Grogros's picture
Training in progress, step 2000, checkpoint
6eab23a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004,
"grad_norm": 161.0,
"learning_rate": 8.000000000000001e-07,
"loss": 16.3125,
"step": 10
},
{
"epoch": 0.008,
"grad_norm": 370.0,
"learning_rate": 1.6000000000000001e-06,
"loss": 15.9951,
"step": 20
},
{
"epoch": 0.012,
"grad_norm": 334.0,
"learning_rate": 2.4000000000000003e-06,
"loss": 16.2349,
"step": 30
},
{
"epoch": 0.016,
"grad_norm": 247.0,
"learning_rate": 3.2000000000000003e-06,
"loss": 16.2399,
"step": 40
},
{
"epoch": 0.02,
"grad_norm": 440.0,
"learning_rate": 4.000000000000001e-06,
"loss": 15.5578,
"step": 50
},
{
"epoch": 0.024,
"grad_norm": 308.0,
"learning_rate": 4.800000000000001e-06,
"loss": 16.0425,
"step": 60
},
{
"epoch": 0.028,
"grad_norm": 197.0,
"learning_rate": 5.600000000000001e-06,
"loss": 15.3377,
"step": 70
},
{
"epoch": 0.032,
"grad_norm": 478.0,
"learning_rate": 6.4000000000000006e-06,
"loss": 15.9414,
"step": 80
},
{
"epoch": 0.036,
"grad_norm": 204.0,
"learning_rate": 7.2000000000000005e-06,
"loss": 14.6811,
"step": 90
},
{
"epoch": 0.04,
"grad_norm": 123.5,
"learning_rate": 8.000000000000001e-06,
"loss": 15.3669,
"step": 100
},
{
"epoch": 0.044,
"grad_norm": 135.0,
"learning_rate": 8.8e-06,
"loss": 15.0323,
"step": 110
},
{
"epoch": 0.048,
"grad_norm": 81.0,
"learning_rate": 9.600000000000001e-06,
"loss": 15.1514,
"step": 120
},
{
"epoch": 0.052,
"grad_norm": 109.0,
"learning_rate": 1.04e-05,
"loss": 14.244,
"step": 130
},
{
"epoch": 0.056,
"grad_norm": 39.75,
"learning_rate": 1.1200000000000001e-05,
"loss": 14.3183,
"step": 140
},
{
"epoch": 0.06,
"grad_norm": 99.5,
"learning_rate": 1.2e-05,
"loss": 14.354,
"step": 150
},
{
"epoch": 0.064,
"grad_norm": 115.0,
"learning_rate": 1.2800000000000001e-05,
"loss": 14.8329,
"step": 160
},
{
"epoch": 0.068,
"grad_norm": 124.5,
"learning_rate": 1.3600000000000002e-05,
"loss": 14.649,
"step": 170
},
{
"epoch": 0.072,
"grad_norm": 60.0,
"learning_rate": 1.4400000000000001e-05,
"loss": 14.1903,
"step": 180
},
{
"epoch": 0.076,
"grad_norm": 74.5,
"learning_rate": 1.5200000000000002e-05,
"loss": 14.0663,
"step": 190
},
{
"epoch": 0.08,
"grad_norm": 98.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 13.9515,
"step": 200
},
{
"epoch": 0.084,
"grad_norm": 146.0,
"learning_rate": 1.6800000000000002e-05,
"loss": 14.2023,
"step": 210
},
{
"epoch": 0.088,
"grad_norm": 195.0,
"learning_rate": 1.76e-05,
"loss": 16.903,
"step": 220
},
{
"epoch": 0.092,
"grad_norm": 123.0,
"learning_rate": 1.8400000000000003e-05,
"loss": 14.2629,
"step": 230
},
{
"epoch": 0.096,
"grad_norm": 197.0,
"learning_rate": 1.9200000000000003e-05,
"loss": 14.205,
"step": 240
},
{
"epoch": 0.1,
"grad_norm": 91.0,
"learning_rate": 2e-05,
"loss": 14.2966,
"step": 250
},
{
"epoch": 0.104,
"grad_norm": 85.0,
"learning_rate": 1.9999025240093045e-05,
"loss": 14.077,
"step": 260
},
{
"epoch": 0.108,
"grad_norm": 63.5,
"learning_rate": 1.9996101150403543e-05,
"loss": 13.4959,
"step": 270
},
{
"epoch": 0.112,
"grad_norm": 79.0,
"learning_rate": 1.9991228300988586e-05,
"loss": 13.2863,
"step": 280
},
{
"epoch": 0.116,
"grad_norm": 77.0,
"learning_rate": 1.9984407641819812e-05,
"loss": 14.0289,
"step": 290
},
{
"epoch": 0.12,
"grad_norm": 32.5,
"learning_rate": 1.9975640502598243e-05,
"loss": 13.218,
"step": 300
},
{
"epoch": 0.124,
"grad_norm": 59.0,
"learning_rate": 1.9964928592495046e-05,
"loss": 13.0716,
"step": 310
},
{
"epoch": 0.128,
"grad_norm": 77.0,
"learning_rate": 1.9952273999818312e-05,
"loss": 13.5455,
"step": 320
},
{
"epoch": 0.132,
"grad_norm": 48.5,
"learning_rate": 1.9937679191605964e-05,
"loss": 12.7523,
"step": 330
},
{
"epoch": 0.136,
"grad_norm": 202.0,
"learning_rate": 1.9921147013144782e-05,
"loss": 13.2838,
"step": 340
},
{
"epoch": 0.14,
"grad_norm": 42.0,
"learning_rate": 1.9902680687415704e-05,
"loss": 13.847,
"step": 350
},
{
"epoch": 0.144,
"grad_norm": 50.5,
"learning_rate": 1.988228381446553e-05,
"loss": 13.4523,
"step": 360
},
{
"epoch": 0.148,
"grad_norm": 55.75,
"learning_rate": 1.985996037070505e-05,
"loss": 12.9266,
"step": 370
},
{
"epoch": 0.152,
"grad_norm": 78.0,
"learning_rate": 1.983571470813386e-05,
"loss": 13.1995,
"step": 380
},
{
"epoch": 0.156,
"grad_norm": 83.0,
"learning_rate": 1.9809551553491918e-05,
"loss": 13.4139,
"step": 390
},
{
"epoch": 0.16,
"grad_norm": 70.0,
"learning_rate": 1.9781476007338058e-05,
"loss": 12.9478,
"step": 400
},
{
"epoch": 0.164,
"grad_norm": 81.5,
"learning_rate": 1.9751493543055634e-05,
"loss": 13.0514,
"step": 410
},
{
"epoch": 0.168,
"grad_norm": 82.5,
"learning_rate": 1.9719610005785466e-05,
"loss": 12.3466,
"step": 420
},
{
"epoch": 0.172,
"grad_norm": 63.0,
"learning_rate": 1.9685831611286312e-05,
"loss": 12.3433,
"step": 430
},
{
"epoch": 0.176,
"grad_norm": 78.0,
"learning_rate": 1.9650164944723116e-05,
"loss": 12.3277,
"step": 440
},
{
"epoch": 0.18,
"grad_norm": 65.5,
"learning_rate": 1.961261695938319e-05,
"loss": 12.2445,
"step": 450
},
{
"epoch": 0.184,
"grad_norm": 75.0,
"learning_rate": 1.9573194975320672e-05,
"loss": 12.6102,
"step": 460
},
{
"epoch": 0.188,
"grad_norm": 57.5,
"learning_rate": 1.9531906677929472e-05,
"loss": 11.9526,
"step": 470
},
{
"epoch": 0.192,
"grad_norm": 37.5,
"learning_rate": 1.9488760116444966e-05,
"loss": 12.2256,
"step": 480
},
{
"epoch": 0.196,
"grad_norm": 76.0,
"learning_rate": 1.944376370237481e-05,
"loss": 12.1101,
"step": 490
},
{
"epoch": 0.2,
"grad_norm": 62.75,
"learning_rate": 1.9396926207859085e-05,
"loss": 12.0318,
"step": 500
},
{
"epoch": 0.204,
"grad_norm": 50.0,
"learning_rate": 1.9348256763960146e-05,
"loss": 11.8137,
"step": 510
},
{
"epoch": 0.208,
"grad_norm": 40.75,
"learning_rate": 1.9297764858882516e-05,
"loss": 11.6243,
"step": 520
},
{
"epoch": 0.212,
"grad_norm": 58.75,
"learning_rate": 1.9245460336123136e-05,
"loss": 11.4784,
"step": 530
},
{
"epoch": 0.216,
"grad_norm": 38.0,
"learning_rate": 1.9191353392552346e-05,
"loss": 11.5528,
"step": 540
},
{
"epoch": 0.22,
"grad_norm": 57.25,
"learning_rate": 1.913545457642601e-05,
"loss": 11.7633,
"step": 550
},
{
"epoch": 0.224,
"grad_norm": 58.75,
"learning_rate": 1.907777478532909e-05,
"loss": 11.7305,
"step": 560
},
{
"epoch": 0.228,
"grad_norm": 62.75,
"learning_rate": 1.901832526405114e-05,
"loss": 11.2947,
"step": 570
},
{
"epoch": 0.232,
"grad_norm": 33.0,
"learning_rate": 1.895711760239413e-05,
"loss": 10.6919,
"step": 580
},
{
"epoch": 0.236,
"grad_norm": 54.75,
"learning_rate": 1.889416373291298e-05,
"loss": 11.3612,
"step": 590
},
{
"epoch": 0.24,
"grad_norm": 45.25,
"learning_rate": 1.8829475928589272e-05,
"loss": 11.083,
"step": 600
},
{
"epoch": 0.244,
"grad_norm": 48.25,
"learning_rate": 1.8763066800438638e-05,
"loss": 10.7844,
"step": 610
},
{
"epoch": 0.248,
"grad_norm": 62.25,
"learning_rate": 1.869494929505219e-05,
"loss": 10.9489,
"step": 620
},
{
"epoch": 0.252,
"grad_norm": 61.5,
"learning_rate": 1.8625136692072577e-05,
"loss": 11.167,
"step": 630
},
{
"epoch": 0.256,
"grad_norm": 58.5,
"learning_rate": 1.855364260160507e-05,
"loss": 11.1507,
"step": 640
},
{
"epoch": 0.26,
"grad_norm": 31.625,
"learning_rate": 1.848048096156426e-05,
"loss": 11.0361,
"step": 650
},
{
"epoch": 0.264,
"grad_norm": 32.5,
"learning_rate": 1.8405666034956842e-05,
"loss": 10.8325,
"step": 660
},
{
"epoch": 0.268,
"grad_norm": 43.0,
"learning_rate": 1.8329212407100996e-05,
"loss": 10.6124,
"step": 670
},
{
"epoch": 0.272,
"grad_norm": 42.5,
"learning_rate": 1.8251134982782952e-05,
"loss": 10.4875,
"step": 680
},
{
"epoch": 0.276,
"grad_norm": 50.5,
"learning_rate": 1.8171448983351284e-05,
"loss": 10.7245,
"step": 690
},
{
"epoch": 0.28,
"grad_norm": 49.0,
"learning_rate": 1.8090169943749477e-05,
"loss": 10.4483,
"step": 700
},
{
"epoch": 0.284,
"grad_norm": 50.0,
"learning_rate": 1.8007313709487334e-05,
"loss": 10.4955,
"step": 710
},
{
"epoch": 0.288,
"grad_norm": 59.0,
"learning_rate": 1.792289643355191e-05,
"loss": 10.2636,
"step": 720
},
{
"epoch": 0.292,
"grad_norm": 37.5,
"learning_rate": 1.78369345732584e-05,
"loss": 10.6835,
"step": 730
},
{
"epoch": 0.296,
"grad_norm": 29.5,
"learning_rate": 1.7749444887041797e-05,
"loss": 10.4424,
"step": 740
},
{
"epoch": 0.3,
"grad_norm": 57.75,
"learning_rate": 1.766044443118978e-05,
"loss": 10.8047,
"step": 750
},
{
"epoch": 0.304,
"grad_norm": 55.5,
"learning_rate": 1.7569950556517566e-05,
"loss": 10.8381,
"step": 760
},
{
"epoch": 0.308,
"grad_norm": 38.0,
"learning_rate": 1.747798090498532e-05,
"loss": 10.1538,
"step": 770
},
{
"epoch": 0.312,
"grad_norm": 48.0,
"learning_rate": 1.7384553406258842e-05,
"loss": 10.5811,
"step": 780
},
{
"epoch": 0.316,
"grad_norm": 34.75,
"learning_rate": 1.7289686274214116e-05,
"loss": 10.4719,
"step": 790
},
{
"epoch": 0.32,
"grad_norm": 35.25,
"learning_rate": 1.7193398003386514e-05,
"loss": 10.4797,
"step": 800
},
{
"epoch": 0.324,
"grad_norm": 47.0,
"learning_rate": 1.709570736536521e-05,
"loss": 10.1552,
"step": 810
},
{
"epoch": 0.328,
"grad_norm": 76.5,
"learning_rate": 1.6996633405133656e-05,
"loss": 10.1025,
"step": 820
},
{
"epoch": 0.332,
"grad_norm": 42.25,
"learning_rate": 1.68961954373567e-05,
"loss": 9.5916,
"step": 830
},
{
"epoch": 0.336,
"grad_norm": 49.0,
"learning_rate": 1.6794413042615168e-05,
"loss": 10.0282,
"step": 840
},
{
"epoch": 0.34,
"grad_norm": 40.5,
"learning_rate": 1.6691306063588583e-05,
"loss": 9.7928,
"step": 850
},
{
"epoch": 0.344,
"grad_norm": 52.25,
"learning_rate": 1.6586894601186804e-05,
"loss": 9.9729,
"step": 860
},
{
"epoch": 0.348,
"grad_norm": 47.0,
"learning_rate": 1.6481199010631312e-05,
"loss": 10.0675,
"step": 870
},
{
"epoch": 0.352,
"grad_norm": 52.25,
"learning_rate": 1.63742398974869e-05,
"loss": 10.001,
"step": 880
},
{
"epoch": 0.356,
"grad_norm": 29.625,
"learning_rate": 1.6266038113644605e-05,
"loss": 9.9393,
"step": 890
},
{
"epoch": 0.36,
"grad_norm": 38.25,
"learning_rate": 1.6156614753256583e-05,
"loss": 9.6362,
"step": 900
},
{
"epoch": 0.364,
"grad_norm": 36.25,
"learning_rate": 1.6045991148623752e-05,
"loss": 9.6987,
"step": 910
},
{
"epoch": 0.368,
"grad_norm": 48.25,
"learning_rate": 1.5934188866037017e-05,
"loss": 10.145,
"step": 920
},
{
"epoch": 0.372,
"grad_norm": 57.0,
"learning_rate": 1.5821229701572897e-05,
"loss": 9.7223,
"step": 930
},
{
"epoch": 0.376,
"grad_norm": 44.75,
"learning_rate": 1.570713567684432e-05,
"loss": 9.664,
"step": 940
},
{
"epoch": 0.38,
"grad_norm": 44.75,
"learning_rate": 1.5591929034707468e-05,
"loss": 9.6058,
"step": 950
},
{
"epoch": 0.384,
"grad_norm": 32.75,
"learning_rate": 1.5475632234925505e-05,
"loss": 9.667,
"step": 960
},
{
"epoch": 0.388,
"grad_norm": 54.75,
"learning_rate": 1.5358267949789968e-05,
"loss": 9.6606,
"step": 970
},
{
"epoch": 0.392,
"grad_norm": 49.25,
"learning_rate": 1.5239859059700794e-05,
"loss": 9.5469,
"step": 980
},
{
"epoch": 0.396,
"grad_norm": 50.75,
"learning_rate": 1.5120428648705716e-05,
"loss": 9.7267,
"step": 990
},
{
"epoch": 0.4,
"grad_norm": 40.75,
"learning_rate": 1.5000000000000002e-05,
"loss": 9.4521,
"step": 1000
},
{
"epoch": 0.404,
"grad_norm": 38.75,
"learning_rate": 1.4878596591387329e-05,
"loss": 9.1752,
"step": 1010
},
{
"epoch": 0.408,
"grad_norm": 35.75,
"learning_rate": 1.4756242090702756e-05,
"loss": 9.1399,
"step": 1020
},
{
"epoch": 0.412,
"grad_norm": 51.5,
"learning_rate": 1.463296035119862e-05,
"loss": 9.3694,
"step": 1030
},
{
"epoch": 0.416,
"grad_norm": 30.375,
"learning_rate": 1.4508775406894308e-05,
"loss": 9.2775,
"step": 1040
},
{
"epoch": 0.42,
"grad_norm": 30.875,
"learning_rate": 1.4383711467890776e-05,
"loss": 9.4338,
"step": 1050
},
{
"epoch": 0.424,
"grad_norm": 41.5,
"learning_rate": 1.4257792915650728e-05,
"loss": 9.5244,
"step": 1060
},
{
"epoch": 0.428,
"grad_norm": 34.25,
"learning_rate": 1.413104429824542e-05,
"loss": 9.3746,
"step": 1070
},
{
"epoch": 0.432,
"grad_norm": 43.0,
"learning_rate": 1.4003490325568953e-05,
"loss": 8.6871,
"step": 1080
},
{
"epoch": 0.436,
"grad_norm": 38.5,
"learning_rate": 1.3875155864521031e-05,
"loss": 8.6404,
"step": 1090
},
{
"epoch": 0.44,
"grad_norm": 33.75,
"learning_rate": 1.3746065934159123e-05,
"loss": 9.036,
"step": 1100
},
{
"epoch": 0.444,
"grad_norm": 30.875,
"learning_rate": 1.3616245700820922e-05,
"loss": 8.8422,
"step": 1110
},
{
"epoch": 0.448,
"grad_norm": 36.5,
"learning_rate": 1.3485720473218153e-05,
"loss": 8.7475,
"step": 1120
},
{
"epoch": 0.452,
"grad_norm": 26.0,
"learning_rate": 1.3354515697502552e-05,
"loss": 8.7999,
"step": 1130
},
{
"epoch": 0.456,
"grad_norm": 24.5,
"learning_rate": 1.3222656952305113e-05,
"loss": 8.4991,
"step": 1140
},
{
"epoch": 0.46,
"grad_norm": 32.75,
"learning_rate": 1.3090169943749475e-05,
"loss": 8.723,
"step": 1150
},
{
"epoch": 0.464,
"grad_norm": 39.75,
"learning_rate": 1.2957080500440469e-05,
"loss": 9.0665,
"step": 1160
},
{
"epoch": 0.468,
"grad_norm": 36.75,
"learning_rate": 1.2823414568428767e-05,
"loss": 8.9529,
"step": 1170
},
{
"epoch": 0.472,
"grad_norm": 30.625,
"learning_rate": 1.2689198206152657e-05,
"loss": 9.0994,
"step": 1180
},
{
"epoch": 0.476,
"grad_norm": 37.25,
"learning_rate": 1.2554457579357906e-05,
"loss": 8.7266,
"step": 1190
},
{
"epoch": 0.48,
"grad_norm": 30.25,
"learning_rate": 1.2419218955996677e-05,
"loss": 8.5609,
"step": 1200
},
{
"epoch": 0.484,
"grad_norm": 30.5,
"learning_rate": 1.2283508701106559e-05,
"loss": 8.6772,
"step": 1210
},
{
"epoch": 0.488,
"grad_norm": 35.0,
"learning_rate": 1.2147353271670634e-05,
"loss": 9.1507,
"step": 1220
},
{
"epoch": 0.492,
"grad_norm": 64.0,
"learning_rate": 1.2010779211459649e-05,
"loss": 9.1438,
"step": 1230
},
{
"epoch": 0.496,
"grad_norm": 30.25,
"learning_rate": 1.187381314585725e-05,
"loss": 8.7913,
"step": 1240
},
{
"epoch": 0.5,
"grad_norm": 29.5,
"learning_rate": 1.1736481776669307e-05,
"loss": 8.8292,
"step": 1250
},
{
"epoch": 0.504,
"grad_norm": 25.125,
"learning_rate": 1.159881187691835e-05,
"loss": 8.3337,
"step": 1260
},
{
"epoch": 0.508,
"grad_norm": 38.75,
"learning_rate": 1.1460830285624119e-05,
"loss": 8.1504,
"step": 1270
},
{
"epoch": 0.512,
"grad_norm": 43.0,
"learning_rate": 1.1322563902571227e-05,
"loss": 8.96,
"step": 1280
},
{
"epoch": 0.516,
"grad_norm": 25.625,
"learning_rate": 1.1184039683065014e-05,
"loss": 8.8024,
"step": 1290
},
{
"epoch": 0.52,
"grad_norm": 23.125,
"learning_rate": 1.1045284632676535e-05,
"loss": 8.4168,
"step": 1300
},
{
"epoch": 0.524,
"grad_norm": 55.75,
"learning_rate": 1.0906325801977804e-05,
"loss": 8.8624,
"step": 1310
},
{
"epoch": 0.528,
"grad_norm": 22.5,
"learning_rate": 1.0767190281268187e-05,
"loss": 8.7217,
"step": 1320
},
{
"epoch": 0.532,
"grad_norm": 18.0,
"learning_rate": 1.0627905195293135e-05,
"loss": 8.3564,
"step": 1330
},
{
"epoch": 0.536,
"grad_norm": 22.625,
"learning_rate": 1.0488497697956134e-05,
"loss": 8.2627,
"step": 1340
},
{
"epoch": 0.54,
"grad_norm": 34.25,
"learning_rate": 1.0348994967025012e-05,
"loss": 8.6016,
"step": 1350
},
{
"epoch": 0.544,
"grad_norm": 24.875,
"learning_rate": 1.0209424198833571e-05,
"loss": 8.2792,
"step": 1360
},
{
"epoch": 0.548,
"grad_norm": 22.0,
"learning_rate": 1.0069812602979617e-05,
"loss": 8.1662,
"step": 1370
},
{
"epoch": 0.552,
"grad_norm": 24.125,
"learning_rate": 9.930187397020385e-06,
"loss": 8.1738,
"step": 1380
},
{
"epoch": 0.556,
"grad_norm": 27.125,
"learning_rate": 9.790575801166432e-06,
"loss": 8.3896,
"step": 1390
},
{
"epoch": 0.56,
"grad_norm": 37.25,
"learning_rate": 9.651005032974994e-06,
"loss": 8.6871,
"step": 1400
},
{
"epoch": 0.564,
"grad_norm": 25.875,
"learning_rate": 9.511502302043867e-06,
"loss": 8.1899,
"step": 1410
},
{
"epoch": 0.568,
"grad_norm": 26.0,
"learning_rate": 9.372094804706867e-06,
"loss": 8.2387,
"step": 1420
},
{
"epoch": 0.572,
"grad_norm": 18.75,
"learning_rate": 9.232809718731815e-06,
"loss": 8.179,
"step": 1430
},
{
"epoch": 0.576,
"grad_norm": 21.75,
"learning_rate": 9.093674198022201e-06,
"loss": 7.9493,
"step": 1440
},
{
"epoch": 0.58,
"grad_norm": 23.875,
"learning_rate": 8.954715367323468e-06,
"loss": 7.8349,
"step": 1450
},
{
"epoch": 0.584,
"grad_norm": 18.625,
"learning_rate": 8.815960316934991e-06,
"loss": 8.1045,
"step": 1460
},
{
"epoch": 0.588,
"grad_norm": 22.5,
"learning_rate": 8.677436097428775e-06,
"loss": 8.0962,
"step": 1470
},
{
"epoch": 0.592,
"grad_norm": 117.0,
"learning_rate": 8.539169714375885e-06,
"loss": 8.2646,
"step": 1480
},
{
"epoch": 0.596,
"grad_norm": 24.25,
"learning_rate": 8.401188123081653e-06,
"loss": 7.8255,
"step": 1490
},
{
"epoch": 0.6,
"grad_norm": 19.125,
"learning_rate": 8.263518223330698e-06,
"loss": 8.2312,
"step": 1500
},
{
"epoch": 0.604,
"grad_norm": 24.0,
"learning_rate": 8.126186854142752e-06,
"loss": 7.9319,
"step": 1510
},
{
"epoch": 0.608,
"grad_norm": 20.375,
"learning_rate": 7.989220788540356e-06,
"loss": 7.6825,
"step": 1520
},
{
"epoch": 0.612,
"grad_norm": 19.125,
"learning_rate": 7.852646728329368e-06,
"loss": 7.6429,
"step": 1530
},
{
"epoch": 0.616,
"grad_norm": 21.125,
"learning_rate": 7.716491298893443e-06,
"loss": 7.859,
"step": 1540
},
{
"epoch": 0.62,
"grad_norm": 36.0,
"learning_rate": 7.580781044003324e-06,
"loss": 7.8929,
"step": 1550
},
{
"epoch": 0.624,
"grad_norm": 20.25,
"learning_rate": 7.445542420642097e-06,
"loss": 7.6639,
"step": 1560
},
{
"epoch": 0.628,
"grad_norm": 44.0,
"learning_rate": 7.310801793847344e-06,
"loss": 8.0845,
"step": 1570
},
{
"epoch": 0.632,
"grad_norm": 18.75,
"learning_rate": 7.176585431571235e-06,
"loss": 8.0448,
"step": 1580
},
{
"epoch": 0.636,
"grad_norm": 27.375,
"learning_rate": 7.042919499559538e-06,
"loss": 7.8568,
"step": 1590
},
{
"epoch": 0.64,
"grad_norm": 23.5,
"learning_rate": 6.909830056250527e-06,
"loss": 7.7187,
"step": 1600
},
{
"epoch": 0.644,
"grad_norm": 25.125,
"learning_rate": 6.777343047694891e-06,
"loss": 8.0309,
"step": 1610
},
{
"epoch": 0.648,
"grad_norm": 46.75,
"learning_rate": 6.645484302497452e-06,
"loss": 7.83,
"step": 1620
},
{
"epoch": 0.652,
"grad_norm": 20.125,
"learning_rate": 6.5142795267818505e-06,
"loss": 7.6632,
"step": 1630
},
{
"epoch": 0.656,
"grad_norm": 28.25,
"learning_rate": 6.383754299179079e-06,
"loss": 8.3427,
"step": 1640
},
{
"epoch": 0.66,
"grad_norm": 19.875,
"learning_rate": 6.25393406584088e-06,
"loss": 7.9251,
"step": 1650
},
{
"epoch": 0.664,
"grad_norm": 23.0,
"learning_rate": 6.124844135478971e-06,
"loss": 8.0911,
"step": 1660
},
{
"epoch": 0.668,
"grad_norm": 18.375,
"learning_rate": 5.996509674431053e-06,
"loss": 7.9677,
"step": 1670
},
{
"epoch": 0.672,
"grad_norm": 22.125,
"learning_rate": 5.868955701754584e-06,
"loss": 7.8718,
"step": 1680
},
{
"epoch": 0.676,
"grad_norm": 22.75,
"learning_rate": 5.742207084349274e-06,
"loss": 7.7885,
"step": 1690
},
{
"epoch": 0.68,
"grad_norm": 20.125,
"learning_rate": 5.616288532109225e-06,
"loss": 8.0545,
"step": 1700
},
{
"epoch": 0.684,
"grad_norm": 17.25,
"learning_rate": 5.491224593105695e-06,
"loss": 7.7132,
"step": 1710
},
{
"epoch": 0.688,
"grad_norm": 20.875,
"learning_rate": 5.367039648801386e-06,
"loss": 8.1375,
"step": 1720
},
{
"epoch": 0.692,
"grad_norm": 17.875,
"learning_rate": 5.243757909297247e-06,
"loss": 7.7855,
"step": 1730
},
{
"epoch": 0.696,
"grad_norm": 20.125,
"learning_rate": 5.121403408612672e-06,
"loss": 8.1988,
"step": 1740
},
{
"epoch": 0.7,
"grad_norm": 28.0,
"learning_rate": 5.000000000000003e-06,
"loss": 7.9834,
"step": 1750
},
{
"epoch": 0.704,
"grad_norm": 23.375,
"learning_rate": 4.879571351294287e-06,
"loss": 8.0007,
"step": 1760
},
{
"epoch": 0.708,
"grad_norm": 17.25,
"learning_rate": 4.76014094029921e-06,
"loss": 7.5913,
"step": 1770
},
{
"epoch": 0.712,
"grad_norm": 18.0,
"learning_rate": 4.641732050210032e-06,
"loss": 7.668,
"step": 1780
},
{
"epoch": 0.716,
"grad_norm": 19.875,
"learning_rate": 4.524367765074499e-06,
"loss": 7.7244,
"step": 1790
},
{
"epoch": 0.72,
"grad_norm": 20.125,
"learning_rate": 4.408070965292534e-06,
"loss": 8.104,
"step": 1800
},
{
"epoch": 0.724,
"grad_norm": 20.875,
"learning_rate": 4.292864323155684e-06,
"loss": 8.0465,
"step": 1810
},
{
"epoch": 0.728,
"grad_norm": 19.0,
"learning_rate": 4.178770298427107e-06,
"loss": 7.8946,
"step": 1820
},
{
"epoch": 0.732,
"grad_norm": 18.75,
"learning_rate": 4.065811133962987e-06,
"loss": 7.8041,
"step": 1830
},
{
"epoch": 0.736,
"grad_norm": 23.25,
"learning_rate": 3.954008851376252e-06,
"loss": 7.4601,
"step": 1840
},
{
"epoch": 0.74,
"grad_norm": 17.125,
"learning_rate": 3.8433852467434175e-06,
"loss": 7.6713,
"step": 1850
},
{
"epoch": 0.744,
"grad_norm": 19.0,
"learning_rate": 3.7339618863553983e-06,
"loss": 7.6553,
"step": 1860
},
{
"epoch": 0.748,
"grad_norm": 25.5,
"learning_rate": 3.625760102513103e-06,
"loss": 7.9183,
"step": 1870
},
{
"epoch": 0.752,
"grad_norm": 40.0,
"learning_rate": 3.5188009893686916e-06,
"loss": 7.7183,
"step": 1880
},
{
"epoch": 0.756,
"grad_norm": 30.375,
"learning_rate": 3.4131053988131947e-06,
"loss": 7.7939,
"step": 1890
},
{
"epoch": 0.76,
"grad_norm": 33.0,
"learning_rate": 3.308693936411421e-06,
"loss": 7.7032,
"step": 1900
},
{
"epoch": 0.764,
"grad_norm": 16.875,
"learning_rate": 3.2055869573848374e-06,
"loss": 7.641,
"step": 1910
},
{
"epoch": 0.768,
"grad_norm": 20.125,
"learning_rate": 3.103804562643302e-06,
"loss": 7.5742,
"step": 1920
},
{
"epoch": 0.772,
"grad_norm": 33.5,
"learning_rate": 3.003366594866345e-06,
"loss": 7.9304,
"step": 1930
},
{
"epoch": 0.776,
"grad_norm": 26.0,
"learning_rate": 2.9042926346347932e-06,
"loss": 7.5508,
"step": 1940
},
{
"epoch": 0.78,
"grad_norm": 19.375,
"learning_rate": 2.8066019966134907e-06,
"loss": 7.6355,
"step": 1950
},
{
"epoch": 0.784,
"grad_norm": 18.125,
"learning_rate": 2.7103137257858867e-06,
"loss": 7.5146,
"step": 1960
},
{
"epoch": 0.788,
"grad_norm": 15.1875,
"learning_rate": 2.615446593741161e-06,
"loss": 7.4347,
"step": 1970
},
{
"epoch": 0.792,
"grad_norm": 17.75,
"learning_rate": 2.522019095014683e-06,
"loss": 7.6477,
"step": 1980
},
{
"epoch": 0.796,
"grad_norm": 18.75,
"learning_rate": 2.4300494434824373e-06,
"loss": 7.4979,
"step": 1990
},
{
"epoch": 0.8,
"grad_norm": 18.0,
"learning_rate": 2.339555568810221e-06,
"loss": 7.6053,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 2500,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.82656621576192e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}