580797314644,
|
|
"num_tokens": 56402480.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 6.3833600044250485,
|
|
"epoch": 2.78923430895179,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042319080824919895,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.1508347600698471,
|
|
"num_tokens": 56413659.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 6.425733613967895,
|
|
"epoch": 2.7897693830595536,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004231620366301871,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.14508638828992843,
|
|
"num_tokens": 56425272.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 6.53260235786438,
|
|
"epoch": 2.7903044571673177,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00042313326073301733,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.1503555953502655,
|
|
"num_tokens": 56436696.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 6.477833318710327,
|
|
"epoch": 2.7908395312750818,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004231044805585204,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.1436576709151268,
|
|
"num_tokens": 56446666.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 6.39180269241333,
|
|
"epoch": 2.7913746053828454,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004230756961075274,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.1507587678730488,
|
|
"num_tokens": 56457082.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 6.378720235824585,
|
|
"epoch": 2.7919096794906095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042304690738086944,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.1521870255470276,
|
|
"num_tokens": 56468492.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 6.441785383224487,
|
|
"epoch": 2.7924447535983736,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004230181143793779,
|
|
"loss": 6.0551,
|
|
"mean_token_accuracy": 0.1534495547413826,
|
|
"num_tokens": 56479353.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 6.439150476455689,
|
|
"epoch": 2.7929798277061373,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00042298931710388414,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.149759179353714,
|
|
"num_tokens": 56490105.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 6.472236633300781,
|
|
"epoch": 2.7935149018139014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004229605155552195,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1475442484021187,
|
|
"num_tokens": 56501528.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 6.48919186592102,
|
|
"epoch": 2.794049975921665,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042293170973421593,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.14328303709626197,
|
|
"num_tokens": 56512952.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 6.501806163787842,
|
|
"epoch": 2.794585050029429,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042290289964170495,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15625403225421905,
|
|
"num_tokens": 56523332.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 6.467695331573486,
|
|
"epoch": 2.795120124137193,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004228740852785185,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.14998308569192886,
|
|
"num_tokens": 56534777.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 6.3937599658966064,
|
|
"epoch": 2.795655198244957,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042284526664548866,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.14366142079234123,
|
|
"num_tokens": 56545706.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 6.370588779449463,
|
|
"epoch": 2.796190272352721,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042281644374344754,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.14527872279286386,
|
|
"num_tokens": 56557014.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 6.445417165756226,
|
|
"epoch": 2.7967253464604847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042278761657322736,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.15204058587551117,
|
|
"num_tokens": 56569707.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 6.4742724895477295,
|
|
"epoch": 2.7972604205682488,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004227587851356605,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.15044934898614884,
|
|
"num_tokens": 56579924.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 6.5041240692138675,
|
|
"epoch": 2.797795494676013,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004227299494315795,
|
|
"loss": 6.0828,
|
|
"mean_token_accuracy": 0.14583077430725097,
|
|
"num_tokens": 56590301.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 6.4372642040252686,
|
|
"epoch": 2.7983305687837765,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042270110946181693,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15271706730127335,
|
|
"num_tokens": 56600717.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 6.463856840133667,
|
|
"epoch": 2.7988656428915406,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00042267226522720556,
|
|
"loss": 6.058,
|
|
"mean_token_accuracy": 0.14681680351495743,
|
|
"num_tokens": 56611547.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 6.413233518600464,
|
|
"epoch": 2.7994007169993043,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004226434167285784,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.15135293006896972,
|
|
"num_tokens": 56622542.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 6.419681024551392,
|
|
"epoch": 2.7999357911070684,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004226145639667683,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.15508953779935836,
|
|
"num_tokens": 56633359.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 6.3672102928161625,
|
|
"epoch": 2.800470865214832,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004225857069426083,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.15799694061279296,
|
|
"num_tokens": 56644101.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 6.458103942871094,
|
|
"epoch": 2.801005939322596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042255684565693183,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.14844557791948318,
|
|
"num_tokens": 56654630.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 6.389373016357422,
|
|
"epoch": 2.80154101343036,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004225279801105722,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.1511190876364708,
|
|
"num_tokens": 56665826.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 6.3908380508422855,
|
|
"epoch": 2.802076087538124,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004224991103043628,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.14940351694822313,
|
|
"num_tokens": 56676431.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 6.459698343276978,
|
|
"epoch": 2.802611161645888,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042247023623913745,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.15339324325323106,
|
|
"num_tokens": 56687297.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 6.367177200317383,
|
|
"epoch": 2.803146235753652,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004224413579157296,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.15312274917960167,
|
|
"num_tokens": 56698392.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 6.439164924621582,
|
|
"epoch": 2.8036813098614157,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004224124753349733,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.1526595890522003,
|
|
"num_tokens": 56710588.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 6.354989147186279,
|
|
"epoch": 2.80421638396918,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004223835884977025,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.1574145197868347,
|
|
"num_tokens": 56723143.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 6.426775741577148,
|
|
"epoch": 2.804751458076944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004223546974047513,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.15531293153762818,
|
|
"num_tokens": 56734097.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 6.447193622589111,
|
|
"epoch": 2.8052865321847076,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004223258020569539,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.14504825249314307,
|
|
"num_tokens": 56745311.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 6.452460050582886,
|
|
"epoch": 2.8058216062924712,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004222969024551447,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.15037810504436494,
|
|
"num_tokens": 56755495.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 6.4384236335754395,
|
|
"epoch": 2.8063566804002353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042226799860015817,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.15909594893455506,
|
|
"num_tokens": 56766107.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 6.411249256134033,
|
|
"epoch": 2.8068917545079994,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004222390904928288,
|
|
"loss": 6.0002,
|
|
"mean_token_accuracy": 0.15537684857845308,
|
|
"num_tokens": 56776877.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 6.433188629150391,
|
|
"epoch": 2.807426828615763,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042221017813399146,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.15274036228656768,
|
|
"num_tokens": 56786439.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 6.394668245315552,
|
|
"epoch": 2.807961902723527,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004221812615244809,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.1435970276594162,
|
|
"num_tokens": 56797433.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 6.5347984790802,
|
|
"epoch": 2.8084969768312913,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042215234066513203,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.14584537744522094,
|
|
"num_tokens": 56808270.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 6.486695766448975,
|
|
"epoch": 2.809032050939055,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042212341555678,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.14755429029464723,
|
|
"num_tokens": 56818590.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 6.395121812820435,
|
|
"epoch": 2.809567125046819,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004220944862002601,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.14349693208932876,
|
|
"num_tokens": 56828799.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 6.4509632110595705,
|
|
"epoch": 2.810102199154583,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042206555259640744,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.14447470605373383,
|
|
"num_tokens": 56839409.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 6.3562744617462155,
|
|
"epoch": 2.810637273262347,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042203661474605775,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.15901046395301818,
|
|
"num_tokens": 56849650.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 6.404301595687866,
|
|
"epoch": 2.811172347370111,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004220076726500464,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.14773694723844527,
|
|
"num_tokens": 56860437.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 6.469612503051758,
|
|
"epoch": 2.8117074214778746,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042197872630920927,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.15329967737197875,
|
|
"num_tokens": 56870314.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 6.4698954105377195,
|
|
"epoch": 2.8122424955856387,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042194977572438194,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.14935247749090194,
|
|
"num_tokens": 56881675.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 6.467679023742676,
|
|
"epoch": 2.8127775696934023,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042192082089640055,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.14070313572883605,
|
|
"num_tokens": 56893148.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 6.469432544708252,
|
|
"epoch": 2.8133126438011664,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004218918618261011,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.15965280681848526,
|
|
"num_tokens": 56904008.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 6.425285863876343,
|
|
"epoch": 2.8138477179089305,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00042186289851431976,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.15042104423046113,
|
|
"num_tokens": 56914731.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 6.453146648406983,
|
|
"epoch": 2.814382792016694,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00042183393096189285,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.14326153546571732,
|
|
"num_tokens": 56926037.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 6.337903356552124,
|
|
"epoch": 2.8149178661244583,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042180495916965686,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.16146292984485627,
|
|
"num_tokens": 56936456.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 6.434628009796143,
|
|
"epoch": 2.8154529402322224,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004217759831384483,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.15641989186406136,
|
|
"num_tokens": 56947929.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 6.406024360656739,
|
|
"epoch": 2.815988014339986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042174700286910376,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.1581709712743759,
|
|
"num_tokens": 56958153.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 6.469569826126099,
|
|
"epoch": 2.81652308844775,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004217180183624602,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.14834050983190536,
|
|
"num_tokens": 56968609.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 6.478921031951904,
|
|
"epoch": 2.817058162555514,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004216890296193545,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.15596452951431275,
|
|
"num_tokens": 56978434.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 6.400845956802368,
|
|
"epoch": 2.817593236663278,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004216600366406236,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15164154171943664,
|
|
"num_tokens": 56988826.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 6.378601503372193,
|
|
"epoch": 2.8181283107710415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042163103942710487,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.14799215495586396,
|
|
"num_tokens": 57000385.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 6.337564897537232,
|
|
"epoch": 2.8186633848788056,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004216020379796354,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.16381412819027902,
|
|
"num_tokens": 57012137.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 6.459012174606324,
|
|
"epoch": 2.8191984589865697,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00042157303229905277,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.1492543637752533,
|
|
"num_tokens": 57022533.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 6.499421882629394,
|
|
"epoch": 2.8197335330943334,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042154402238619434,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.14749213978648185,
|
|
"num_tokens": 57034438.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 6.470699071884155,
|
|
"epoch": 2.8202686072020975,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00042151500824189785,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.1473413124680519,
|
|
"num_tokens": 57046343.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 6.453160429000855,
|
|
"epoch": 2.8208036813098616,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042148598986700117,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.14620157182216645,
|
|
"num_tokens": 57058269.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 6.411958503723144,
|
|
"epoch": 2.8213387554176252,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042145696726234207,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.15512288808822633,
|
|
"num_tokens": 57069192.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 6.482750320434571,
|
|
"epoch": 2.8218738295253893,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004214279404287586,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.15206675976514816,
|
|
"num_tokens": 57080021.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 6.400658655166626,
|
|
"epoch": 2.8224089036331534,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004213989093670889,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.15042894184589387,
|
|
"num_tokens": 57090336.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 6.367533254623413,
|
|
"epoch": 2.822943977740917,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004213698740781713,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.15316496342420577,
|
|
"num_tokens": 57101942.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 6.409625911712647,
|
|
"epoch": 2.823479051848681,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004213408345628442,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.15230459123849868,
|
|
"num_tokens": 57112353.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 6.296683311462402,
|
|
"epoch": 2.824014125956445,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000421311790821946,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1791028618812561,
|
|
"num_tokens": 57123796.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 6.427670907974243,
|
|
"epoch": 2.824549200064209,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042128274285631545,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.1501665234565735,
|
|
"num_tokens": 57134463.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 6.385494089126587,
|
|
"epoch": 2.8250842741719726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042125369066679124,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.15315476357936858,
|
|
"num_tokens": 57146964.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 6.468384552001953,
|
|
"epoch": 2.8256193482797367,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042122463425421224,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.14576466307044028,
|
|
"num_tokens": 57157322.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 6.382465791702271,
|
|
"epoch": 2.826154422387501,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004211955736194175,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.15780599564313888,
|
|
"num_tokens": 57168758.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 6.398380136489868,
|
|
"epoch": 2.8266894964952645,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042116650876324616,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.15427615046501159,
|
|
"num_tokens": 57180322.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 6.41349687576294,
|
|
"epoch": 2.8272245706030286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004211374396865373,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.14819267392158508,
|
|
"num_tokens": 57190836.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 6.36381311416626,
|
|
"epoch": 2.8277596447107927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004211083663901305,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.15367063581943513,
|
|
"num_tokens": 57202439.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 6.490589761734009,
|
|
"epoch": 2.8282947188185563,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004210792888748651,
|
|
"loss": 6.1876,
|
|
"mean_token_accuracy": 0.13698135167360306,
|
|
"num_tokens": 57213335.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 6.464270114898682,
|
|
"epoch": 2.8288297929263204,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042105020714158076,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.14554350972175598,
|
|
"num_tokens": 57223840.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 6.436989593505859,
|
|
"epoch": 2.829364867034084,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042102112119111725,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.14175086393952369,
|
|
"num_tokens": 57234702.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 6.332023239135742,
|
|
"epoch": 2.829899941141848,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004209920310243144,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.15748982429504393,
|
|
"num_tokens": 57247415.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 6.385210418701172,
|
|
"epoch": 2.830435015249612,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004209629366420121,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15433283820748328,
|
|
"num_tokens": 57257768.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 6.505837678909302,
|
|
"epoch": 2.830970089357376,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004209338380450506,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.14097389876842498,
|
|
"num_tokens": 57268114.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 6.484896898269653,
|
|
"epoch": 2.83150516346514,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042090473523426994,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.14675534069538115,
|
|
"num_tokens": 57278680.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 6.498466634750367,
|
|
"epoch": 2.8320402375729037,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042087562821051055,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14393219649791716,
|
|
"num_tokens": 57289823.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 6.427369689941406,
|
|
"epoch": 2.832575311680668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042084651697461297,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.14882372915744782,
|
|
"num_tokens": 57300137.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 6.400393676757813,
|
|
"epoch": 2.833110385788432,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042081740152741763,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.16098742187023163,
|
|
"num_tokens": 57311160.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 6.400449657440186,
|
|
"epoch": 2.8336454598961955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004207882818697654,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.1490056574344635,
|
|
"num_tokens": 57322708.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 6.414525842666626,
|
|
"epoch": 2.8341805340039596,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000420759158002497,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.15236240327358247,
|
|
"num_tokens": 57333788.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 6.450986528396607,
|
|
"epoch": 2.8347156081117237,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042073002992645337,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.15622793436050414,
|
|
"num_tokens": 57344806.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 6.469390726089477,
|
|
"epoch": 2.8352506822194874,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004207008976424756,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14586670994758605,
|
|
"num_tokens": 57355086.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 6.382518625259399,
|
|
"epoch": 2.835785756327251,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004206717611514049,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.1586865097284317,
|
|
"num_tokens": 57364837.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 6.403486156463623,
|
|
"epoch": 2.836320830435015,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004206426204540825,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.1502322018146515,
|
|
"num_tokens": 57376049.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 6.4489173412323,
|
|
"epoch": 2.8368559045427792,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042061347555135,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.1436118006706238,
|
|
"num_tokens": 57387829.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 6.458997583389282,
|
|
"epoch": 2.837390978650543,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004205843264440488,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15300317704677582,
|
|
"num_tokens": 57397165.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 6.392493343353271,
|
|
"epoch": 2.837926052758307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042055517313302064,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.1520601987838745,
|
|
"num_tokens": 57408602.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 6.389436435699463,
|
|
"epoch": 2.838461126866071,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004205260156191073,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.15610310882329942,
|
|
"num_tokens": 57419393.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 6.384090375900269,
|
|
"epoch": 2.8389962009738348,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042049685390315074,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.14963267594575883,
|
|
"num_tokens": 57431238.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 6.448880290985107,
|
|
"epoch": 2.839531275081599,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00042046768798599293,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1601277098059654,
|
|
"num_tokens": 57442080.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 6.407636880874634,
|
|
"epoch": 2.840066349189363,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004204385178684761,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.15068115368485452,
|
|
"num_tokens": 57452539.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 6.436146354675293,
|
|
"epoch": 2.8406014232971266,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042040934355144245,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.14302660301327705,
|
|
"num_tokens": 57464936.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 6.438657236099243,
|
|
"epoch": 2.8411364974048907,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004203801650357346,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.15072648823261262,
|
|
"num_tokens": 57477460.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 6.457589626312256,
|
|
"epoch": 2.8416715715126544,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004203509823221947,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.1504028744995594,
|
|
"num_tokens": 57487707.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 6.40608811378479,
|
|
"epoch": 2.8422066456204185,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004203217954116657,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.14950546324253083,
|
|
"num_tokens": 57498107.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 6.437542152404785,
|
|
"epoch": 2.842741719728182,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042029260430499033,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.14859019666910173,
|
|
"num_tokens": 57509035.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 6.410235452651977,
|
|
"epoch": 2.8432767938359462,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00042026340900301135,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1445617437362671,
|
|
"num_tokens": 57521234.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 6.414348936080932,
|
|
"epoch": 2.8438118679437103,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004202342095065719,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.15504412353038788,
|
|
"num_tokens": 57532294.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 6.470386123657226,
|
|
"epoch": 2.844346942051474,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000420205005816515,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.15683928579092027,
|
|
"num_tokens": 57542047.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 6.353037595748901,
|
|
"epoch": 2.844882016159238,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000420175797933684,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.15064765363931656,
|
|
"num_tokens": 57553254.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 6.3797187328338625,
|
|
"epoch": 2.845417090267002,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042014658585892223,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.16147678792476655,
|
|
"num_tokens": 57564321.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 6.345517015457153,
|
|
"epoch": 2.845952164374766,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00042011736959307323,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.15159724205732344,
|
|
"num_tokens": 57575018.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 6.385954093933106,
|
|
"epoch": 2.84648723848253,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042008814913698054,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.15120517313480378,
|
|
"num_tokens": 57585698.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 6.409604167938232,
|
|
"epoch": 2.8470223125902936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004200589244914879,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.15515661984682083,
|
|
"num_tokens": 57595363.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 6.3503913402557375,
|
|
"epoch": 2.8475573866980577,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042002969565743925,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.16248847618699075,
|
|
"num_tokens": 57605908.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 6.310200881958008,
|
|
"epoch": 2.8480924608058213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004200004626356785,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.15958615243434907,
|
|
"num_tokens": 57616172.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 6.408188056945801,
|
|
"epoch": 2.8486275349135854,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041997122542704974,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.15232954770326615,
|
|
"num_tokens": 57626770.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 6.360273742675782,
|
|
"epoch": 2.8491626090213495,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004199419840323972,
|
|
"loss": 5.9103,
|
|
"mean_token_accuracy": 0.16150974929332734,
|
|
"num_tokens": 57636576.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 6.303816223144532,
|
|
"epoch": 2.849697683129113,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041991273845256536,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15867117643356324,
|
|
"num_tokens": 57646431.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 6.354286861419678,
|
|
"epoch": 2.8502327572368773,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00041988348868839836,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.1539828896522522,
|
|
"num_tokens": 57657412.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 6.45865387916565,
|
|
"epoch": 2.8507678313446414,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004198542347407412,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.15559379905462264,
|
|
"num_tokens": 57667434.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 6.401463174819947,
|
|
"epoch": 2.851302905452405,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004198249766104382,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15440521091222764,
|
|
"num_tokens": 57677640.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 6.408425569534302,
|
|
"epoch": 2.851837979560169,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004197957142983344,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.15036824494600295,
|
|
"num_tokens": 57687909.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 6.488574838638305,
|
|
"epoch": 2.8523730536679333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004197664478052747,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.1438972160220146,
|
|
"num_tokens": 57700374.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 6.481727600097656,
|
|
"epoch": 2.852908127775697,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004197371771321042,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.1529959946870804,
|
|
"num_tokens": 57711577.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 6.341199541091919,
|
|
"epoch": 2.853443201883461,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041970790227966804,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.1603742554783821,
|
|
"num_tokens": 57721259.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 6.35086989402771,
|
|
"epoch": 2.8539782759912247,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041967862324881154,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.15057576596736907,
|
|
"num_tokens": 57731499.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 6.474545526504516,
|
|
"epoch": 2.8545133500989888,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004196493400403801,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.14337437376379966,
|
|
"num_tokens": 57742343.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 6.468021583557129,
|
|
"epoch": 2.8550484242067524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004196200526552193,
|
|
"loss": 6.0299,
|
|
"mean_token_accuracy": 0.15668390989303588,
|
|
"num_tokens": 57752942.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 6.479112720489502,
|
|
"epoch": 2.8555834983145165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004195907610941748,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.15321232080459596,
|
|
"num_tokens": 57763623.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 6.334421682357788,
|
|
"epoch": 2.8561185724222806,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004195614653580924,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.1475632146000862,
|
|
"num_tokens": 57774538.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 6.361044788360596,
|
|
"epoch": 2.8566536465300443,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041953216544781796,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.15029519498348237,
|
|
"num_tokens": 57785420.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 6.420391607284546,
|
|
"epoch": 2.8571887206378084,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041950286136419756,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.14479026794433594,
|
|
"num_tokens": 57796488.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 6.480253791809082,
|
|
"epoch": 2.8577237947455725,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041947355310807737,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.1494418740272522,
|
|
"num_tokens": 57806391.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 6.378093719482422,
|
|
"epoch": 2.858258868853336,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00041944424068030364,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.14750756174325944,
|
|
"num_tokens": 57817410.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 6.43929352760315,
|
|
"epoch": 2.8587939429611002,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041941492408172277,
|
|
"loss": 6.0654,
|
|
"mean_token_accuracy": 0.14923201352357865,
|
|
"num_tokens": 57828582.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 6.347782039642334,
|
|
"epoch": 2.859329017068864,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041938560331318124,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.16159299165010452,
|
|
"num_tokens": 57838962.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 6.4341823101043705,
|
|
"epoch": 2.859864091176628,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004193562783755257,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.15648251697421073,
|
|
"num_tokens": 57849335.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 6.452866268157959,
|
|
"epoch": 2.8603991652843916,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004193269492696029,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.15065740644931794,
|
|
"num_tokens": 57860904.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 6.449029970169067,
|
|
"epoch": 2.8609342393921557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004192976159962597,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.1481325715780258,
|
|
"num_tokens": 57870861.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 6.354551792144775,
|
|
"epoch": 2.86146931349992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004192682785563432,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.14433916807174682,
|
|
"num_tokens": 57881590.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 6.410019636154175,
|
|
"epoch": 2.8620043876076835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004192389369507004,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.15093303620815277,
|
|
"num_tokens": 57892736.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 6.542281436920166,
|
|
"epoch": 2.8625394617154476,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004192095911801785,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.1412319876253605,
|
|
"num_tokens": 57904340.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 6.458233070373535,
|
|
"epoch": 2.8630745358232117,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000419180241245625,
|
|
"loss": 6.0322,
|
|
"mean_token_accuracy": 0.15415556877851486,
|
|
"num_tokens": 57916369.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 6.366694164276123,
|
|
"epoch": 2.8636096099309754,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004191508871478873,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.14483662545681,
|
|
"num_tokens": 57926867.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 6.406448221206665,
|
|
"epoch": 2.8641446840387395,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041912152888781283,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.1496852308511734,
|
|
"num_tokens": 57938408.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 6.488473749160766,
|
|
"epoch": 2.8646797581465036,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041909216646624967,
|
|
"loss": 5.9853,
|
|
"mean_token_accuracy": 0.1590641990303993,
|
|
"num_tokens": 57948821.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 6.411574125289917,
|
|
"epoch": 2.865214832254267,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004190627998840453,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.15112300589680672,
|
|
"num_tokens": 57959589.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 6.400305986404419,
|
|
"epoch": 2.8657499063620313,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004190334291420479,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.14814646989107133,
|
|
"num_tokens": 57970508.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 6.4455334663391115,
|
|
"epoch": 2.866284980469795,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004190040542411055,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.15378978252410888,
|
|
"num_tokens": 57980411.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 6.424951362609863,
|
|
"epoch": 2.866820054577559,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041897467518206614,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.1573548808693886,
|
|
"num_tokens": 57991457.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 6.458602666854858,
|
|
"epoch": 2.8673551286853227,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004189452919657784,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.13983291909098625,
|
|
"num_tokens": 58001860.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 6.472284555435181,
|
|
"epoch": 2.867890202793087,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041891590459309055,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.14592931792140007,
|
|
"num_tokens": 58011958.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 6.407073545455932,
|
|
"epoch": 2.868425276900851,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041888651306485117,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.153120244294405,
|
|
"num_tokens": 58022216.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 6.403811883926392,
|
|
"epoch": 2.8689603510086146,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041885711738190895,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.15083375424146653,
|
|
"num_tokens": 58032502.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 6.372001981735229,
|
|
"epoch": 2.8694954251163787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004188277175451126,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.1517692118883133,
|
|
"num_tokens": 58043944.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 6.443247604370117,
|
|
"epoch": 2.8700304992241428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041879831355531123,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.14562223106622696,
|
|
"num_tokens": 58055857.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 6.3814051151275635,
|
|
"epoch": 2.8705655733319064,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004187689054133537,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.15365127250552177,
|
|
"num_tokens": 58067070.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 6.332041263580322,
|
|
"epoch": 2.8711006474396705,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004187394931200893,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.15968974828720092,
|
|
"num_tokens": 58077922.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 6.412332010269165,
|
|
"epoch": 2.871635721547434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004187100766763671,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.15546340197324754,
|
|
"num_tokens": 58089698.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 6.462100601196289,
|
|
"epoch": 2.8721707956551983,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041868065608303674,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.15846218764781952,
|
|
"num_tokens": 58100640.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 6.404068088531494,
|
|
"epoch": 2.872705869762962,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004186512313409476,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.1470884382724762,
|
|
"num_tokens": 58112810.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 6.468878316879272,
|
|
"epoch": 2.873240943870726,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004186218024509493,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.14706760197877883,
|
|
"num_tokens": 58123818.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 6.450071716308594,
|
|
"epoch": 2.87377601797849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041859236941389175,
|
|
"loss": 6.0636,
|
|
"mean_token_accuracy": 0.14915749058127403,
|
|
"num_tokens": 58134785.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 6.4456321716308596,
|
|
"epoch": 2.874311092086254,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004185629322306246,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.15013698488473892,
|
|
"num_tokens": 58144987.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 6.416501665115357,
|
|
"epoch": 2.874846166194018,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041853349090199805,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.15730877071619034,
|
|
"num_tokens": 58155031.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 6.322882843017578,
|
|
"epoch": 2.875381240301782,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000418504045428862,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.1569364346563816,
|
|
"num_tokens": 58165216.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 6.395208215713501,
|
|
"epoch": 2.8759163144095456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004184745958120669,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.15620874911546706,
|
|
"num_tokens": 58176329.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 6.495823526382447,
|
|
"epoch": 2.8764513885173097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041844514205246293,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.1500655770301819,
|
|
"num_tokens": 58187058.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 6.457627201080323,
|
|
"epoch": 2.876986462625074,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004184156841509007,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.15183956176042557,
|
|
"num_tokens": 58196579.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 6.296269464492798,
|
|
"epoch": 2.8775215367328375,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041838622210823076,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.15458275824785234,
|
|
"num_tokens": 58206689.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 6.426440954208374,
|
|
"epoch": 2.878056610840601,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004183567559253037,
|
|
"loss": 6.0319,
|
|
"mean_token_accuracy": 0.1525313824415207,
|
|
"num_tokens": 58218093.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 6.464215850830078,
|
|
"epoch": 2.8785916849483653,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041832728560297055,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14989352375268936,
|
|
"num_tokens": 58228587.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 6.3886962890625,
|
|
"epoch": 2.8791267590561294,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00041829781114208214,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.15750156939029694,
|
|
"num_tokens": 58240500.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 6.350870990753174,
|
|
"epoch": 2.879661833163893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041826833254348956,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.14876446574926377,
|
|
"num_tokens": 58252253.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 6.457035493850708,
|
|
"epoch": 2.880196907271657,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041823884980804406,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.1494783192873001,
|
|
"num_tokens": 58263356.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 6.3225400924682615,
|
|
"epoch": 2.880731981379421,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041820936293659685,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1557753175497055,
|
|
"num_tokens": 58273270.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 6.409237098693848,
|
|
"epoch": 2.881267055487185,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041817987192999947,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.14683982580900193,
|
|
"num_tokens": 58284669.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 6.453193140029907,
|
|
"epoch": 2.881802129594949,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00041815037678910334,
|
|
"loss": 6.1108,
|
|
"mean_token_accuracy": 0.15075706243515014,
|
|
"num_tokens": 58294791.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 6.490873908996582,
|
|
"epoch": 2.882337203702713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004181208775147602,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.1498957723379135,
|
|
"num_tokens": 58305789.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 6.452756404876709,
|
|
"epoch": 2.8828722778104767,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004180913741078218,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.14747522994875908,
|
|
"num_tokens": 58317547.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 6.401312923431396,
|
|
"epoch": 2.883407351918241,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004180618665691402,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.1527828760445118,
|
|
"num_tokens": 58328408.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 6.290218782424927,
|
|
"epoch": 2.8839424260260045,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004180323548995672,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.17409270107746125,
|
|
"num_tokens": 58339356.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 6.368633222579956,
|
|
"epoch": 2.8844775001337686,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00041800283909995505,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.1625841073691845,
|
|
"num_tokens": 58349016.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 6.4525960922241214,
|
|
"epoch": 2.8850125742415322,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004179733191711561,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.14001980572938919,
|
|
"num_tokens": 58360188.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 6.518548202514649,
|
|
"epoch": 2.8855476483492963,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00041794379511402263,
|
|
"loss": 6.0611,
|
|
"mean_token_accuracy": 0.14841486513614655,
|
|
"num_tokens": 58370733.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 6.398956918716431,
|
|
"epoch": 2.8860827224570604,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004179142669294071,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.1466510623693466,
|
|
"num_tokens": 58382249.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 6.369844722747803,
|
|
"epoch": 2.886617796564824,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00041788473461816224,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.15576791763305664,
|
|
"num_tokens": 58393598.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 6.414325380325318,
|
|
"epoch": 2.887152870672588,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041785519818114073,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.14889776557683945,
|
|
"num_tokens": 58403920.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 6.387530279159546,
|
|
"epoch": 2.8876879447803523,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041782565761919546,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.14682680740952492,
|
|
"num_tokens": 58413691.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 6.472382116317749,
|
|
"epoch": 2.888223018888116,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041779611293317936,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.14470405876636505,
|
|
"num_tokens": 58425995.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 6.456513118743897,
|
|
"epoch": 2.88875809299588,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004177665641239456,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.14884288981556892,
|
|
"num_tokens": 58435984.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 6.4106457233428955,
|
|
"epoch": 2.8892931671036437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041773701119234734,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1486773058772087,
|
|
"num_tokens": 58447630.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.8892931671036437,
|
|
"eval_entropy": 6.218136414042059,
|
|
"eval_loss": 6.141349792480469,
|
|
"eval_mean_token_accuracy": 0.15345027208970885,
|
|
"eval_num_tokens": 58447630.0,
|
|
"eval_runtime": 22.5656,
|
|
"eval_samples_per_second": 1315.232,
|
|
"eval_steps_per_second": 164.41,
|
|
"step": 27000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 93440,
|
|
"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": 8.5939567852032e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|