Kat380's picture
upload model checkpoints
d451f22 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 2080,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004807692307692308,
"grad_norm": 416.0,
"learning_rate": 9.615384615384617e-07,
"loss": 51.8221,
"step": 1
},
{
"epoch": 0.02403846153846154,
"grad_norm": 386.0,
"learning_rate": 4.807692307692308e-06,
"loss": 49.6687,
"step": 5
},
{
"epoch": 0.04807692307692308,
"grad_norm": 202.0,
"learning_rate": 9.615384615384616e-06,
"loss": 45.9328,
"step": 10
},
{
"epoch": 0.07211538461538461,
"grad_norm": 126.5,
"learning_rate": 1.4423076923076923e-05,
"loss": 37.1137,
"step": 15
},
{
"epoch": 0.09615384615384616,
"grad_norm": 49.75,
"learning_rate": 1.923076923076923e-05,
"loss": 29.2088,
"step": 20
},
{
"epoch": 0.1201923076923077,
"grad_norm": 20.125,
"learning_rate": 2.4038461538461542e-05,
"loss": 25.4723,
"step": 25
},
{
"epoch": 0.14423076923076922,
"grad_norm": 15.9375,
"learning_rate": 2.8846153846153845e-05,
"loss": 23.5413,
"step": 30
},
{
"epoch": 0.16826923076923078,
"grad_norm": 9.1875,
"learning_rate": 3.365384615384616e-05,
"loss": 21.2424,
"step": 35
},
{
"epoch": 0.19230769230769232,
"grad_norm": 4.8125,
"learning_rate": 3.846153846153846e-05,
"loss": 20.2839,
"step": 40
},
{
"epoch": 0.21634615384615385,
"grad_norm": 4.59375,
"learning_rate": 4.326923076923077e-05,
"loss": 19.3389,
"step": 45
},
{
"epoch": 0.2403846153846154,
"grad_norm": 6.40625,
"learning_rate": 4.8076923076923084e-05,
"loss": 18.9421,
"step": 50
},
{
"epoch": 0.2644230769230769,
"grad_norm": 8.4375,
"learning_rate": 5.288461538461539e-05,
"loss": 18.0351,
"step": 55
},
{
"epoch": 0.28846153846153844,
"grad_norm": 13.875,
"learning_rate": 5.769230769230769e-05,
"loss": 17.0595,
"step": 60
},
{
"epoch": 0.3125,
"grad_norm": 23.625,
"learning_rate": 6.25e-05,
"loss": 14.7782,
"step": 65
},
{
"epoch": 0.33653846153846156,
"grad_norm": 30.75,
"learning_rate": 6.730769230769232e-05,
"loss": 10.9389,
"step": 70
},
{
"epoch": 0.3605769230769231,
"grad_norm": 24.625,
"learning_rate": 7.211538461538462e-05,
"loss": 5.5696,
"step": 75
},
{
"epoch": 0.38461538461538464,
"grad_norm": 6.34375,
"learning_rate": 7.692307692307693e-05,
"loss": 2.548,
"step": 80
},
{
"epoch": 0.40865384615384615,
"grad_norm": 5.71875,
"learning_rate": 8.173076923076923e-05,
"loss": 2.0589,
"step": 85
},
{
"epoch": 0.4326923076923077,
"grad_norm": 3.03125,
"learning_rate": 8.653846153846155e-05,
"loss": 1.8063,
"step": 90
},
{
"epoch": 0.4567307692307692,
"grad_norm": 1.0390625,
"learning_rate": 9.134615384615385e-05,
"loss": 1.6319,
"step": 95
},
{
"epoch": 0.4807692307692308,
"grad_norm": 1.28125,
"learning_rate": 9.615384615384617e-05,
"loss": 1.502,
"step": 100
},
{
"epoch": 0.5048076923076923,
"grad_norm": 0.65234375,
"learning_rate": 0.00010096153846153846,
"loss": 1.4262,
"step": 105
},
{
"epoch": 0.5288461538461539,
"grad_norm": 2.625,
"learning_rate": 0.00010576923076923077,
"loss": 1.3708,
"step": 110
},
{
"epoch": 0.5528846153846154,
"grad_norm": 0.95703125,
"learning_rate": 0.00011057692307692309,
"loss": 1.309,
"step": 115
},
{
"epoch": 0.5769230769230769,
"grad_norm": 1.0546875,
"learning_rate": 0.00011538461538461538,
"loss": 1.2806,
"step": 120
},
{
"epoch": 0.6009615384615384,
"grad_norm": 1.4296875,
"learning_rate": 0.0001201923076923077,
"loss": 1.2449,
"step": 125
},
{
"epoch": 0.625,
"grad_norm": 0.6484375,
"learning_rate": 0.000125,
"loss": 1.2165,
"step": 130
},
{
"epoch": 0.6490384615384616,
"grad_norm": 0.828125,
"learning_rate": 0.0001298076923076923,
"loss": 1.1992,
"step": 135
},
{
"epoch": 0.6730769230769231,
"grad_norm": 2.328125,
"learning_rate": 0.00013461538461538464,
"loss": 1.1854,
"step": 140
},
{
"epoch": 0.6971153846153846,
"grad_norm": 1.5078125,
"learning_rate": 0.0001394230769230769,
"loss": 1.1787,
"step": 145
},
{
"epoch": 0.7211538461538461,
"grad_norm": 2.6875,
"learning_rate": 0.00014423076923076924,
"loss": 1.1479,
"step": 150
},
{
"epoch": 0.7451923076923077,
"grad_norm": 1.8828125,
"learning_rate": 0.00014903846153846155,
"loss": 1.1501,
"step": 155
},
{
"epoch": 0.7692307692307693,
"grad_norm": 2.25,
"learning_rate": 0.00015384615384615385,
"loss": 1.121,
"step": 160
},
{
"epoch": 0.7932692307692307,
"grad_norm": 3.0625,
"learning_rate": 0.00015865384615384616,
"loss": 1.1039,
"step": 165
},
{
"epoch": 0.8173076923076923,
"grad_norm": 0.76953125,
"learning_rate": 0.00016346153846153846,
"loss": 1.1093,
"step": 170
},
{
"epoch": 0.8413461538461539,
"grad_norm": 2.4375,
"learning_rate": 0.0001682692307692308,
"loss": 1.1086,
"step": 175
},
{
"epoch": 0.8653846153846154,
"grad_norm": 3.765625,
"learning_rate": 0.0001730769230769231,
"loss": 1.1016,
"step": 180
},
{
"epoch": 0.8894230769230769,
"grad_norm": 5.8125,
"learning_rate": 0.00017788461538461537,
"loss": 1.0919,
"step": 185
},
{
"epoch": 0.9134615384615384,
"grad_norm": 0.95703125,
"learning_rate": 0.0001826923076923077,
"loss": 1.0958,
"step": 190
},
{
"epoch": 0.9375,
"grad_norm": 3.765625,
"learning_rate": 0.0001875,
"loss": 1.0871,
"step": 195
},
{
"epoch": 0.9615384615384616,
"grad_norm": 3.328125,
"learning_rate": 0.00019230769230769233,
"loss": 1.072,
"step": 200
},
{
"epoch": 0.9855769230769231,
"grad_norm": 1.453125,
"learning_rate": 0.00019711538461538464,
"loss": 1.067,
"step": 205
},
{
"epoch": 1.0,
"eval_loss": 2.5660059452056885,
"eval_runtime": 0.2581,
"eval_samples_per_second": 38.744,
"eval_steps_per_second": 3.874,
"step": 208
},
{
"epoch": 1.0096153846153846,
"grad_norm": 2.90625,
"learning_rate": 0.0001999994367286727,
"loss": 1.0461,
"step": 210
},
{
"epoch": 1.0336538461538463,
"grad_norm": 2.53125,
"learning_rate": 0.00019999309999911409,
"loss": 1.0479,
"step": 215
},
{
"epoch": 1.0576923076923077,
"grad_norm": 1.1875,
"learning_rate": 0.00019997972289848503,
"loss": 1.0469,
"step": 220
},
{
"epoch": 1.0817307692307692,
"grad_norm": 1.5703125,
"learning_rate": 0.00019995930636864802,
"loss": 1.0353,
"step": 225
},
{
"epoch": 1.1057692307692308,
"grad_norm": 0.80078125,
"learning_rate": 0.00019993185184710165,
"loss": 1.0479,
"step": 230
},
{
"epoch": 1.1298076923076923,
"grad_norm": 13.0625,
"learning_rate": 0.00019989736126687963,
"loss": 1.0327,
"step": 235
},
{
"epoch": 1.1538461538461537,
"grad_norm": 1.421875,
"learning_rate": 0.00019985583705641418,
"loss": 1.0344,
"step": 240
},
{
"epoch": 1.1778846153846154,
"grad_norm": 4.5625,
"learning_rate": 0.00019980728213936567,
"loss": 1.0178,
"step": 245
},
{
"epoch": 1.2019230769230769,
"grad_norm": 1.6640625,
"learning_rate": 0.00019975169993441627,
"loss": 1.0139,
"step": 250
},
{
"epoch": 1.2259615384615385,
"grad_norm": 2.6875,
"learning_rate": 0.0001996890943550295,
"loss": 0.9975,
"step": 255
},
{
"epoch": 1.25,
"grad_norm": 2.375,
"learning_rate": 0.00019961946980917456,
"loss": 0.9845,
"step": 260
},
{
"epoch": 1.2740384615384617,
"grad_norm": 5.25,
"learning_rate": 0.00019954283119901615,
"loss": 0.9965,
"step": 265
},
{
"epoch": 1.2980769230769231,
"grad_norm": 1.8125,
"learning_rate": 0.0001994591839205691,
"loss": 0.9998,
"step": 270
},
{
"epoch": 1.3221153846153846,
"grad_norm": 2.15625,
"learning_rate": 0.00019936853386331858,
"loss": 0.9872,
"step": 275
},
{
"epoch": 1.3461538461538463,
"grad_norm": 0.8671875,
"learning_rate": 0.0001992708874098054,
"loss": 0.9926,
"step": 280
},
{
"epoch": 1.3701923076923077,
"grad_norm": 2.625,
"learning_rate": 0.00019916625143517663,
"loss": 0.9819,
"step": 285
},
{
"epoch": 1.3942307692307692,
"grad_norm": 0.98828125,
"learning_rate": 0.00019905463330670143,
"loss": 0.9828,
"step": 290
},
{
"epoch": 1.4182692307692308,
"grad_norm": 4.9375,
"learning_rate": 0.00019893604088325257,
"loss": 0.9768,
"step": 295
},
{
"epoch": 1.4423076923076923,
"grad_norm": 1.7734375,
"learning_rate": 0.0001988104825147528,
"loss": 0.9772,
"step": 300
},
{
"epoch": 1.4663461538461537,
"grad_norm": 4.0,
"learning_rate": 0.0001986779670415872,
"loss": 0.9754,
"step": 305
},
{
"epoch": 1.4903846153846154,
"grad_norm": 3.25,
"learning_rate": 0.0001985385037939806,
"loss": 0.9712,
"step": 310
},
{
"epoch": 1.5144230769230769,
"grad_norm": 2.375,
"learning_rate": 0.00019839210259134062,
"loss": 0.9726,
"step": 315
},
{
"epoch": 1.5384615384615383,
"grad_norm": 1.484375,
"learning_rate": 0.00019823877374156647,
"loss": 0.954,
"step": 320
},
{
"epoch": 1.5625,
"grad_norm": 1.4140625,
"learning_rate": 0.00019807852804032305,
"loss": 0.9547,
"step": 325
},
{
"epoch": 1.5865384615384617,
"grad_norm": 1.328125,
"learning_rate": 0.00019791137677028082,
"loss": 0.9552,
"step": 330
},
{
"epoch": 1.6105769230769231,
"grad_norm": 2.109375,
"learning_rate": 0.0001977373317003215,
"loss": 0.9472,
"step": 335
},
{
"epoch": 1.6346153846153846,
"grad_norm": 3.6875,
"learning_rate": 0.00019755640508470942,
"loss": 0.9488,
"step": 340
},
{
"epoch": 1.6586538461538463,
"grad_norm": 1.6171875,
"learning_rate": 0.0001973686096622286,
"loss": 0.9445,
"step": 345
},
{
"epoch": 1.6826923076923077,
"grad_norm": 5.40625,
"learning_rate": 0.00019717395865528602,
"loss": 0.9428,
"step": 350
},
{
"epoch": 1.7067307692307692,
"grad_norm": 2.40625,
"learning_rate": 0.0001969724657689805,
"loss": 0.9394,
"step": 355
},
{
"epoch": 1.7307692307692308,
"grad_norm": 0.9921875,
"learning_rate": 0.00019676414519013781,
"loss": 0.9524,
"step": 360
},
{
"epoch": 1.7548076923076923,
"grad_norm": 1.7265625,
"learning_rate": 0.00019654901158631182,
"loss": 0.9384,
"step": 365
},
{
"epoch": 1.7788461538461537,
"grad_norm": 2.5625,
"learning_rate": 0.00019632708010475165,
"loss": 0.9354,
"step": 370
},
{
"epoch": 1.8028846153846154,
"grad_norm": 2.078125,
"learning_rate": 0.0001960983663713353,
"loss": 0.9314,
"step": 375
},
{
"epoch": 1.8269230769230769,
"grad_norm": 2.53125,
"learning_rate": 0.00019586288648946947,
"loss": 0.9466,
"step": 380
},
{
"epoch": 1.8509615384615383,
"grad_norm": 9.25,
"learning_rate": 0.0001956206570389556,
"loss": 0.947,
"step": 385
},
{
"epoch": 1.875,
"grad_norm": 1.890625,
"learning_rate": 0.0001953716950748227,
"loss": 0.9377,
"step": 390
},
{
"epoch": 1.8990384615384617,
"grad_norm": 0.734375,
"learning_rate": 0.0001951160181261263,
"loss": 0.9395,
"step": 395
},
{
"epoch": 1.9230769230769231,
"grad_norm": 1.8515625,
"learning_rate": 0.00019485364419471454,
"loss": 0.9244,
"step": 400
},
{
"epoch": 1.9471153846153846,
"grad_norm": 1.25,
"learning_rate": 0.00019458459175396043,
"loss": 0.9304,
"step": 405
},
{
"epoch": 1.9711538461538463,
"grad_norm": 2.34375,
"learning_rate": 0.0001943088797474612,
"loss": 0.9328,
"step": 410
},
{
"epoch": 1.9951923076923077,
"grad_norm": 8.625,
"learning_rate": 0.00019402652758770475,
"loss": 0.9432,
"step": 415
},
{
"epoch": 2.0,
"eval_loss": 2.447457790374756,
"eval_runtime": 0.2388,
"eval_samples_per_second": 41.883,
"eval_steps_per_second": 4.188,
"step": 416
},
{
"epoch": 2.019230769230769,
"grad_norm": 7.15625,
"learning_rate": 0.00019373755515470254,
"loss": 0.926,
"step": 420
},
{
"epoch": 2.043269230769231,
"grad_norm": 2.5,
"learning_rate": 0.00019344198279459,
"loss": 0.9221,
"step": 425
},
{
"epoch": 2.0673076923076925,
"grad_norm": 1.0703125,
"learning_rate": 0.00019313983131819407,
"loss": 0.9142,
"step": 430
},
{
"epoch": 2.0913461538461537,
"grad_norm": 2.359375,
"learning_rate": 0.00019283112199956775,
"loss": 0.9251,
"step": 435
},
{
"epoch": 2.1153846153846154,
"grad_norm": 1.2265625,
"learning_rate": 0.00019251587657449236,
"loss": 0.9006,
"step": 440
},
{
"epoch": 2.139423076923077,
"grad_norm": 0.98046875,
"learning_rate": 0.00019219411723894717,
"loss": 0.9073,
"step": 445
},
{
"epoch": 2.1634615384615383,
"grad_norm": 4.9375,
"learning_rate": 0.0001918658666475465,
"loss": 0.9052,
"step": 450
},
{
"epoch": 2.1875,
"grad_norm": 4.125,
"learning_rate": 0.00019153114791194473,
"loss": 0.9128,
"step": 455
},
{
"epoch": 2.2115384615384617,
"grad_norm": 1.1953125,
"learning_rate": 0.00019118998459920902,
"loss": 0.914,
"step": 460
},
{
"epoch": 2.235576923076923,
"grad_norm": 7.84375,
"learning_rate": 0.00019084240073015998,
"loss": 0.9143,
"step": 465
},
{
"epoch": 2.2596153846153846,
"grad_norm": 2.53125,
"learning_rate": 0.0001904884207776804,
"loss": 0.9272,
"step": 470
},
{
"epoch": 2.2836538461538463,
"grad_norm": 0.6796875,
"learning_rate": 0.00019012806966499217,
"loss": 0.9118,
"step": 475
},
{
"epoch": 2.3076923076923075,
"grad_norm": 2.8125,
"learning_rate": 0.0001897613727639014,
"loss": 0.935,
"step": 480
},
{
"epoch": 2.331730769230769,
"grad_norm": 2.71875,
"learning_rate": 0.00018938835589301216,
"loss": 0.9075,
"step": 485
},
{
"epoch": 2.355769230769231,
"grad_norm": 3.203125,
"learning_rate": 0.00018900904531590846,
"loss": 0.8945,
"step": 490
},
{
"epoch": 2.3798076923076925,
"grad_norm": 1.5859375,
"learning_rate": 0.00018862346773930523,
"loss": 0.8932,
"step": 495
},
{
"epoch": 2.4038461538461537,
"grad_norm": 2.609375,
"learning_rate": 0.0001882316503111678,
"loss": 0.8981,
"step": 500
},
{
"epoch": 2.4278846153846154,
"grad_norm": 1.921875,
"learning_rate": 0.00018783362061880062,
"loss": 0.895,
"step": 505
},
{
"epoch": 2.451923076923077,
"grad_norm": 7.25,
"learning_rate": 0.00018742940668690464,
"loss": 0.8995,
"step": 510
},
{
"epoch": 2.4759615384615383,
"grad_norm": 7.90625,
"learning_rate": 0.00018701903697560437,
"loss": 0.8864,
"step": 515
},
{
"epoch": 2.5,
"grad_norm": 4.75,
"learning_rate": 0.00018660254037844388,
"loss": 0.8893,
"step": 520
},
{
"epoch": 2.5240384615384617,
"grad_norm": 13.375,
"learning_rate": 0.00018617994622035253,
"loss": 0.9098,
"step": 525
},
{
"epoch": 2.5480769230769234,
"grad_norm": 1.2265625,
"learning_rate": 0.00018575128425558023,
"loss": 0.9133,
"step": 530
},
{
"epoch": 2.5721153846153846,
"grad_norm": 0.90625,
"learning_rate": 0.00018531658466560246,
"loss": 0.9042,
"step": 535
},
{
"epoch": 2.5961538461538463,
"grad_norm": 1.8125,
"learning_rate": 0.00018487587805699526,
"loss": 0.8994,
"step": 540
},
{
"epoch": 2.6201923076923075,
"grad_norm": 1.21875,
"learning_rate": 0.00018442919545928022,
"loss": 0.8857,
"step": 545
},
{
"epoch": 2.644230769230769,
"grad_norm": 1.703125,
"learning_rate": 0.0001839765683227398,
"loss": 0.8794,
"step": 550
},
{
"epoch": 2.668269230769231,
"grad_norm": 1.078125,
"learning_rate": 0.00018351802851620294,
"loss": 0.8803,
"step": 555
},
{
"epoch": 2.6923076923076925,
"grad_norm": 2.625,
"learning_rate": 0.00018305360832480117,
"loss": 0.8835,
"step": 560
},
{
"epoch": 2.7163461538461537,
"grad_norm": 1.1640625,
"learning_rate": 0.00018258334044769558,
"loss": 0.881,
"step": 565
},
{
"epoch": 2.7403846153846154,
"grad_norm": 10.125,
"learning_rate": 0.00018210725799577439,
"loss": 0.8897,
"step": 570
},
{
"epoch": 2.7644230769230766,
"grad_norm": 8.0625,
"learning_rate": 0.00018162539448932164,
"loss": 0.8743,
"step": 575
},
{
"epoch": 2.7884615384615383,
"grad_norm": 1.5546875,
"learning_rate": 0.00018113778385565733,
"loss": 0.8811,
"step": 580
},
{
"epoch": 2.8125,
"grad_norm": 1.5078125,
"learning_rate": 0.00018064446042674828,
"loss": 0.887,
"step": 585
},
{
"epoch": 2.8365384615384617,
"grad_norm": 2.578125,
"learning_rate": 0.00018014545893679115,
"loss": 0.8917,
"step": 590
},
{
"epoch": 2.8605769230769234,
"grad_norm": 1.6640625,
"learning_rate": 0.00017964081451976672,
"loss": 0.8733,
"step": 595
},
{
"epoch": 2.8846153846153846,
"grad_norm": 2.890625,
"learning_rate": 0.0001791305627069662,
"loss": 0.9015,
"step": 600
},
{
"epoch": 2.9086538461538463,
"grad_norm": 2.75,
"learning_rate": 0.00017861473942448953,
"loss": 0.8923,
"step": 605
},
{
"epoch": 2.9326923076923075,
"grad_norm": 17.125,
"learning_rate": 0.00017809338099071577,
"loss": 0.8995,
"step": 610
},
{
"epoch": 2.956730769230769,
"grad_norm": 2.390625,
"learning_rate": 0.00017756652411374618,
"loss": 0.9079,
"step": 615
},
{
"epoch": 2.980769230769231,
"grad_norm": 2.234375,
"learning_rate": 0.00017703420588881946,
"loss": 0.9222,
"step": 620
},
{
"epoch": 3.0,
"eval_loss": 2.442279815673828,
"eval_runtime": 0.238,
"eval_samples_per_second": 42.025,
"eval_steps_per_second": 4.202,
"step": 624
},
{
"epoch": 3.0048076923076925,
"grad_norm": 7.46875,
"learning_rate": 0.0001764964637957,
"loss": 0.896,
"step": 625
},
{
"epoch": 3.0288461538461537,
"grad_norm": 2.140625,
"learning_rate": 0.0001759533356960391,
"loss": 0.888,
"step": 630
},
{
"epoch": 3.0528846153846154,
"grad_norm": 0.8984375,
"learning_rate": 0.00017540485983070887,
"loss": 0.8629,
"step": 635
},
{
"epoch": 3.076923076923077,
"grad_norm": 2.75,
"learning_rate": 0.00017485107481711012,
"loss": 0.8652,
"step": 640
},
{
"epoch": 3.1009615384615383,
"grad_norm": 0.90234375,
"learning_rate": 0.00017429201964645313,
"loss": 0.8815,
"step": 645
},
{
"epoch": 3.125,
"grad_norm": 15.375,
"learning_rate": 0.0001737277336810124,
"loss": 0.8888,
"step": 650
},
{
"epoch": 3.1490384615384617,
"grad_norm": 2.78125,
"learning_rate": 0.00017315825665135522,
"loss": 0.8722,
"step": 655
},
{
"epoch": 3.173076923076923,
"grad_norm": 1.0,
"learning_rate": 0.00017258362865354426,
"loss": 0.8506,
"step": 660
},
{
"epoch": 3.1971153846153846,
"grad_norm": 1.3359375,
"learning_rate": 0.00017200389014631446,
"loss": 0.8684,
"step": 665
},
{
"epoch": 3.2211538461538463,
"grad_norm": 5.84375,
"learning_rate": 0.00017141908194822446,
"loss": 0.8432,
"step": 670
},
{
"epoch": 3.2451923076923075,
"grad_norm": 0.8046875,
"learning_rate": 0.00017082924523478262,
"loss": 0.8466,
"step": 675
},
{
"epoch": 3.269230769230769,
"grad_norm": 9.75,
"learning_rate": 0.00017023442153554777,
"loss": 0.8492,
"step": 680
},
{
"epoch": 3.293269230769231,
"grad_norm": 1.1171875,
"learning_rate": 0.0001696346527312053,
"loss": 0.8435,
"step": 685
},
{
"epoch": 3.3173076923076925,
"grad_norm": 5.28125,
"learning_rate": 0.00016902998105061844,
"loss": 0.8578,
"step": 690
},
{
"epoch": 3.3413461538461537,
"grad_norm": 0.95703125,
"learning_rate": 0.00016842044906785483,
"loss": 0.8517,
"step": 695
},
{
"epoch": 3.3653846153846154,
"grad_norm": 2.21875,
"learning_rate": 0.0001678060996991891,
"loss": 0.87,
"step": 700
},
{
"epoch": 3.389423076923077,
"grad_norm": 1.4453125,
"learning_rate": 0.0001671869762000811,
"loss": 0.8582,
"step": 705
},
{
"epoch": 3.4134615384615383,
"grad_norm": 19.625,
"learning_rate": 0.00016656312216213034,
"loss": 0.8727,
"step": 710
},
{
"epoch": 3.4375,
"grad_norm": 1.390625,
"learning_rate": 0.00016593458151000688,
"loss": 0.878,
"step": 715
},
{
"epoch": 3.4615384615384617,
"grad_norm": 1.0390625,
"learning_rate": 0.0001653013984983585,
"loss": 0.851,
"step": 720
},
{
"epoch": 3.485576923076923,
"grad_norm": 4.0625,
"learning_rate": 0.00016466361770869494,
"loss": 0.8602,
"step": 725
},
{
"epoch": 3.5096153846153846,
"grad_norm": 1.2734375,
"learning_rate": 0.00016402128404624882,
"loss": 0.8497,
"step": 730
},
{
"epoch": 3.5336538461538463,
"grad_norm": 15.0,
"learning_rate": 0.00016337444273681407,
"loss": 0.8458,
"step": 735
},
{
"epoch": 3.5576923076923075,
"grad_norm": 2.53125,
"learning_rate": 0.00016272313932356162,
"loss": 0.8353,
"step": 740
},
{
"epoch": 3.581730769230769,
"grad_norm": 2.125,
"learning_rate": 0.0001620674196638327,
"loss": 0.8244,
"step": 745
},
{
"epoch": 3.605769230769231,
"grad_norm": 11.625,
"learning_rate": 0.0001614073299259101,
"loss": 0.8282,
"step": 750
},
{
"epoch": 3.6298076923076925,
"grad_norm": 12.4375,
"learning_rate": 0.00016074291658576772,
"loss": 0.8396,
"step": 755
},
{
"epoch": 3.6538461538461537,
"grad_norm": 17.25,
"learning_rate": 0.0001600742264237979,
"loss": 0.8315,
"step": 760
},
{
"epoch": 3.6778846153846154,
"grad_norm": 3.046875,
"learning_rate": 0.00015940130652151803,
"loss": 0.8336,
"step": 765
},
{
"epoch": 3.7019230769230766,
"grad_norm": 14.4375,
"learning_rate": 0.0001587242042582554,
"loss": 0.8239,
"step": 770
},
{
"epoch": 3.7259615384615383,
"grad_norm": 0.703125,
"learning_rate": 0.00015804296730781135,
"loss": 0.8185,
"step": 775
},
{
"epoch": 3.75,
"grad_norm": 1.9296875,
"learning_rate": 0.0001573576436351046,
"loss": 0.8416,
"step": 780
},
{
"epoch": 3.7740384615384617,
"grad_norm": 1.2578125,
"learning_rate": 0.0001566682814927943,
"loss": 0.8347,
"step": 785
},
{
"epoch": 3.7980769230769234,
"grad_norm": 2.5625,
"learning_rate": 0.00015597492941788222,
"loss": 0.8497,
"step": 790
},
{
"epoch": 3.8221153846153846,
"grad_norm": 10.1875,
"learning_rate": 0.00015527763622829577,
"loss": 0.8309,
"step": 795
},
{
"epoch": 3.8461538461538463,
"grad_norm": 1.7890625,
"learning_rate": 0.00015457645101945046,
"loss": 0.8141,
"step": 800
},
{
"epoch": 3.8701923076923075,
"grad_norm": 1.25,
"learning_rate": 0.00015387142316079347,
"loss": 0.8212,
"step": 805
},
{
"epoch": 3.894230769230769,
"grad_norm": 1.6484375,
"learning_rate": 0.00015316260229232727,
"loss": 0.8197,
"step": 810
},
{
"epoch": 3.918269230769231,
"grad_norm": 4.25,
"learning_rate": 0.00015245003832111483,
"loss": 0.8395,
"step": 815
},
{
"epoch": 3.9423076923076925,
"grad_norm": 4.09375,
"learning_rate": 0.00015173378141776568,
"loss": 0.8238,
"step": 820
},
{
"epoch": 3.9663461538461537,
"grad_norm": 2.390625,
"learning_rate": 0.0001510138820129033,
"loss": 0.8065,
"step": 825
},
{
"epoch": 3.9903846153846154,
"grad_norm": 7.375,
"learning_rate": 0.00015029039079361448,
"loss": 0.8069,
"step": 830
},
{
"epoch": 4.0,
"eval_loss": 2.4326889514923096,
"eval_runtime": 0.2383,
"eval_samples_per_second": 41.965,
"eval_steps_per_second": 4.196,
"step": 832
},
{
"epoch": 4.014423076923077,
"grad_norm": 12.3125,
"learning_rate": 0.0001495633586998807,
"loss": 0.8046,
"step": 835
},
{
"epoch": 4.038461538461538,
"grad_norm": 10.3125,
"learning_rate": 0.00014883283692099112,
"loss": 0.8045,
"step": 840
},
{
"epoch": 4.0625,
"grad_norm": 0.6640625,
"learning_rate": 0.00014809887689193877,
"loss": 0.8012,
"step": 845
},
{
"epoch": 4.086538461538462,
"grad_norm": 0.79296875,
"learning_rate": 0.00014736153028979893,
"loss": 0.7927,
"step": 850
},
{
"epoch": 4.110576923076923,
"grad_norm": 1.359375,
"learning_rate": 0.00014662084903009065,
"loss": 0.8012,
"step": 855
},
{
"epoch": 4.134615384615385,
"grad_norm": 1.03125,
"learning_rate": 0.00014587688526312143,
"loss": 0.7909,
"step": 860
},
{
"epoch": 4.158653846153846,
"grad_norm": 0.69921875,
"learning_rate": 0.00014512969137031538,
"loss": 0.7764,
"step": 865
},
{
"epoch": 4.1826923076923075,
"grad_norm": 2.828125,
"learning_rate": 0.00014437931996052518,
"loss": 0.7747,
"step": 870
},
{
"epoch": 4.206730769230769,
"grad_norm": 1.203125,
"learning_rate": 0.00014362582386632798,
"loss": 0.7841,
"step": 875
},
{
"epoch": 4.230769230769231,
"grad_norm": 0.72265625,
"learning_rate": 0.00014286925614030542,
"loss": 0.7827,
"step": 880
},
{
"epoch": 4.2548076923076925,
"grad_norm": 1.046875,
"learning_rate": 0.00014210967005130837,
"loss": 0.7824,
"step": 885
},
{
"epoch": 4.278846153846154,
"grad_norm": 0.7578125,
"learning_rate": 0.00014134711908070631,
"loss": 0.7813,
"step": 890
},
{
"epoch": 4.302884615384615,
"grad_norm": 1.0703125,
"learning_rate": 0.00014058165691862174,
"loss": 0.7777,
"step": 895
},
{
"epoch": 4.326923076923077,
"grad_norm": 0.453125,
"learning_rate": 0.0001398133374601501,
"loss": 0.7812,
"step": 900
},
{
"epoch": 4.350961538461538,
"grad_norm": 1.1796875,
"learning_rate": 0.0001390422148015649,
"loss": 0.7779,
"step": 905
},
{
"epoch": 4.375,
"grad_norm": 4.90625,
"learning_rate": 0.000138268343236509,
"loss": 0.7778,
"step": 910
},
{
"epoch": 4.399038461538462,
"grad_norm": 0.435546875,
"learning_rate": 0.00013749177725217175,
"loss": 0.7731,
"step": 915
},
{
"epoch": 4.423076923076923,
"grad_norm": 0.63671875,
"learning_rate": 0.00013671257152545277,
"loss": 0.7759,
"step": 920
},
{
"epoch": 4.447115384615385,
"grad_norm": 0.57421875,
"learning_rate": 0.00013593078091911218,
"loss": 0.7759,
"step": 925
},
{
"epoch": 4.471153846153846,
"grad_norm": 0.6640625,
"learning_rate": 0.00013514646047790775,
"loss": 0.7716,
"step": 930
},
{
"epoch": 4.4951923076923075,
"grad_norm": 0.4921875,
"learning_rate": 0.00013435966542471928,
"loss": 0.7764,
"step": 935
},
{
"epoch": 4.519230769230769,
"grad_norm": 0.49609375,
"learning_rate": 0.0001335704511566605,
"loss": 0.7836,
"step": 940
},
{
"epoch": 4.543269230769231,
"grad_norm": 0.48046875,
"learning_rate": 0.00013277887324117857,
"loss": 0.7786,
"step": 945
},
{
"epoch": 4.5673076923076925,
"grad_norm": 0.5078125,
"learning_rate": 0.00013198498741214166,
"loss": 0.7694,
"step": 950
},
{
"epoch": 4.591346153846154,
"grad_norm": 0.48828125,
"learning_rate": 0.0001311888495659149,
"loss": 0.773,
"step": 955
},
{
"epoch": 4.615384615384615,
"grad_norm": 0.55078125,
"learning_rate": 0.0001303905157574247,
"loss": 0.77,
"step": 960
},
{
"epoch": 4.639423076923077,
"grad_norm": 0.4765625,
"learning_rate": 0.00012959004219621195,
"loss": 0.7649,
"step": 965
},
{
"epoch": 4.663461538461538,
"grad_norm": 0.494140625,
"learning_rate": 0.00012878748524247462,
"loss": 0.7749,
"step": 970
},
{
"epoch": 4.6875,
"grad_norm": 0.45703125,
"learning_rate": 0.00012798290140309923,
"loss": 0.7666,
"step": 975
},
{
"epoch": 4.711538461538462,
"grad_norm": 0.4296875,
"learning_rate": 0.00012717634732768243,
"loss": 0.7723,
"step": 980
},
{
"epoch": 4.735576923076923,
"grad_norm": 0.44921875,
"learning_rate": 0.0001263678798045425,
"loss": 0.7713,
"step": 985
},
{
"epoch": 4.759615384615385,
"grad_norm": 0.376953125,
"learning_rate": 0.0001255575557567207,
"loss": 0.7692,
"step": 990
},
{
"epoch": 4.783653846153846,
"grad_norm": 0.416015625,
"learning_rate": 0.00012474543223797352,
"loss": 0.7608,
"step": 995
},
{
"epoch": 4.8076923076923075,
"grad_norm": 0.466796875,
"learning_rate": 0.0001239315664287558,
"loss": 0.7612,
"step": 1000
},
{
"epoch": 4.831730769230769,
"grad_norm": 0.443359375,
"learning_rate": 0.00012311601563219434,
"loss": 0.7632,
"step": 1005
},
{
"epoch": 4.855769230769231,
"grad_norm": 0.7109375,
"learning_rate": 0.00012229883727005365,
"loss": 0.7703,
"step": 1010
},
{
"epoch": 4.8798076923076925,
"grad_norm": 0.439453125,
"learning_rate": 0.00012148008887869269,
"loss": 0.7666,
"step": 1015
},
{
"epoch": 4.903846153846154,
"grad_norm": 0.404296875,
"learning_rate": 0.00012065982810501404,
"loss": 0.7706,
"step": 1020
},
{
"epoch": 4.927884615384615,
"grad_norm": 0.423828125,
"learning_rate": 0.00011983811270240484,
"loss": 0.7655,
"step": 1025
},
{
"epoch": 4.951923076923077,
"grad_norm": 0.59375,
"learning_rate": 0.00011901500052667068,
"loss": 0.7597,
"step": 1030
},
{
"epoch": 4.975961538461538,
"grad_norm": 0.455078125,
"learning_rate": 0.00011819054953196186,
"loss": 0.7652,
"step": 1035
},
{
"epoch": 5.0,
"grad_norm": 1.0625,
"learning_rate": 0.00011736481776669306,
"loss": 0.7635,
"step": 1040
},
{
"epoch": 5.0,
"eval_loss": 2.423292875289917,
"eval_runtime": 0.2377,
"eval_samples_per_second": 42.07,
"eval_steps_per_second": 4.207,
"step": 1040
},
{
"epoch": 5.024038461538462,
"grad_norm": 0.96484375,
"learning_rate": 0.00011653786336945614,
"loss": 0.7427,
"step": 1045
},
{
"epoch": 5.048076923076923,
"grad_norm": 0.423828125,
"learning_rate": 0.00011570974456492678,
"loss": 0.7423,
"step": 1050
},
{
"epoch": 5.072115384615385,
"grad_norm": 0.52734375,
"learning_rate": 0.00011488051965976486,
"loss": 0.7404,
"step": 1055
},
{
"epoch": 5.096153846153846,
"grad_norm": 0.44921875,
"learning_rate": 0.00011405024703850929,
"loss": 0.7424,
"step": 1060
},
{
"epoch": 5.1201923076923075,
"grad_norm": 0.388671875,
"learning_rate": 0.00011321898515946708,
"loss": 0.7388,
"step": 1065
},
{
"epoch": 5.144230769230769,
"grad_norm": 0.47265625,
"learning_rate": 0.00011238679255059752,
"loss": 0.7479,
"step": 1070
},
{
"epoch": 5.168269230769231,
"grad_norm": 0.45703125,
"learning_rate": 0.00011155372780539124,
"loss": 0.7477,
"step": 1075
},
{
"epoch": 5.1923076923076925,
"grad_norm": 0.490234375,
"learning_rate": 0.00011071984957874479,
"loss": 0.7426,
"step": 1080
},
{
"epoch": 5.216346153846154,
"grad_norm": 0.396484375,
"learning_rate": 0.00010988521658283071,
"loss": 0.744,
"step": 1085
},
{
"epoch": 5.240384615384615,
"grad_norm": 0.4375,
"learning_rate": 0.0001090498875829638,
"loss": 0.74,
"step": 1090
},
{
"epoch": 5.264423076923077,
"grad_norm": 0.53515625,
"learning_rate": 0.00010821392139346351,
"loss": 0.7365,
"step": 1095
},
{
"epoch": 5.288461538461538,
"grad_norm": 0.51171875,
"learning_rate": 0.00010737737687351284,
"loss": 0.7429,
"step": 1100
},
{
"epoch": 5.3125,
"grad_norm": 0.45703125,
"learning_rate": 0.00010654031292301432,
"loss": 0.7501,
"step": 1105
},
{
"epoch": 5.336538461538462,
"grad_norm": 0.7734375,
"learning_rate": 0.00010570278847844275,
"loss": 0.7378,
"step": 1110
},
{
"epoch": 5.360576923076923,
"grad_norm": 0.76171875,
"learning_rate": 0.0001048648625086957,
"loss": 0.7476,
"step": 1115
},
{
"epoch": 5.384615384615385,
"grad_norm": 0.42578125,
"learning_rate": 0.00010402659401094152,
"loss": 0.7388,
"step": 1120
},
{
"epoch": 5.408653846153846,
"grad_norm": 0.64453125,
"learning_rate": 0.00010318804200646553,
"loss": 0.747,
"step": 1125
},
{
"epoch": 5.4326923076923075,
"grad_norm": 1.0859375,
"learning_rate": 0.00010234926553651422,
"loss": 0.7353,
"step": 1130
},
{
"epoch": 5.456730769230769,
"grad_norm": 0.54296875,
"learning_rate": 0.00010151032365813859,
"loss": 0.7411,
"step": 1135
},
{
"epoch": 5.480769230769231,
"grad_norm": 0.50390625,
"learning_rate": 0.00010067127544003563,
"loss": 0.7377,
"step": 1140
},
{
"epoch": 5.5048076923076925,
"grad_norm": 0.400390625,
"learning_rate": 9.983217995838956e-05,
"loss": 0.7351,
"step": 1145
},
{
"epoch": 5.528846153846154,
"grad_norm": 0.427734375,
"learning_rate": 9.899309629271246e-05,
"loss": 0.7383,
"step": 1150
},
{
"epoch": 5.552884615384615,
"grad_norm": 0.51171875,
"learning_rate": 9.815408352168442e-05,
"loss": 0.7406,
"step": 1155
},
{
"epoch": 5.576923076923077,
"grad_norm": 0.62890625,
"learning_rate": 9.73152007189939e-05,
"loss": 0.7419,
"step": 1160
},
{
"epoch": 5.600961538461538,
"grad_norm": 1.515625,
"learning_rate": 9.647650694917856e-05,
"loss": 0.7503,
"step": 1165
},
{
"epoch": 5.625,
"grad_norm": 0.45703125,
"learning_rate": 9.563806126346642e-05,
"loss": 0.7448,
"step": 1170
},
{
"epoch": 5.649038461538462,
"grad_norm": 0.6015625,
"learning_rate": 9.479992269561833e-05,
"loss": 0.7376,
"step": 1175
},
{
"epoch": 5.673076923076923,
"grad_norm": 0.52734375,
"learning_rate": 9.396215025777139e-05,
"loss": 0.7505,
"step": 1180
},
{
"epoch": 5.697115384615385,
"grad_norm": 0.51171875,
"learning_rate": 9.312480293628404e-05,
"loss": 0.7411,
"step": 1185
},
{
"epoch": 5.721153846153846,
"grad_norm": 0.55078125,
"learning_rate": 9.22879396875828e-05,
"loss": 0.7402,
"step": 1190
},
{
"epoch": 5.7451923076923075,
"grad_norm": 0.384765625,
"learning_rate": 9.145161943401142e-05,
"loss": 0.7341,
"step": 1195
},
{
"epoch": 5.769230769230769,
"grad_norm": 0.369140625,
"learning_rate": 9.061590105968208e-05,
"loss": 0.7441,
"step": 1200
},
{
"epoch": 5.793269230769231,
"grad_norm": 0.38671875,
"learning_rate": 8.97808434063295e-05,
"loss": 0.7372,
"step": 1205
},
{
"epoch": 5.8173076923076925,
"grad_norm": 0.46484375,
"learning_rate": 8.894650526916803e-05,
"loss": 0.7381,
"step": 1210
},
{
"epoch": 5.841346153846154,
"grad_norm": 0.404296875,
"learning_rate": 8.811294539275185e-05,
"loss": 0.7381,
"step": 1215
},
{
"epoch": 5.865384615384615,
"grad_norm": 0.435546875,
"learning_rate": 8.728022246683894e-05,
"loss": 0.7374,
"step": 1220
},
{
"epoch": 5.889423076923077,
"grad_norm": 0.4453125,
"learning_rate": 8.644839512225886e-05,
"loss": 0.7356,
"step": 1225
},
{
"epoch": 5.913461538461538,
"grad_norm": 0.447265625,
"learning_rate": 8.561752192678443e-05,
"loss": 0.7434,
"step": 1230
},
{
"epoch": 5.9375,
"grad_norm": 0.4453125,
"learning_rate": 8.478766138100834e-05,
"loss": 0.7391,
"step": 1235
},
{
"epoch": 5.961538461538462,
"grad_norm": 1.171875,
"learning_rate": 8.395887191422397e-05,
"loss": 0.7421,
"step": 1240
},
{
"epoch": 5.985576923076923,
"grad_norm": 0.484375,
"learning_rate": 8.313121188031164e-05,
"loss": 0.7364,
"step": 1245
},
{
"epoch": 6.0,
"eval_loss": 2.4450995922088623,
"eval_runtime": 0.238,
"eval_samples_per_second": 42.022,
"eval_steps_per_second": 4.202,
"step": 1248
},
{
"epoch": 6.009615384615385,
"grad_norm": 0.5078125,
"learning_rate": 8.23047395536298e-05,
"loss": 0.7278,
"step": 1250
},
{
"epoch": 6.033653846153846,
"grad_norm": 0.51171875,
"learning_rate": 8.147951312491227e-05,
"loss": 0.7181,
"step": 1255
},
{
"epoch": 6.0576923076923075,
"grad_norm": 0.400390625,
"learning_rate": 8.065559069717088e-05,
"loss": 0.7184,
"step": 1260
},
{
"epoch": 6.081730769230769,
"grad_norm": 0.46875,
"learning_rate": 7.983303028160464e-05,
"loss": 0.7117,
"step": 1265
},
{
"epoch": 6.105769230769231,
"grad_norm": 0.55078125,
"learning_rate": 7.901188979351526e-05,
"loss": 0.7159,
"step": 1270
},
{
"epoch": 6.1298076923076925,
"grad_norm": 0.6875,
"learning_rate": 7.819222704822937e-05,
"loss": 0.7092,
"step": 1275
},
{
"epoch": 6.153846153846154,
"grad_norm": 0.466796875,
"learning_rate": 7.73740997570278e-05,
"loss": 0.7244,
"step": 1280
},
{
"epoch": 6.177884615384615,
"grad_norm": 0.404296875,
"learning_rate": 7.655756552308238e-05,
"loss": 0.72,
"step": 1285
},
{
"epoch": 6.201923076923077,
"grad_norm": 0.3828125,
"learning_rate": 7.574268183739989e-05,
"loss": 0.7184,
"step": 1290
},
{
"epoch": 6.225961538461538,
"grad_norm": 0.46875,
"learning_rate": 7.492950607477451e-05,
"loss": 0.716,
"step": 1295
},
{
"epoch": 6.25,
"grad_norm": 0.443359375,
"learning_rate": 7.411809548974792e-05,
"loss": 0.7183,
"step": 1300
},
{
"epoch": 6.274038461538462,
"grad_norm": 0.3828125,
"learning_rate": 7.330850721257825e-05,
"loss": 0.7159,
"step": 1305
},
{
"epoch": 6.298076923076923,
"grad_norm": 0.451171875,
"learning_rate": 7.250079824521743e-05,
"loss": 0.7263,
"step": 1310
},
{
"epoch": 6.322115384615385,
"grad_norm": 0.40625,
"learning_rate": 7.169502545729797e-05,
"loss": 0.7194,
"step": 1315
},
{
"epoch": 6.346153846153846,
"grad_norm": 0.466796875,
"learning_rate": 7.089124558212871e-05,
"loss": 0.7148,
"step": 1320
},
{
"epoch": 6.3701923076923075,
"grad_norm": 0.373046875,
"learning_rate": 7.008951521270037e-05,
"loss": 0.7188,
"step": 1325
},
{
"epoch": 6.394230769230769,
"grad_norm": 0.4140625,
"learning_rate": 6.928989079770094e-05,
"loss": 0.7241,
"step": 1330
},
{
"epoch": 6.418269230769231,
"grad_norm": 0.37109375,
"learning_rate": 6.849242863754108e-05,
"loss": 0.7144,
"step": 1335
},
{
"epoch": 6.4423076923076925,
"grad_norm": 0.380859375,
"learning_rate": 6.769718488039023e-05,
"loss": 0.7228,
"step": 1340
},
{
"epoch": 6.466346153846154,
"grad_norm": 0.50390625,
"learning_rate": 6.690421551822333e-05,
"loss": 0.7197,
"step": 1345
},
{
"epoch": 6.490384615384615,
"grad_norm": 0.376953125,
"learning_rate": 6.611357638287823e-05,
"loss": 0.7258,
"step": 1350
},
{
"epoch": 6.514423076923077,
"grad_norm": 0.41796875,
"learning_rate": 6.532532314212508e-05,
"loss": 0.7134,
"step": 1355
},
{
"epoch": 6.538461538461538,
"grad_norm": 0.369140625,
"learning_rate": 6.453951129574644e-05,
"loss": 0.7222,
"step": 1360
},
{
"epoch": 6.5625,
"grad_norm": 0.59765625,
"learning_rate": 6.375619617162985e-05,
"loss": 0.7274,
"step": 1365
},
{
"epoch": 6.586538461538462,
"grad_norm": 0.380859375,
"learning_rate": 6.297543292187215e-05,
"loss": 0.7236,
"step": 1370
},
{
"epoch": 6.610576923076923,
"grad_norm": 0.447265625,
"learning_rate": 6.219727651889646e-05,
"loss": 0.7235,
"step": 1375
},
{
"epoch": 6.634615384615385,
"grad_norm": 0.37890625,
"learning_rate": 6.142178175158149e-05,
"loss": 0.7162,
"step": 1380
},
{
"epoch": 6.658653846153846,
"grad_norm": 0.388671875,
"learning_rate": 6.064900322140392e-05,
"loss": 0.7285,
"step": 1385
},
{
"epoch": 6.6826923076923075,
"grad_norm": 0.38671875,
"learning_rate": 5.9878995338594224e-05,
"loss": 0.7136,
"step": 1390
},
{
"epoch": 6.706730769230769,
"grad_norm": 0.36328125,
"learning_rate": 5.9111812318305425e-05,
"loss": 0.7169,
"step": 1395
},
{
"epoch": 6.730769230769231,
"grad_norm": 0.4921875,
"learning_rate": 5.834750817679606e-05,
"loss": 0.7146,
"step": 1400
},
{
"epoch": 6.7548076923076925,
"grad_norm": 0.408203125,
"learning_rate": 5.75861367276269e-05,
"loss": 0.7164,
"step": 1405
},
{
"epoch": 6.778846153846154,
"grad_norm": 0.4140625,
"learning_rate": 5.682775157787213e-05,
"loss": 0.718,
"step": 1410
},
{
"epoch": 6.802884615384615,
"grad_norm": 0.490234375,
"learning_rate": 5.6072406124344855e-05,
"loss": 0.7112,
"step": 1415
},
{
"epoch": 6.826923076923077,
"grad_norm": 0.369140625,
"learning_rate": 5.5320153549837415e-05,
"loss": 0.7109,
"step": 1420
},
{
"epoch": 6.850961538461538,
"grad_norm": 0.462890625,
"learning_rate": 5.457104681937706e-05,
"loss": 0.7192,
"step": 1425
},
{
"epoch": 6.875,
"grad_norm": 0.482421875,
"learning_rate": 5.382513867649663e-05,
"loss": 0.7143,
"step": 1430
},
{
"epoch": 6.899038461538462,
"grad_norm": 0.369140625,
"learning_rate": 5.308248163952096e-05,
"loss": 0.723,
"step": 1435
},
{
"epoch": 6.923076923076923,
"grad_norm": 0.380859375,
"learning_rate": 5.234312799786921e-05,
"loss": 0.7089,
"step": 1440
},
{
"epoch": 6.947115384615385,
"grad_norm": 0.359375,
"learning_rate": 5.1607129808373254e-05,
"loss": 0.7096,
"step": 1445
},
{
"epoch": 6.971153846153846,
"grad_norm": 0.37109375,
"learning_rate": 5.087453889161229e-05,
"loss": 0.7133,
"step": 1450
},
{
"epoch": 6.9951923076923075,
"grad_norm": 0.359375,
"learning_rate": 5.014540682826434e-05,
"loss": 0.7168,
"step": 1455
},
{
"epoch": 7.0,
"eval_loss": 2.450974464416504,
"eval_runtime": 0.2387,
"eval_samples_per_second": 41.885,
"eval_steps_per_second": 4.189,
"step": 1456
},
{
"epoch": 7.019230769230769,
"grad_norm": 0.36328125,
"learning_rate": 4.9419784955474524e-05,
"loss": 0.7018,
"step": 1460
},
{
"epoch": 7.043269230769231,
"grad_norm": 0.375,
"learning_rate": 4.869772436324045e-05,
"loss": 0.7019,
"step": 1465
},
{
"epoch": 7.0673076923076925,
"grad_norm": 0.388671875,
"learning_rate": 4.797927589081509e-05,
"loss": 0.7056,
"step": 1470
},
{
"epoch": 7.091346153846154,
"grad_norm": 0.43359375,
"learning_rate": 4.726449012312726e-05,
"loss": 0.7081,
"step": 1475
},
{
"epoch": 7.115384615384615,
"grad_norm": 0.408203125,
"learning_rate": 4.6553417387219886e-05,
"loss": 0.709,
"step": 1480
},
{
"epoch": 7.139423076923077,
"grad_norm": 0.361328125,
"learning_rate": 4.58461077487067e-05,
"loss": 0.7028,
"step": 1485
},
{
"epoch": 7.163461538461538,
"grad_norm": 0.44921875,
"learning_rate": 4.514261100824709e-05,
"loss": 0.7022,
"step": 1490
},
{
"epoch": 7.1875,
"grad_norm": 0.41796875,
"learning_rate": 4.444297669803981e-05,
"loss": 0.7063,
"step": 1495
},
{
"epoch": 7.211538461538462,
"grad_norm": 0.38671875,
"learning_rate": 4.374725407833532e-05,
"loss": 0.7101,
"step": 1500
},
{
"epoch": 7.235576923076923,
"grad_norm": 0.361328125,
"learning_rate": 4.305549213396772e-05,
"loss": 0.7046,
"step": 1505
},
{
"epoch": 7.259615384615385,
"grad_norm": 0.390625,
"learning_rate": 4.236773957090548e-05,
"loss": 0.7018,
"step": 1510
},
{
"epoch": 7.283653846153846,
"grad_norm": 0.37890625,
"learning_rate": 4.168404481282233e-05,
"loss": 0.7038,
"step": 1515
},
{
"epoch": 7.3076923076923075,
"grad_norm": 0.390625,
"learning_rate": 4.100445599768774e-05,
"loss": 0.7072,
"step": 1520
},
{
"epoch": 7.331730769230769,
"grad_norm": 0.3671875,
"learning_rate": 4.0329020974377596e-05,
"loss": 0.7026,
"step": 1525
},
{
"epoch": 7.355769230769231,
"grad_norm": 0.427734375,
"learning_rate": 3.96577872993053e-05,
"loss": 0.7117,
"step": 1530
},
{
"epoch": 7.3798076923076925,
"grad_norm": 0.39453125,
"learning_rate": 3.899080223307335e-05,
"loss": 0.7008,
"step": 1535
},
{
"epoch": 7.403846153846154,
"grad_norm": 0.44140625,
"learning_rate": 3.832811273714569e-05,
"loss": 0.699,
"step": 1540
},
{
"epoch": 7.427884615384615,
"grad_norm": 0.484375,
"learning_rate": 3.7669765470541365e-05,
"loss": 0.7069,
"step": 1545
},
{
"epoch": 7.451923076923077,
"grad_norm": 0.494140625,
"learning_rate": 3.701580678654925e-05,
"loss": 0.7055,
"step": 1550
},
{
"epoch": 7.475961538461538,
"grad_norm": 0.404296875,
"learning_rate": 3.636628272946434e-05,
"loss": 0.7088,
"step": 1555
},
{
"epoch": 7.5,
"grad_norm": 0.40234375,
"learning_rate": 3.5721239031346066e-05,
"loss": 0.7042,
"step": 1560
},
{
"epoch": 7.524038461538462,
"grad_norm": 0.392578125,
"learning_rate": 3.508072110879804e-05,
"loss": 0.703,
"step": 1565
},
{
"epoch": 7.548076923076923,
"grad_norm": 0.447265625,
"learning_rate": 3.4444774059770536e-05,
"loss": 0.7064,
"step": 1570
},
{
"epoch": 7.572115384615385,
"grad_norm": 0.390625,
"learning_rate": 3.381344266038518e-05,
"loss": 0.7007,
"step": 1575
},
{
"epoch": 7.596153846153846,
"grad_norm": 0.388671875,
"learning_rate": 3.318677136178228e-05,
"loss": 0.7018,
"step": 1580
},
{
"epoch": 7.6201923076923075,
"grad_norm": 0.4921875,
"learning_rate": 3.2564804286991135e-05,
"loss": 0.7029,
"step": 1585
},
{
"epoch": 7.644230769230769,
"grad_norm": 0.40234375,
"learning_rate": 3.1947585227823394e-05,
"loss": 0.7023,
"step": 1590
},
{
"epoch": 7.668269230769231,
"grad_norm": 0.41796875,
"learning_rate": 3.1335157641789756e-05,
"loss": 0.7134,
"step": 1595
},
{
"epoch": 7.6923076923076925,
"grad_norm": 0.3984375,
"learning_rate": 3.072756464904006e-05,
"loss": 0.7034,
"step": 1600
},
{
"epoch": 7.716346153846154,
"grad_norm": 0.392578125,
"learning_rate": 3.0124849029327405e-05,
"loss": 0.7026,
"step": 1605
},
{
"epoch": 7.740384615384615,
"grad_norm": 0.39453125,
"learning_rate": 2.9527053218996037e-05,
"loss": 0.7046,
"step": 1610
},
{
"epoch": 7.764423076923077,
"grad_norm": 0.3671875,
"learning_rate": 2.8934219307993394e-05,
"loss": 0.7015,
"step": 1615
},
{
"epoch": 7.788461538461538,
"grad_norm": 0.376953125,
"learning_rate": 2.8346389036906828e-05,
"loss": 0.7023,
"step": 1620
},
{
"epoch": 7.8125,
"grad_norm": 0.3984375,
"learning_rate": 2.776360379402445e-05,
"loss": 0.704,
"step": 1625
},
{
"epoch": 7.836538461538462,
"grad_norm": 0.37109375,
"learning_rate": 2.7185904612421176e-05,
"loss": 0.6993,
"step": 1630
},
{
"epoch": 7.860576923076923,
"grad_norm": 0.361328125,
"learning_rate": 2.6613332167069638e-05,
"loss": 0.7017,
"step": 1635
},
{
"epoch": 7.884615384615385,
"grad_norm": 0.375,
"learning_rate": 2.6045926771976303e-05,
"loss": 0.7071,
"step": 1640
},
{
"epoch": 7.908653846153846,
"grad_norm": 0.36328125,
"learning_rate": 2.5483728377342984e-05,
"loss": 0.7057,
"step": 1645
},
{
"epoch": 7.9326923076923075,
"grad_norm": 0.353515625,
"learning_rate": 2.492677656675414e-05,
"loss": 0.7088,
"step": 1650
},
{
"epoch": 7.956730769230769,
"grad_norm": 0.40625,
"learning_rate": 2.4375110554389702e-05,
"loss": 0.6981,
"step": 1655
},
{
"epoch": 7.980769230769231,
"grad_norm": 0.3828125,
"learning_rate": 2.382876918226409e-05,
"loss": 0.7064,
"step": 1660
},
{
"epoch": 8.0,
"eval_loss": 2.4729323387145996,
"eval_runtime": 0.3036,
"eval_samples_per_second": 32.941,
"eval_steps_per_second": 3.294,
"step": 1664
},
{
"epoch": 8.004807692307692,
"grad_norm": 0.42578125,
"learning_rate": 2.328779091749145e-05,
"loss": 0.7012,
"step": 1665
},
{
"epoch": 8.028846153846153,
"grad_norm": 0.390625,
"learning_rate": 2.2752213849577188e-05,
"loss": 0.6971,
"step": 1670
},
{
"epoch": 8.052884615384615,
"grad_norm": 0.380859375,
"learning_rate": 2.2222075687736187e-05,
"loss": 0.7013,
"step": 1675
},
{
"epoch": 8.076923076923077,
"grad_norm": 0.37890625,
"learning_rate": 2.1697413758237784e-05,
"loss": 0.6927,
"step": 1680
},
{
"epoch": 8.100961538461538,
"grad_norm": 0.373046875,
"learning_rate": 2.1178265001777554e-05,
"loss": 0.69,
"step": 1685
},
{
"epoch": 8.125,
"grad_norm": 0.384765625,
"learning_rate": 2.0664665970876496e-05,
"loss": 0.6943,
"step": 1690
},
{
"epoch": 8.149038461538462,
"grad_norm": 0.3671875,
"learning_rate": 2.0156652827307364e-05,
"loss": 0.7043,
"step": 1695
},
{
"epoch": 8.173076923076923,
"grad_norm": 0.369140625,
"learning_rate": 1.965426133954854e-05,
"loss": 0.7023,
"step": 1700
},
{
"epoch": 8.197115384615385,
"grad_norm": 0.3671875,
"learning_rate": 1.9157526880265765e-05,
"loss": 0.7036,
"step": 1705
},
{
"epoch": 8.221153846153847,
"grad_norm": 0.369140625,
"learning_rate": 1.8666484423821373e-05,
"loss": 0.6978,
"step": 1710
},
{
"epoch": 8.245192307692308,
"grad_norm": 0.359375,
"learning_rate": 1.8181168543812066e-05,
"loss": 0.6973,
"step": 1715
},
{
"epoch": 8.26923076923077,
"grad_norm": 0.361328125,
"learning_rate": 1.7701613410634365e-05,
"loss": 0.6943,
"step": 1720
},
{
"epoch": 8.29326923076923,
"grad_norm": 0.40625,
"learning_rate": 1.7227852789078913e-05,
"loss": 0.6965,
"step": 1725
},
{
"epoch": 8.317307692307692,
"grad_norm": 0.365234375,
"learning_rate": 1.6759920035953093e-05,
"loss": 0.6942,
"step": 1730
},
{
"epoch": 8.341346153846153,
"grad_norm": 0.365234375,
"learning_rate": 1.6297848097732338e-05,
"loss": 0.7008,
"step": 1735
},
{
"epoch": 8.365384615384615,
"grad_norm": 0.41796875,
"learning_rate": 1.584166950824061e-05,
"loss": 0.7029,
"step": 1740
},
{
"epoch": 8.389423076923077,
"grad_norm": 0.359375,
"learning_rate": 1.5391416386359524e-05,
"loss": 0.695,
"step": 1745
},
{
"epoch": 8.413461538461538,
"grad_norm": 0.359375,
"learning_rate": 1.4947120433767047e-05,
"loss": 0.7025,
"step": 1750
},
{
"epoch": 8.4375,
"grad_norm": 0.373046875,
"learning_rate": 1.4508812932705363e-05,
"loss": 0.6916,
"step": 1755
},
{
"epoch": 8.461538461538462,
"grad_norm": 0.400390625,
"learning_rate": 1.4076524743778319e-05,
"loss": 0.7005,
"step": 1760
},
{
"epoch": 8.485576923076923,
"grad_norm": 0.36328125,
"learning_rate": 1.3650286303778714e-05,
"loss": 0.6944,
"step": 1765
},
{
"epoch": 8.509615384615385,
"grad_norm": 0.3671875,
"learning_rate": 1.3230127623545064e-05,
"loss": 0.6951,
"step": 1770
},
{
"epoch": 8.533653846153847,
"grad_norm": 0.375,
"learning_rate": 1.2816078285848799e-05,
"loss": 0.7039,
"step": 1775
},
{
"epoch": 8.557692307692308,
"grad_norm": 0.373046875,
"learning_rate": 1.2408167443311214e-05,
"loss": 0.6976,
"step": 1780
},
{
"epoch": 8.58173076923077,
"grad_norm": 0.3671875,
"learning_rate": 1.2006423816350977e-05,
"loss": 0.6949,
"step": 1785
},
{
"epoch": 8.60576923076923,
"grad_norm": 0.40625,
"learning_rate": 1.1610875691161915e-05,
"loss": 0.7008,
"step": 1790
},
{
"epoch": 8.629807692307692,
"grad_norm": 0.3671875,
"learning_rate": 1.1221550917721436e-05,
"loss": 0.693,
"step": 1795
},
{
"epoch": 8.653846153846153,
"grad_norm": 0.390625,
"learning_rate": 1.083847690782972e-05,
"loss": 0.6887,
"step": 1800
},
{
"epoch": 8.677884615384615,
"grad_norm": 0.365234375,
"learning_rate": 1.046168063317956e-05,
"loss": 0.7022,
"step": 1805
},
{
"epoch": 8.701923076923077,
"grad_norm": 0.375,
"learning_rate": 1.0091188623457415e-05,
"loss": 0.7058,
"step": 1810
},
{
"epoch": 8.725961538461538,
"grad_norm": 0.37109375,
"learning_rate": 9.727026964475483e-06,
"loss": 0.6948,
"step": 1815
},
{
"epoch": 8.75,
"grad_norm": 0.3828125,
"learning_rate": 9.369221296335006e-06,
"loss": 0.7025,
"step": 1820
},
{
"epoch": 8.774038461538462,
"grad_norm": 0.375,
"learning_rate": 9.017796811621049e-06,
"loss": 0.7007,
"step": 1825
},
{
"epoch": 8.798076923076923,
"grad_norm": 0.365234375,
"learning_rate": 8.672778253628621e-06,
"loss": 0.6992,
"step": 1830
},
{
"epoch": 8.822115384615385,
"grad_norm": 0.380859375,
"learning_rate": 8.334189914620671e-06,
"loss": 0.6934,
"step": 1835
},
{
"epoch": 8.846153846153847,
"grad_norm": 0.35546875,
"learning_rate": 8.002055634117578e-06,
"loss": 0.6955,
"step": 1840
},
{
"epoch": 8.870192307692308,
"grad_norm": 0.357421875,
"learning_rate": 7.67639879721872e-06,
"loss": 0.7001,
"step": 1845
},
{
"epoch": 8.89423076923077,
"grad_norm": 0.36328125,
"learning_rate": 7.357242332955916e-06,
"loss": 0.6982,
"step": 1850
},
{
"epoch": 8.91826923076923,
"grad_norm": 0.376953125,
"learning_rate": 7.0446087126790575e-06,
"loss": 0.702,
"step": 1855
},
{
"epoch": 8.942307692307692,
"grad_norm": 0.376953125,
"learning_rate": 6.738519948473976e-06,
"loss": 0.7033,
"step": 1860
},
{
"epoch": 8.966346153846153,
"grad_norm": 0.384765625,
"learning_rate": 6.4389975916125056e-06,
"loss": 0.6961,
"step": 1865
},
{
"epoch": 8.990384615384615,
"grad_norm": 0.359375,
"learning_rate": 6.146062731035129e-06,
"loss": 0.6934,
"step": 1870
},
{
"epoch": 9.0,
"eval_loss": 2.4781441688537598,
"eval_runtime": 0.2396,
"eval_samples_per_second": 41.728,
"eval_steps_per_second": 4.173,
"step": 1872
},
{
"epoch": 9.014423076923077,
"grad_norm": 0.349609375,
"learning_rate": 5.859735991866166e-06,
"loss": 0.6903,
"step": 1875
},
{
"epoch": 9.038461538461538,
"grad_norm": 0.375,
"learning_rate": 5.580037533961546e-06,
"loss": 0.6989,
"step": 1880
},
{
"epoch": 9.0625,
"grad_norm": 0.359375,
"learning_rate": 5.306987050489442e-06,
"loss": 0.6981,
"step": 1885
},
{
"epoch": 9.086538461538462,
"grad_norm": 0.369140625,
"learning_rate": 5.040603766543594e-06,
"loss": 0.6943,
"step": 1890
},
{
"epoch": 9.110576923076923,
"grad_norm": 0.36328125,
"learning_rate": 4.780906437789845e-06,
"loss": 0.6896,
"step": 1895
},
{
"epoch": 9.134615384615385,
"grad_norm": 0.369140625,
"learning_rate": 4.527913349145441e-06,
"loss": 0.6998,
"step": 1900
},
{
"epoch": 9.158653846153847,
"grad_norm": 0.388671875,
"learning_rate": 4.281642313491685e-06,
"loss": 0.6957,
"step": 1905
},
{
"epoch": 9.182692307692308,
"grad_norm": 0.380859375,
"learning_rate": 4.042110670419763e-06,
"loss": 0.7036,
"step": 1910
},
{
"epoch": 9.20673076923077,
"grad_norm": 0.373046875,
"learning_rate": 3.809335285009863e-06,
"loss": 0.7007,
"step": 1915
},
{
"epoch": 9.23076923076923,
"grad_norm": 0.3515625,
"learning_rate": 3.5833325466437694e-06,
"loss": 0.6963,
"step": 1920
},
{
"epoch": 9.254807692307692,
"grad_norm": 0.400390625,
"learning_rate": 3.3641183678508327e-06,
"loss": 0.6982,
"step": 1925
},
{
"epoch": 9.278846153846153,
"grad_norm": 0.353515625,
"learning_rate": 3.1517081831876737e-06,
"loss": 0.689,
"step": 1930
},
{
"epoch": 9.302884615384615,
"grad_norm": 0.361328125,
"learning_rate": 2.9461169481514005e-06,
"loss": 0.6964,
"step": 1935
},
{
"epoch": 9.326923076923077,
"grad_norm": 0.396484375,
"learning_rate": 2.7473591381266708e-06,
"loss": 0.6911,
"step": 1940
},
{
"epoch": 9.350961538461538,
"grad_norm": 0.359375,
"learning_rate": 2.55544874736644e-06,
"loss": 0.6924,
"step": 1945
},
{
"epoch": 9.375,
"grad_norm": 0.3671875,
"learning_rate": 2.3703992880066638e-06,
"loss": 0.6946,
"step": 1950
},
{
"epoch": 9.399038461538462,
"grad_norm": 0.365234375,
"learning_rate": 2.1922237891149667e-06,
"loss": 0.7009,
"step": 1955
},
{
"epoch": 9.423076923076923,
"grad_norm": 0.361328125,
"learning_rate": 2.0209347957732328e-06,
"loss": 0.693,
"step": 1960
},
{
"epoch": 9.447115384615385,
"grad_norm": 0.353515625,
"learning_rate": 1.8565443681943461e-06,
"loss": 0.6947,
"step": 1965
},
{
"epoch": 9.471153846153847,
"grad_norm": 0.36328125,
"learning_rate": 1.6990640808730696e-06,
"loss": 0.7001,
"step": 1970
},
{
"epoch": 9.495192307692308,
"grad_norm": 0.39453125,
"learning_rate": 1.5485050217710295e-06,
"loss": 0.6956,
"step": 1975
},
{
"epoch": 9.51923076923077,
"grad_norm": 0.376953125,
"learning_rate": 1.404877791536141e-06,
"loss": 0.6952,
"step": 1980
},
{
"epoch": 9.54326923076923,
"grad_norm": 0.380859375,
"learning_rate": 1.2681925027561382e-06,
"loss": 0.6965,
"step": 1985
},
{
"epoch": 9.567307692307692,
"grad_norm": 0.37109375,
"learning_rate": 1.1384587792465872e-06,
"loss": 0.6953,
"step": 1990
},
{
"epoch": 9.591346153846153,
"grad_norm": 0.388671875,
"learning_rate": 1.0156857553732857e-06,
"loss": 0.694,
"step": 1995
},
{
"epoch": 9.615384615384615,
"grad_norm": 0.36328125,
"learning_rate": 8.998820754091531e-07,
"loss": 0.692,
"step": 2000
},
{
"epoch": 9.639423076923077,
"grad_norm": 0.373046875,
"learning_rate": 7.910558929255851e-07,
"loss": 0.6951,
"step": 2005
},
{
"epoch": 9.663461538461538,
"grad_norm": 0.361328125,
"learning_rate": 6.892148702183133e-07,
"loss": 0.6955,
"step": 2010
},
{
"epoch": 9.6875,
"grad_norm": 0.361328125,
"learning_rate": 5.943661777680354e-07,
"loss": 0.6957,
"step": 2015
},
{
"epoch": 9.711538461538462,
"grad_norm": 0.359375,
"learning_rate": 5.065164937354428e-07,
"loss": 0.698,
"step": 2020
},
{
"epoch": 9.735576923076923,
"grad_norm": 0.3671875,
"learning_rate": 4.256720034910511e-07,
"loss": 0.6988,
"step": 2025
},
{
"epoch": 9.759615384615385,
"grad_norm": 0.40234375,
"learning_rate": 3.5183839917972697e-07,
"loss": 0.6933,
"step": 2030
},
{
"epoch": 9.783653846153847,
"grad_norm": 0.369140625,
"learning_rate": 2.850208793198861e-07,
"loss": 0.705,
"step": 2035
},
{
"epoch": 9.807692307692308,
"grad_norm": 0.3671875,
"learning_rate": 2.2522414843748618e-07,
"loss": 0.6993,
"step": 2040
},
{
"epoch": 9.83173076923077,
"grad_norm": 0.359375,
"learning_rate": 1.7245241673476965e-07,
"loss": 0.6974,
"step": 2045
},
{
"epoch": 9.85576923076923,
"grad_norm": 0.359375,
"learning_rate": 1.2670939979384512e-07,
"loss": 0.7062,
"step": 2050
},
{
"epoch": 9.879807692307692,
"grad_norm": 0.365234375,
"learning_rate": 8.799831831506344e-08,
"loss": 0.691,
"step": 2055
},
{
"epoch": 9.903846153846153,
"grad_norm": 0.359375,
"learning_rate": 5.632189789027687e-08,
"loss": 0.6951,
"step": 2060
},
{
"epoch": 9.927884615384615,
"grad_norm": 0.37890625,
"learning_rate": 3.168236881092579e-08,
"loss": 0.698,
"step": 2065
},
{
"epoch": 9.951923076923077,
"grad_norm": 0.33984375,
"learning_rate": 1.4081465910975588e-08,
"loss": 0.686,
"step": 2070
},
{
"epoch": 9.975961538461538,
"grad_norm": 0.37109375,
"learning_rate": 3.520428444825363e-09,
"loss": 0.7005,
"step": 2075
},
{
"epoch": 10.0,
"grad_norm": 0.369140625,
"learning_rate": 0.0,
"loss": 0.7018,
"step": 2080
},
{
"epoch": 10.0,
"eval_loss": 2.4814841747283936,
"eval_runtime": 0.2382,
"eval_samples_per_second": 41.987,
"eval_steps_per_second": 4.199,
"step": 2080
},
{
"epoch": 10.0,
"step": 2080,
"total_flos": 6.350169378683617e+18,
"train_loss": 1.6486573993013456,
"train_runtime": 5073.9705,
"train_samples_per_second": 26.214,
"train_steps_per_second": 0.41
}
],
"logging_steps": 5,
"max_steps": 2080,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"total_flos": 6.350169378683617e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}