sedrickkeh's picture
End of training
a9e1044 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1850,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02702702702702703,
"grad_norm": 3.48477044162232,
"learning_rate": 5e-06,
"loss": 0.8622,
"step": 10
},
{
"epoch": 0.05405405405405406,
"grad_norm": 2.360261766882162,
"learning_rate": 5e-06,
"loss": 0.6871,
"step": 20
},
{
"epoch": 0.08108108108108109,
"grad_norm": 2.861337031562045,
"learning_rate": 5e-06,
"loss": 0.6496,
"step": 30
},
{
"epoch": 0.10810810810810811,
"grad_norm": 2.110955586370757,
"learning_rate": 5e-06,
"loss": 0.6379,
"step": 40
},
{
"epoch": 0.13513513513513514,
"grad_norm": 2.6603965950552375,
"learning_rate": 5e-06,
"loss": 0.6224,
"step": 50
},
{
"epoch": 0.16216216216216217,
"grad_norm": 2.3295005659015637,
"learning_rate": 5e-06,
"loss": 0.6158,
"step": 60
},
{
"epoch": 0.1891891891891892,
"grad_norm": 1.4436743736286393,
"learning_rate": 5e-06,
"loss": 0.6121,
"step": 70
},
{
"epoch": 0.21621621621621623,
"grad_norm": 1.480185038939668,
"learning_rate": 5e-06,
"loss": 0.6048,
"step": 80
},
{
"epoch": 0.24324324324324326,
"grad_norm": 1.7946241900816966,
"learning_rate": 5e-06,
"loss": 0.6027,
"step": 90
},
{
"epoch": 0.2702702702702703,
"grad_norm": 2.953041989671829,
"learning_rate": 5e-06,
"loss": 0.6057,
"step": 100
},
{
"epoch": 0.2972972972972973,
"grad_norm": 2.3672617838763292,
"learning_rate": 5e-06,
"loss": 0.603,
"step": 110
},
{
"epoch": 0.32432432432432434,
"grad_norm": 2.570180323617788,
"learning_rate": 5e-06,
"loss": 0.5968,
"step": 120
},
{
"epoch": 0.35135135135135137,
"grad_norm": 2.4395069709384405,
"learning_rate": 5e-06,
"loss": 0.5971,
"step": 130
},
{
"epoch": 0.3783783783783784,
"grad_norm": 2.139806105177032,
"learning_rate": 5e-06,
"loss": 0.5967,
"step": 140
},
{
"epoch": 0.40540540540540543,
"grad_norm": 1.8058881040832764,
"learning_rate": 5e-06,
"loss": 0.588,
"step": 150
},
{
"epoch": 0.43243243243243246,
"grad_norm": 1.906112223883072,
"learning_rate": 5e-06,
"loss": 0.5911,
"step": 160
},
{
"epoch": 0.4594594594594595,
"grad_norm": 1.7152010217915816,
"learning_rate": 5e-06,
"loss": 0.5929,
"step": 170
},
{
"epoch": 0.4864864864864865,
"grad_norm": 1.4638072286809918,
"learning_rate": 5e-06,
"loss": 0.592,
"step": 180
},
{
"epoch": 0.5135135135135135,
"grad_norm": 1.4052441733855927,
"learning_rate": 5e-06,
"loss": 0.5881,
"step": 190
},
{
"epoch": 0.5405405405405406,
"grad_norm": 1.3473253327847512,
"learning_rate": 5e-06,
"loss": 0.5863,
"step": 200
},
{
"epoch": 0.5675675675675675,
"grad_norm": 1.6317553588784817,
"learning_rate": 5e-06,
"loss": 0.5888,
"step": 210
},
{
"epoch": 0.5945945945945946,
"grad_norm": 1.4742582489032408,
"learning_rate": 5e-06,
"loss": 0.5846,
"step": 220
},
{
"epoch": 0.6216216216216216,
"grad_norm": 1.3786710575715564,
"learning_rate": 5e-06,
"loss": 0.5858,
"step": 230
},
{
"epoch": 0.6486486486486487,
"grad_norm": 1.3706145590107932,
"learning_rate": 5e-06,
"loss": 0.5823,
"step": 240
},
{
"epoch": 0.6756756756756757,
"grad_norm": 2.9406828647293684,
"learning_rate": 5e-06,
"loss": 0.5759,
"step": 250
},
{
"epoch": 0.7027027027027027,
"grad_norm": 1.874695043037241,
"learning_rate": 5e-06,
"loss": 0.5788,
"step": 260
},
{
"epoch": 0.7297297297297297,
"grad_norm": 1.6258297787646745,
"learning_rate": 5e-06,
"loss": 0.5807,
"step": 270
},
{
"epoch": 0.7567567567567568,
"grad_norm": 1.3370174946548334,
"learning_rate": 5e-06,
"loss": 0.5753,
"step": 280
},
{
"epoch": 0.7837837837837838,
"grad_norm": 1.4879061874672985,
"learning_rate": 5e-06,
"loss": 0.5751,
"step": 290
},
{
"epoch": 0.8108108108108109,
"grad_norm": 1.4797771423522537,
"learning_rate": 5e-06,
"loss": 0.5752,
"step": 300
},
{
"epoch": 0.8378378378378378,
"grad_norm": 1.349831755648445,
"learning_rate": 5e-06,
"loss": 0.5731,
"step": 310
},
{
"epoch": 0.8648648648648649,
"grad_norm": 1.487488462220457,
"learning_rate": 5e-06,
"loss": 0.5719,
"step": 320
},
{
"epoch": 0.8918918918918919,
"grad_norm": 1.3196199401162108,
"learning_rate": 5e-06,
"loss": 0.5736,
"step": 330
},
{
"epoch": 0.918918918918919,
"grad_norm": 1.2813534915454334,
"learning_rate": 5e-06,
"loss": 0.581,
"step": 340
},
{
"epoch": 0.9459459459459459,
"grad_norm": 1.2493996252660173,
"learning_rate": 5e-06,
"loss": 0.5726,
"step": 350
},
{
"epoch": 0.972972972972973,
"grad_norm": 1.3169592287464336,
"learning_rate": 5e-06,
"loss": 0.5717,
"step": 360
},
{
"epoch": 1.0,
"grad_norm": 1.6256059905335656,
"learning_rate": 5e-06,
"loss": 0.5735,
"step": 370
},
{
"epoch": 1.0,
"eval_loss": 0.28570452332496643,
"eval_runtime": 96.5261,
"eval_samples_per_second": 103.236,
"eval_steps_per_second": 0.404,
"step": 370
},
{
"epoch": 1.027027027027027,
"grad_norm": 1.7234414441453492,
"learning_rate": 5e-06,
"loss": 0.4828,
"step": 380
},
{
"epoch": 1.054054054054054,
"grad_norm": 1.542357388344519,
"learning_rate": 5e-06,
"loss": 0.4753,
"step": 390
},
{
"epoch": 1.0810810810810811,
"grad_norm": 1.4861195617131548,
"learning_rate": 5e-06,
"loss": 0.4799,
"step": 400
},
{
"epoch": 1.1081081081081081,
"grad_norm": 1.4134885594853346,
"learning_rate": 5e-06,
"loss": 0.4728,
"step": 410
},
{
"epoch": 1.135135135135135,
"grad_norm": 1.8446040240127095,
"learning_rate": 5e-06,
"loss": 0.4775,
"step": 420
},
{
"epoch": 1.1621621621621623,
"grad_norm": 1.8467841301436136,
"learning_rate": 5e-06,
"loss": 0.484,
"step": 430
},
{
"epoch": 1.1891891891891893,
"grad_norm": 2.42665171779706,
"learning_rate": 5e-06,
"loss": 0.4749,
"step": 440
},
{
"epoch": 1.2162162162162162,
"grad_norm": 1.8049502845392928,
"learning_rate": 5e-06,
"loss": 0.48,
"step": 450
},
{
"epoch": 1.2432432432432432,
"grad_norm": 2.0761863031810375,
"learning_rate": 5e-06,
"loss": 0.4809,
"step": 460
},
{
"epoch": 1.2702702702702702,
"grad_norm": 2.0655543660952476,
"learning_rate": 5e-06,
"loss": 0.481,
"step": 470
},
{
"epoch": 1.2972972972972974,
"grad_norm": 1.6759566925998968,
"learning_rate": 5e-06,
"loss": 0.4764,
"step": 480
},
{
"epoch": 1.3243243243243243,
"grad_norm": 1.396353193003371,
"learning_rate": 5e-06,
"loss": 0.4761,
"step": 490
},
{
"epoch": 1.3513513513513513,
"grad_norm": 1.397142398326265,
"learning_rate": 5e-06,
"loss": 0.482,
"step": 500
},
{
"epoch": 1.3783783783783785,
"grad_norm": 1.5036245472795235,
"learning_rate": 5e-06,
"loss": 0.4817,
"step": 510
},
{
"epoch": 1.4054054054054055,
"grad_norm": 1.5607076153200972,
"learning_rate": 5e-06,
"loss": 0.4861,
"step": 520
},
{
"epoch": 1.4324324324324325,
"grad_norm": 1.7026202176545633,
"learning_rate": 5e-06,
"loss": 0.4801,
"step": 530
},
{
"epoch": 1.4594594594594594,
"grad_norm": 1.694705438287125,
"learning_rate": 5e-06,
"loss": 0.4834,
"step": 540
},
{
"epoch": 1.4864864864864864,
"grad_norm": 1.8913973826320096,
"learning_rate": 5e-06,
"loss": 0.4815,
"step": 550
},
{
"epoch": 1.5135135135135136,
"grad_norm": 1.3860850720137203,
"learning_rate": 5e-06,
"loss": 0.4853,
"step": 560
},
{
"epoch": 1.5405405405405406,
"grad_norm": 1.6545389203896799,
"learning_rate": 5e-06,
"loss": 0.4775,
"step": 570
},
{
"epoch": 1.5675675675675675,
"grad_norm": 1.6330744148753316,
"learning_rate": 5e-06,
"loss": 0.484,
"step": 580
},
{
"epoch": 1.5945945945945947,
"grad_norm": 1.749422453289866,
"learning_rate": 5e-06,
"loss": 0.4842,
"step": 590
},
{
"epoch": 1.6216216216216215,
"grad_norm": 1.4714668834139133,
"learning_rate": 5e-06,
"loss": 0.4815,
"step": 600
},
{
"epoch": 1.6486486486486487,
"grad_norm": 1.7987332350786904,
"learning_rate": 5e-06,
"loss": 0.4803,
"step": 610
},
{
"epoch": 1.6756756756756757,
"grad_norm": 1.4458046351621974,
"learning_rate": 5e-06,
"loss": 0.4867,
"step": 620
},
{
"epoch": 1.7027027027027026,
"grad_norm": 1.5250625163041274,
"learning_rate": 5e-06,
"loss": 0.4898,
"step": 630
},
{
"epoch": 1.7297297297297298,
"grad_norm": 1.682061525596803,
"learning_rate": 5e-06,
"loss": 0.4903,
"step": 640
},
{
"epoch": 1.7567567567567568,
"grad_norm": 1.725604337448065,
"learning_rate": 5e-06,
"loss": 0.4832,
"step": 650
},
{
"epoch": 1.7837837837837838,
"grad_norm": 1.451360087475008,
"learning_rate": 5e-06,
"loss": 0.4825,
"step": 660
},
{
"epoch": 1.810810810810811,
"grad_norm": 1.6609825444761357,
"learning_rate": 5e-06,
"loss": 0.4826,
"step": 670
},
{
"epoch": 1.8378378378378377,
"grad_norm": 1.9683314087008068,
"learning_rate": 5e-06,
"loss": 0.4864,
"step": 680
},
{
"epoch": 1.864864864864865,
"grad_norm": 1.6782355490104197,
"learning_rate": 5e-06,
"loss": 0.485,
"step": 690
},
{
"epoch": 1.8918918918918919,
"grad_norm": 1.9940863134776443,
"learning_rate": 5e-06,
"loss": 0.4884,
"step": 700
},
{
"epoch": 1.9189189189189189,
"grad_norm": 1.558943375608973,
"learning_rate": 5e-06,
"loss": 0.4926,
"step": 710
},
{
"epoch": 1.945945945945946,
"grad_norm": 1.2455247588814846,
"learning_rate": 5e-06,
"loss": 0.4855,
"step": 720
},
{
"epoch": 1.972972972972973,
"grad_norm": 1.4348648241338484,
"learning_rate": 5e-06,
"loss": 0.4845,
"step": 730
},
{
"epoch": 2.0,
"grad_norm": 1.2414831162937485,
"learning_rate": 5e-06,
"loss": 0.4841,
"step": 740
},
{
"epoch": 2.0,
"eval_loss": 0.2870478928089142,
"eval_runtime": 96.6141,
"eval_samples_per_second": 103.142,
"eval_steps_per_second": 0.404,
"step": 740
},
{
"epoch": 2.027027027027027,
"grad_norm": 2.327501959947698,
"learning_rate": 5e-06,
"loss": 0.3857,
"step": 750
},
{
"epoch": 2.054054054054054,
"grad_norm": 1.7853879802404622,
"learning_rate": 5e-06,
"loss": 0.3828,
"step": 760
},
{
"epoch": 2.081081081081081,
"grad_norm": 1.6129872542969907,
"learning_rate": 5e-06,
"loss": 0.3811,
"step": 770
},
{
"epoch": 2.108108108108108,
"grad_norm": 1.6822958801213699,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 780
},
{
"epoch": 2.135135135135135,
"grad_norm": 1.5765921764422512,
"learning_rate": 5e-06,
"loss": 0.3804,
"step": 790
},
{
"epoch": 2.1621621621621623,
"grad_norm": 1.4901475659604642,
"learning_rate": 5e-06,
"loss": 0.3877,
"step": 800
},
{
"epoch": 2.189189189189189,
"grad_norm": 1.6201893013251834,
"learning_rate": 5e-06,
"loss": 0.3865,
"step": 810
},
{
"epoch": 2.2162162162162162,
"grad_norm": 1.5437549027848532,
"learning_rate": 5e-06,
"loss": 0.3847,
"step": 820
},
{
"epoch": 2.2432432432432434,
"grad_norm": 1.8632952369866993,
"learning_rate": 5e-06,
"loss": 0.392,
"step": 830
},
{
"epoch": 2.27027027027027,
"grad_norm": 1.7661982815559183,
"learning_rate": 5e-06,
"loss": 0.394,
"step": 840
},
{
"epoch": 2.2972972972972974,
"grad_norm": 1.7332904607598014,
"learning_rate": 5e-06,
"loss": 0.3879,
"step": 850
},
{
"epoch": 2.3243243243243246,
"grad_norm": 2.252072555591542,
"learning_rate": 5e-06,
"loss": 0.3904,
"step": 860
},
{
"epoch": 2.3513513513513513,
"grad_norm": 1.6253901818998244,
"learning_rate": 5e-06,
"loss": 0.397,
"step": 870
},
{
"epoch": 2.3783783783783785,
"grad_norm": 2.211017287566556,
"learning_rate": 5e-06,
"loss": 0.3931,
"step": 880
},
{
"epoch": 2.4054054054054053,
"grad_norm": 2.398472470432874,
"learning_rate": 5e-06,
"loss": 0.3938,
"step": 890
},
{
"epoch": 2.4324324324324325,
"grad_norm": 1.5682213825969358,
"learning_rate": 5e-06,
"loss": 0.3916,
"step": 900
},
{
"epoch": 2.4594594594594597,
"grad_norm": 2.1044553282329077,
"learning_rate": 5e-06,
"loss": 0.3881,
"step": 910
},
{
"epoch": 2.4864864864864864,
"grad_norm": 1.7564401087246682,
"learning_rate": 5e-06,
"loss": 0.391,
"step": 920
},
{
"epoch": 2.5135135135135136,
"grad_norm": 1.6382220101052676,
"learning_rate": 5e-06,
"loss": 0.391,
"step": 930
},
{
"epoch": 2.5405405405405403,
"grad_norm": 1.4798359424940517,
"learning_rate": 5e-06,
"loss": 0.3979,
"step": 940
},
{
"epoch": 2.5675675675675675,
"grad_norm": 1.4676265261223125,
"learning_rate": 5e-06,
"loss": 0.3963,
"step": 950
},
{
"epoch": 2.5945945945945947,
"grad_norm": 1.6295486852060186,
"learning_rate": 5e-06,
"loss": 0.399,
"step": 960
},
{
"epoch": 2.6216216216216215,
"grad_norm": 1.6192977742906878,
"learning_rate": 5e-06,
"loss": 0.4023,
"step": 970
},
{
"epoch": 2.6486486486486487,
"grad_norm": 1.4805451072812197,
"learning_rate": 5e-06,
"loss": 0.4037,
"step": 980
},
{
"epoch": 2.6756756756756754,
"grad_norm": 1.6037076836111144,
"learning_rate": 5e-06,
"loss": 0.4037,
"step": 990
},
{
"epoch": 2.7027027027027026,
"grad_norm": 1.5225333016382139,
"learning_rate": 5e-06,
"loss": 0.3945,
"step": 1000
},
{
"epoch": 2.72972972972973,
"grad_norm": 1.6212777115845565,
"learning_rate": 5e-06,
"loss": 0.4051,
"step": 1010
},
{
"epoch": 2.756756756756757,
"grad_norm": 1.5016437573712755,
"learning_rate": 5e-06,
"loss": 0.406,
"step": 1020
},
{
"epoch": 2.7837837837837838,
"grad_norm": 1.5902877384401621,
"learning_rate": 5e-06,
"loss": 0.4029,
"step": 1030
},
{
"epoch": 2.810810810810811,
"grad_norm": 1.3912722358421692,
"learning_rate": 5e-06,
"loss": 0.4055,
"step": 1040
},
{
"epoch": 2.8378378378378377,
"grad_norm": 1.5492106652733648,
"learning_rate": 5e-06,
"loss": 0.4046,
"step": 1050
},
{
"epoch": 2.864864864864865,
"grad_norm": 1.5663312579126816,
"learning_rate": 5e-06,
"loss": 0.4016,
"step": 1060
},
{
"epoch": 2.891891891891892,
"grad_norm": 1.40383114587804,
"learning_rate": 5e-06,
"loss": 0.4079,
"step": 1070
},
{
"epoch": 2.918918918918919,
"grad_norm": 1.6190187870975588,
"learning_rate": 5e-06,
"loss": 0.4049,
"step": 1080
},
{
"epoch": 2.945945945945946,
"grad_norm": 1.640627877455668,
"learning_rate": 5e-06,
"loss": 0.4065,
"step": 1090
},
{
"epoch": 2.972972972972973,
"grad_norm": 1.4897415581729503,
"learning_rate": 5e-06,
"loss": 0.4066,
"step": 1100
},
{
"epoch": 3.0,
"grad_norm": 1.4711135774031523,
"learning_rate": 5e-06,
"loss": 0.408,
"step": 1110
},
{
"epoch": 3.0,
"eval_loss": 0.3071748912334442,
"eval_runtime": 96.698,
"eval_samples_per_second": 103.053,
"eval_steps_per_second": 0.403,
"step": 1110
},
{
"epoch": 3.027027027027027,
"grad_norm": 2.6131814809186613,
"learning_rate": 5e-06,
"loss": 0.2928,
"step": 1120
},
{
"epoch": 3.054054054054054,
"grad_norm": 2.2485831495990847,
"learning_rate": 5e-06,
"loss": 0.2851,
"step": 1130
},
{
"epoch": 3.081081081081081,
"grad_norm": 1.928587031956844,
"learning_rate": 5e-06,
"loss": 0.2828,
"step": 1140
},
{
"epoch": 3.108108108108108,
"grad_norm": 1.743854950076673,
"learning_rate": 5e-06,
"loss": 0.2809,
"step": 1150
},
{
"epoch": 3.135135135135135,
"grad_norm": 1.8950206315568565,
"learning_rate": 5e-06,
"loss": 0.2814,
"step": 1160
},
{
"epoch": 3.1621621621621623,
"grad_norm": 1.9383522044886479,
"learning_rate": 5e-06,
"loss": 0.2865,
"step": 1170
},
{
"epoch": 3.189189189189189,
"grad_norm": 1.9203849142483256,
"learning_rate": 5e-06,
"loss": 0.2851,
"step": 1180
},
{
"epoch": 3.2162162162162162,
"grad_norm": 1.9070432540284974,
"learning_rate": 5e-06,
"loss": 0.2874,
"step": 1190
},
{
"epoch": 3.2432432432432434,
"grad_norm": 1.9642273546651734,
"learning_rate": 5e-06,
"loss": 0.2874,
"step": 1200
},
{
"epoch": 3.27027027027027,
"grad_norm": 2.371293282521119,
"learning_rate": 5e-06,
"loss": 0.2921,
"step": 1210
},
{
"epoch": 3.2972972972972974,
"grad_norm": 2.69733157052314,
"learning_rate": 5e-06,
"loss": 0.2891,
"step": 1220
},
{
"epoch": 3.3243243243243246,
"grad_norm": 2.4462972161470073,
"learning_rate": 5e-06,
"loss": 0.287,
"step": 1230
},
{
"epoch": 3.3513513513513513,
"grad_norm": 2.09306288923572,
"learning_rate": 5e-06,
"loss": 0.2895,
"step": 1240
},
{
"epoch": 3.3783783783783785,
"grad_norm": 2.260854207612739,
"learning_rate": 5e-06,
"loss": 0.2865,
"step": 1250
},
{
"epoch": 3.4054054054054053,
"grad_norm": 2.692817562351766,
"learning_rate": 5e-06,
"loss": 0.2899,
"step": 1260
},
{
"epoch": 3.4324324324324325,
"grad_norm": 3.125964731548184,
"learning_rate": 5e-06,
"loss": 0.2907,
"step": 1270
},
{
"epoch": 3.4594594594594597,
"grad_norm": 2.442243961667573,
"learning_rate": 5e-06,
"loss": 0.291,
"step": 1280
},
{
"epoch": 3.4864864864864864,
"grad_norm": 2.0307566267966344,
"learning_rate": 5e-06,
"loss": 0.2934,
"step": 1290
},
{
"epoch": 3.5135135135135136,
"grad_norm": 2.098894756875353,
"learning_rate": 5e-06,
"loss": 0.2878,
"step": 1300
},
{
"epoch": 3.5405405405405403,
"grad_norm": 2.1484942546619985,
"learning_rate": 5e-06,
"loss": 0.2918,
"step": 1310
},
{
"epoch": 3.5675675675675675,
"grad_norm": 1.8339116955180341,
"learning_rate": 5e-06,
"loss": 0.2943,
"step": 1320
},
{
"epoch": 3.5945945945945947,
"grad_norm": 1.9887758275282583,
"learning_rate": 5e-06,
"loss": 0.2925,
"step": 1330
},
{
"epoch": 3.6216216216216215,
"grad_norm": 1.9845485688385418,
"learning_rate": 5e-06,
"loss": 0.2955,
"step": 1340
},
{
"epoch": 3.6486486486486487,
"grad_norm": 1.969672930852857,
"learning_rate": 5e-06,
"loss": 0.2988,
"step": 1350
},
{
"epoch": 3.6756756756756754,
"grad_norm": 1.7604665753983029,
"learning_rate": 5e-06,
"loss": 0.2954,
"step": 1360
},
{
"epoch": 3.7027027027027026,
"grad_norm": 1.8509109071012708,
"learning_rate": 5e-06,
"loss": 0.2962,
"step": 1370
},
{
"epoch": 3.72972972972973,
"grad_norm": 1.6839851527778709,
"learning_rate": 5e-06,
"loss": 0.2991,
"step": 1380
},
{
"epoch": 3.756756756756757,
"grad_norm": 1.9195065233001387,
"learning_rate": 5e-06,
"loss": 0.2997,
"step": 1390
},
{
"epoch": 3.7837837837837838,
"grad_norm": 2.0352568345546262,
"learning_rate": 5e-06,
"loss": 0.3012,
"step": 1400
},
{
"epoch": 3.810810810810811,
"grad_norm": 1.8158735733043123,
"learning_rate": 5e-06,
"loss": 0.3005,
"step": 1410
},
{
"epoch": 3.8378378378378377,
"grad_norm": 1.9516953165324797,
"learning_rate": 5e-06,
"loss": 0.3022,
"step": 1420
},
{
"epoch": 3.864864864864865,
"grad_norm": 1.863346672591352,
"learning_rate": 5e-06,
"loss": 0.3018,
"step": 1430
},
{
"epoch": 3.891891891891892,
"grad_norm": 1.8751695571197564,
"learning_rate": 5e-06,
"loss": 0.3019,
"step": 1440
},
{
"epoch": 3.918918918918919,
"grad_norm": 1.9801631273484928,
"learning_rate": 5e-06,
"loss": 0.307,
"step": 1450
},
{
"epoch": 3.945945945945946,
"grad_norm": 2.003514563060868,
"learning_rate": 5e-06,
"loss": 0.3058,
"step": 1460
},
{
"epoch": 3.972972972972973,
"grad_norm": 2.0763911612682837,
"learning_rate": 5e-06,
"loss": 0.3032,
"step": 1470
},
{
"epoch": 4.0,
"grad_norm": 2.336230273567409,
"learning_rate": 5e-06,
"loss": 0.3066,
"step": 1480
},
{
"epoch": 4.0,
"eval_loss": 0.3498997688293457,
"eval_runtime": 96.4986,
"eval_samples_per_second": 103.266,
"eval_steps_per_second": 0.404,
"step": 1480
},
{
"epoch": 4.027027027027027,
"grad_norm": 3.0158703873058617,
"learning_rate": 5e-06,
"loss": 0.1986,
"step": 1490
},
{
"epoch": 4.054054054054054,
"grad_norm": 2.369544566010332,
"learning_rate": 5e-06,
"loss": 0.1914,
"step": 1500
},
{
"epoch": 4.081081081081081,
"grad_norm": 2.183015942133232,
"learning_rate": 5e-06,
"loss": 0.1906,
"step": 1510
},
{
"epoch": 4.108108108108108,
"grad_norm": 2.158995110143315,
"learning_rate": 5e-06,
"loss": 0.1894,
"step": 1520
},
{
"epoch": 4.135135135135135,
"grad_norm": 2.15897438632279,
"learning_rate": 5e-06,
"loss": 0.1923,
"step": 1530
},
{
"epoch": 4.162162162162162,
"grad_norm": 2.3012908533453316,
"learning_rate": 5e-06,
"loss": 0.1918,
"step": 1540
},
{
"epoch": 4.1891891891891895,
"grad_norm": 2.3397981392039133,
"learning_rate": 5e-06,
"loss": 0.1955,
"step": 1550
},
{
"epoch": 4.216216216216216,
"grad_norm": 2.3318950522877544,
"learning_rate": 5e-06,
"loss": 0.1967,
"step": 1560
},
{
"epoch": 4.243243243243243,
"grad_norm": 2.2558016269733017,
"learning_rate": 5e-06,
"loss": 0.1973,
"step": 1570
},
{
"epoch": 4.27027027027027,
"grad_norm": 2.0308981605993557,
"learning_rate": 5e-06,
"loss": 0.2001,
"step": 1580
},
{
"epoch": 4.297297297297297,
"grad_norm": 2.2105682816818604,
"learning_rate": 5e-06,
"loss": 0.1999,
"step": 1590
},
{
"epoch": 4.324324324324325,
"grad_norm": 2.0611643054991777,
"learning_rate": 5e-06,
"loss": 0.1977,
"step": 1600
},
{
"epoch": 4.351351351351352,
"grad_norm": 2.244438029380733,
"learning_rate": 5e-06,
"loss": 0.1988,
"step": 1610
},
{
"epoch": 4.378378378378378,
"grad_norm": 2.1171487595846683,
"learning_rate": 5e-06,
"loss": 0.2016,
"step": 1620
},
{
"epoch": 4.405405405405405,
"grad_norm": 2.129014172266156,
"learning_rate": 5e-06,
"loss": 0.2045,
"step": 1630
},
{
"epoch": 4.4324324324324325,
"grad_norm": 2.0849845815435284,
"learning_rate": 5e-06,
"loss": 0.2049,
"step": 1640
},
{
"epoch": 4.45945945945946,
"grad_norm": 2.107058909660221,
"learning_rate": 5e-06,
"loss": 0.2058,
"step": 1650
},
{
"epoch": 4.486486486486487,
"grad_norm": 2.4419601951125274,
"learning_rate": 5e-06,
"loss": 0.2063,
"step": 1660
},
{
"epoch": 4.513513513513513,
"grad_norm": 2.242862620136703,
"learning_rate": 5e-06,
"loss": 0.2079,
"step": 1670
},
{
"epoch": 4.54054054054054,
"grad_norm": 2.1964969220779498,
"learning_rate": 5e-06,
"loss": 0.2063,
"step": 1680
},
{
"epoch": 4.5675675675675675,
"grad_norm": 2.144927893368169,
"learning_rate": 5e-06,
"loss": 0.2073,
"step": 1690
},
{
"epoch": 4.594594594594595,
"grad_norm": 2.4089173007864986,
"learning_rate": 5e-06,
"loss": 0.2064,
"step": 1700
},
{
"epoch": 4.621621621621622,
"grad_norm": 2.236620269865094,
"learning_rate": 5e-06,
"loss": 0.208,
"step": 1710
},
{
"epoch": 4.648648648648649,
"grad_norm": 2.2273265321363964,
"learning_rate": 5e-06,
"loss": 0.2091,
"step": 1720
},
{
"epoch": 4.675675675675675,
"grad_norm": 2.043537478772687,
"learning_rate": 5e-06,
"loss": 0.2083,
"step": 1730
},
{
"epoch": 4.702702702702703,
"grad_norm": 2.2566729233438516,
"learning_rate": 5e-06,
"loss": 0.2099,
"step": 1740
},
{
"epoch": 4.72972972972973,
"grad_norm": 2.3414348548757853,
"learning_rate": 5e-06,
"loss": 0.2107,
"step": 1750
},
{
"epoch": 4.756756756756757,
"grad_norm": 2.231457361542356,
"learning_rate": 5e-06,
"loss": 0.2096,
"step": 1760
},
{
"epoch": 4.783783783783784,
"grad_norm": 2.182368419604419,
"learning_rate": 5e-06,
"loss": 0.2111,
"step": 1770
},
{
"epoch": 4.8108108108108105,
"grad_norm": 2.3022522015009526,
"learning_rate": 5e-06,
"loss": 0.2097,
"step": 1780
},
{
"epoch": 4.837837837837838,
"grad_norm": 2.154576582443656,
"learning_rate": 5e-06,
"loss": 0.2132,
"step": 1790
},
{
"epoch": 4.864864864864865,
"grad_norm": 2.185745168624507,
"learning_rate": 5e-06,
"loss": 0.212,
"step": 1800
},
{
"epoch": 4.891891891891892,
"grad_norm": 2.1651574566981395,
"learning_rate": 5e-06,
"loss": 0.2143,
"step": 1810
},
{
"epoch": 4.918918918918919,
"grad_norm": 2.2200846915512127,
"learning_rate": 5e-06,
"loss": 0.2137,
"step": 1820
},
{
"epoch": 4.945945945945946,
"grad_norm": 2.344248992891754,
"learning_rate": 5e-06,
"loss": 0.2162,
"step": 1830
},
{
"epoch": 4.972972972972973,
"grad_norm": 2.150842096847866,
"learning_rate": 5e-06,
"loss": 0.215,
"step": 1840
},
{
"epoch": 5.0,
"grad_norm": 2.3030280373590335,
"learning_rate": 5e-06,
"loss": 0.2144,
"step": 1850
},
{
"epoch": 5.0,
"eval_loss": 0.4100167155265808,
"eval_runtime": 95.571,
"eval_samples_per_second": 104.268,
"eval_steps_per_second": 0.408,
"step": 1850
},
{
"epoch": 5.0,
"step": 1850,
"total_flos": 3097981385441280.0,
"train_loss": 0.3954814358659693,
"train_runtime": 27395.2752,
"train_samples_per_second": 34.555,
"train_steps_per_second": 0.068
}
],
"logging_steps": 10,
"max_steps": 1850,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3097981385441280.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}