6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.27213352685050796,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742568969726562,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7846,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10827.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742588996887207,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7602,
|
|
"mean_token_accuracy": 6.963788182474673e-05,
|
|
"num_tokens": 21025.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742573070526124,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7437,
|
|
"mean_token_accuracy": 9.000900317914783e-05,
|
|
"num_tokens": 31678.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742661285400391,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6591,
|
|
"mean_token_accuracy": 0.0005137635511346161,
|
|
"num_tokens": 41025.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742550945281982,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.5792,
|
|
"mean_token_accuracy": 0.006170097610447556,
|
|
"num_tokens": 51270.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.742267036437989,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4637,
|
|
"mean_token_accuracy": 0.027165642101317646,
|
|
"num_tokens": 62142.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.741279792785644,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3199,
|
|
"mean_token_accuracy": 0.04252696111798286,
|
|
"num_tokens": 72709.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.738855934143066,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1477,
|
|
"mean_token_accuracy": 0.041494901105761525,
|
|
"num_tokens": 82313.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.734966659545899,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0172,
|
|
"mean_token_accuracy": 0.048007883876562116,
|
|
"num_tokens": 92450.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.731274795532226,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9997,
|
|
"mean_token_accuracy": 0.0419012438505888,
|
|
"num_tokens": 103978.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.729759407043456,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.8946,
|
|
"mean_token_accuracy": 0.04565211050212383,
|
|
"num_tokens": 114134.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.727651214599609,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.8734,
|
|
"mean_token_accuracy": 0.04470008127391338,
|
|
"num_tokens": 125037.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.725145721435547,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7559,
|
|
"mean_token_accuracy": 0.04514850843697786,
|
|
"num_tokens": 134721.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.723241519927978,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.6935,
|
|
"mean_token_accuracy": 0.04249380584806204,
|
|
"num_tokens": 144448.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.721195030212403,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.635,
|
|
"mean_token_accuracy": 0.04518970362842083,
|
|
"num_tokens": 154343.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.7159348487854,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6121,
|
|
"mean_token_accuracy": 0.041934683173894885,
|
|
"num_tokens": 165650.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.709981918334961,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6128,
|
|
"mean_token_accuracy": 0.03882604259997606,
|
|
"num_tokens": 177098.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.703641796112061,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4133,
|
|
"mean_token_accuracy": 0.04838715270161629,
|
|
"num_tokens": 187903.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.691870975494385,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3442,
|
|
"mean_token_accuracy": 0.04516914151608944,
|
|
"num_tokens": 198077.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.677101039886475,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3156,
|
|
"mean_token_accuracy": 0.04309112168848515,
|
|
"num_tokens": 208641.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.661001300811767,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1598,
|
|
"mean_token_accuracy": 0.05524700954556465,
|
|
"num_tokens": 218398.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.64128761291504,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.035,
|
|
"mean_token_accuracy": 0.06018046177923679,
|
|
"num_tokens": 229059.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.614240169525146,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9594,
|
|
"mean_token_accuracy": 0.05966283418238163,
|
|
"num_tokens": 239775.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.567374324798584,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8042,
|
|
"mean_token_accuracy": 0.06268535517156124,
|
|
"num_tokens": 249954.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.49941110610962,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7019,
|
|
"mean_token_accuracy": 0.06550404466688634,
|
|
"num_tokens": 260056.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.433360958099366,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5999,
|
|
"mean_token_accuracy": 0.06795549392700195,
|
|
"num_tokens": 269904.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.364013862609863,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.4687,
|
|
"mean_token_accuracy": 0.06760800294578076,
|
|
"num_tokens": 280900.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.2804931640625,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3637,
|
|
"mean_token_accuracy": 0.067552350461483,
|
|
"num_tokens": 290844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.172641277313232,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2257,
|
|
"mean_token_accuracy": 0.07797299772500992,
|
|
"num_tokens": 301345.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.0338849067688,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.0893,
|
|
"mean_token_accuracy": 0.07597564421594143,
|
|
"num_tokens": 312681.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.874010562896729,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9627,
|
|
"mean_token_accuracy": 0.08046026974916458,
|
|
"num_tokens": 323492.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.684037780761718,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9031,
|
|
"mean_token_accuracy": 0.07810574918985366,
|
|
"num_tokens": 334521.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.470422744750977,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8175,
|
|
"mean_token_accuracy": 0.08020211830735206,
|
|
"num_tokens": 345468.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.22849702835083,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6913,
|
|
"mean_token_accuracy": 0.07718781009316444,
|
|
"num_tokens": 355911.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.006134128570556,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6633,
|
|
"mean_token_accuracy": 0.07722515687346458,
|
|
"num_tokens": 367537.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.818270492553712,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7245,
|
|
"mean_token_accuracy": 0.07779238075017929,
|
|
"num_tokens": 377918.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.593470573425293,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5619,
|
|
"mean_token_accuracy": 0.07740958072245122,
|
|
"num_tokens": 388461.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.449785518646241,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5162,
|
|
"mean_token_accuracy": 0.07913253530859947,
|
|
"num_tokens": 399771.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.267493534088135,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3798,
|
|
"mean_token_accuracy": 0.08124997988343238,
|
|
"num_tokens": 410254.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.230424785614014,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3917,
|
|
"mean_token_accuracy": 0.07860286422073841,
|
|
"num_tokens": 419792.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.091243362426757,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3759,
|
|
"mean_token_accuracy": 0.08409927114844322,
|
|
"num_tokens": 429264.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.078143405914307,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.3197,
|
|
"mean_token_accuracy": 0.08545555844902993,
|
|
"num_tokens": 439624.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.048319149017335,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3071,
|
|
"mean_token_accuracy": 0.08367115408182144,
|
|
"num_tokens": 449556.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.937560939788819,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3073,
|
|
"mean_token_accuracy": 0.08580821454524994,
|
|
"num_tokens": 460243.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.98973650932312,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3523,
|
|
"mean_token_accuracy": 0.08153139427304268,
|
|
"num_tokens": 469767.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.94960503578186,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2779,
|
|
"mean_token_accuracy": 0.08782213702797889,
|
|
"num_tokens": 480329.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.937411499023438,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2332,
|
|
"mean_token_accuracy": 0.08278771415352822,
|
|
"num_tokens": 490096.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.9301097869873045,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2751,
|
|
"mean_token_accuracy": 0.0801933728158474,
|
|
"num_tokens": 501231.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.883290576934814,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1802,
|
|
"mean_token_accuracy": 0.09071151316165924,
|
|
"num_tokens": 510722.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.763730192184449,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.225,
|
|
"mean_token_accuracy": 0.08499881774187087,
|
|
"num_tokens": 521452.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.808817529678345,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.2137,
|
|
"mean_token_accuracy": 0.08842154070734978,
|
|
"num_tokens": 532397.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.740368890762329,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1927,
|
|
"mean_token_accuracy": 0.08906038105487823,
|
|
"num_tokens": 542271.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.7880730628967285,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1677,
|
|
"mean_token_accuracy": 0.09267213717103004,
|
|
"num_tokens": 552411.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.73106369972229,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1675,
|
|
"mean_token_accuracy": 0.09035667106509208,
|
|
"num_tokens": 561518.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.755526113510132,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1846,
|
|
"mean_token_accuracy": 0.09218391999602318,
|
|
"num_tokens": 571361.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.656434154510498,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0893,
|
|
"mean_token_accuracy": 0.09728347510099411,
|
|
"num_tokens": 580926.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.710359334945679,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1891,
|
|
"mean_token_accuracy": 0.08993546590209008,
|
|
"num_tokens": 592282.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.69242033958435,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1904,
|
|
"mean_token_accuracy": 0.09070137366652489,
|
|
"num_tokens": 602767.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.715097570419312,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1064,
|
|
"mean_token_accuracy": 0.0925739623606205,
|
|
"num_tokens": 612763.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.563499784469604,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0617,
|
|
"mean_token_accuracy": 0.09330770447850227,
|
|
"num_tokens": 622796.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.630935192108154,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0426,
|
|
"mean_token_accuracy": 0.09754194170236588,
|
|
"num_tokens": 633136.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.510959100723267,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0335,
|
|
"mean_token_accuracy": 0.09690061807632447,
|
|
"num_tokens": 643347.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.634088945388794,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0192,
|
|
"mean_token_accuracy": 0.10197105258703232,
|
|
"num_tokens": 653096.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.5339111328125,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.0519,
|
|
"mean_token_accuracy": 0.09302655458450318,
|
|
"num_tokens": 663557.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.588706541061401,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.1186,
|
|
"mean_token_accuracy": 0.0957950733602047,
|
|
"num_tokens": 674395.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.544366073608399,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0165,
|
|
"mean_token_accuracy": 0.0989912673830986,
|
|
"num_tokens": 684776.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.589376211166382,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9936,
|
|
"mean_token_accuracy": 0.09702750965952874,
|
|
"num_tokens": 694886.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.451715087890625,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0626,
|
|
"mean_token_accuracy": 0.09623553976416588,
|
|
"num_tokens": 705426.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.509190368652344,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0567,
|
|
"mean_token_accuracy": 0.09196493923664092,
|
|
"num_tokens": 716271.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.5583083152771,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0486,
|
|
"mean_token_accuracy": 0.09727451354265212,
|
|
"num_tokens": 726875.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.49442138671875,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9698,
|
|
"mean_token_accuracy": 0.09514860436320305,
|
|
"num_tokens": 737825.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.501305818557739,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9607,
|
|
"mean_token_accuracy": 0.0989458367228508,
|
|
"num_tokens": 747424.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.407667875289917,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9748,
|
|
"mean_token_accuracy": 0.09646827578544617,
|
|
"num_tokens": 757649.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.480729293823242,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.946,
|
|
"mean_token_accuracy": 0.09825383350253106,
|
|
"num_tokens": 768556.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.410275650024414,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9456,
|
|
"mean_token_accuracy": 0.0978932335972786,
|
|
"num_tokens": 778331.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.457346200942993,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9326,
|
|
"mean_token_accuracy": 0.10083384290337563,
|
|
"num_tokens": 788065.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.39845495223999,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9717,
|
|
"mean_token_accuracy": 0.10045002475380897,
|
|
"num_tokens": 798912.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.406559228897095,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9143,
|
|
"mean_token_accuracy": 0.10309505760669709,
|
|
"num_tokens": 809580.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.444182062149048,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0008,
|
|
"mean_token_accuracy": 0.09738668501377105,
|
|
"num_tokens": 820207.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.290267753601074,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8228,
|
|
"mean_token_accuracy": 0.0949432410299778,
|
|
"num_tokens": 831038.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.429319906234741,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9129,
|
|
"mean_token_accuracy": 0.10030955821275711,
|
|
"num_tokens": 842144.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.347342252731323,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.905,
|
|
"mean_token_accuracy": 0.10373404398560523,
|
|
"num_tokens": 851315.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.323047733306884,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.912,
|
|
"mean_token_accuracy": 0.10021007284522057,
|
|
"num_tokens": 861233.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.350712013244629,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8978,
|
|
"mean_token_accuracy": 0.09711670130491257,
|
|
"num_tokens": 871131.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.294861841201782,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8749,
|
|
"mean_token_accuracy": 0.09577203691005706,
|
|
"num_tokens": 882195.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.353318929672241,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8527,
|
|
"mean_token_accuracy": 0.10149310603737831,
|
|
"num_tokens": 891806.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.362502574920654,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9129,
|
|
"mean_token_accuracy": 0.09761691987514495,
|
|
"num_tokens": 901350.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.301689004898071,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8293,
|
|
"mean_token_accuracy": 0.09842056706547737,
|
|
"num_tokens": 912061.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.250009202957154,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7954,
|
|
"mean_token_accuracy": 0.09848268181085587,
|
|
"num_tokens": 922220.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.2643632888793945,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8122,
|
|
"mean_token_accuracy": 0.1012580119073391,
|
|
"num_tokens": 932319.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.2017487525939945,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8351,
|
|
"mean_token_accuracy": 0.10266126319766045,
|
|
"num_tokens": 943254.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.330859661102295,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.09818541109561921,
|
|
"num_tokens": 953921.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.193669176101684,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.10723233297467231,
|
|
"num_tokens": 963832.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.234699535369873,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.09933211356401443,
|
|
"num_tokens": 974066.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.233931684494019,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8441,
|
|
"mean_token_accuracy": 0.10467069000005721,
|
|
"num_tokens": 984402.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.256547212600708,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7629,
|
|
"mean_token_accuracy": 0.1010866865515709,
|
|
"num_tokens": 993555.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.208513498306274,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7524,
|
|
"mean_token_accuracy": 0.10970519632101058,
|
|
"num_tokens": 1002920.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.203861713409424,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8285,
|
|
"mean_token_accuracy": 0.09806114360690117,
|
|
"num_tokens": 1013611.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.1150740623474125,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.10193079337477684,
|
|
"num_tokens": 1024121.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.323940992355347,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9503,
|
|
"mean_token_accuracy": 0.10487301424145698,
|
|
"num_tokens": 1033845.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.164136552810669,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7388,
|
|
"mean_token_accuracy": 0.10410365164279937,
|
|
"num_tokens": 1044642.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.172935676574707,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8158,
|
|
"mean_token_accuracy": 0.10116696879267692,
|
|
"num_tokens": 1054728.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.138863849639892,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.10025905445218086,
|
|
"num_tokens": 1065743.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.10414080619812,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6969,
|
|
"mean_token_accuracy": 0.10323216244578362,
|
|
"num_tokens": 1076798.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.174085855484009,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8163,
|
|
"mean_token_accuracy": 0.0997597634792328,
|
|
"num_tokens": 1087445.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.094452857971191,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7197,
|
|
"mean_token_accuracy": 0.10675485357642174,
|
|
"num_tokens": 1098379.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.202598142623901,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8289,
|
|
"mean_token_accuracy": 0.0993705414235592,
|
|
"num_tokens": 1108016.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.089155960083008,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.701,
|
|
"mean_token_accuracy": 0.10358337983489037,
|
|
"num_tokens": 1117887.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.104513120651245,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6948,
|
|
"mean_token_accuracy": 0.09933766350150108,
|
|
"num_tokens": 1128497.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.055957365036011,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7188,
|
|
"mean_token_accuracy": 0.10837908834218979,
|
|
"num_tokens": 1138168.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.0923104763031,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.691,
|
|
"mean_token_accuracy": 0.10448997020721436,
|
|
"num_tokens": 1148357.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.086644268035888,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7185,
|
|
"mean_token_accuracy": 0.10321378186345101,
|
|
"num_tokens": 1159964.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.139619493484497,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7781,
|
|
"mean_token_accuracy": 0.10231135338544846,
|
|
"num_tokens": 1170683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.115566444396973,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7343,
|
|
"mean_token_accuracy": 0.10421703606843949,
|
|
"num_tokens": 1181680.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.0173659324646,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6227,
|
|
"mean_token_accuracy": 0.10645965486764908,
|
|
"num_tokens": 1191619.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.977677965164185,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6222,
|
|
"mean_token_accuracy": 0.10420064777135848,
|
|
"num_tokens": 1202264.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.002698135375977,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6254,
|
|
"mean_token_accuracy": 0.10796518102288247,
|
|
"num_tokens": 1212119.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.092545223236084,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7588,
|
|
"mean_token_accuracy": 0.10538023859262466,
|
|
"num_tokens": 1222317.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.060644435882568,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.703,
|
|
"mean_token_accuracy": 0.1080887496471405,
|
|
"num_tokens": 1232914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.919224500656128,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.11217400431632996,
|
|
"num_tokens": 1244214.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.022872066497802,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6491,
|
|
"mean_token_accuracy": 0.10687957927584649,
|
|
"num_tokens": 1254626.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.948216915130615,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7394,
|
|
"mean_token_accuracy": 0.10631354376673699,
|
|
"num_tokens": 1265461.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.030997228622437,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.10827788710594177,
|
|
"num_tokens": 1275810.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.895572900772095,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6276,
|
|
"mean_token_accuracy": 0.11254601404070855,
|
|
"num_tokens": 1285170.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.06603364944458,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5641,
|
|
"mean_token_accuracy": 0.11045938208699227,
|
|
"num_tokens": 1295460.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.950644588470459,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.10515375509858131,
|
|
"num_tokens": 1306656.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.004617834091187,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.10941670313477517,
|
|
"num_tokens": 1318019.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.8719371318817135,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5802,
|
|
"mean_token_accuracy": 0.11324906200170518,
|
|
"num_tokens": 1328120.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.002581357955933,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6842,
|
|
"mean_token_accuracy": 0.10679537355899811,
|
|
"num_tokens": 1338354.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.0219018936157225,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6503,
|
|
"mean_token_accuracy": 0.10833998396992683,
|
|
"num_tokens": 1348666.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.952841186523438,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6921,
|
|
"mean_token_accuracy": 0.11318251714110375,
|
|
"num_tokens": 1359713.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.950813102722168,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5549,
|
|
"mean_token_accuracy": 0.11367055401206017,
|
|
"num_tokens": 1369507.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.984795665740966,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.7111,
|
|
"mean_token_accuracy": 0.10242682620882988,
|
|
"num_tokens": 1380726.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.01419677734375,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.11175172179937362,
|
|
"num_tokens": 1391423.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.930062580108642,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6054,
|
|
"mean_token_accuracy": 0.11288354322314262,
|
|
"num_tokens": 1402492.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.939368772506714,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.1099183864891529,
|
|
"num_tokens": 1412497.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.999884557723999,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.11455832123756408,
|
|
"num_tokens": 1423214.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.856761169433594,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.11103508621454239,
|
|
"num_tokens": 1434044.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.9463762760162355,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.11131571531295777,
|
|
"num_tokens": 1444387.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.848030471801758,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.10915688425302505,
|
|
"num_tokens": 1455157.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.915933418273926,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.11529198288917542,
|
|
"num_tokens": 1466145.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.937824773788452,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.1114728607237339,
|
|
"num_tokens": 1476713.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.905196857452393,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6113,
|
|
"mean_token_accuracy": 0.11422201618552208,
|
|
"num_tokens": 1486908.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.866687297821045,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.11563119068741798,
|
|
"num_tokens": 1498185.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.873838233947754,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5814,
|
|
"mean_token_accuracy": 0.10893168300390244,
|
|
"num_tokens": 1508376.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.905275201797485,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6695,
|
|
"mean_token_accuracy": 0.11235518902540206,
|
|
"num_tokens": 1519953.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.795944786071777,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5408,
|
|
"mean_token_accuracy": 0.11527841538190842,
|
|
"num_tokens": 1529793.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.8445906162261965,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5363,
|
|
"mean_token_accuracy": 0.11552815213799476,
|
|
"num_tokens": 1540859.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.8253929138183596,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.11656396687030793,
|
|
"num_tokens": 1549783.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.756074047088623,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.11289834827184678,
|
|
"num_tokens": 1560522.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.810197973251343,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.11671004444360733,
|
|
"num_tokens": 1570668.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.83150315284729,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6122,
|
|
"mean_token_accuracy": 0.1193370096385479,
|
|
"num_tokens": 1581523.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.850863075256347,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.11707687377929688,
|
|
"num_tokens": 1591356.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.784787607192993,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.11673457846045494,
|
|
"num_tokens": 1601779.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.848218965530395,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5091,
|
|
"mean_token_accuracy": 0.11470222994685172,
|
|
"num_tokens": 1611995.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.800413322448731,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.11278748363256455,
|
|
"num_tokens": 1621834.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.780804920196533,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.1113444909453392,
|
|
"num_tokens": 1632881.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.707678127288818,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.11073025166988373,
|
|
"num_tokens": 1642870.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.871548318862915,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4402,
|
|
"mean_token_accuracy": 0.12203826904296874,
|
|
"num_tokens": 1653390.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.7886035442352295,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.11627909317612647,
|
|
"num_tokens": 1663382.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.804583787918091,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5652,
|
|
"mean_token_accuracy": 0.1136283002793789,
|
|
"num_tokens": 1673601.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.703377294540405,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4891,
|
|
"mean_token_accuracy": 0.12096939235925674,
|
|
"num_tokens": 1683565.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.758061265945434,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.11798930242657661,
|
|
"num_tokens": 1693636.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.882167196273803,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5623,
|
|
"mean_token_accuracy": 0.11476152688264847,
|
|
"num_tokens": 1703415.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.755157995223999,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5396,
|
|
"mean_token_accuracy": 0.11611356288194656,
|
|
"num_tokens": 1713579.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.7464526176452635,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5394,
|
|
"mean_token_accuracy": 0.11386027708649635,
|
|
"num_tokens": 1724583.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.758458185195923,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.12356605678796768,
|
|
"num_tokens": 1735293.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.7750757217407225,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.12075236141681671,
|
|
"num_tokens": 1745623.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.725871658325195,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.11627071723341942,
|
|
"num_tokens": 1755713.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.776280164718628,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.11393775343894959,
|
|
"num_tokens": 1765264.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.824870538711548,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.11867988780140877,
|
|
"num_tokens": 1775769.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.691818761825561,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.11789206489920616,
|
|
"num_tokens": 1786245.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.627203035354614,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.1227649137377739,
|
|
"num_tokens": 1796040.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.691270112991333,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.11697295233607292,
|
|
"num_tokens": 1806007.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.88080358505249,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5665,
|
|
"mean_token_accuracy": 0.10995617434382439,
|
|
"num_tokens": 1816935.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.631897354125977,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.11615645289421081,
|
|
"num_tokens": 1827419.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.766531658172608,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.11622850596904755,
|
|
"num_tokens": 1837933.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.714184427261353,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5854,
|
|
"mean_token_accuracy": 0.11893809214234352,
|
|
"num_tokens": 1848551.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.7861744403839115,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.11503675356507301,
|
|
"num_tokens": 1858380.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.660554695129394,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3853,
|
|
"mean_token_accuracy": 0.11978982239961625,
|
|
"num_tokens": 1868291.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.629644966125488,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4839,
|
|
"mean_token_accuracy": 0.11984607204794884,
|
|
"num_tokens": 1879219.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.754321718215943,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4652,
|
|
"mean_token_accuracy": 0.1155819833278656,
|
|
"num_tokens": 1889809.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.659244441986084,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.11736063361167907,
|
|
"num_tokens": 1899986.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.727784872055054,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4192,
|
|
"mean_token_accuracy": 0.11866439804434777,
|
|
"num_tokens": 1909314.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.709451198577881,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4667,
|
|
"mean_token_accuracy": 0.1235547974705696,
|
|
"num_tokens": 1918443.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.680801582336426,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.12087266743183137,
|
|
"num_tokens": 1928683.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.541482257843017,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.11764199584722519,
|
|
"num_tokens": 1938293.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.629144906997681,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4449,
|
|
"mean_token_accuracy": 0.11702702939510345,
|
|
"num_tokens": 1948233.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.660422420501709,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.12124838382005691,
|
|
"num_tokens": 1958611.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.661191082000732,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.1220276914536953,
|
|
"num_tokens": 1968957.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.65334038734436,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.12157930657267571,
|
|
"num_tokens": 1978503.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.552236032485962,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.12029609382152558,
|
|
"num_tokens": 1988458.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.655647468566895,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.491,
|
|
"mean_token_accuracy": 0.11715313494205475,
|
|
"num_tokens": 1999984.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.510547399520874,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3364,
|
|
"mean_token_accuracy": 0.12651536986231804,
|
|
"num_tokens": 2010645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.751053190231323,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.11614105999469757,
|
|
"num_tokens": 2020196.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.587527418136597,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3423,
|
|
"mean_token_accuracy": 0.1243398666381836,
|
|
"num_tokens": 2030101.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.5954345703125,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4263,
|
|
"mean_token_accuracy": 0.1206196092069149,
|
|
"num_tokens": 2040454.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.529821062088013,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.11969397887587548,
|
|
"num_tokens": 2050378.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.656999588012695,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.11806954741477967,
|
|
"num_tokens": 2060282.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.559673261642456,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.12180240452289581,
|
|
"num_tokens": 2070563.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.661390542984009,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.4743,
|
|
"mean_token_accuracy": 0.12212796434760094,
|
|
"num_tokens": 2080153.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.525332069396972,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.12526472061872482,
|
|
"num_tokens": 2090590.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.613137102127075,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.11499982699751854,
|
|
"num_tokens": 2101945.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.613913679122925,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.4031,
|
|
"mean_token_accuracy": 0.12405626773834229,
|
|
"num_tokens": 2112514.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.498817586898804,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.1212070882320404,
|
|
"num_tokens": 2122296.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.740924310684204,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.4899,
|
|
"mean_token_accuracy": 0.11208800077438355,
|
|
"num_tokens": 2134512.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.578291606903076,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.12014863640069962,
|
|
"num_tokens": 2143934.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.489139556884766,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.12084058821201324,
|
|
"num_tokens": 2155730.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.6251708984375,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.1186050683259964,
|
|
"num_tokens": 2166422.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.549373722076416,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.11772651746869087,
|
|
"num_tokens": 2177842.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.614485788345337,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.4994,
|
|
"mean_token_accuracy": 0.12015130147337913,
|
|
"num_tokens": 2188614.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.645506238937378,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.12434962838888168,
|
|
"num_tokens": 2197886.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.450875282287598,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.12345030084252358,
|
|
"num_tokens": 2209930.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.616359043121338,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.11785119250416756,
|
|
"num_tokens": 2219767.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.475496864318847,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.1218901552259922,
|
|
"num_tokens": 2230082.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.539343738555909,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.1269037939608097,
|
|
"num_tokens": 2240066.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.536786890029907,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.3427,
|
|
"mean_token_accuracy": 0.12274787575006485,
|
|
"num_tokens": 2250732.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.519191551208496,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.12317501232028008,
|
|
"num_tokens": 2261452.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.529998350143432,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.12049490809440613,
|
|
"num_tokens": 2271929.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.48491473197937,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.3314,
|
|
"mean_token_accuracy": 0.12258056998252868,
|
|
"num_tokens": 2282987.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.453391408920288,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.12670305147767066,
|
|
"num_tokens": 2292796.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.591043186187744,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.12217535674571992,
|
|
"num_tokens": 2303057.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.426148223876953,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.12347318157553673,
|
|
"num_tokens": 2314168.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.5130480289459225,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.12410474196076393,
|
|
"num_tokens": 2325241.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.5921142578125,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.12369295954704285,
|
|
"num_tokens": 2334866.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.381993150711059,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.12018040791153908,
|
|
"num_tokens": 2345422.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.5917377948760985,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.12131484672427177,
|
|
"num_tokens": 2356285.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.436669492721558,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.12863264828920365,
|
|
"num_tokens": 2366861.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.494740104675293,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.12933464497327804,
|
|
"num_tokens": 2376851.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.544817733764648,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.13027909770607948,
|
|
"num_tokens": 2386857.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.5093776226043705,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.12735775336623192,
|
|
"num_tokens": 2397035.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.470782279968262,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.12582893818616867,
|
|
"num_tokens": 2408177.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.572890186309815,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.12205304279923439,
|
|
"num_tokens": 2418445.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.472396755218506,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.1242362380027771,
|
|
"num_tokens": 2428990.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.47665491104126,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.11929563954472541,
|
|
"num_tokens": 2439643.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.585198831558228,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.12422708719968796,
|
|
"num_tokens": 2450691.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.567696046829224,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.3221,
|
|
"mean_token_accuracy": 0.12464427575469017,
|
|
"num_tokens": 2460706.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.306331729888916,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.1348014645278454,
|
|
"num_tokens": 2470947.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.511581468582153,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.1275109112262726,
|
|
"num_tokens": 2481132.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.452719688415527,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.12854906544089317,
|
|
"num_tokens": 2491701.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.320997333526611,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.12324495241045952,
|
|
"num_tokens": 2502360.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.524869346618653,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.13170049339532852,
|
|
"num_tokens": 2512140.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.4425348281860355,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.12556114420294762,
|
|
"num_tokens": 2522721.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.40459713935852,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.12824239879846572,
|
|
"num_tokens": 2531786.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.501996803283691,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.12112325578927993,
|
|
"num_tokens": 2542895.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.3701423645019535,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.12341128513216973,
|
|
"num_tokens": 2554120.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.539844799041748,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.12485537752509117,
|
|
"num_tokens": 2563935.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.355460834503174,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.12797416001558304,
|
|
"num_tokens": 2574465.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.420122289657593,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.13132491633296012,
|
|
"num_tokens": 2584694.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.382951498031616,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.1340431585907936,
|
|
"num_tokens": 2594540.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.32035346031189,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.13378870859742165,
|
|
"num_tokens": 2604896.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.4604442596435545,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.13821497261524202,
|
|
"num_tokens": 2614143.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.316441440582276,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.12574966847896576,
|
|
"num_tokens": 2623999.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.501933288574219,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.12551918104290963,
|
|
"num_tokens": 2636208.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.424142551422119,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.2436,
|
|
"mean_token_accuracy": 0.13297036662697792,
|
|
"num_tokens": 2645854.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.461622619628907,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.13188307881355285,
|
|
"num_tokens": 2655877.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.463164520263672,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.13034509047865867,
|
|
"num_tokens": 2666157.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.322438955307007,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.12801435366272926,
|
|
"num_tokens": 2676647.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.35759539604187,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.13719891905784606,
|
|
"num_tokens": 2686417.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.4111240863800045,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.12441546320915223,
|
|
"num_tokens": 2697540.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.4009637355804445,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.11752010956406593,
|
|
"num_tokens": 2709397.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.34979658126831,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.1235676109790802,
|
|
"num_tokens": 2720430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.358980894088745,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1748,
|
|
"mean_token_accuracy": 0.12498210072517395,
|
|
"num_tokens": 2730648.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.358032989501953,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.12824709638953208,
|
|
"num_tokens": 2739979.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.410165405273437,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.1253784976899624,
|
|
"num_tokens": 2750329.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.337530565261841,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.13555875271558762,
|
|
"num_tokens": 2760535.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.363765001296997,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.12614675164222716,
|
|
"num_tokens": 2770470.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.35250883102417,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.2192,
|
|
"mean_token_accuracy": 0.12356962338089943,
|
|
"num_tokens": 2781506.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.300785732269287,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.13543135821819305,
|
|
"num_tokens": 2791245.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.336817073822021,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.13693180531263352,
|
|
"num_tokens": 2801680.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.373439359664917,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.1356772594153881,
|
|
"num_tokens": 2812805.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.366350793838501,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.13203392773866654,
|
|
"num_tokens": 2822834.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.361548852920532,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.1361112043261528,
|
|
"num_tokens": 2832312.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.335978317260742,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.13540629148483277,
|
|
"num_tokens": 2842998.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.394313335418701,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.13257036805152894,
|
|
"num_tokens": 2854218.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.33300895690918,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.13703012093901634,
|
|
"num_tokens": 2864484.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.370788526535034,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.2028,
|
|
"mean_token_accuracy": 0.13148538768291473,
|
|
"num_tokens": 2873800.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.390060663223267,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.13013821244239807,
|
|
"num_tokens": 2884247.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.341064691543579,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.13113176226615905,
|
|
"num_tokens": 2894739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.234110736846924,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.13198944479227065,
|
|
"num_tokens": 2904376.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.4315849304199215,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.12843010425567628,
|
|
"num_tokens": 2914304.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.319644594192505,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.13285723477602004,
|
|
"num_tokens": 2924400.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.456520843505859,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.1338380053639412,
|
|
"num_tokens": 2935040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.279810905456543,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.1344787932932377,
|
|
"num_tokens": 2945536.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.234977674484253,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.13450392782688142,
|
|
"num_tokens": 2954969.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.315559005737304,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.13059850856661798,
|
|
"num_tokens": 2966218.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.379030179977417,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.127619219571352,
|
|
"num_tokens": 2976640.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.313711643218994,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.1332421600818634,
|
|
"num_tokens": 2985883.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.321325731277466,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.12692199870944024,
|
|
"num_tokens": 2996695.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.334502124786377,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.1343579739332199,
|
|
"num_tokens": 3007500.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.184367370605469,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.13415692150592803,
|
|
"num_tokens": 3017299.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.403480911254883,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.12249834388494492,
|
|
"num_tokens": 3028389.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.317180013656616,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.1368947669863701,
|
|
"num_tokens": 3038883.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.403723573684692,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.13426837772130967,
|
|
"num_tokens": 3049904.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.2098509788513185,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.13349713161587715,
|
|
"num_tokens": 3059788.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.351387977600098,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.1320554032921791,
|
|
"num_tokens": 3070413.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.270417833328247,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.12884705662727355,
|
|
"num_tokens": 3081093.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.342434740066528,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.13011036217212676,
|
|
"num_tokens": 3090594.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.322659873962403,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.13068215921521187,
|
|
"num_tokens": 3101061.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.294349813461304,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.13425096422433852,
|
|
"num_tokens": 3111715.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.270824289321899,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.13947287648916246,
|
|
"num_tokens": 3121378.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.246769809722901,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.1401647448539734,
|
|
"num_tokens": 3131229.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.208933019638062,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.13210750818252565,
|
|
"num_tokens": 3140859.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.351792240142823,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.13336024880409242,
|
|
"num_tokens": 3151692.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.221499061584472,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.13277293592691422,
|
|
"num_tokens": 3161879.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.278037405014038,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.13772518262267114,
|
|
"num_tokens": 3171282.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.244936561584472,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.13918796479701995,
|
|
"num_tokens": 3181398.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.294873476028442,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.13689608871936798,
|
|
"num_tokens": 3191431.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.297893095016479,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.1275126539170742,
|
|
"num_tokens": 3202147.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.362968301773071,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.13779982998967172,
|
|
"num_tokens": 3212428.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.222197484970093,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.13455342650413513,
|
|
"num_tokens": 3222099.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.321711540222168,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.13806343004107474,
|
|
"num_tokens": 3232079.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.153911828994751,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.14627765491604805,
|
|
"num_tokens": 3241762.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.244314336776734,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.1394437588751316,
|
|
"num_tokens": 3252571.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.215821599960327,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.13461477681994438,
|
|
"num_tokens": 3263542.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.340892887115478,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.1811,
|
|
"mean_token_accuracy": 0.13378583863377572,
|
|
"num_tokens": 3273295.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.3619109153747555,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.136061330139637,
|
|
"num_tokens": 3283605.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.243741178512574,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.14292106181383132,
|
|
"num_tokens": 3293837.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.130685424804687,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.14042141437530517,
|
|
"num_tokens": 3304131.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.302355670928955,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.0746,
|
|
"mean_token_accuracy": 0.13077147156000138,
|
|
"num_tokens": 3313543.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.222482824325562,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.1355305939912796,
|
|
"num_tokens": 3324487.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.281767272949219,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.1388099044561386,
|
|
"num_tokens": 3335094.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.182447385787964,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.13585399314761162,
|
|
"num_tokens": 3344252.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.219208812713623,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.13364078626036643,
|
|
"num_tokens": 3354265.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.3048234462738035,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.13599163964390754,
|
|
"num_tokens": 3364616.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.33318829536438,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.14277874156832696,
|
|
"num_tokens": 3373650.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.114496469497681,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.13961085602641105,
|
|
"num_tokens": 3384590.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.34743185043335,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.13647577166557312,
|
|
"num_tokens": 3395616.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.165446662902832,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.1349581092596054,
|
|
"num_tokens": 3405810.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.321514320373535,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.1055,
|
|
"mean_token_accuracy": 0.1329289957880974,
|
|
"num_tokens": 3415932.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.197605752944947,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.13647494986653327,
|
|
"num_tokens": 3425626.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.155983877182007,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.1348869502544403,
|
|
"num_tokens": 3434837.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.258736085891724,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.14022651612758635,
|
|
"num_tokens": 3445238.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.191891717910766,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.13351622000336646,
|
|
"num_tokens": 3456738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.110352945327759,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.14009969010949136,
|
|
"num_tokens": 3466296.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.319712066650391,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.1345,
|
|
"mean_token_accuracy": 0.13245827108621597,
|
|
"num_tokens": 3476989.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.156819915771484,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 5.97,
|
|
"mean_token_accuracy": 0.1411023445427418,
|
|
"num_tokens": 3487050.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.2730926990509035,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.12993267178535461,
|
|
"num_tokens": 3497777.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.238672304153442,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.13315979093313218,
|
|
"num_tokens": 3509066.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.142438983917236,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 6.026,
|
|
"mean_token_accuracy": 0.13728305473923683,
|
|
"num_tokens": 3519567.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.209616088867188,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.13899025991559028,
|
|
"num_tokens": 3529402.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.3146570205688475,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.1440271407365799,
|
|
"num_tokens": 3539805.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.143733882904053,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.14397806972265242,
|
|
"num_tokens": 3550477.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.110523653030396,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.139139074832201,
|
|
"num_tokens": 3560729.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.220071601867676,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.13195881322026254,
|
|
"num_tokens": 3571538.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.214411115646362,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 6.1078,
|
|
"mean_token_accuracy": 0.13914671614766122,
|
|
"num_tokens": 3583128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.246854066848755,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.14036523252725602,
|
|
"num_tokens": 3594358.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.198376893997192,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.14713839516043664,
|
|
"num_tokens": 3604345.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.148045206069947,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.13767840191721917,
|
|
"num_tokens": 3616129.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.18104510307312,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.13979990035295486,
|
|
"num_tokens": 3627458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.226989650726319,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.14392665922641754,
|
|
"num_tokens": 3636047.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.051787710189819,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.1413258582353592,
|
|
"num_tokens": 3646930.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.218035459518433,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.14086730852723123,
|
|
"num_tokens": 3657279.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.123547697067261,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.1423609510064125,
|
|
"num_tokens": 3667070.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.166107845306397,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1381991073489189,
|
|
"num_tokens": 3677560.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.090453720092773,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.1474891871213913,
|
|
"num_tokens": 3686701.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.152267122268677,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.14551690965890884,
|
|
"num_tokens": 3696338.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.150699281692505,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 5.9993,
|
|
"mean_token_accuracy": 0.14381766989827155,
|
|
"num_tokens": 3705752.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.229558277130127,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.13718133196234703,
|
|
"num_tokens": 3716225.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.1720422267913815,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.14193314164876938,
|
|
"num_tokens": 3726593.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.101333570480347,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.13523678332567216,
|
|
"num_tokens": 3737563.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.307489013671875,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.1370485432446003,
|
|
"num_tokens": 3747752.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.057960081100464,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.139044688642025,
|
|
"num_tokens": 3758795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.2216832637786865,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.14233563393354415,
|
|
"num_tokens": 3768690.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.090987873077393,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.13934776037931443,
|
|
"num_tokens": 3779018.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.219239854812622,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.14526350796222687,
|
|
"num_tokens": 3788985.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.173433303833008,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.13157572448253632,
|
|
"num_tokens": 3800787.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.16374773979187,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.13687085136771202,
|
|
"num_tokens": 3811381.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.157071971893311,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.14529063701629638,
|
|
"num_tokens": 3822055.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.190087890625,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.1372029162943363,
|
|
"num_tokens": 3831900.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.127886390686035,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.14112438708543779,
|
|
"num_tokens": 3842702.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.237508106231689,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.14055541008710862,
|
|
"num_tokens": 3852690.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.039614915847778,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.1505817547440529,
|
|
"num_tokens": 3863040.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.180584526062011,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.13932662308216096,
|
|
"num_tokens": 3873613.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.042843770980835,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.1480574920773506,
|
|
"num_tokens": 3883936.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.060999536514283,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.14890880212187768,
|
|
"num_tokens": 3893788.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.056200647354126,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.14825719892978667,
|
|
"num_tokens": 3903434.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.1081467628479,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.1487080954015255,
|
|
"num_tokens": 3913476.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.991112613677979,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.1485322192311287,
|
|
"num_tokens": 3923301.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.099672555923462,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.13689797297120093,
|
|
"num_tokens": 3933335.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.197177267074585,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.13568304777145385,
|
|
"num_tokens": 3944171.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.177489757537842,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.14412558674812317,
|
|
"num_tokens": 3954160.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.171565389633178,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.14805472120642663,
|
|
"num_tokens": 3964110.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.134349346160889,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 5.9675,
|
|
"mean_token_accuracy": 0.1452759712934494,
|
|
"num_tokens": 3974293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.078616380691528,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.15142350345849992,
|
|
"num_tokens": 3984346.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.053181409835815,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.15365748405456542,
|
|
"num_tokens": 3992897.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.05509238243103,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.15057138204574586,
|
|
"num_tokens": 4002575.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.070607757568359,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.14099667817354203,
|
|
"num_tokens": 4013752.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.107510566711426,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.14898938685655594,
|
|
"num_tokens": 4023718.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.064271402359009,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.1369916170835495,
|
|
"num_tokens": 4034210.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.2005760192871096,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.1424011543393135,
|
|
"num_tokens": 4044868.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.97287278175354,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.14433022439479828,
|
|
"num_tokens": 4055049.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.208456897735596,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.14180623665452002,
|
|
"num_tokens": 4065889.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.090062475204467,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 6.0282,
|
|
"mean_token_accuracy": 0.1386457771062851,
|
|
"num_tokens": 4077288.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.084208917617798,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.1426486611366272,
|
|
"num_tokens": 4087402.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.152999305725098,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.13648915737867356,
|
|
"num_tokens": 4098150.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.015424156188965,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.1459066838026047,
|
|
"num_tokens": 4108134.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.190234994888305,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.13577395901083947,
|
|
"num_tokens": 4118251.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.0451069355010985,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.1469724267721176,
|
|
"num_tokens": 4129228.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.0451616764068605,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.15002663657069207,
|
|
"num_tokens": 4139391.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.0800574779510494,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.1524651437997818,
|
|
"num_tokens": 4148891.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.2835156440734865,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.138189584761858,
|
|
"num_tokens": 4159551.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.138812065124512,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.14381420388817787,
|
|
"num_tokens": 4170055.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.033186531066894,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.14449694454669954,
|
|
"num_tokens": 4180767.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.07762713432312,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.14416737630963325,
|
|
"num_tokens": 4190654.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.103671360015869,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.1454018011689186,
|
|
"num_tokens": 4200753.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.093059635162353,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.14127395525574685,
|
|
"num_tokens": 4210994.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.107717561721802,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.1447222650051117,
|
|
"num_tokens": 4220883.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.123315095901489,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.13728086575865744,
|
|
"num_tokens": 4231269.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.056053113937378,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.14049455970525743,
|
|
"num_tokens": 4241559.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.045488786697388,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.14596481025218963,
|
|
"num_tokens": 4250870.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.027891731262207,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.1532222166657448,
|
|
"num_tokens": 4260848.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.0480344772338865,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.14905711114406586,
|
|
"num_tokens": 4270973.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.159943771362305,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.14108132272958757,
|
|
"num_tokens": 4281211.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.0061546802520756,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.14745167195796965,
|
|
"num_tokens": 4291425.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.123989725112915,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.1410026654601097,
|
|
"num_tokens": 4301079.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.104276657104492,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.14320143908262253,
|
|
"num_tokens": 4312374.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.043295049667359,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.15539209097623824,
|
|
"num_tokens": 4322810.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.002667427062988,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.14834146052598954,
|
|
"num_tokens": 4332082.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.0972264289855955,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.14356174021959306,
|
|
"num_tokens": 4342632.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.016445589065552,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1432491272687912,
|
|
"num_tokens": 4353544.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.031062507629395,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.14226981848478318,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.133910322189331,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.1426288031041622,
|
|
"num_tokens": 4373672.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.938132858276367,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.14870256185531616,
|
|
"num_tokens": 4383199.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.071506214141846,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.14334884583950042,
|
|
"num_tokens": 4394446.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.126976585388183,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.1414870209991932,
|
|
"num_tokens": 4405882.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.956241512298584,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.15368922352790831,
|
|
"num_tokens": 4415280.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.030566740036011,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.13928496092557907,
|
|
"num_tokens": 4425755.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.020366859436035,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.14801339209079742,
|
|
"num_tokens": 4436259.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.056359338760376,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.14185069352388383,
|
|
"num_tokens": 4446423.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.050050067901611,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.15231530964374543,
|
|
"num_tokens": 4456678.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.006132411956787,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.15113169997930526,
|
|
"num_tokens": 4467031.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.0697108745574955,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.13495565131306647,
|
|
"num_tokens": 4477771.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.000240993499756,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.14246328622102739,
|
|
"num_tokens": 4488426.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.17234845161438,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.13979932889342309,
|
|
"num_tokens": 4499735.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.042126989364624,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.14715081751346587,
|
|
"num_tokens": 4509500.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.014921045303344,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.14634579196572303,
|
|
"num_tokens": 4520431.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.034388875961303,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.14680968075990677,
|
|
"num_tokens": 4532294.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.020555639266968,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.14305620416998863,
|
|
"num_tokens": 4542488.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.039434766769409,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.13846864104270934,
|
|
"num_tokens": 4552933.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.0450187683105465,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.15138240456581115,
|
|
"num_tokens": 4562373.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.943200492858887,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.14522400572896005,
|
|
"num_tokens": 4572715.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.120235109329224,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.14360565692186356,
|
|
"num_tokens": 4582782.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.041302442550659,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.13825485333800316,
|
|
"num_tokens": 4594108.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.074282169342041,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.14501106441020967,
|
|
"num_tokens": 4604732.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.039686012268066,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.13512664213776587,
|
|
"num_tokens": 4614998.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.029949378967285,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.14373639225959778,
|
|
"num_tokens": 4624665.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.060518264770508,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 5.8374,
|
|
"mean_token_accuracy": 0.15260313004255294,
|
|
"num_tokens": 4633731.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.0299561500549315,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.1454593777656555,
|
|
"num_tokens": 4643421.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.054778814315796,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.1441769301891327,
|
|
"num_tokens": 4653795.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.058734989166259,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.1450178414583206,
|
|
"num_tokens": 4664840.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.073224878311157,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.14578341245651244,
|
|
"num_tokens": 4675508.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.989795446395874,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.14992504566907883,
|
|
"num_tokens": 4685995.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.086735725402832,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.14490637332201003,
|
|
"num_tokens": 4696659.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.985673189163208,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.15447261780500413,
|
|
"num_tokens": 4706438.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.944012832641602,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.1460217833518982,
|
|
"num_tokens": 4716402.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.024405479431152,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.14774347990751266,
|
|
"num_tokens": 4728488.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.027887296676636,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.14974903911352158,
|
|
"num_tokens": 4738693.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.020720100402832,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.1517803430557251,
|
|
"num_tokens": 4748895.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.089075136184692,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.14135059341788292,
|
|
"num_tokens": 4760135.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.095640230178833,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 5.9916,
|
|
"mean_token_accuracy": 0.15003142952919007,
|
|
"num_tokens": 4769935.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.164234828948975,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.14601739197969438,
|
|
"num_tokens": 4779520.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.891173362731934,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.1525731474161148,
|
|
"num_tokens": 4791256.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.922054576873779,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.15643645375967025,
|
|
"num_tokens": 4801334.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.940741872787475,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.15321901589632034,
|
|
"num_tokens": 4811361.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.995629167556762,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.14930329322814942,
|
|
"num_tokens": 4821190.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.996551895141602,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.15249975472688676,
|
|
"num_tokens": 4830694.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.9884954452514645,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.8478,
|
|
"mean_token_accuracy": 0.14835911467671395,
|
|
"num_tokens": 4841344.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.958621692657471,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.1466705918312073,
|
|
"num_tokens": 4851161.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.9765862941741945,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.1497928962111473,
|
|
"num_tokens": 4860740.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.9823229789733885,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.14942808002233504,
|
|
"num_tokens": 4871733.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.0018017292022705,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.14177072122693063,
|
|
"num_tokens": 4883617.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.005364894866943,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.14455199390649795,
|
|
"num_tokens": 4894519.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.98149266242981,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.8014,
|
|
"mean_token_accuracy": 0.14887023940682412,
|
|
"num_tokens": 4904965.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.936092567443848,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1545273095369339,
|
|
"num_tokens": 4914618.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.868344449996949,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.15782049298286438,
|
|
"num_tokens": 4924341.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.880142879486084,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.15210559889674186,
|
|
"num_tokens": 4934231.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.974342632293701,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.1491807922720909,
|
|
"num_tokens": 4944303.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.959984636306762,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.15104133933782576,
|
|
"num_tokens": 4954571.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.957349252700806,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14804138243198395,
|
|
"num_tokens": 4964418.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.975922727584839,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.1464727595448494,
|
|
"num_tokens": 4975036.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.98774995803833,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.14540747702121734,
|
|
"num_tokens": 4985272.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.043728685379028,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.15086397528648376,
|
|
"num_tokens": 4995187.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.0442393779754635,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.15320269912481307,
|
|
"num_tokens": 5005013.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.054208087921142,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.9139,
|
|
"mean_token_accuracy": 0.1428740605711937,
|
|
"num_tokens": 5016789.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.934090423583984,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.8588,
|
|
"mean_token_accuracy": 0.147943913936615,
|
|
"num_tokens": 5026913.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.962672376632691,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.1470245487987995,
|
|
"num_tokens": 5037501.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.027901649475098,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.14490654170513154,
|
|
"num_tokens": 5048478.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.919871520996094,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1465262070298195,
|
|
"num_tokens": 5059118.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.006969404220581,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.15497831404209136,
|
|
"num_tokens": 5070180.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.935058832168579,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.14882795214653016,
|
|
"num_tokens": 5079912.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.052799558639526,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.1513648509979248,
|
|
"num_tokens": 5090549.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.9224653244018555,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15711326152086258,
|
|
"num_tokens": 5100880.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.927716445922852,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.14909446835517884,
|
|
"num_tokens": 5111796.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.045079755783081,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.862,
|
|
"mean_token_accuracy": 0.1490783780813217,
|
|
"num_tokens": 5123468.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.968772125244141,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.15539813786745071,
|
|
"num_tokens": 5132925.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.98187403678894,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.14465042054653168,
|
|
"num_tokens": 5143445.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.025763702392578,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.7817,
|
|
"mean_token_accuracy": 0.14337050616741182,
|
|
"num_tokens": 5153176.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.005899715423584,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.1517674669623375,
|
|
"num_tokens": 5162765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.946051549911499,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.8804,
|
|
"mean_token_accuracy": 0.15172123089432715,
|
|
"num_tokens": 5173390.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.946356534957886,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.14956301152706147,
|
|
"num_tokens": 5184212.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.886882019042969,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.15003687813878058,
|
|
"num_tokens": 5194311.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.916078996658325,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.15247755497694016,
|
|
"num_tokens": 5204708.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.87827501296997,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15128237307071685,
|
|
"num_tokens": 5214566.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.943019533157349,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.15266707986593248,
|
|
"num_tokens": 5224762.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.9829565525054935,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.15028240010142327,
|
|
"num_tokens": 5235146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.023767328262329,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.14803099185228347,
|
|
"num_tokens": 5243867.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.893141078948974,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.1500532016158104,
|
|
"num_tokens": 5254279.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.080553483963013,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.14982936531305313,
|
|
"num_tokens": 5264769.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.93544192314148,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.14275677353143693,
|
|
"num_tokens": 5274291.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.883300113677978,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.15632595419883727,
|
|
"num_tokens": 5284366.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.95240535736084,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.15440944731235504,
|
|
"num_tokens": 5294494.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.928846740722657,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.15485012233257295,
|
|
"num_tokens": 5305606.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.960556077957153,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.150348149985075,
|
|
"num_tokens": 5315677.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.986758232116699,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.1463898465037346,
|
|
"num_tokens": 5326453.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.92100830078125,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.15171819776296616,
|
|
"num_tokens": 5337591.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.9538902759552,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.15522343516349793,
|
|
"num_tokens": 5349400.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.00141224861145,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.1506360337138176,
|
|
"num_tokens": 5359984.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.916184520721435,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.15854744762182235,
|
|
"num_tokens": 5369254.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.9528069496154785,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.15245212465524674,
|
|
"num_tokens": 5379648.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.849475145339966,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.154351457208395,
|
|
"num_tokens": 5390321.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.919327926635742,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.15511986911296843,
|
|
"num_tokens": 5401078.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.961600828170776,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.1566541612148285,
|
|
"num_tokens": 5411977.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.893222713470459,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.15138195902109147,
|
|
"num_tokens": 5422967.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.9912902355194095,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.16118090003728866,
|
|
"num_tokens": 5432260.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.888670158386231,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.15361348688602447,
|
|
"num_tokens": 5441706.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.94991717338562,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.1588932454586029,
|
|
"num_tokens": 5452397.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.880772686004638,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.15416701436042785,
|
|
"num_tokens": 5463762.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.901000833511352,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.14654496908187867,
|
|
"num_tokens": 5474622.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.944158935546875,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.15286272019147873,
|
|
"num_tokens": 5484697.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.847146940231323,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.15464416444301604,
|
|
"num_tokens": 5496433.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.972603416442871,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.1483437992632389,
|
|
"num_tokens": 5507917.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.07913875579834,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.14761385768651963,
|
|
"num_tokens": 5519159.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.928588962554931,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.15743801593780518,
|
|
"num_tokens": 5529180.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.884641027450561,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.16192516684532166,
|
|
"num_tokens": 5539363.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.909084510803223,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.15110581144690513,
|
|
"num_tokens": 5549841.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.940350866317749,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.161916483938694,
|
|
"num_tokens": 5560299.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.962108039855957,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.15469845086336137,
|
|
"num_tokens": 5571081.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.871194362640381,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.15739612132310868,
|
|
"num_tokens": 5581389.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.881601572036743,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.14633584022521973,
|
|
"num_tokens": 5592347.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.889206314086914,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.15528458803892137,
|
|
"num_tokens": 5603411.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.930398607254029,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.7452,
|
|
"mean_token_accuracy": 0.15865262895822524,
|
|
"num_tokens": 5614615.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.811875200271606,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.15606526732444764,
|
|
"num_tokens": 5624582.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.876440620422363,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.15305925607681276,
|
|
"num_tokens": 5634310.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.932286167144776,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.15080375373363494,
|
|
"num_tokens": 5644018.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.862547779083252,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.15690971165895462,
|
|
"num_tokens": 5653592.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.973826742172241,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.155655175447464,
|
|
"num_tokens": 5662812.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.936570167541504,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.1513756588101387,
|
|
"num_tokens": 5672939.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.83735408782959,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.15465778708457947,
|
|
"num_tokens": 5683350.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.977609300613404,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.1457457385957241,
|
|
"num_tokens": 5694516.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.897079944610596,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.15890194922685624,
|
|
"num_tokens": 5705443.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.876714992523193,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.772,
|
|
"mean_token_accuracy": 0.1513215646147728,
|
|
"num_tokens": 5715933.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.92222113609314,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.835,
|
|
"mean_token_accuracy": 0.14457671642303466,
|
|
"num_tokens": 5726630.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.002235460281372,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.1539665475487709,
|
|
"num_tokens": 5736890.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.778037357330322,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.1656890943646431,
|
|
"num_tokens": 5747042.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.874831628799439,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.1548820838332176,
|
|
"num_tokens": 5757367.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.933564472198486,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.14902109056711196,
|
|
"num_tokens": 5769557.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.887054443359375,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.15811785459518432,
|
|
"num_tokens": 5780615.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.939122200012207,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.1549833208322525,
|
|
"num_tokens": 5791271.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.814103412628174,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15836629867553711,
|
|
"num_tokens": 5801117.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.859375476837158,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.15782571583986282,
|
|
"num_tokens": 5811696.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.879450893402099,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.16295181214809418,
|
|
"num_tokens": 5822207.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.838560342788696,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.16222673356533052,
|
|
"num_tokens": 5831927.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.844130134582519,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.15631944462656974,
|
|
"num_tokens": 5842093.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.862317848205566,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.1637733742594719,
|
|
"num_tokens": 5850551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.831214189529419,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.15734255760908128,
|
|
"num_tokens": 5860651.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.736221647262573,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.15711580514907836,
|
|
"num_tokens": 5871500.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.837002754211426,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15363348871469498,
|
|
"num_tokens": 5881523.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.969505023956299,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15440904647111892,
|
|
"num_tokens": 5891162.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.825331020355224,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.15304600223898887,
|
|
"num_tokens": 5901818.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.837537527084351,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.7802,
|
|
"mean_token_accuracy": 0.15388137996196746,
|
|
"num_tokens": 5913889.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.898041200637818,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.15773886442184448,
|
|
"num_tokens": 5923429.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.9350752353668215,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.15665830671787262,
|
|
"num_tokens": 5933847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.846282577514648,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15802753269672393,
|
|
"num_tokens": 5943874.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.893306922912598,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.1564636617898941,
|
|
"num_tokens": 5953653.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.912632322311401,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.1598701536655426,
|
|
"num_tokens": 5964039.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.934096145629883,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.7888,
|
|
"mean_token_accuracy": 0.15126357972621918,
|
|
"num_tokens": 5974083.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.802870368957519,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.1535191372036934,
|
|
"num_tokens": 5984629.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.837651777267456,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.16809626668691635,
|
|
"num_tokens": 5994295.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.847111940383911,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.15560346096754074,
|
|
"num_tokens": 6004156.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.842682647705078,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.15826719254255295,
|
|
"num_tokens": 6014188.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.951080179214477,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.15130359828472137,
|
|
"num_tokens": 6024879.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.973435401916504,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.8978,
|
|
"mean_token_accuracy": 0.1513467513024807,
|
|
"num_tokens": 6036374.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.852985286712647,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.7384,
|
|
"mean_token_accuracy": 0.15605844408273697,
|
|
"num_tokens": 6046432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.9294966697692875,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.14988288134336472,
|
|
"num_tokens": 6056864.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.9699132442474365,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1611533209681511,
|
|
"num_tokens": 6067294.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.882857704162598,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.7721,
|
|
"mean_token_accuracy": 0.15410346388816834,
|
|
"num_tokens": 6077587.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.921375894546509,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.15302591323852538,
|
|
"num_tokens": 6089306.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.801258993148804,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.15564401000738143,
|
|
"num_tokens": 6099651.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.831615734100342,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.15340599417686462,
|
|
"num_tokens": 6110063.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.866582584381104,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.1569851815700531,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.845797681808472,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.1586455672979355,
|
|
"num_tokens": 6131274.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.888718032836914,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.15850588232278823,
|
|
"num_tokens": 6140878.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.895853567123413,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.15040715038776398,
|
|
"num_tokens": 6152229.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.802438020706177,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.15607988238334655,
|
|
"num_tokens": 6162311.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.942750644683838,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.15298964083194733,
|
|
"num_tokens": 6172806.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.87895131111145,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.15776319652795792,
|
|
"num_tokens": 6183479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.886080932617188,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.15342071503400803,
|
|
"num_tokens": 6194201.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.82788724899292,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.1564711168408394,
|
|
"num_tokens": 6204774.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.886050224304199,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.1526743471622467,
|
|
"num_tokens": 6215056.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.7014565256386325,
|
|
"eval_loss": 5.748072624206543,
|
|
"eval_mean_token_accuracy": 0.1622600189245799,
|
|
"eval_num_tokens": 6215056.0,
|
|
"eval_runtime": 20.702,
|
|
"eval_samples_per_second": 1708.048,
|
|
"eval_steps_per_second": 213.506,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"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": 1338598636093440.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|