Files
eng_100mb_baseline_seed3407/checkpoint-10000/trainer_state.json
ModelHub XC d1cda2f931 初始化项目,由ModelHub XC社区提供模型
Model: fpadovani/eng_100mb_baseline_seed3407
Source: Original Platform
2026-05-30 03:10:20 +08:00

14114 lines
319 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.492362982929021,
"eval_steps": 1000,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0022461814914645105,
"grad_norm": 54.0,
"learning_rate": 7.499999999999999e-07,
"loss": 10.989,
"step": 5
},
{
"epoch": 0.004492362982929021,
"grad_norm": 52.75,
"learning_rate": 1.4999999999999998e-06,
"loss": 10.984,
"step": 10
},
{
"epoch": 0.006738544474393531,
"grad_norm": 52.5,
"learning_rate": 2.2499999999999996e-06,
"loss": 10.9491,
"step": 15
},
{
"epoch": 0.008984725965858042,
"grad_norm": 50.25,
"learning_rate": 2.9999999999999997e-06,
"loss": 10.8608,
"step": 20
},
{
"epoch": 0.011230907457322551,
"grad_norm": 44.75,
"learning_rate": 3.7499999999999997e-06,
"loss": 10.7375,
"step": 25
},
{
"epoch": 0.013477088948787063,
"grad_norm": 38.0,
"learning_rate": 4.499999999999999e-06,
"loss": 10.5621,
"step": 30
},
{
"epoch": 0.015723270440251572,
"grad_norm": 25.5,
"learning_rate": 5.25e-06,
"loss": 10.3304,
"step": 35
},
{
"epoch": 0.017969451931716084,
"grad_norm": 19.25,
"learning_rate": 5.999999999999999e-06,
"loss": 10.1403,
"step": 40
},
{
"epoch": 0.02021563342318059,
"grad_norm": 13.8125,
"learning_rate": 6.749999999999999e-06,
"loss": 9.9521,
"step": 45
},
{
"epoch": 0.022461814914645103,
"grad_norm": 11.1875,
"learning_rate": 7.499999999999999e-06,
"loss": 9.843,
"step": 50
},
{
"epoch": 0.024707996406109614,
"grad_norm": 10.5,
"learning_rate": 8.249999999999999e-06,
"loss": 9.7584,
"step": 55
},
{
"epoch": 0.026954177897574125,
"grad_norm": 10.0625,
"learning_rate": 8.999999999999999e-06,
"loss": 9.7293,
"step": 60
},
{
"epoch": 0.029200359389038633,
"grad_norm": 9.1875,
"learning_rate": 9.75e-06,
"loss": 9.719,
"step": 65
},
{
"epoch": 0.031446540880503145,
"grad_norm": 8.9375,
"learning_rate": 1.05e-05,
"loss": 9.6908,
"step": 70
},
{
"epoch": 0.03369272237196765,
"grad_norm": 9.125,
"learning_rate": 1.1249999999999999e-05,
"loss": 9.6617,
"step": 75
},
{
"epoch": 0.03593890386343217,
"grad_norm": 9.0625,
"learning_rate": 1.1999999999999999e-05,
"loss": 9.6228,
"step": 80
},
{
"epoch": 0.038185085354896675,
"grad_norm": 9.125,
"learning_rate": 1.275e-05,
"loss": 9.6069,
"step": 85
},
{
"epoch": 0.04043126684636118,
"grad_norm": 9.3125,
"learning_rate": 1.3499999999999998e-05,
"loss": 9.5342,
"step": 90
},
{
"epoch": 0.0426774483378257,
"grad_norm": 8.9375,
"learning_rate": 1.4249999999999999e-05,
"loss": 9.5187,
"step": 95
},
{
"epoch": 0.044923629829290206,
"grad_norm": 9.125,
"learning_rate": 1.4999999999999999e-05,
"loss": 9.4719,
"step": 100
},
{
"epoch": 0.04716981132075472,
"grad_norm": 9.0,
"learning_rate": 1.5749999999999997e-05,
"loss": 9.4167,
"step": 105
},
{
"epoch": 0.04941599281221923,
"grad_norm": 8.9375,
"learning_rate": 1.6499999999999998e-05,
"loss": 9.3825,
"step": 110
},
{
"epoch": 0.051662174303683736,
"grad_norm": 8.75,
"learning_rate": 1.725e-05,
"loss": 9.3577,
"step": 115
},
{
"epoch": 0.05390835579514825,
"grad_norm": 8.625,
"learning_rate": 1.7999999999999997e-05,
"loss": 9.3387,
"step": 120
},
{
"epoch": 0.05615453728661276,
"grad_norm": 9.375,
"learning_rate": 1.875e-05,
"loss": 9.2947,
"step": 125
},
{
"epoch": 0.05840071877807727,
"grad_norm": 8.75,
"learning_rate": 1.95e-05,
"loss": 9.2177,
"step": 130
},
{
"epoch": 0.06064690026954178,
"grad_norm": 8.8125,
"learning_rate": 2.025e-05,
"loss": 9.1683,
"step": 135
},
{
"epoch": 0.06289308176100629,
"grad_norm": 9.875,
"learning_rate": 2.1e-05,
"loss": 9.1444,
"step": 140
},
{
"epoch": 0.0651392632524708,
"grad_norm": 9.625,
"learning_rate": 2.1749999999999997e-05,
"loss": 9.0632,
"step": 145
},
{
"epoch": 0.0673854447439353,
"grad_norm": 8.8125,
"learning_rate": 2.2499999999999998e-05,
"loss": 9.0828,
"step": 150
},
{
"epoch": 0.06963162623539983,
"grad_norm": 9.5625,
"learning_rate": 2.325e-05,
"loss": 9.0005,
"step": 155
},
{
"epoch": 0.07187780772686433,
"grad_norm": 11.1875,
"learning_rate": 2.3999999999999997e-05,
"loss": 8.9463,
"step": 160
},
{
"epoch": 0.07412398921832884,
"grad_norm": 9.3125,
"learning_rate": 2.475e-05,
"loss": 8.9145,
"step": 165
},
{
"epoch": 0.07637017070979335,
"grad_norm": 8.1875,
"learning_rate": 2.55e-05,
"loss": 8.8803,
"step": 170
},
{
"epoch": 0.07861635220125786,
"grad_norm": 7.65625,
"learning_rate": 2.6249999999999998e-05,
"loss": 8.8266,
"step": 175
},
{
"epoch": 0.08086253369272237,
"grad_norm": 7.78125,
"learning_rate": 2.6999999999999996e-05,
"loss": 8.7826,
"step": 180
},
{
"epoch": 0.08310871518418689,
"grad_norm": 8.875,
"learning_rate": 2.7749999999999997e-05,
"loss": 8.7463,
"step": 185
},
{
"epoch": 0.0853548966756514,
"grad_norm": 8.375,
"learning_rate": 2.8499999999999998e-05,
"loss": 8.6836,
"step": 190
},
{
"epoch": 0.0876010781671159,
"grad_norm": 8.5,
"learning_rate": 2.925e-05,
"loss": 8.6827,
"step": 195
},
{
"epoch": 0.08984725965858041,
"grad_norm": 8.25,
"learning_rate": 2.9999999999999997e-05,
"loss": 8.588,
"step": 200
},
{
"epoch": 0.09209344115004492,
"grad_norm": 8.3125,
"learning_rate": 3.0749999999999995e-05,
"loss": 8.5417,
"step": 205
},
{
"epoch": 0.09433962264150944,
"grad_norm": 9.4375,
"learning_rate": 3.149999999999999e-05,
"loss": 8.5287,
"step": 210
},
{
"epoch": 0.09658580413297395,
"grad_norm": 8.125,
"learning_rate": 3.225e-05,
"loss": 8.49,
"step": 215
},
{
"epoch": 0.09883198562443846,
"grad_norm": 7.59375,
"learning_rate": 3.2999999999999996e-05,
"loss": 8.4025,
"step": 220
},
{
"epoch": 0.10107816711590296,
"grad_norm": 8.75,
"learning_rate": 3.375e-05,
"loss": 8.3121,
"step": 225
},
{
"epoch": 0.10332434860736747,
"grad_norm": 7.8125,
"learning_rate": 3.45e-05,
"loss": 8.2635,
"step": 230
},
{
"epoch": 0.10557053009883198,
"grad_norm": 8.3125,
"learning_rate": 3.5249999999999996e-05,
"loss": 8.2691,
"step": 235
},
{
"epoch": 0.1078167115902965,
"grad_norm": 9.4375,
"learning_rate": 3.5999999999999994e-05,
"loss": 8.1828,
"step": 240
},
{
"epoch": 0.11006289308176101,
"grad_norm": 7.0625,
"learning_rate": 3.675e-05,
"loss": 8.0901,
"step": 245
},
{
"epoch": 0.11230907457322552,
"grad_norm": 8.125,
"learning_rate": 3.75e-05,
"loss": 8.0418,
"step": 250
},
{
"epoch": 0.11455525606469003,
"grad_norm": 7.0625,
"learning_rate": 3.8249999999999995e-05,
"loss": 8.0148,
"step": 255
},
{
"epoch": 0.11680143755615453,
"grad_norm": 7.5625,
"learning_rate": 3.9e-05,
"loss": 7.9943,
"step": 260
},
{
"epoch": 0.11904761904761904,
"grad_norm": 7.0625,
"learning_rate": 3.975e-05,
"loss": 7.852,
"step": 265
},
{
"epoch": 0.12129380053908356,
"grad_norm": 6.6875,
"learning_rate": 4.05e-05,
"loss": 7.8506,
"step": 270
},
{
"epoch": 0.12353998203054807,
"grad_norm": 7.46875,
"learning_rate": 4.125e-05,
"loss": 7.7912,
"step": 275
},
{
"epoch": 0.12578616352201258,
"grad_norm": 6.0,
"learning_rate": 4.2e-05,
"loss": 7.7331,
"step": 280
},
{
"epoch": 0.1280323450134771,
"grad_norm": 6.75,
"learning_rate": 4.2749999999999996e-05,
"loss": 7.6362,
"step": 285
},
{
"epoch": 0.1302785265049416,
"grad_norm": 5.9375,
"learning_rate": 4.3499999999999993e-05,
"loss": 7.5867,
"step": 290
},
{
"epoch": 0.13252470799640612,
"grad_norm": 6.40625,
"learning_rate": 4.424999999999999e-05,
"loss": 7.5268,
"step": 295
},
{
"epoch": 0.1347708894878706,
"grad_norm": 5.71875,
"learning_rate": 4.4999999999999996e-05,
"loss": 7.5554,
"step": 300
},
{
"epoch": 0.13701707097933513,
"grad_norm": 5.5,
"learning_rate": 4.5749999999999994e-05,
"loss": 7.4486,
"step": 305
},
{
"epoch": 0.13926325247079965,
"grad_norm": 5.15625,
"learning_rate": 4.65e-05,
"loss": 7.4554,
"step": 310
},
{
"epoch": 0.14150943396226415,
"grad_norm": 4.84375,
"learning_rate": 4.7249999999999997e-05,
"loss": 7.3681,
"step": 315
},
{
"epoch": 0.14375561545372867,
"grad_norm": 7.625,
"learning_rate": 4.7999999999999994e-05,
"loss": 7.2977,
"step": 320
},
{
"epoch": 0.14600179694519316,
"grad_norm": 5.25,
"learning_rate": 4.875e-05,
"loss": 7.2572,
"step": 325
},
{
"epoch": 0.14824797843665768,
"grad_norm": 5.125,
"learning_rate": 4.95e-05,
"loss": 7.322,
"step": 330
},
{
"epoch": 0.15049415992812218,
"grad_norm": 4.96875,
"learning_rate": 5.025e-05,
"loss": 7.2646,
"step": 335
},
{
"epoch": 0.1527403414195867,
"grad_norm": 4.96875,
"learning_rate": 5.1e-05,
"loss": 7.32,
"step": 340
},
{
"epoch": 0.15498652291105122,
"grad_norm": 5.3125,
"learning_rate": 5.174999999999999e-05,
"loss": 7.209,
"step": 345
},
{
"epoch": 0.15723270440251572,
"grad_norm": 5.40625,
"learning_rate": 5.2499999999999995e-05,
"loss": 7.1961,
"step": 350
},
{
"epoch": 0.15947888589398024,
"grad_norm": 4.15625,
"learning_rate": 5.324999999999999e-05,
"loss": 7.2062,
"step": 355
},
{
"epoch": 0.16172506738544473,
"grad_norm": 4.65625,
"learning_rate": 5.399999999999999e-05,
"loss": 7.1401,
"step": 360
},
{
"epoch": 0.16397124887690925,
"grad_norm": 5.71875,
"learning_rate": 5.4749999999999996e-05,
"loss": 7.1402,
"step": 365
},
{
"epoch": 0.16621743036837378,
"grad_norm": 5.34375,
"learning_rate": 5.5499999999999994e-05,
"loss": 7.073,
"step": 370
},
{
"epoch": 0.16846361185983827,
"grad_norm": 5.96875,
"learning_rate": 5.625e-05,
"loss": 7.115,
"step": 375
},
{
"epoch": 0.1707097933513028,
"grad_norm": 4.625,
"learning_rate": 5.6999999999999996e-05,
"loss": 7.1363,
"step": 380
},
{
"epoch": 0.17295597484276728,
"grad_norm": 5.34375,
"learning_rate": 5.7749999999999994e-05,
"loss": 7.1075,
"step": 385
},
{
"epoch": 0.1752021563342318,
"grad_norm": 4.46875,
"learning_rate": 5.85e-05,
"loss": 7.0746,
"step": 390
},
{
"epoch": 0.17744833782569633,
"grad_norm": 4.53125,
"learning_rate": 5.925e-05,
"loss": 7.0877,
"step": 395
},
{
"epoch": 0.17969451931716082,
"grad_norm": 4.6875,
"learning_rate": 5.9999999999999995e-05,
"loss": 7.033,
"step": 400
},
{
"epoch": 0.18194070080862534,
"grad_norm": 4.9375,
"learning_rate": 6.075e-05,
"loss": 7.0603,
"step": 405
},
{
"epoch": 0.18418688230008984,
"grad_norm": 4.8125,
"learning_rate": 6.149999999999999e-05,
"loss": 7.0149,
"step": 410
},
{
"epoch": 0.18643306379155436,
"grad_norm": 4.6875,
"learning_rate": 6.225e-05,
"loss": 6.9823,
"step": 415
},
{
"epoch": 0.18867924528301888,
"grad_norm": 5.65625,
"learning_rate": 6.299999999999999e-05,
"loss": 7.0107,
"step": 420
},
{
"epoch": 0.19092542677448338,
"grad_norm": 4.5625,
"learning_rate": 6.374999999999999e-05,
"loss": 7.0235,
"step": 425
},
{
"epoch": 0.1931716082659479,
"grad_norm": 4.71875,
"learning_rate": 6.45e-05,
"loss": 6.9444,
"step": 430
},
{
"epoch": 0.1954177897574124,
"grad_norm": 4.6875,
"learning_rate": 6.525e-05,
"loss": 6.9067,
"step": 435
},
{
"epoch": 0.1976639712488769,
"grad_norm": 4.375,
"learning_rate": 6.599999999999999e-05,
"loss": 6.9952,
"step": 440
},
{
"epoch": 0.1999101527403414,
"grad_norm": 4.46875,
"learning_rate": 6.675e-05,
"loss": 6.8992,
"step": 445
},
{
"epoch": 0.20215633423180593,
"grad_norm": 4.875,
"learning_rate": 6.75e-05,
"loss": 6.931,
"step": 450
},
{
"epoch": 0.20440251572327045,
"grad_norm": 4.6875,
"learning_rate": 6.824999999999999e-05,
"loss": 6.9036,
"step": 455
},
{
"epoch": 0.20664869721473494,
"grad_norm": 4.75,
"learning_rate": 6.9e-05,
"loss": 6.9332,
"step": 460
},
{
"epoch": 0.20889487870619947,
"grad_norm": 4.25,
"learning_rate": 6.975e-05,
"loss": 7.0612,
"step": 465
},
{
"epoch": 0.21114106019766396,
"grad_norm": 4.59375,
"learning_rate": 7.049999999999999e-05,
"loss": 6.8777,
"step": 470
},
{
"epoch": 0.21338724168912848,
"grad_norm": 4.59375,
"learning_rate": 7.125e-05,
"loss": 6.8593,
"step": 475
},
{
"epoch": 0.215633423180593,
"grad_norm": 5.1875,
"learning_rate": 7.199999999999999e-05,
"loss": 6.9541,
"step": 480
},
{
"epoch": 0.2178796046720575,
"grad_norm": 4.65625,
"learning_rate": 7.274999999999999e-05,
"loss": 6.878,
"step": 485
},
{
"epoch": 0.22012578616352202,
"grad_norm": 5.1875,
"learning_rate": 7.35e-05,
"loss": 6.8284,
"step": 490
},
{
"epoch": 0.2223719676549865,
"grad_norm": 3.9375,
"learning_rate": 7.424999999999999e-05,
"loss": 6.8567,
"step": 495
},
{
"epoch": 0.22461814914645103,
"grad_norm": 5.1875,
"learning_rate": 7.5e-05,
"loss": 6.8235,
"step": 500
},
{
"epoch": 0.22686433063791556,
"grad_norm": 4.65625,
"learning_rate": 7.575e-05,
"loss": 6.8903,
"step": 505
},
{
"epoch": 0.22911051212938005,
"grad_norm": 5.875,
"learning_rate": 7.649999999999999e-05,
"loss": 6.8404,
"step": 510
},
{
"epoch": 0.23135669362084457,
"grad_norm": 5.0625,
"learning_rate": 7.725e-05,
"loss": 6.8318,
"step": 515
},
{
"epoch": 0.23360287511230907,
"grad_norm": 4.5625,
"learning_rate": 7.8e-05,
"loss": 6.8522,
"step": 520
},
{
"epoch": 0.2358490566037736,
"grad_norm": 5.03125,
"learning_rate": 7.874999999999999e-05,
"loss": 6.859,
"step": 525
},
{
"epoch": 0.23809523809523808,
"grad_norm": 4.71875,
"learning_rate": 7.95e-05,
"loss": 6.8336,
"step": 530
},
{
"epoch": 0.2403414195867026,
"grad_norm": 4.875,
"learning_rate": 8.025e-05,
"loss": 6.7897,
"step": 535
},
{
"epoch": 0.24258760107816713,
"grad_norm": 4.375,
"learning_rate": 8.1e-05,
"loss": 6.7873,
"step": 540
},
{
"epoch": 0.24483378256963162,
"grad_norm": 4.34375,
"learning_rate": 8.175e-05,
"loss": 6.7691,
"step": 545
},
{
"epoch": 0.24707996406109614,
"grad_norm": 4.40625,
"learning_rate": 8.25e-05,
"loss": 6.8252,
"step": 550
},
{
"epoch": 0.24932614555256064,
"grad_norm": 4.6875,
"learning_rate": 8.325e-05,
"loss": 6.8071,
"step": 555
},
{
"epoch": 0.25157232704402516,
"grad_norm": 4.65625,
"learning_rate": 8.4e-05,
"loss": 6.7156,
"step": 560
},
{
"epoch": 0.25381850853548965,
"grad_norm": 4.875,
"learning_rate": 8.474999999999999e-05,
"loss": 6.8189,
"step": 565
},
{
"epoch": 0.2560646900269542,
"grad_norm": 4.53125,
"learning_rate": 8.549999999999999e-05,
"loss": 6.8159,
"step": 570
},
{
"epoch": 0.2583108715184187,
"grad_norm": 3.75,
"learning_rate": 8.624999999999998e-05,
"loss": 6.847,
"step": 575
},
{
"epoch": 0.2605570530098832,
"grad_norm": 4.71875,
"learning_rate": 8.699999999999999e-05,
"loss": 6.7576,
"step": 580
},
{
"epoch": 0.2628032345013477,
"grad_norm": 5.375,
"learning_rate": 8.774999999999999e-05,
"loss": 6.7211,
"step": 585
},
{
"epoch": 0.26504941599281223,
"grad_norm": 4.875,
"learning_rate": 8.849999999999998e-05,
"loss": 6.7255,
"step": 590
},
{
"epoch": 0.2672955974842767,
"grad_norm": 4.71875,
"learning_rate": 8.924999999999999e-05,
"loss": 6.6598,
"step": 595
},
{
"epoch": 0.2695417789757412,
"grad_norm": 4.25,
"learning_rate": 8.999999999999999e-05,
"loss": 6.7735,
"step": 600
},
{
"epoch": 0.27178796046720577,
"grad_norm": 4.3125,
"learning_rate": 9.074999999999998e-05,
"loss": 6.7253,
"step": 605
},
{
"epoch": 0.27403414195867026,
"grad_norm": 4.8125,
"learning_rate": 9.149999999999999e-05,
"loss": 6.6825,
"step": 610
},
{
"epoch": 0.27628032345013476,
"grad_norm": 4.40625,
"learning_rate": 9.224999999999999e-05,
"loss": 6.7523,
"step": 615
},
{
"epoch": 0.2785265049415993,
"grad_norm": 4.46875,
"learning_rate": 9.3e-05,
"loss": 6.7212,
"step": 620
},
{
"epoch": 0.2807726864330638,
"grad_norm": 4.875,
"learning_rate": 9.374999999999999e-05,
"loss": 6.7052,
"step": 625
},
{
"epoch": 0.2830188679245283,
"grad_norm": 4.6875,
"learning_rate": 9.449999999999999e-05,
"loss": 6.7031,
"step": 630
},
{
"epoch": 0.2852650494159928,
"grad_norm": 4.1875,
"learning_rate": 9.525e-05,
"loss": 6.7163,
"step": 635
},
{
"epoch": 0.28751123090745734,
"grad_norm": 4.15625,
"learning_rate": 9.599999999999999e-05,
"loss": 6.7148,
"step": 640
},
{
"epoch": 0.28975741239892183,
"grad_norm": 3.78125,
"learning_rate": 9.675e-05,
"loss": 6.7027,
"step": 645
},
{
"epoch": 0.2920035938903863,
"grad_norm": 4.375,
"learning_rate": 9.75e-05,
"loss": 6.6511,
"step": 650
},
{
"epoch": 0.2942497753818509,
"grad_norm": 4.0625,
"learning_rate": 9.824999999999999e-05,
"loss": 6.704,
"step": 655
},
{
"epoch": 0.29649595687331537,
"grad_norm": 4.09375,
"learning_rate": 9.9e-05,
"loss": 6.689,
"step": 660
},
{
"epoch": 0.29874213836477986,
"grad_norm": 3.875,
"learning_rate": 9.975e-05,
"loss": 6.6784,
"step": 665
},
{
"epoch": 0.30098831985624436,
"grad_norm": 4.5,
"learning_rate": 0.0001005,
"loss": 6.597,
"step": 670
},
{
"epoch": 0.3032345013477089,
"grad_norm": 4.3125,
"learning_rate": 0.00010125,
"loss": 6.6198,
"step": 675
},
{
"epoch": 0.3054806828391734,
"grad_norm": 4.03125,
"learning_rate": 0.000102,
"loss": 6.6226,
"step": 680
},
{
"epoch": 0.3077268643306379,
"grad_norm": 4.03125,
"learning_rate": 0.00010275,
"loss": 6.627,
"step": 685
},
{
"epoch": 0.30997304582210244,
"grad_norm": 5.1875,
"learning_rate": 0.00010349999999999998,
"loss": 6.6003,
"step": 690
},
{
"epoch": 0.31221922731356694,
"grad_norm": 3.640625,
"learning_rate": 0.00010424999999999999,
"loss": 6.5845,
"step": 695
},
{
"epoch": 0.31446540880503143,
"grad_norm": 4.4375,
"learning_rate": 0.00010499999999999999,
"loss": 6.6143,
"step": 700
},
{
"epoch": 0.316711590296496,
"grad_norm": 4.90625,
"learning_rate": 0.00010574999999999998,
"loss": 6.6305,
"step": 705
},
{
"epoch": 0.3189577717879605,
"grad_norm": 4.3125,
"learning_rate": 0.00010649999999999999,
"loss": 6.5312,
"step": 710
},
{
"epoch": 0.32120395327942497,
"grad_norm": 4.15625,
"learning_rate": 0.00010724999999999999,
"loss": 6.63,
"step": 715
},
{
"epoch": 0.32345013477088946,
"grad_norm": 4.53125,
"learning_rate": 0.00010799999999999998,
"loss": 6.564,
"step": 720
},
{
"epoch": 0.325696316262354,
"grad_norm": 4.03125,
"learning_rate": 0.00010874999999999999,
"loss": 6.6572,
"step": 725
},
{
"epoch": 0.3279424977538185,
"grad_norm": 4.40625,
"learning_rate": 0.00010949999999999999,
"loss": 6.5728,
"step": 730
},
{
"epoch": 0.330188679245283,
"grad_norm": 4.34375,
"learning_rate": 0.00011024999999999998,
"loss": 6.5245,
"step": 735
},
{
"epoch": 0.33243486073674755,
"grad_norm": 5.5,
"learning_rate": 0.00011099999999999999,
"loss": 6.5883,
"step": 740
},
{
"epoch": 0.33468104222821204,
"grad_norm": 5.53125,
"learning_rate": 0.00011174999999999999,
"loss": 6.5549,
"step": 745
},
{
"epoch": 0.33692722371967654,
"grad_norm": 4.40625,
"learning_rate": 0.0001125,
"loss": 6.5269,
"step": 750
},
{
"epoch": 0.33917340521114103,
"grad_norm": 4.65625,
"learning_rate": 0.00011324999999999999,
"loss": 6.5262,
"step": 755
},
{
"epoch": 0.3414195867026056,
"grad_norm": 4.25,
"learning_rate": 0.00011399999999999999,
"loss": 6.4958,
"step": 760
},
{
"epoch": 0.3436657681940701,
"grad_norm": 4.34375,
"learning_rate": 0.00011475,
"loss": 6.4719,
"step": 765
},
{
"epoch": 0.34591194968553457,
"grad_norm": 3.828125,
"learning_rate": 0.00011549999999999999,
"loss": 6.4948,
"step": 770
},
{
"epoch": 0.3481581311769991,
"grad_norm": 3.890625,
"learning_rate": 0.00011624999999999999,
"loss": 6.5652,
"step": 775
},
{
"epoch": 0.3504043126684636,
"grad_norm": 3.828125,
"learning_rate": 0.000117,
"loss": 6.633,
"step": 780
},
{
"epoch": 0.3526504941599281,
"grad_norm": 3.78125,
"learning_rate": 0.00011774999999999999,
"loss": 6.4617,
"step": 785
},
{
"epoch": 0.35489667565139266,
"grad_norm": 3.9375,
"learning_rate": 0.0001185,
"loss": 6.524,
"step": 790
},
{
"epoch": 0.35714285714285715,
"grad_norm": 7.25,
"learning_rate": 0.00011925,
"loss": 6.4985,
"step": 795
},
{
"epoch": 0.35938903863432164,
"grad_norm": 3.828125,
"learning_rate": 0.00011999999999999999,
"loss": 6.4988,
"step": 800
},
{
"epoch": 0.36163522012578614,
"grad_norm": 5.125,
"learning_rate": 0.00012075,
"loss": 6.5393,
"step": 805
},
{
"epoch": 0.3638814016172507,
"grad_norm": 4.90625,
"learning_rate": 0.0001215,
"loss": 6.4869,
"step": 810
},
{
"epoch": 0.3661275831087152,
"grad_norm": 4.1875,
"learning_rate": 0.00012225,
"loss": 6.4419,
"step": 815
},
{
"epoch": 0.3683737646001797,
"grad_norm": 3.765625,
"learning_rate": 0.00012299999999999998,
"loss": 6.574,
"step": 820
},
{
"epoch": 0.3706199460916442,
"grad_norm": 3.796875,
"learning_rate": 0.00012374999999999997,
"loss": 6.5063,
"step": 825
},
{
"epoch": 0.3728661275831087,
"grad_norm": 3.734375,
"learning_rate": 0.0001245,
"loss": 6.5404,
"step": 830
},
{
"epoch": 0.3751123090745732,
"grad_norm": 3.65625,
"learning_rate": 0.00012524999999999998,
"loss": 6.4726,
"step": 835
},
{
"epoch": 0.37735849056603776,
"grad_norm": 4.0,
"learning_rate": 0.00012599999999999997,
"loss": 6.4099,
"step": 840
},
{
"epoch": 0.37960467205750226,
"grad_norm": 4.25,
"learning_rate": 0.00012675,
"loss": 6.3966,
"step": 845
},
{
"epoch": 0.38185085354896675,
"grad_norm": 3.828125,
"learning_rate": 0.00012749999999999998,
"loss": 6.4607,
"step": 850
},
{
"epoch": 0.38409703504043125,
"grad_norm": 4.28125,
"learning_rate": 0.00012824999999999997,
"loss": 6.4718,
"step": 855
},
{
"epoch": 0.3863432165318958,
"grad_norm": 4.71875,
"learning_rate": 0.000129,
"loss": 6.4569,
"step": 860
},
{
"epoch": 0.3885893980233603,
"grad_norm": 4.375,
"learning_rate": 0.00012974999999999998,
"loss": 6.3576,
"step": 865
},
{
"epoch": 0.3908355795148248,
"grad_norm": 4.65625,
"learning_rate": 0.0001305,
"loss": 6.4259,
"step": 870
},
{
"epoch": 0.39308176100628933,
"grad_norm": 4.96875,
"learning_rate": 0.00013125,
"loss": 6.3831,
"step": 875
},
{
"epoch": 0.3953279424977538,
"grad_norm": 3.90625,
"learning_rate": 0.00013199999999999998,
"loss": 6.4086,
"step": 880
},
{
"epoch": 0.3975741239892183,
"grad_norm": 3.75,
"learning_rate": 0.00013275,
"loss": 6.3207,
"step": 885
},
{
"epoch": 0.3998203054806828,
"grad_norm": 4.28125,
"learning_rate": 0.0001335,
"loss": 6.4129,
"step": 890
},
{
"epoch": 0.40206648697214736,
"grad_norm": 3.8125,
"learning_rate": 0.00013424999999999998,
"loss": 6.4397,
"step": 895
},
{
"epoch": 0.40431266846361186,
"grad_norm": 3.921875,
"learning_rate": 0.000135,
"loss": 6.4104,
"step": 900
},
{
"epoch": 0.40655884995507635,
"grad_norm": 3.984375,
"learning_rate": 0.00013575,
"loss": 6.3327,
"step": 905
},
{
"epoch": 0.4088050314465409,
"grad_norm": 3.859375,
"learning_rate": 0.00013649999999999998,
"loss": 6.3965,
"step": 910
},
{
"epoch": 0.4110512129380054,
"grad_norm": 4.03125,
"learning_rate": 0.00013725,
"loss": 6.3614,
"step": 915
},
{
"epoch": 0.4132973944294699,
"grad_norm": 3.734375,
"learning_rate": 0.000138,
"loss": 6.3743,
"step": 920
},
{
"epoch": 0.41554357592093444,
"grad_norm": 3.984375,
"learning_rate": 0.00013874999999999998,
"loss": 6.4228,
"step": 925
},
{
"epoch": 0.41778975741239893,
"grad_norm": 4.03125,
"learning_rate": 0.0001395,
"loss": 6.4047,
"step": 930
},
{
"epoch": 0.4200359389038634,
"grad_norm": 3.984375,
"learning_rate": 0.00014025,
"loss": 6.3634,
"step": 935
},
{
"epoch": 0.4222821203953279,
"grad_norm": 4.0,
"learning_rate": 0.00014099999999999998,
"loss": 6.3866,
"step": 940
},
{
"epoch": 0.42452830188679247,
"grad_norm": 3.796875,
"learning_rate": 0.00014174999999999998,
"loss": 6.3599,
"step": 945
},
{
"epoch": 0.42677448337825696,
"grad_norm": 4.03125,
"learning_rate": 0.0001425,
"loss": 6.3422,
"step": 950
},
{
"epoch": 0.42902066486972146,
"grad_norm": 4.15625,
"learning_rate": 0.00014324999999999999,
"loss": 6.2791,
"step": 955
},
{
"epoch": 0.431266846361186,
"grad_norm": 3.96875,
"learning_rate": 0.00014399999999999998,
"loss": 6.3505,
"step": 960
},
{
"epoch": 0.4335130278526505,
"grad_norm": 4.5,
"learning_rate": 0.00014475,
"loss": 6.3671,
"step": 965
},
{
"epoch": 0.435759209344115,
"grad_norm": 3.65625,
"learning_rate": 0.00014549999999999999,
"loss": 6.318,
"step": 970
},
{
"epoch": 0.4380053908355795,
"grad_norm": 4.28125,
"learning_rate": 0.00014624999999999998,
"loss": 6.3299,
"step": 975
},
{
"epoch": 0.44025157232704404,
"grad_norm": 3.578125,
"learning_rate": 0.000147,
"loss": 6.4073,
"step": 980
},
{
"epoch": 0.44249775381850853,
"grad_norm": 3.734375,
"learning_rate": 0.00014774999999999999,
"loss": 6.4377,
"step": 985
},
{
"epoch": 0.444743935309973,
"grad_norm": 3.765625,
"learning_rate": 0.00014849999999999998,
"loss": 6.2784,
"step": 990
},
{
"epoch": 0.4469901168014376,
"grad_norm": 3.953125,
"learning_rate": 0.00014925,
"loss": 6.2901,
"step": 995
},
{
"epoch": 0.44923629829290207,
"grad_norm": 4.375,
"learning_rate": 0.00015,
"loss": 6.2973,
"step": 1000
},
{
"epoch": 0.44923629829290207,
"eval_loss": 6.229096412658691,
"eval_runtime": 16.2469,
"eval_samples_per_second": 1908.854,
"eval_steps_per_second": 238.63,
"step": 1000
},
{
"epoch": 0.45148247978436656,
"grad_norm": 3.78125,
"learning_rate": 0.00015074999999999998,
"loss": 6.3253,
"step": 1005
},
{
"epoch": 0.4537286612758311,
"grad_norm": 3.953125,
"learning_rate": 0.0001515,
"loss": 6.2906,
"step": 1010
},
{
"epoch": 0.4559748427672956,
"grad_norm": 3.90625,
"learning_rate": 0.00015224999999999996,
"loss": 6.3351,
"step": 1015
},
{
"epoch": 0.4582210242587601,
"grad_norm": 3.6875,
"learning_rate": 0.00015299999999999998,
"loss": 6.368,
"step": 1020
},
{
"epoch": 0.4604672057502246,
"grad_norm": 3.796875,
"learning_rate": 0.00015374999999999997,
"loss": 6.3008,
"step": 1025
},
{
"epoch": 0.46271338724168914,
"grad_norm": 3.703125,
"learning_rate": 0.0001545,
"loss": 6.283,
"step": 1030
},
{
"epoch": 0.46495956873315364,
"grad_norm": 3.734375,
"learning_rate": 0.00015524999999999998,
"loss": 6.3212,
"step": 1035
},
{
"epoch": 0.46720575022461813,
"grad_norm": 4.15625,
"learning_rate": 0.000156,
"loss": 6.2874,
"step": 1040
},
{
"epoch": 0.4694519317160827,
"grad_norm": 3.484375,
"learning_rate": 0.00015675,
"loss": 6.2944,
"step": 1045
},
{
"epoch": 0.4716981132075472,
"grad_norm": 4.3125,
"learning_rate": 0.00015749999999999998,
"loss": 6.3099,
"step": 1050
},
{
"epoch": 0.47394429469901167,
"grad_norm": 3.734375,
"learning_rate": 0.00015824999999999997,
"loss": 6.2531,
"step": 1055
},
{
"epoch": 0.47619047619047616,
"grad_norm": 3.609375,
"learning_rate": 0.000159,
"loss": 6.2326,
"step": 1060
},
{
"epoch": 0.4784366576819407,
"grad_norm": 3.8125,
"learning_rate": 0.00015974999999999998,
"loss": 6.2059,
"step": 1065
},
{
"epoch": 0.4806828391734052,
"grad_norm": 3.625,
"learning_rate": 0.0001605,
"loss": 6.2798,
"step": 1070
},
{
"epoch": 0.4829290206648697,
"grad_norm": 3.890625,
"learning_rate": 0.00016125,
"loss": 6.2814,
"step": 1075
},
{
"epoch": 0.48517520215633425,
"grad_norm": 3.84375,
"learning_rate": 0.000162,
"loss": 6.1955,
"step": 1080
},
{
"epoch": 0.48742138364779874,
"grad_norm": 4.0,
"learning_rate": 0.00016274999999999997,
"loss": 6.3142,
"step": 1085
},
{
"epoch": 0.48966756513926324,
"grad_norm": 3.71875,
"learning_rate": 0.0001635,
"loss": 6.193,
"step": 1090
},
{
"epoch": 0.4919137466307278,
"grad_norm": 4.0,
"learning_rate": 0.00016424999999999998,
"loss": 6.26,
"step": 1095
},
{
"epoch": 0.4941599281221923,
"grad_norm": 4.0625,
"learning_rate": 0.000165,
"loss": 6.2443,
"step": 1100
},
{
"epoch": 0.4964061096136568,
"grad_norm": 3.671875,
"learning_rate": 0.00016575,
"loss": 6.2278,
"step": 1105
},
{
"epoch": 0.49865229110512127,
"grad_norm": 3.6875,
"learning_rate": 0.0001665,
"loss": 6.2254,
"step": 1110
},
{
"epoch": 0.5008984725965858,
"grad_norm": 3.921875,
"learning_rate": 0.00016724999999999997,
"loss": 6.3325,
"step": 1115
},
{
"epoch": 0.5031446540880503,
"grad_norm": 3.921875,
"learning_rate": 0.000168,
"loss": 6.186,
"step": 1120
},
{
"epoch": 0.5053908355795148,
"grad_norm": 3.859375,
"learning_rate": 0.00016874999999999998,
"loss": 6.2389,
"step": 1125
},
{
"epoch": 0.5076370170709793,
"grad_norm": 4.71875,
"learning_rate": 0.00016949999999999997,
"loss": 6.1268,
"step": 1130
},
{
"epoch": 0.5098831985624438,
"grad_norm": 3.90625,
"learning_rate": 0.00017025,
"loss": 6.1445,
"step": 1135
},
{
"epoch": 0.5121293800539084,
"grad_norm": 3.484375,
"learning_rate": 0.00017099999999999998,
"loss": 6.1658,
"step": 1140
},
{
"epoch": 0.5143755615453729,
"grad_norm": 3.78125,
"learning_rate": 0.00017175,
"loss": 6.1832,
"step": 1145
},
{
"epoch": 0.5166217430368374,
"grad_norm": 3.96875,
"learning_rate": 0.00017249999999999996,
"loss": 6.1621,
"step": 1150
},
{
"epoch": 0.5188679245283019,
"grad_norm": 3.765625,
"learning_rate": 0.00017324999999999998,
"loss": 6.22,
"step": 1155
},
{
"epoch": 0.5211141060197664,
"grad_norm": 3.890625,
"learning_rate": 0.00017399999999999997,
"loss": 6.1432,
"step": 1160
},
{
"epoch": 0.5233602875112309,
"grad_norm": 3.59375,
"learning_rate": 0.00017475,
"loss": 6.1223,
"step": 1165
},
{
"epoch": 0.5256064690026954,
"grad_norm": 3.28125,
"learning_rate": 0.00017549999999999998,
"loss": 6.1839,
"step": 1170
},
{
"epoch": 0.52785265049416,
"grad_norm": 3.9375,
"learning_rate": 0.00017625,
"loss": 6.2021,
"step": 1175
},
{
"epoch": 0.5300988319856245,
"grad_norm": 4.03125,
"learning_rate": 0.00017699999999999997,
"loss": 6.1947,
"step": 1180
},
{
"epoch": 0.532345013477089,
"grad_norm": 4.5,
"learning_rate": 0.00017774999999999998,
"loss": 6.1474,
"step": 1185
},
{
"epoch": 0.5345911949685535,
"grad_norm": 3.671875,
"learning_rate": 0.00017849999999999997,
"loss": 6.1488,
"step": 1190
},
{
"epoch": 0.536837376460018,
"grad_norm": 3.734375,
"learning_rate": 0.00017925,
"loss": 6.1943,
"step": 1195
},
{
"epoch": 0.5390835579514824,
"grad_norm": 3.8125,
"learning_rate": 0.00017999999999999998,
"loss": 6.13,
"step": 1200
},
{
"epoch": 0.541329739442947,
"grad_norm": 3.828125,
"learning_rate": 0.00018075,
"loss": 6.0818,
"step": 1205
},
{
"epoch": 0.5435759209344115,
"grad_norm": 3.546875,
"learning_rate": 0.00018149999999999997,
"loss": 6.1505,
"step": 1210
},
{
"epoch": 0.545822102425876,
"grad_norm": 4.03125,
"learning_rate": 0.00018224999999999998,
"loss": 6.1578,
"step": 1215
},
{
"epoch": 0.5480682839173405,
"grad_norm": 3.921875,
"learning_rate": 0.00018299999999999998,
"loss": 6.0904,
"step": 1220
},
{
"epoch": 0.550314465408805,
"grad_norm": 4.1875,
"learning_rate": 0.00018375,
"loss": 6.0851,
"step": 1225
},
{
"epoch": 0.5525606469002695,
"grad_norm": 4.21875,
"learning_rate": 0.00018449999999999999,
"loss": 6.1133,
"step": 1230
},
{
"epoch": 0.554806828391734,
"grad_norm": 3.765625,
"learning_rate": 0.00018525,
"loss": 6.1453,
"step": 1235
},
{
"epoch": 0.5570530098831986,
"grad_norm": 3.671875,
"learning_rate": 0.000186,
"loss": 6.1572,
"step": 1240
},
{
"epoch": 0.5592991913746631,
"grad_norm": 3.8125,
"learning_rate": 0.00018675,
"loss": 6.2205,
"step": 1245
},
{
"epoch": 0.5615453728661276,
"grad_norm": 4.4375,
"learning_rate": 0.00018749999999999998,
"loss": 6.1114,
"step": 1250
},
{
"epoch": 0.5637915543575921,
"grad_norm": 4.03125,
"learning_rate": 0.00018824999999999997,
"loss": 6.1407,
"step": 1255
},
{
"epoch": 0.5660377358490566,
"grad_norm": 4.1875,
"learning_rate": 0.00018899999999999999,
"loss": 6.1272,
"step": 1260
},
{
"epoch": 0.5682839173405211,
"grad_norm": 4.03125,
"learning_rate": 0.00018974999999999998,
"loss": 6.1264,
"step": 1265
},
{
"epoch": 0.5705300988319856,
"grad_norm": 4.09375,
"learning_rate": 0.0001905,
"loss": 6.0308,
"step": 1270
},
{
"epoch": 0.5727762803234502,
"grad_norm": 3.421875,
"learning_rate": 0.00019124999999999996,
"loss": 6.1028,
"step": 1275
},
{
"epoch": 0.5750224618149147,
"grad_norm": 3.953125,
"learning_rate": 0.00019199999999999998,
"loss": 6.1002,
"step": 1280
},
{
"epoch": 0.5772686433063792,
"grad_norm": 4.1875,
"learning_rate": 0.00019274999999999997,
"loss": 6.1451,
"step": 1285
},
{
"epoch": 0.5795148247978437,
"grad_norm": 4.0625,
"learning_rate": 0.0001935,
"loss": 6.0798,
"step": 1290
},
{
"epoch": 0.5817610062893082,
"grad_norm": 3.609375,
"learning_rate": 0.00019424999999999998,
"loss": 6.0831,
"step": 1295
},
{
"epoch": 0.5840071877807727,
"grad_norm": 3.671875,
"learning_rate": 0.000195,
"loss": 6.1054,
"step": 1300
},
{
"epoch": 0.5862533692722371,
"grad_norm": 3.625,
"learning_rate": 0.00019574999999999996,
"loss": 6.0122,
"step": 1305
},
{
"epoch": 0.5884995507637018,
"grad_norm": 4.0625,
"learning_rate": 0.00019649999999999998,
"loss": 6.0397,
"step": 1310
},
{
"epoch": 0.5907457322551662,
"grad_norm": 3.59375,
"learning_rate": 0.00019724999999999997,
"loss": 5.9765,
"step": 1315
},
{
"epoch": 0.5929919137466307,
"grad_norm": 3.296875,
"learning_rate": 0.000198,
"loss": 6.0359,
"step": 1320
},
{
"epoch": 0.5952380952380952,
"grad_norm": 3.828125,
"learning_rate": 0.00019874999999999998,
"loss": 6.0552,
"step": 1325
},
{
"epoch": 0.5974842767295597,
"grad_norm": 3.5625,
"learning_rate": 0.0001995,
"loss": 6.0254,
"step": 1330
},
{
"epoch": 0.5997304582210242,
"grad_norm": 3.703125,
"learning_rate": 0.00020025,
"loss": 6.0575,
"step": 1335
},
{
"epoch": 0.6019766397124887,
"grad_norm": 3.59375,
"learning_rate": 0.000201,
"loss": 6.004,
"step": 1340
},
{
"epoch": 0.6042228212039533,
"grad_norm": 3.65625,
"learning_rate": 0.00020174999999999997,
"loss": 6.0784,
"step": 1345
},
{
"epoch": 0.6064690026954178,
"grad_norm": 3.78125,
"learning_rate": 0.0002025,
"loss": 6.1157,
"step": 1350
},
{
"epoch": 0.6087151841868823,
"grad_norm": 3.65625,
"learning_rate": 0.00020324999999999998,
"loss": 6.0583,
"step": 1355
},
{
"epoch": 0.6109613656783468,
"grad_norm": 3.4375,
"learning_rate": 0.000204,
"loss": 6.0366,
"step": 1360
},
{
"epoch": 0.6132075471698113,
"grad_norm": 3.4375,
"learning_rate": 0.00020475,
"loss": 6.1213,
"step": 1365
},
{
"epoch": 0.6154537286612758,
"grad_norm": 3.8125,
"learning_rate": 0.0002055,
"loss": 6.1744,
"step": 1370
},
{
"epoch": 0.6176999101527404,
"grad_norm": 3.8125,
"learning_rate": 0.00020624999999999997,
"loss": 6.0912,
"step": 1375
},
{
"epoch": 0.6199460916442049,
"grad_norm": 3.421875,
"learning_rate": 0.00020699999999999996,
"loss": 5.9619,
"step": 1380
},
{
"epoch": 0.6221922731356694,
"grad_norm": 3.78125,
"learning_rate": 0.00020774999999999998,
"loss": 5.9658,
"step": 1385
},
{
"epoch": 0.6244384546271339,
"grad_norm": 3.484375,
"learning_rate": 0.00020849999999999997,
"loss": 6.0913,
"step": 1390
},
{
"epoch": 0.6266846361185984,
"grad_norm": 3.484375,
"learning_rate": 0.00020925,
"loss": 6.0363,
"step": 1395
},
{
"epoch": 0.6289308176100629,
"grad_norm": 3.890625,
"learning_rate": 0.00020999999999999998,
"loss": 5.9513,
"step": 1400
},
{
"epoch": 0.6311769991015274,
"grad_norm": 4.0625,
"learning_rate": 0.00021074999999999997,
"loss": 5.9931,
"step": 1405
},
{
"epoch": 0.633423180592992,
"grad_norm": 4.0,
"learning_rate": 0.00021149999999999996,
"loss": 5.9732,
"step": 1410
},
{
"epoch": 0.6356693620844565,
"grad_norm": 3.671875,
"learning_rate": 0.00021224999999999998,
"loss": 6.0028,
"step": 1415
},
{
"epoch": 0.637915543575921,
"grad_norm": 3.5,
"learning_rate": 0.00021299999999999997,
"loss": 6.0171,
"step": 1420
},
{
"epoch": 0.6401617250673854,
"grad_norm": 3.421875,
"learning_rate": 0.00021375,
"loss": 5.9886,
"step": 1425
},
{
"epoch": 0.6424079065588499,
"grad_norm": 3.875,
"learning_rate": 0.00021449999999999998,
"loss": 5.9436,
"step": 1430
},
{
"epoch": 0.6446540880503144,
"grad_norm": 3.3125,
"learning_rate": 0.00021525,
"loss": 6.0565,
"step": 1435
},
{
"epoch": 0.6469002695417789,
"grad_norm": 3.640625,
"learning_rate": 0.00021599999999999996,
"loss": 6.1117,
"step": 1440
},
{
"epoch": 0.6491464510332435,
"grad_norm": 3.625,
"learning_rate": 0.00021674999999999998,
"loss": 5.9778,
"step": 1445
},
{
"epoch": 0.651392632524708,
"grad_norm": 4.0625,
"learning_rate": 0.00021749999999999997,
"loss": 5.9706,
"step": 1450
},
{
"epoch": 0.6536388140161725,
"grad_norm": 4.15625,
"learning_rate": 0.00021825,
"loss": 5.9358,
"step": 1455
},
{
"epoch": 0.655884995507637,
"grad_norm": 3.5,
"learning_rate": 0.00021899999999999998,
"loss": 6.0584,
"step": 1460
},
{
"epoch": 0.6581311769991015,
"grad_norm": 3.734375,
"learning_rate": 0.00021975,
"loss": 6.0055,
"step": 1465
},
{
"epoch": 0.660377358490566,
"grad_norm": 3.78125,
"learning_rate": 0.00022049999999999997,
"loss": 5.9678,
"step": 1470
},
{
"epoch": 0.6626235399820305,
"grad_norm": 3.703125,
"learning_rate": 0.00022124999999999998,
"loss": 5.9747,
"step": 1475
},
{
"epoch": 0.6648697214734951,
"grad_norm": 3.46875,
"learning_rate": 0.00022199999999999998,
"loss": 5.9542,
"step": 1480
},
{
"epoch": 0.6671159029649596,
"grad_norm": 3.34375,
"learning_rate": 0.00022275,
"loss": 5.9001,
"step": 1485
},
{
"epoch": 0.6693620844564241,
"grad_norm": 3.65625,
"learning_rate": 0.00022349999999999998,
"loss": 5.9689,
"step": 1490
},
{
"epoch": 0.6716082659478886,
"grad_norm": 3.953125,
"learning_rate": 0.00022425,
"loss": 5.9823,
"step": 1495
},
{
"epoch": 0.6738544474393531,
"grad_norm": 3.53125,
"learning_rate": 0.000225,
"loss": 5.9758,
"step": 1500
},
{
"epoch": 0.6761006289308176,
"grad_norm": 3.484375,
"learning_rate": 0.00022574999999999996,
"loss": 5.9994,
"step": 1505
},
{
"epoch": 0.6783468104222821,
"grad_norm": 3.6875,
"learning_rate": 0.00022649999999999998,
"loss": 5.8979,
"step": 1510
},
{
"epoch": 0.6805929919137467,
"grad_norm": 3.328125,
"learning_rate": 0.00022724999999999997,
"loss": 6.0046,
"step": 1515
},
{
"epoch": 0.6828391734052112,
"grad_norm": 3.75,
"learning_rate": 0.00022799999999999999,
"loss": 5.9637,
"step": 1520
},
{
"epoch": 0.6850853548966757,
"grad_norm": 3.296875,
"learning_rate": 0.00022874999999999998,
"loss": 5.939,
"step": 1525
},
{
"epoch": 0.6873315363881402,
"grad_norm": 3.484375,
"learning_rate": 0.0002295,
"loss": 6.0089,
"step": 1530
},
{
"epoch": 0.6895777178796046,
"grad_norm": 3.46875,
"learning_rate": 0.00023024999999999996,
"loss": 5.9247,
"step": 1535
},
{
"epoch": 0.6918238993710691,
"grad_norm": 3.3125,
"learning_rate": 0.00023099999999999998,
"loss": 5.8969,
"step": 1540
},
{
"epoch": 0.6940700808625337,
"grad_norm": 3.734375,
"learning_rate": 0.00023174999999999997,
"loss": 5.8485,
"step": 1545
},
{
"epoch": 0.6963162623539982,
"grad_norm": 3.375,
"learning_rate": 0.00023249999999999999,
"loss": 5.9481,
"step": 1550
},
{
"epoch": 0.6985624438454627,
"grad_norm": 3.5625,
"learning_rate": 0.00023324999999999998,
"loss": 5.9145,
"step": 1555
},
{
"epoch": 0.7008086253369272,
"grad_norm": 3.5,
"learning_rate": 0.000234,
"loss": 5.8711,
"step": 1560
},
{
"epoch": 0.7030548068283917,
"grad_norm": 3.703125,
"learning_rate": 0.00023474999999999996,
"loss": 5.9697,
"step": 1565
},
{
"epoch": 0.7053009883198562,
"grad_norm": 3.75,
"learning_rate": 0.00023549999999999998,
"loss": 5.8905,
"step": 1570
},
{
"epoch": 0.7075471698113207,
"grad_norm": 3.59375,
"learning_rate": 0.00023624999999999997,
"loss": 5.9357,
"step": 1575
},
{
"epoch": 0.7097933513027853,
"grad_norm": 3.453125,
"learning_rate": 0.000237,
"loss": 5.8548,
"step": 1580
},
{
"epoch": 0.7120395327942498,
"grad_norm": 3.484375,
"learning_rate": 0.00023774999999999998,
"loss": 5.9498,
"step": 1585
},
{
"epoch": 0.7142857142857143,
"grad_norm": 3.78125,
"learning_rate": 0.0002385,
"loss": 5.8457,
"step": 1590
},
{
"epoch": 0.7165318957771788,
"grad_norm": 3.5625,
"learning_rate": 0.00023925,
"loss": 5.8717,
"step": 1595
},
{
"epoch": 0.7187780772686433,
"grad_norm": 3.328125,
"learning_rate": 0.00023999999999999998,
"loss": 5.8193,
"step": 1600
},
{
"epoch": 0.7210242587601078,
"grad_norm": 3.296875,
"learning_rate": 0.00024074999999999997,
"loss": 5.8618,
"step": 1605
},
{
"epoch": 0.7232704402515723,
"grad_norm": 3.625,
"learning_rate": 0.0002415,
"loss": 5.8882,
"step": 1610
},
{
"epoch": 0.7255166217430369,
"grad_norm": 3.28125,
"learning_rate": 0.00024224999999999998,
"loss": 5.9087,
"step": 1615
},
{
"epoch": 0.7277628032345014,
"grad_norm": 3.53125,
"learning_rate": 0.000243,
"loss": 5.8994,
"step": 1620
},
{
"epoch": 0.7300089847259659,
"grad_norm": 3.34375,
"learning_rate": 0.00024375,
"loss": 5.9156,
"step": 1625
},
{
"epoch": 0.7322551662174304,
"grad_norm": 3.78125,
"learning_rate": 0.0002445,
"loss": 5.889,
"step": 1630
},
{
"epoch": 0.7345013477088949,
"grad_norm": 3.5,
"learning_rate": 0.00024524999999999997,
"loss": 5.8538,
"step": 1635
},
{
"epoch": 0.7367475292003594,
"grad_norm": 3.53125,
"learning_rate": 0.00024599999999999996,
"loss": 5.914,
"step": 1640
},
{
"epoch": 0.7389937106918238,
"grad_norm": 3.25,
"learning_rate": 0.00024675,
"loss": 5.8628,
"step": 1645
},
{
"epoch": 0.7412398921832885,
"grad_norm": 3.5,
"learning_rate": 0.00024749999999999994,
"loss": 5.8555,
"step": 1650
},
{
"epoch": 0.743486073674753,
"grad_norm": 3.4375,
"learning_rate": 0.00024825,
"loss": 5.8846,
"step": 1655
},
{
"epoch": 0.7457322551662174,
"grad_norm": 3.703125,
"learning_rate": 0.000249,
"loss": 5.8957,
"step": 1660
},
{
"epoch": 0.7479784366576819,
"grad_norm": 3.25,
"learning_rate": 0.00024974999999999997,
"loss": 5.8036,
"step": 1665
},
{
"epoch": 0.7502246181491464,
"grad_norm": 3.375,
"learning_rate": 0.00025049999999999996,
"loss": 5.845,
"step": 1670
},
{
"epoch": 0.7524707996406109,
"grad_norm": 3.1875,
"learning_rate": 0.00025125,
"loss": 5.8801,
"step": 1675
},
{
"epoch": 0.7547169811320755,
"grad_norm": 3.53125,
"learning_rate": 0.00025199999999999995,
"loss": 5.8356,
"step": 1680
},
{
"epoch": 0.75696316262354,
"grad_norm": 3.375,
"learning_rate": 0.00025275,
"loss": 5.851,
"step": 1685
},
{
"epoch": 0.7592093441150045,
"grad_norm": 3.546875,
"learning_rate": 0.0002535,
"loss": 5.8647,
"step": 1690
},
{
"epoch": 0.761455525606469,
"grad_norm": 3.4375,
"learning_rate": 0.00025425,
"loss": 5.8168,
"step": 1695
},
{
"epoch": 0.7637017070979335,
"grad_norm": 3.609375,
"learning_rate": 0.00025499999999999996,
"loss": 5.8514,
"step": 1700
},
{
"epoch": 0.765947888589398,
"grad_norm": 3.3125,
"learning_rate": 0.00025575,
"loss": 5.7495,
"step": 1705
},
{
"epoch": 0.7681940700808625,
"grad_norm": 3.515625,
"learning_rate": 0.00025649999999999995,
"loss": 5.8702,
"step": 1710
},
{
"epoch": 0.7704402515723271,
"grad_norm": 3.640625,
"learning_rate": 0.00025725,
"loss": 5.9178,
"step": 1715
},
{
"epoch": 0.7726864330637916,
"grad_norm": 3.1875,
"learning_rate": 0.000258,
"loss": 5.82,
"step": 1720
},
{
"epoch": 0.7749326145552561,
"grad_norm": 3.765625,
"learning_rate": 0.00025875,
"loss": 5.823,
"step": 1725
},
{
"epoch": 0.7771787960467206,
"grad_norm": 3.4375,
"learning_rate": 0.00025949999999999997,
"loss": 5.8712,
"step": 1730
},
{
"epoch": 0.7794249775381851,
"grad_norm": 3.140625,
"learning_rate": 0.00026025,
"loss": 5.8173,
"step": 1735
},
{
"epoch": 0.7816711590296496,
"grad_norm": 3.28125,
"learning_rate": 0.000261,
"loss": 5.8169,
"step": 1740
},
{
"epoch": 0.7839173405211141,
"grad_norm": 3.4375,
"learning_rate": 0.00026175,
"loss": 5.8047,
"step": 1745
},
{
"epoch": 0.7861635220125787,
"grad_norm": 3.21875,
"learning_rate": 0.0002625,
"loss": 5.8384,
"step": 1750
},
{
"epoch": 0.7884097035040432,
"grad_norm": 3.40625,
"learning_rate": 0.00026325,
"loss": 5.7996,
"step": 1755
},
{
"epoch": 0.7906558849955077,
"grad_norm": 3.4375,
"learning_rate": 0.00026399999999999997,
"loss": 5.7611,
"step": 1760
},
{
"epoch": 0.7929020664869721,
"grad_norm": 3.390625,
"learning_rate": 0.00026474999999999996,
"loss": 5.7925,
"step": 1765
},
{
"epoch": 0.7951482479784366,
"grad_norm": 3.375,
"learning_rate": 0.0002655,
"loss": 5.8187,
"step": 1770
},
{
"epoch": 0.7973944294699011,
"grad_norm": 3.53125,
"learning_rate": 0.00026624999999999994,
"loss": 5.7791,
"step": 1775
},
{
"epoch": 0.7996406109613656,
"grad_norm": 3.8125,
"learning_rate": 0.000267,
"loss": 5.8063,
"step": 1780
},
{
"epoch": 0.8018867924528302,
"grad_norm": 3.25,
"learning_rate": 0.00026775,
"loss": 5.8167,
"step": 1785
},
{
"epoch": 0.8041329739442947,
"grad_norm": 3.46875,
"learning_rate": 0.00026849999999999997,
"loss": 5.7916,
"step": 1790
},
{
"epoch": 0.8063791554357592,
"grad_norm": 3.28125,
"learning_rate": 0.00026924999999999996,
"loss": 5.8446,
"step": 1795
},
{
"epoch": 0.8086253369272237,
"grad_norm": 3.65625,
"learning_rate": 0.00027,
"loss": 5.8757,
"step": 1800
},
{
"epoch": 0.8108715184186882,
"grad_norm": 3.734375,
"learning_rate": 0.00027074999999999994,
"loss": 5.7271,
"step": 1805
},
{
"epoch": 0.8131176999101527,
"grad_norm": 3.765625,
"learning_rate": 0.0002715,
"loss": 5.8397,
"step": 1810
},
{
"epoch": 0.8153638814016172,
"grad_norm": 3.34375,
"learning_rate": 0.00027225,
"loss": 5.7838,
"step": 1815
},
{
"epoch": 0.8176100628930818,
"grad_norm": 3.59375,
"learning_rate": 0.00027299999999999997,
"loss": 5.7907,
"step": 1820
},
{
"epoch": 0.8198562443845463,
"grad_norm": 3.921875,
"learning_rate": 0.00027374999999999996,
"loss": 5.8579,
"step": 1825
},
{
"epoch": 0.8221024258760108,
"grad_norm": 3.46875,
"learning_rate": 0.0002745,
"loss": 5.8342,
"step": 1830
},
{
"epoch": 0.8243486073674753,
"grad_norm": 3.75,
"learning_rate": 0.00027525,
"loss": 5.7949,
"step": 1835
},
{
"epoch": 0.8265947888589398,
"grad_norm": 3.4375,
"learning_rate": 0.000276,
"loss": 5.7715,
"step": 1840
},
{
"epoch": 0.8288409703504043,
"grad_norm": 3.703125,
"learning_rate": 0.00027675,
"loss": 5.7804,
"step": 1845
},
{
"epoch": 0.8310871518418689,
"grad_norm": 3.4375,
"learning_rate": 0.00027749999999999997,
"loss": 5.7288,
"step": 1850
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.109375,
"learning_rate": 0.00027824999999999996,
"loss": 5.7319,
"step": 1855
},
{
"epoch": 0.8355795148247979,
"grad_norm": 3.21875,
"learning_rate": 0.000279,
"loss": 5.7636,
"step": 1860
},
{
"epoch": 0.8378256963162624,
"grad_norm": 3.234375,
"learning_rate": 0.00027975,
"loss": 5.7395,
"step": 1865
},
{
"epoch": 0.8400718778077269,
"grad_norm": 3.6875,
"learning_rate": 0.0002805,
"loss": 5.7519,
"step": 1870
},
{
"epoch": 0.8423180592991913,
"grad_norm": 3.265625,
"learning_rate": 0.00028125,
"loss": 5.706,
"step": 1875
},
{
"epoch": 0.8445642407906558,
"grad_norm": 3.390625,
"learning_rate": 0.00028199999999999997,
"loss": 5.799,
"step": 1880
},
{
"epoch": 0.8468104222821204,
"grad_norm": 3.265625,
"learning_rate": 0.00028274999999999996,
"loss": 5.7856,
"step": 1885
},
{
"epoch": 0.8490566037735849,
"grad_norm": 3.421875,
"learning_rate": 0.00028349999999999995,
"loss": 5.8625,
"step": 1890
},
{
"epoch": 0.8513027852650494,
"grad_norm": 3.203125,
"learning_rate": 0.00028425,
"loss": 5.7212,
"step": 1895
},
{
"epoch": 0.8535489667565139,
"grad_norm": 3.296875,
"learning_rate": 0.000285,
"loss": 5.7326,
"step": 1900
},
{
"epoch": 0.8557951482479784,
"grad_norm": 3.5,
"learning_rate": 0.00028575,
"loss": 5.7664,
"step": 1905
},
{
"epoch": 0.8580413297394429,
"grad_norm": 3.34375,
"learning_rate": 0.00028649999999999997,
"loss": 5.7231,
"step": 1910
},
{
"epoch": 0.8602875112309074,
"grad_norm": 3.40625,
"learning_rate": 0.00028724999999999996,
"loss": 5.7759,
"step": 1915
},
{
"epoch": 0.862533692722372,
"grad_norm": 3.125,
"learning_rate": 0.00028799999999999995,
"loss": 5.7442,
"step": 1920
},
{
"epoch": 0.8647798742138365,
"grad_norm": 3.15625,
"learning_rate": 0.00028875,
"loss": 5.7252,
"step": 1925
},
{
"epoch": 0.867026055705301,
"grad_norm": 3.265625,
"learning_rate": 0.0002895,
"loss": 5.7196,
"step": 1930
},
{
"epoch": 0.8692722371967655,
"grad_norm": 3.328125,
"learning_rate": 0.00029025,
"loss": 5.7376,
"step": 1935
},
{
"epoch": 0.87151841868823,
"grad_norm": 3.1875,
"learning_rate": 0.00029099999999999997,
"loss": 5.8077,
"step": 1940
},
{
"epoch": 0.8737646001796945,
"grad_norm": 3.625,
"learning_rate": 0.00029174999999999996,
"loss": 5.7826,
"step": 1945
},
{
"epoch": 0.876010781671159,
"grad_norm": 3.609375,
"learning_rate": 0.00029249999999999995,
"loss": 5.736,
"step": 1950
},
{
"epoch": 0.8782569631626236,
"grad_norm": 3.421875,
"learning_rate": 0.00029325,
"loss": 5.7531,
"step": 1955
},
{
"epoch": 0.8805031446540881,
"grad_norm": 3.4375,
"learning_rate": 0.000294,
"loss": 5.7246,
"step": 1960
},
{
"epoch": 0.8827493261455526,
"grad_norm": 3.375,
"learning_rate": 0.00029475,
"loss": 5.7786,
"step": 1965
},
{
"epoch": 0.8849955076370171,
"grad_norm": 3.296875,
"learning_rate": 0.00029549999999999997,
"loss": 5.7237,
"step": 1970
},
{
"epoch": 0.8872416891284816,
"grad_norm": 2.96875,
"learning_rate": 0.00029624999999999996,
"loss": 5.8053,
"step": 1975
},
{
"epoch": 0.889487870619946,
"grad_norm": 3.328125,
"learning_rate": 0.00029699999999999996,
"loss": 5.6918,
"step": 1980
},
{
"epoch": 0.8917340521114105,
"grad_norm": 3.015625,
"learning_rate": 0.00029775,
"loss": 5.8251,
"step": 1985
},
{
"epoch": 0.8939802336028752,
"grad_norm": 3.78125,
"learning_rate": 0.0002985,
"loss": 5.7529,
"step": 1990
},
{
"epoch": 0.8962264150943396,
"grad_norm": 3.640625,
"learning_rate": 0.00029925,
"loss": 5.7181,
"step": 1995
},
{
"epoch": 0.8984725965858041,
"grad_norm": 3.234375,
"learning_rate": 0.0003,
"loss": 5.7413,
"step": 2000
},
{
"epoch": 0.8984725965858041,
"eval_loss": 5.639461517333984,
"eval_runtime": 16.0491,
"eval_samples_per_second": 1932.383,
"eval_steps_per_second": 241.571,
"step": 2000
},
{
"epoch": 0.9007187780772686,
"grad_norm": 3.140625,
"learning_rate": 0.00029999995942443054,
"loss": 5.6436,
"step": 2005
},
{
"epoch": 0.9029649595687331,
"grad_norm": 3.328125,
"learning_rate": 0.00029999983769774674,
"loss": 5.7627,
"step": 2010
},
{
"epoch": 0.9052111410601976,
"grad_norm": 3.171875,
"learning_rate": 0.0002999996348200217,
"loss": 5.7181,
"step": 2015
},
{
"epoch": 0.9074573225516622,
"grad_norm": 3.34375,
"learning_rate": 0.0002999993507913773,
"loss": 5.7097,
"step": 2020
},
{
"epoch": 0.9097035040431267,
"grad_norm": 3.1875,
"learning_rate": 0.0002999989856119844,
"loss": 5.6407,
"step": 2025
},
{
"epoch": 0.9119496855345912,
"grad_norm": 3.453125,
"learning_rate": 0.0002999985392820624,
"loss": 5.6532,
"step": 2030
},
{
"epoch": 0.9141958670260557,
"grad_norm": 3.140625,
"learning_rate": 0.0002999980118018797,
"loss": 5.6993,
"step": 2035
},
{
"epoch": 0.9164420485175202,
"grad_norm": 3.546875,
"learning_rate": 0.0002999974031717533,
"loss": 5.6507,
"step": 2040
},
{
"epoch": 0.9186882300089847,
"grad_norm": 3.546875,
"learning_rate": 0.0002999967133920491,
"loss": 5.6629,
"step": 2045
},
{
"epoch": 0.9209344115004492,
"grad_norm": 3.203125,
"learning_rate": 0.0002999959424631818,
"loss": 5.7172,
"step": 2050
},
{
"epoch": 0.9231805929919138,
"grad_norm": 3.140625,
"learning_rate": 0.0002999950903856147,
"loss": 5.5766,
"step": 2055
},
{
"epoch": 0.9254267744833783,
"grad_norm": 3.234375,
"learning_rate": 0.00029999415715986,
"loss": 5.6546,
"step": 2060
},
{
"epoch": 0.9276729559748428,
"grad_norm": 3.34375,
"learning_rate": 0.0002999931427864788,
"loss": 5.6317,
"step": 2065
},
{
"epoch": 0.9299191374663073,
"grad_norm": 3.1875,
"learning_rate": 0.00029999204726608076,
"loss": 5.6605,
"step": 2070
},
{
"epoch": 0.9321653189577718,
"grad_norm": 3.40625,
"learning_rate": 0.0002999908705993245,
"loss": 5.6958,
"step": 2075
},
{
"epoch": 0.9344115004492363,
"grad_norm": 3.046875,
"learning_rate": 0.00029998961278691725,
"loss": 5.6498,
"step": 2080
},
{
"epoch": 0.9366576819407008,
"grad_norm": 3.203125,
"learning_rate": 0.0002999882738296152,
"loss": 5.6887,
"step": 2085
},
{
"epoch": 0.9389038634321654,
"grad_norm": 3.453125,
"learning_rate": 0.0002999868537282231,
"loss": 5.617,
"step": 2090
},
{
"epoch": 0.9411500449236299,
"grad_norm": 3.25,
"learning_rate": 0.0002999853524835947,
"loss": 5.7708,
"step": 2095
},
{
"epoch": 0.9433962264150944,
"grad_norm": 3.421875,
"learning_rate": 0.0002999837700966324,
"loss": 5.6733,
"step": 2100
},
{
"epoch": 0.9456424079065588,
"grad_norm": 3.359375,
"learning_rate": 0.00029998210656828736,
"loss": 5.7,
"step": 2105
},
{
"epoch": 0.9478885893980233,
"grad_norm": 3.296875,
"learning_rate": 0.0002999803618995596,
"loss": 5.6652,
"step": 2110
},
{
"epoch": 0.9501347708894878,
"grad_norm": 3.71875,
"learning_rate": 0.00029997853609149797,
"loss": 5.7413,
"step": 2115
},
{
"epoch": 0.9523809523809523,
"grad_norm": 3.3125,
"learning_rate": 0.00029997662914519983,
"loss": 5.7038,
"step": 2120
},
{
"epoch": 0.9546271338724169,
"grad_norm": 3.546875,
"learning_rate": 0.0002999746410618116,
"loss": 5.6402,
"step": 2125
},
{
"epoch": 0.9568733153638814,
"grad_norm": 3.09375,
"learning_rate": 0.00029997257184252827,
"loss": 5.5762,
"step": 2130
},
{
"epoch": 0.9591194968553459,
"grad_norm": 3.421875,
"learning_rate": 0.00029997042148859374,
"loss": 5.7327,
"step": 2135
},
{
"epoch": 0.9613656783468104,
"grad_norm": 3.296875,
"learning_rate": 0.0002999681900013006,
"loss": 5.6974,
"step": 2140
},
{
"epoch": 0.9636118598382749,
"grad_norm": 3.140625,
"learning_rate": 0.0002999658773819903,
"loss": 5.7185,
"step": 2145
},
{
"epoch": 0.9658580413297394,
"grad_norm": 3.34375,
"learning_rate": 0.00029996348363205296,
"loss": 5.7269,
"step": 2150
},
{
"epoch": 0.968104222821204,
"grad_norm": 3.0,
"learning_rate": 0.0002999610087529275,
"loss": 5.6719,
"step": 2155
},
{
"epoch": 0.9703504043126685,
"grad_norm": 3.375,
"learning_rate": 0.00029995845274610164,
"loss": 5.6067,
"step": 2160
},
{
"epoch": 0.972596585804133,
"grad_norm": 3.25,
"learning_rate": 0.00029995581561311185,
"loss": 5.612,
"step": 2165
},
{
"epoch": 0.9748427672955975,
"grad_norm": 3.390625,
"learning_rate": 0.00029995309735554327,
"loss": 5.6163,
"step": 2170
},
{
"epoch": 0.977088948787062,
"grad_norm": 3.265625,
"learning_rate": 0.00029995029797503007,
"loss": 5.6468,
"step": 2175
},
{
"epoch": 0.9793351302785265,
"grad_norm": 3.03125,
"learning_rate": 0.00029994741747325487,
"loss": 5.6653,
"step": 2180
},
{
"epoch": 0.981581311769991,
"grad_norm": 3.1875,
"learning_rate": 0.00029994445585194925,
"loss": 5.6416,
"step": 2185
},
{
"epoch": 0.9838274932614556,
"grad_norm": 3.09375,
"learning_rate": 0.00029994141311289347,
"loss": 5.5982,
"step": 2190
},
{
"epoch": 0.9860736747529201,
"grad_norm": 3.328125,
"learning_rate": 0.00029993828925791664,
"loss": 5.6288,
"step": 2195
},
{
"epoch": 0.9883198562443846,
"grad_norm": 3.203125,
"learning_rate": 0.0002999350842888965,
"loss": 5.6725,
"step": 2200
},
{
"epoch": 0.9905660377358491,
"grad_norm": 3.40625,
"learning_rate": 0.0002999317982077596,
"loss": 5.6444,
"step": 2205
},
{
"epoch": 0.9928122192273136,
"grad_norm": 2.921875,
"learning_rate": 0.00029992843101648144,
"loss": 5.6642,
"step": 2210
},
{
"epoch": 0.995058400718778,
"grad_norm": 3.015625,
"learning_rate": 0.00029992498271708595,
"loss": 5.6011,
"step": 2215
},
{
"epoch": 0.9973045822102425,
"grad_norm": 2.90625,
"learning_rate": 0.00029992145331164596,
"loss": 5.6432,
"step": 2220
},
{
"epoch": 0.9995507637017071,
"grad_norm": 3.140625,
"learning_rate": 0.0002999178428022831,
"loss": 5.6428,
"step": 2225
},
{
"epoch": 1.0017969451931716,
"grad_norm": 3.265625,
"learning_rate": 0.0002999141511911678,
"loss": 5.5542,
"step": 2230
},
{
"epoch": 1.0040431266846361,
"grad_norm": 3.296875,
"learning_rate": 0.000299910378480519,
"loss": 5.6403,
"step": 2235
},
{
"epoch": 1.0062893081761006,
"grad_norm": 3.21875,
"learning_rate": 0.0002999065246726047,
"loss": 5.5451,
"step": 2240
},
{
"epoch": 1.0085354896675651,
"grad_norm": 3.0625,
"learning_rate": 0.0002999025897697414,
"loss": 5.6575,
"step": 2245
},
{
"epoch": 1.0107816711590296,
"grad_norm": 3.140625,
"learning_rate": 0.0002998985737742945,
"loss": 5.5892,
"step": 2250
},
{
"epoch": 1.013027852650494,
"grad_norm": 3.203125,
"learning_rate": 0.0002998944766886781,
"loss": 5.6127,
"step": 2255
},
{
"epoch": 1.0152740341419586,
"grad_norm": 3.078125,
"learning_rate": 0.000299890298515355,
"loss": 5.5885,
"step": 2260
},
{
"epoch": 1.017520215633423,
"grad_norm": 3.265625,
"learning_rate": 0.0002998860392568368,
"loss": 5.5215,
"step": 2265
},
{
"epoch": 1.0197663971248876,
"grad_norm": 3.171875,
"learning_rate": 0.00029988169891568373,
"loss": 5.6074,
"step": 2270
},
{
"epoch": 1.0220125786163523,
"grad_norm": 3.171875,
"learning_rate": 0.00029987727749450506,
"loss": 5.6192,
"step": 2275
},
{
"epoch": 1.0242587601078168,
"grad_norm": 3.328125,
"learning_rate": 0.00029987277499595843,
"loss": 5.5663,
"step": 2280
},
{
"epoch": 1.0265049415992813,
"grad_norm": 3.265625,
"learning_rate": 0.0002998681914227504,
"loss": 5.5862,
"step": 2285
},
{
"epoch": 1.0287511230907458,
"grad_norm": 3.0,
"learning_rate": 0.0002998635267776363,
"loss": 5.5536,
"step": 2290
},
{
"epoch": 1.0309973045822103,
"grad_norm": 3.3125,
"learning_rate": 0.0002998587810634201,
"loss": 5.5818,
"step": 2295
},
{
"epoch": 1.0332434860736748,
"grad_norm": 3.234375,
"learning_rate": 0.0002998539542829546,
"loss": 5.6147,
"step": 2300
},
{
"epoch": 1.0354896675651393,
"grad_norm": 3.09375,
"learning_rate": 0.00029984904643914114,
"loss": 5.6629,
"step": 2305
},
{
"epoch": 1.0377358490566038,
"grad_norm": 3.15625,
"learning_rate": 0.00029984405753493006,
"loss": 5.5412,
"step": 2310
},
{
"epoch": 1.0399820305480683,
"grad_norm": 2.984375,
"learning_rate": 0.00029983898757332024,
"loss": 5.5598,
"step": 2315
},
{
"epoch": 1.0422282120395328,
"grad_norm": 2.96875,
"learning_rate": 0.0002998338365573593,
"loss": 5.6111,
"step": 2320
},
{
"epoch": 1.0444743935309972,
"grad_norm": 3.234375,
"learning_rate": 0.0002998286044901436,
"loss": 5.4899,
"step": 2325
},
{
"epoch": 1.0467205750224617,
"grad_norm": 3.453125,
"learning_rate": 0.0002998232913748184,
"loss": 5.5567,
"step": 2330
},
{
"epoch": 1.0489667565139262,
"grad_norm": 3.40625,
"learning_rate": 0.0002998178972145773,
"loss": 5.4968,
"step": 2335
},
{
"epoch": 1.0512129380053907,
"grad_norm": 3.03125,
"learning_rate": 0.000299812422012663,
"loss": 5.6119,
"step": 2340
},
{
"epoch": 1.0534591194968554,
"grad_norm": 3.15625,
"learning_rate": 0.0002998068657723666,
"loss": 5.5563,
"step": 2345
},
{
"epoch": 1.05570530098832,
"grad_norm": 3.203125,
"learning_rate": 0.0002998012284970282,
"loss": 5.5985,
"step": 2350
},
{
"epoch": 1.0579514824797844,
"grad_norm": 3.46875,
"learning_rate": 0.00029979551019003643,
"loss": 5.5002,
"step": 2355
},
{
"epoch": 1.060197663971249,
"grad_norm": 3.046875,
"learning_rate": 0.0002997897108548286,
"loss": 5.6114,
"step": 2360
},
{
"epoch": 1.0624438454627134,
"grad_norm": 3.140625,
"learning_rate": 0.00029978383049489093,
"loss": 5.5056,
"step": 2365
},
{
"epoch": 1.064690026954178,
"grad_norm": 3.109375,
"learning_rate": 0.0002997778691137582,
"loss": 5.515,
"step": 2370
},
{
"epoch": 1.0669362084456424,
"grad_norm": 3.15625,
"learning_rate": 0.00029977182671501383,
"loss": 5.5303,
"step": 2375
},
{
"epoch": 1.069182389937107,
"grad_norm": 3.140625,
"learning_rate": 0.00029976570330229006,
"loss": 5.5147,
"step": 2380
},
{
"epoch": 1.0714285714285714,
"grad_norm": 3.109375,
"learning_rate": 0.00029975949887926784,
"loss": 5.5098,
"step": 2385
},
{
"epoch": 1.073674752920036,
"grad_norm": 3.046875,
"learning_rate": 0.00029975321344967676,
"loss": 5.5533,
"step": 2390
},
{
"epoch": 1.0759209344115004,
"grad_norm": 3.28125,
"learning_rate": 0.000299746847017295,
"loss": 5.5429,
"step": 2395
},
{
"epoch": 1.0781671159029649,
"grad_norm": 3.265625,
"learning_rate": 0.00029974039958594967,
"loss": 5.508,
"step": 2400
},
{
"epoch": 1.0804132973944294,
"grad_norm": 3.1875,
"learning_rate": 0.0002997338711595165,
"loss": 5.5494,
"step": 2405
},
{
"epoch": 1.082659478885894,
"grad_norm": 3.203125,
"learning_rate": 0.00029972726174191965,
"loss": 5.4273,
"step": 2410
},
{
"epoch": 1.0849056603773586,
"grad_norm": 3.0625,
"learning_rate": 0.00029972057133713235,
"loss": 5.5474,
"step": 2415
},
{
"epoch": 1.087151841868823,
"grad_norm": 2.84375,
"learning_rate": 0.00029971379994917624,
"loss": 5.5008,
"step": 2420
},
{
"epoch": 1.0893980233602876,
"grad_norm": 3.359375,
"learning_rate": 0.00029970694758212177,
"loss": 5.4682,
"step": 2425
},
{
"epoch": 1.091644204851752,
"grad_norm": 3.0,
"learning_rate": 0.000299700014240088,
"loss": 5.4666,
"step": 2430
},
{
"epoch": 1.0938903863432166,
"grad_norm": 3.3125,
"learning_rate": 0.00029969299992724273,
"loss": 5.5844,
"step": 2435
},
{
"epoch": 1.096136567834681,
"grad_norm": 3.3125,
"learning_rate": 0.00029968590464780247,
"loss": 5.5141,
"step": 2440
},
{
"epoch": 1.0983827493261455,
"grad_norm": 3.046875,
"learning_rate": 0.0002996787284060322,
"loss": 5.4897,
"step": 2445
},
{
"epoch": 1.10062893081761,
"grad_norm": 3.125,
"learning_rate": 0.00029967147120624573,
"loss": 5.4318,
"step": 2450
},
{
"epoch": 1.1028751123090745,
"grad_norm": 3.4375,
"learning_rate": 0.00029966413305280553,
"loss": 5.506,
"step": 2455
},
{
"epoch": 1.105121293800539,
"grad_norm": 3.390625,
"learning_rate": 0.00029965671395012274,
"loss": 5.4363,
"step": 2460
},
{
"epoch": 1.1073674752920035,
"grad_norm": 3.265625,
"learning_rate": 0.0002996492139026571,
"loss": 5.4077,
"step": 2465
},
{
"epoch": 1.109613656783468,
"grad_norm": 3.265625,
"learning_rate": 0.000299641632914917,
"loss": 5.4435,
"step": 2470
},
{
"epoch": 1.1118598382749325,
"grad_norm": 3.078125,
"learning_rate": 0.0002996339709914596,
"loss": 5.4641,
"step": 2475
},
{
"epoch": 1.1141060197663972,
"grad_norm": 3.015625,
"learning_rate": 0.0002996262281368905,
"loss": 5.5053,
"step": 2480
},
{
"epoch": 1.1163522012578617,
"grad_norm": 3.34375,
"learning_rate": 0.0002996184043558642,
"loss": 5.3987,
"step": 2485
},
{
"epoch": 1.1185983827493262,
"grad_norm": 3.03125,
"learning_rate": 0.0002996104996530837,
"loss": 5.6063,
"step": 2490
},
{
"epoch": 1.1208445642407907,
"grad_norm": 3.328125,
"learning_rate": 0.0002996025140333006,
"loss": 5.4782,
"step": 2495
},
{
"epoch": 1.1230907457322552,
"grad_norm": 3.25,
"learning_rate": 0.00029959444750131533,
"loss": 5.4836,
"step": 2500
},
{
"epoch": 1.1253369272237197,
"grad_norm": 3.140625,
"learning_rate": 0.0002995863000619768,
"loss": 5.5181,
"step": 2505
},
{
"epoch": 1.1275831087151842,
"grad_norm": 3.1875,
"learning_rate": 0.0002995780717201825,
"loss": 5.4469,
"step": 2510
},
{
"epoch": 1.1298292902066487,
"grad_norm": 3.03125,
"learning_rate": 0.0002995697624808788,
"loss": 5.4445,
"step": 2515
},
{
"epoch": 1.1320754716981132,
"grad_norm": 3.125,
"learning_rate": 0.00029956137234906044,
"loss": 5.4844,
"step": 2520
},
{
"epoch": 1.1343216531895777,
"grad_norm": 2.953125,
"learning_rate": 0.00029955290132977093,
"loss": 5.5633,
"step": 2525
},
{
"epoch": 1.1365678346810422,
"grad_norm": 3.109375,
"learning_rate": 0.0002995443494281024,
"loss": 5.4724,
"step": 2530
},
{
"epoch": 1.1388140161725067,
"grad_norm": 3.34375,
"learning_rate": 0.00029953571664919547,
"loss": 5.4786,
"step": 2535
},
{
"epoch": 1.1410601976639712,
"grad_norm": 3.328125,
"learning_rate": 0.0002995270029982396,
"loss": 5.5004,
"step": 2540
},
{
"epoch": 1.1433063791554359,
"grad_norm": 3.0625,
"learning_rate": 0.00029951820848047255,
"loss": 5.4758,
"step": 2545
},
{
"epoch": 1.1455525606469004,
"grad_norm": 3.0,
"learning_rate": 0.0002995093331011811,
"loss": 5.4789,
"step": 2550
},
{
"epoch": 1.1477987421383649,
"grad_norm": 3.03125,
"learning_rate": 0.00029950037686570023,
"loss": 5.3991,
"step": 2555
},
{
"epoch": 1.1500449236298294,
"grad_norm": 3.3125,
"learning_rate": 0.0002994913397794138,
"loss": 5.5046,
"step": 2560
},
{
"epoch": 1.1522911051212938,
"grad_norm": 3.46875,
"learning_rate": 0.00029948222184775415,
"loss": 5.5293,
"step": 2565
},
{
"epoch": 1.1545372866127583,
"grad_norm": 3.125,
"learning_rate": 0.00029947302307620227,
"loss": 5.4079,
"step": 2570
},
{
"epoch": 1.1567834681042228,
"grad_norm": 3.203125,
"learning_rate": 0.0002994637434702877,
"loss": 5.425,
"step": 2575
},
{
"epoch": 1.1590296495956873,
"grad_norm": 3.296875,
"learning_rate": 0.0002994543830355886,
"loss": 5.4591,
"step": 2580
},
{
"epoch": 1.1612758310871518,
"grad_norm": 3.296875,
"learning_rate": 0.0002994449417777317,
"loss": 5.5263,
"step": 2585
},
{
"epoch": 1.1635220125786163,
"grad_norm": 3.140625,
"learning_rate": 0.00029943541970239233,
"loss": 5.4458,
"step": 2590
},
{
"epoch": 1.1657681940700808,
"grad_norm": 3.1875,
"learning_rate": 0.00029942581681529447,
"loss": 5.4449,
"step": 2595
},
{
"epoch": 1.1680143755615453,
"grad_norm": 3.34375,
"learning_rate": 0.00029941613312221046,
"loss": 5.5558,
"step": 2600
},
{
"epoch": 1.1702605570530098,
"grad_norm": 3.0,
"learning_rate": 0.00029940636862896145,
"loss": 5.5165,
"step": 2605
},
{
"epoch": 1.1725067385444743,
"grad_norm": 3.3125,
"learning_rate": 0.0002993965233414171,
"loss": 5.4624,
"step": 2610
},
{
"epoch": 1.1747529200359388,
"grad_norm": 3.203125,
"learning_rate": 0.0002993865972654955,
"loss": 5.4336,
"step": 2615
},
{
"epoch": 1.1769991015274035,
"grad_norm": 3.5,
"learning_rate": 0.0002993765904071635,
"loss": 5.5293,
"step": 2620
},
{
"epoch": 1.179245283018868,
"grad_norm": 3.15625,
"learning_rate": 0.00029936650277243633,
"loss": 5.5603,
"step": 2625
},
{
"epoch": 1.1814914645103325,
"grad_norm": 3.140625,
"learning_rate": 0.0002993563343673779,
"loss": 5.4785,
"step": 2630
},
{
"epoch": 1.183737646001797,
"grad_norm": 3.09375,
"learning_rate": 0.0002993460851981007,
"loss": 5.4188,
"step": 2635
},
{
"epoch": 1.1859838274932615,
"grad_norm": 3.078125,
"learning_rate": 0.00029933575527076565,
"loss": 5.5139,
"step": 2640
},
{
"epoch": 1.188230008984726,
"grad_norm": 3.015625,
"learning_rate": 0.0002993253445915823,
"loss": 5.3998,
"step": 2645
},
{
"epoch": 1.1904761904761905,
"grad_norm": 3.328125,
"learning_rate": 0.0002993148531668087,
"loss": 5.5066,
"step": 2650
},
{
"epoch": 1.192722371967655,
"grad_norm": 3.125,
"learning_rate": 0.0002993042810027514,
"loss": 5.416,
"step": 2655
},
{
"epoch": 1.1949685534591195,
"grad_norm": 3.171875,
"learning_rate": 0.0002992936281057656,
"loss": 5.4367,
"step": 2660
},
{
"epoch": 1.197214734950584,
"grad_norm": 3.125,
"learning_rate": 0.000299282894482255,
"loss": 5.3912,
"step": 2665
},
{
"epoch": 1.1994609164420484,
"grad_norm": 2.9375,
"learning_rate": 0.00029927208013867164,
"loss": 5.4456,
"step": 2670
},
{
"epoch": 1.201707097933513,
"grad_norm": 3.296875,
"learning_rate": 0.0002992611850815163,
"loss": 5.5036,
"step": 2675
},
{
"epoch": 1.2039532794249777,
"grad_norm": 3.234375,
"learning_rate": 0.0002992502093173383,
"loss": 5.4467,
"step": 2680
},
{
"epoch": 1.2061994609164421,
"grad_norm": 3.375,
"learning_rate": 0.0002992391528527353,
"loss": 5.3611,
"step": 2685
},
{
"epoch": 1.2084456424079066,
"grad_norm": 3.359375,
"learning_rate": 0.00029922801569435366,
"loss": 5.4635,
"step": 2690
},
{
"epoch": 1.2106918238993711,
"grad_norm": 3.671875,
"learning_rate": 0.00029921679784888797,
"loss": 5.4823,
"step": 2695
},
{
"epoch": 1.2129380053908356,
"grad_norm": 2.875,
"learning_rate": 0.0002992054993230816,
"loss": 5.378,
"step": 2700
},
{
"epoch": 1.2151841868823001,
"grad_norm": 2.765625,
"learning_rate": 0.0002991941201237263,
"loss": 5.4737,
"step": 2705
},
{
"epoch": 1.2174303683737646,
"grad_norm": 3.0625,
"learning_rate": 0.0002991826602576624,
"loss": 5.4399,
"step": 2710
},
{
"epoch": 1.219676549865229,
"grad_norm": 3.046875,
"learning_rate": 0.00029917111973177857,
"loss": 5.4663,
"step": 2715
},
{
"epoch": 1.2219227313566936,
"grad_norm": 3.484375,
"learning_rate": 0.00029915949855301204,
"loss": 5.3946,
"step": 2720
},
{
"epoch": 1.224168912848158,
"grad_norm": 2.953125,
"learning_rate": 0.0002991477967283485,
"loss": 5.4415,
"step": 2725
},
{
"epoch": 1.2264150943396226,
"grad_norm": 3.125,
"learning_rate": 0.00029913601426482226,
"loss": 5.3648,
"step": 2730
},
{
"epoch": 1.228661275831087,
"grad_norm": 2.953125,
"learning_rate": 0.00029912415116951593,
"loss": 5.4543,
"step": 2735
},
{
"epoch": 1.2309074573225516,
"grad_norm": 2.921875,
"learning_rate": 0.0002991122074495606,
"loss": 5.381,
"step": 2740
},
{
"epoch": 1.233153638814016,
"grad_norm": 3.015625,
"learning_rate": 0.0002991001831121359,
"loss": 5.4367,
"step": 2745
},
{
"epoch": 1.2353998203054806,
"grad_norm": 3.796875,
"learning_rate": 0.00029908807816446994,
"loss": 5.5144,
"step": 2750
},
{
"epoch": 1.2376460017969453,
"grad_norm": 3.140625,
"learning_rate": 0.0002990758926138392,
"loss": 5.4193,
"step": 2755
},
{
"epoch": 1.2398921832884098,
"grad_norm": 3.078125,
"learning_rate": 0.0002990636264675687,
"loss": 5.4758,
"step": 2760
},
{
"epoch": 1.2421383647798743,
"grad_norm": 3.265625,
"learning_rate": 0.00029905127973303176,
"loss": 5.4093,
"step": 2765
},
{
"epoch": 1.2443845462713388,
"grad_norm": 3.015625,
"learning_rate": 0.00029903885241765036,
"loss": 5.4189,
"step": 2770
},
{
"epoch": 1.2466307277628033,
"grad_norm": 2.90625,
"learning_rate": 0.0002990263445288947,
"loss": 5.4447,
"step": 2775
},
{
"epoch": 1.2488769092542678,
"grad_norm": 3.03125,
"learning_rate": 0.0002990137560742836,
"loss": 5.3926,
"step": 2780
},
{
"epoch": 1.2511230907457322,
"grad_norm": 3.203125,
"learning_rate": 0.00029900108706138416,
"loss": 5.3857,
"step": 2785
},
{
"epoch": 1.2533692722371967,
"grad_norm": 2.890625,
"learning_rate": 0.000298988337497812,
"loss": 5.4141,
"step": 2790
},
{
"epoch": 1.2556154537286612,
"grad_norm": 3.0625,
"learning_rate": 0.0002989755073912311,
"loss": 5.422,
"step": 2795
},
{
"epoch": 1.2578616352201257,
"grad_norm": 3.1875,
"learning_rate": 0.0002989625967493541,
"loss": 5.3838,
"step": 2800
},
{
"epoch": 1.2601078167115902,
"grad_norm": 3.046875,
"learning_rate": 0.00029894960557994146,
"loss": 5.5335,
"step": 2805
},
{
"epoch": 1.262353998203055,
"grad_norm": 2.9375,
"learning_rate": 0.00029893653389080274,
"loss": 5.3528,
"step": 2810
},
{
"epoch": 1.2646001796945194,
"grad_norm": 3.15625,
"learning_rate": 0.0002989233816897954,
"loss": 5.3309,
"step": 2815
},
{
"epoch": 1.266846361185984,
"grad_norm": 3.09375,
"learning_rate": 0.0002989101489848256,
"loss": 5.4407,
"step": 2820
},
{
"epoch": 1.2690925426774484,
"grad_norm": 3.421875,
"learning_rate": 0.0002988968357838477,
"loss": 5.3808,
"step": 2825
},
{
"epoch": 1.271338724168913,
"grad_norm": 2.9375,
"learning_rate": 0.0002988834420948647,
"loss": 5.4058,
"step": 2830
},
{
"epoch": 1.2735849056603774,
"grad_norm": 2.953125,
"learning_rate": 0.0002988699679259275,
"loss": 5.4674,
"step": 2835
},
{
"epoch": 1.275831087151842,
"grad_norm": 3.0,
"learning_rate": 0.00029885641328513594,
"loss": 5.4242,
"step": 2840
},
{
"epoch": 1.2780772686433064,
"grad_norm": 3.109375,
"learning_rate": 0.0002988427781806379,
"loss": 5.4332,
"step": 2845
},
{
"epoch": 1.280323450134771,
"grad_norm": 2.953125,
"learning_rate": 0.0002988290626206297,
"loss": 5.3583,
"step": 2850
},
{
"epoch": 1.2825696316262354,
"grad_norm": 3.328125,
"learning_rate": 0.000298815266613356,
"loss": 5.3448,
"step": 2855
},
{
"epoch": 1.2848158131176999,
"grad_norm": 3.03125,
"learning_rate": 0.0002988013901671099,
"loss": 5.4957,
"step": 2860
},
{
"epoch": 1.2870619946091644,
"grad_norm": 3.078125,
"learning_rate": 0.0002987874332902328,
"loss": 5.4692,
"step": 2865
},
{
"epoch": 1.2893081761006289,
"grad_norm": 3.09375,
"learning_rate": 0.0002987733959911144,
"loss": 5.3743,
"step": 2870
},
{
"epoch": 1.2915543575920934,
"grad_norm": 2.890625,
"learning_rate": 0.00029875927827819286,
"loss": 5.368,
"step": 2875
},
{
"epoch": 1.2938005390835579,
"grad_norm": 3.046875,
"learning_rate": 0.00029874508015995463,
"loss": 5.3748,
"step": 2880
},
{
"epoch": 1.2960467205750223,
"grad_norm": 3.140625,
"learning_rate": 0.0002987308016449344,
"loss": 5.3995,
"step": 2885
},
{
"epoch": 1.2982929020664868,
"grad_norm": 3.1875,
"learning_rate": 0.00029871644274171534,
"loss": 5.3753,
"step": 2890
},
{
"epoch": 1.3005390835579516,
"grad_norm": 3.234375,
"learning_rate": 0.00029870200345892876,
"loss": 5.4296,
"step": 2895
},
{
"epoch": 1.302785265049416,
"grad_norm": 3.09375,
"learning_rate": 0.00029868748380525444,
"loss": 5.315,
"step": 2900
},
{
"epoch": 1.3050314465408805,
"grad_norm": 3.125,
"learning_rate": 0.0002986728837894205,
"loss": 5.4592,
"step": 2905
},
{
"epoch": 1.307277628032345,
"grad_norm": 3.203125,
"learning_rate": 0.00029865820342020325,
"loss": 5.4735,
"step": 2910
},
{
"epoch": 1.3095238095238095,
"grad_norm": 3.109375,
"learning_rate": 0.0002986434427064273,
"loss": 5.3768,
"step": 2915
},
{
"epoch": 1.311769991015274,
"grad_norm": 2.890625,
"learning_rate": 0.0002986286016569657,
"loss": 5.381,
"step": 2920
},
{
"epoch": 1.3140161725067385,
"grad_norm": 2.890625,
"learning_rate": 0.0002986136802807396,
"loss": 5.4079,
"step": 2925
},
{
"epoch": 1.316262353998203,
"grad_norm": 3.21875,
"learning_rate": 0.00029859867858671857,
"loss": 5.435,
"step": 2930
},
{
"epoch": 1.3185085354896675,
"grad_norm": 3.171875,
"learning_rate": 0.00029858359658392045,
"loss": 5.4919,
"step": 2935
},
{
"epoch": 1.320754716981132,
"grad_norm": 2.859375,
"learning_rate": 0.00029856843428141127,
"loss": 5.3849,
"step": 2940
},
{
"epoch": 1.3230008984725967,
"grad_norm": 3.703125,
"learning_rate": 0.00029855319168830543,
"loss": 5.4001,
"step": 2945
},
{
"epoch": 1.3252470799640612,
"grad_norm": 3.375,
"learning_rate": 0.0002985378688137656,
"loss": 5.5048,
"step": 2950
},
{
"epoch": 1.3274932614555257,
"grad_norm": 3.03125,
"learning_rate": 0.00029852246566700253,
"loss": 5.367,
"step": 2955
},
{
"epoch": 1.3297394429469902,
"grad_norm": 2.921875,
"learning_rate": 0.0002985069822572754,
"loss": 5.3137,
"step": 2960
},
{
"epoch": 1.3319856244384547,
"grad_norm": 3.15625,
"learning_rate": 0.0002984914185938916,
"loss": 5.3961,
"step": 2965
},
{
"epoch": 1.3342318059299192,
"grad_norm": 3.1875,
"learning_rate": 0.0002984757746862068,
"loss": 5.4488,
"step": 2970
},
{
"epoch": 1.3364779874213837,
"grad_norm": 3.171875,
"learning_rate": 0.00029846005054362474,
"loss": 5.4318,
"step": 2975
},
{
"epoch": 1.3387241689128482,
"grad_norm": 2.96875,
"learning_rate": 0.0002984442461755977,
"loss": 5.3834,
"step": 2980
},
{
"epoch": 1.3409703504043127,
"grad_norm": 3.0625,
"learning_rate": 0.00029842836159162583,
"loss": 5.4205,
"step": 2985
},
{
"epoch": 1.3432165318957772,
"grad_norm": 2.90625,
"learning_rate": 0.0002984123968012577,
"loss": 5.4352,
"step": 2990
},
{
"epoch": 1.3454627133872417,
"grad_norm": 3.03125,
"learning_rate": 0.0002983963518140901,
"loss": 5.4451,
"step": 2995
},
{
"epoch": 1.3477088948787062,
"grad_norm": 3.0625,
"learning_rate": 0.00029838022663976793,
"loss": 5.3171,
"step": 3000
},
{
"epoch": 1.3477088948787062,
"eval_loss": 5.344548225402832,
"eval_runtime": 16.0596,
"eval_samples_per_second": 1931.124,
"eval_steps_per_second": 241.414,
"step": 3000
},
{
"epoch": 1.3499550763701706,
"grad_norm": 2.984375,
"learning_rate": 0.0002983640212879844,
"loss": 5.4371,
"step": 3005
},
{
"epoch": 1.3522012578616351,
"grad_norm": 3.265625,
"learning_rate": 0.0002983477357684809,
"loss": 5.3769,
"step": 3010
},
{
"epoch": 1.3544474393530996,
"grad_norm": 3.421875,
"learning_rate": 0.0002983313700910468,
"loss": 5.4952,
"step": 3015
},
{
"epoch": 1.3566936208445641,
"grad_norm": 2.96875,
"learning_rate": 0.00029831492426552,
"loss": 5.3494,
"step": 3020
},
{
"epoch": 1.3589398023360286,
"grad_norm": 3.0625,
"learning_rate": 0.00029829839830178636,
"loss": 5.4431,
"step": 3025
},
{
"epoch": 1.3611859838274933,
"grad_norm": 2.953125,
"learning_rate": 0.00029828179220977994,
"loss": 5.3644,
"step": 3030
},
{
"epoch": 1.3634321653189578,
"grad_norm": 3.1875,
"learning_rate": 0.000298265105999483,
"loss": 5.3982,
"step": 3035
},
{
"epoch": 1.3656783468104223,
"grad_norm": 3.03125,
"learning_rate": 0.00029824833968092595,
"loss": 5.3913,
"step": 3040
},
{
"epoch": 1.3679245283018868,
"grad_norm": 2.96875,
"learning_rate": 0.00029823149326418735,
"loss": 5.3851,
"step": 3045
},
{
"epoch": 1.3701707097933513,
"grad_norm": 3.0,
"learning_rate": 0.0002982145667593939,
"loss": 5.3206,
"step": 3050
},
{
"epoch": 1.3724168912848158,
"grad_norm": 3.203125,
"learning_rate": 0.00029819756017672043,
"loss": 5.3429,
"step": 3055
},
{
"epoch": 1.3746630727762803,
"grad_norm": 3.25,
"learning_rate": 0.00029818047352639,
"loss": 5.4596,
"step": 3060
},
{
"epoch": 1.3769092542677448,
"grad_norm": 3.078125,
"learning_rate": 0.00029816330681867366,
"loss": 5.3423,
"step": 3065
},
{
"epoch": 1.3791554357592093,
"grad_norm": 2.875,
"learning_rate": 0.0002981460600638907,
"loss": 5.3283,
"step": 3070
},
{
"epoch": 1.3814016172506738,
"grad_norm": 2.921875,
"learning_rate": 0.00029812873327240844,
"loss": 5.3159,
"step": 3075
},
{
"epoch": 1.3836477987421385,
"grad_norm": 2.890625,
"learning_rate": 0.0002981113264546424,
"loss": 5.3529,
"step": 3080
},
{
"epoch": 1.385893980233603,
"grad_norm": 3.125,
"learning_rate": 0.0002980938396210561,
"loss": 5.46,
"step": 3085
},
{
"epoch": 1.3881401617250675,
"grad_norm": 2.890625,
"learning_rate": 0.00029807627278216126,
"loss": 5.4219,
"step": 3090
},
{
"epoch": 1.390386343216532,
"grad_norm": 3.03125,
"learning_rate": 0.0002980586259485177,
"loss": 5.4519,
"step": 3095
},
{
"epoch": 1.3926325247079965,
"grad_norm": 3.15625,
"learning_rate": 0.00029804089913073315,
"loss": 5.4067,
"step": 3100
},
{
"epoch": 1.394878706199461,
"grad_norm": 3.046875,
"learning_rate": 0.0002980230923394637,
"loss": 5.348,
"step": 3105
},
{
"epoch": 1.3971248876909255,
"grad_norm": 3.109375,
"learning_rate": 0.00029800520558541317,
"loss": 5.3693,
"step": 3110
},
{
"epoch": 1.39937106918239,
"grad_norm": 2.96875,
"learning_rate": 0.0002979872388793338,
"loss": 5.3537,
"step": 3115
},
{
"epoch": 1.4016172506738545,
"grad_norm": 2.75,
"learning_rate": 0.00029796919223202563,
"loss": 5.3571,
"step": 3120
},
{
"epoch": 1.403863432165319,
"grad_norm": 3.0,
"learning_rate": 0.0002979510656543369,
"loss": 5.3759,
"step": 3125
},
{
"epoch": 1.4061096136567834,
"grad_norm": 3.109375,
"learning_rate": 0.0002979328591571639,
"loss": 5.3222,
"step": 3130
},
{
"epoch": 1.408355795148248,
"grad_norm": 3.0,
"learning_rate": 0.00029791457275145085,
"loss": 5.2987,
"step": 3135
},
{
"epoch": 1.4106019766397124,
"grad_norm": 2.984375,
"learning_rate": 0.00029789620644819005,
"loss": 5.3843,
"step": 3140
},
{
"epoch": 1.412848158131177,
"grad_norm": 3.03125,
"learning_rate": 0.00029787776025842186,
"loss": 5.3461,
"step": 3145
},
{
"epoch": 1.4150943396226414,
"grad_norm": 3.015625,
"learning_rate": 0.00029785923419323467,
"loss": 5.3381,
"step": 3150
},
{
"epoch": 1.417340521114106,
"grad_norm": 2.890625,
"learning_rate": 0.0002978406282637648,
"loss": 5.3985,
"step": 3155
},
{
"epoch": 1.4195867026055704,
"grad_norm": 2.953125,
"learning_rate": 0.0002978219424811967,
"loss": 5.3383,
"step": 3160
},
{
"epoch": 1.4218328840970351,
"grad_norm": 3.125,
"learning_rate": 0.00029780317685676276,
"loss": 5.4033,
"step": 3165
},
{
"epoch": 1.4240790655884996,
"grad_norm": 3.03125,
"learning_rate": 0.0002977843314017433,
"loss": 5.4135,
"step": 3170
},
{
"epoch": 1.426325247079964,
"grad_norm": 3.0,
"learning_rate": 0.0002977654061274668,
"loss": 5.3461,
"step": 3175
},
{
"epoch": 1.4285714285714286,
"grad_norm": 3.0625,
"learning_rate": 0.0002977464010453095,
"loss": 5.281,
"step": 3180
},
{
"epoch": 1.430817610062893,
"grad_norm": 3.359375,
"learning_rate": 0.0002977273161666957,
"loss": 5.4328,
"step": 3185
},
{
"epoch": 1.4330637915543576,
"grad_norm": 3.0,
"learning_rate": 0.00029770815150309787,
"loss": 5.3081,
"step": 3190
},
{
"epoch": 1.435309973045822,
"grad_norm": 2.984375,
"learning_rate": 0.0002976889070660361,
"loss": 5.4198,
"step": 3195
},
{
"epoch": 1.4375561545372866,
"grad_norm": 2.90625,
"learning_rate": 0.0002976695828670787,
"loss": 5.3054,
"step": 3200
},
{
"epoch": 1.439802336028751,
"grad_norm": 2.984375,
"learning_rate": 0.00029765017891784175,
"loss": 5.4182,
"step": 3205
},
{
"epoch": 1.4420485175202156,
"grad_norm": 2.765625,
"learning_rate": 0.00029763069522998936,
"loss": 5.3818,
"step": 3210
},
{
"epoch": 1.44429469901168,
"grad_norm": 2.78125,
"learning_rate": 0.0002976111318152336,
"loss": 5.34,
"step": 3215
},
{
"epoch": 1.4465408805031448,
"grad_norm": 2.96875,
"learning_rate": 0.0002975914886853344,
"loss": 5.4218,
"step": 3220
},
{
"epoch": 1.4487870619946093,
"grad_norm": 3.078125,
"learning_rate": 0.00029757176585209957,
"loss": 5.3399,
"step": 3225
},
{
"epoch": 1.4510332434860738,
"grad_norm": 3.265625,
"learning_rate": 0.000297551963327385,
"loss": 5.2921,
"step": 3230
},
{
"epoch": 1.4532794249775383,
"grad_norm": 2.890625,
"learning_rate": 0.00029753208112309423,
"loss": 5.3799,
"step": 3235
},
{
"epoch": 1.4555256064690028,
"grad_norm": 2.890625,
"learning_rate": 0.00029751211925117897,
"loss": 5.2984,
"step": 3240
},
{
"epoch": 1.4577717879604672,
"grad_norm": 3.265625,
"learning_rate": 0.00029749207772363867,
"loss": 5.379,
"step": 3245
},
{
"epoch": 1.4600179694519317,
"grad_norm": 3.0,
"learning_rate": 0.0002974719565525207,
"loss": 5.3465,
"step": 3250
},
{
"epoch": 1.4622641509433962,
"grad_norm": 2.90625,
"learning_rate": 0.0002974517557499201,
"loss": 5.413,
"step": 3255
},
{
"epoch": 1.4645103324348607,
"grad_norm": 3.40625,
"learning_rate": 0.00029743147532798023,
"loss": 5.2814,
"step": 3260
},
{
"epoch": 1.4667565139263252,
"grad_norm": 2.96875,
"learning_rate": 0.00029741111529889194,
"loss": 5.3454,
"step": 3265
},
{
"epoch": 1.4690026954177897,
"grad_norm": 3.078125,
"learning_rate": 0.000297390675674894,
"loss": 5.3013,
"step": 3270
},
{
"epoch": 1.4712488769092542,
"grad_norm": 3.09375,
"learning_rate": 0.0002973701564682731,
"loss": 5.2762,
"step": 3275
},
{
"epoch": 1.4734950584007187,
"grad_norm": 3.015625,
"learning_rate": 0.00029734955769136377,
"loss": 5.3686,
"step": 3280
},
{
"epoch": 1.4757412398921832,
"grad_norm": 3.140625,
"learning_rate": 0.00029732887935654827,
"loss": 5.3697,
"step": 3285
},
{
"epoch": 1.4779874213836477,
"grad_norm": 2.953125,
"learning_rate": 0.0002973081214762568,
"loss": 5.2504,
"step": 3290
},
{
"epoch": 1.4802336028751122,
"grad_norm": 2.9375,
"learning_rate": 0.00029728728406296735,
"loss": 5.3318,
"step": 3295
},
{
"epoch": 1.482479784366577,
"grad_norm": 3.078125,
"learning_rate": 0.00029726636712920564,
"loss": 5.3078,
"step": 3300
},
{
"epoch": 1.4847259658580414,
"grad_norm": 3.046875,
"learning_rate": 0.0002972453706875453,
"loss": 5.3814,
"step": 3305
},
{
"epoch": 1.486972147349506,
"grad_norm": 2.875,
"learning_rate": 0.0002972242947506076,
"loss": 5.2753,
"step": 3310
},
{
"epoch": 1.4892183288409704,
"grad_norm": 3.046875,
"learning_rate": 0.0002972031393310619,
"loss": 5.3256,
"step": 3315
},
{
"epoch": 1.4914645103324349,
"grad_norm": 3.0625,
"learning_rate": 0.0002971819044416249,
"loss": 5.3758,
"step": 3320
},
{
"epoch": 1.4937106918238994,
"grad_norm": 2.75,
"learning_rate": 0.00029716059009506145,
"loss": 5.3209,
"step": 3325
},
{
"epoch": 1.4959568733153639,
"grad_norm": 3.109375,
"learning_rate": 0.000297139196304184,
"loss": 5.3075,
"step": 3330
},
{
"epoch": 1.4982030548068284,
"grad_norm": 2.859375,
"learning_rate": 0.0002971177230818527,
"loss": 5.3805,
"step": 3335
},
{
"epoch": 1.5004492362982929,
"grad_norm": 3.0625,
"learning_rate": 0.0002970961704409756,
"loss": 5.3156,
"step": 3340
},
{
"epoch": 1.5026954177897576,
"grad_norm": 2.90625,
"learning_rate": 0.0002970745383945084,
"loss": 5.3465,
"step": 3345
},
{
"epoch": 1.504941599281222,
"grad_norm": 3.015625,
"learning_rate": 0.00029705282695545454,
"loss": 5.3717,
"step": 3350
},
{
"epoch": 1.5071877807726866,
"grad_norm": 3.09375,
"learning_rate": 0.00029703103613686527,
"loss": 5.2288,
"step": 3355
},
{
"epoch": 1.509433962264151,
"grad_norm": 3.1875,
"learning_rate": 0.0002970091659518393,
"loss": 5.2978,
"step": 3360
},
{
"epoch": 1.5116801437556155,
"grad_norm": 2.9375,
"learning_rate": 0.0002969872164135234,
"loss": 5.2993,
"step": 3365
},
{
"epoch": 1.51392632524708,
"grad_norm": 3.0625,
"learning_rate": 0.00029696518753511173,
"loss": 5.3231,
"step": 3370
},
{
"epoch": 1.5161725067385445,
"grad_norm": 2.796875,
"learning_rate": 0.0002969430793298464,
"loss": 5.334,
"step": 3375
},
{
"epoch": 1.518418688230009,
"grad_norm": 3.03125,
"learning_rate": 0.00029692089181101696,
"loss": 5.2514,
"step": 3380
},
{
"epoch": 1.5206648697214735,
"grad_norm": 2.890625,
"learning_rate": 0.0002968986249919609,
"loss": 5.3403,
"step": 3385
},
{
"epoch": 1.522911051212938,
"grad_norm": 3.0625,
"learning_rate": 0.0002968762788860631,
"loss": 5.3209,
"step": 3390
},
{
"epoch": 1.5251572327044025,
"grad_norm": 3.125,
"learning_rate": 0.0002968538535067564,
"loss": 5.3657,
"step": 3395
},
{
"epoch": 1.527403414195867,
"grad_norm": 2.96875,
"learning_rate": 0.000296831348867521,
"loss": 5.3167,
"step": 3400
},
{
"epoch": 1.5296495956873315,
"grad_norm": 2.953125,
"learning_rate": 0.0002968087649818848,
"loss": 5.2753,
"step": 3405
},
{
"epoch": 1.531895777178796,
"grad_norm": 2.984375,
"learning_rate": 0.0002967861018634237,
"loss": 5.3678,
"step": 3410
},
{
"epoch": 1.5341419586702605,
"grad_norm": 3.265625,
"learning_rate": 0.00029676335952576074,
"loss": 5.3243,
"step": 3415
},
{
"epoch": 1.536388140161725,
"grad_norm": 3.109375,
"learning_rate": 0.0002967405379825668,
"loss": 5.2466,
"step": 3420
},
{
"epoch": 1.5386343216531895,
"grad_norm": 2.953125,
"learning_rate": 0.0002967176372475604,
"loss": 5.2428,
"step": 3425
},
{
"epoch": 1.540880503144654,
"grad_norm": 2.890625,
"learning_rate": 0.0002966946573345076,
"loss": 5.2614,
"step": 3430
},
{
"epoch": 1.5431266846361185,
"grad_norm": 2.921875,
"learning_rate": 0.00029667159825722206,
"loss": 5.3399,
"step": 3435
},
{
"epoch": 1.545372866127583,
"grad_norm": 3.0625,
"learning_rate": 0.00029664846002956506,
"loss": 5.2338,
"step": 3440
},
{
"epoch": 1.5476190476190477,
"grad_norm": 3.09375,
"learning_rate": 0.0002966252426654454,
"loss": 5.3445,
"step": 3445
},
{
"epoch": 1.5498652291105122,
"grad_norm": 2.875,
"learning_rate": 0.0002966019461788196,
"loss": 5.2916,
"step": 3450
},
{
"epoch": 1.5521114106019767,
"grad_norm": 2.9375,
"learning_rate": 0.0002965785705836915,
"loss": 5.3159,
"step": 3455
},
{
"epoch": 1.5543575920934412,
"grad_norm": 3.1875,
"learning_rate": 0.0002965551158941127,
"loss": 5.3027,
"step": 3460
},
{
"epoch": 1.5566037735849056,
"grad_norm": 2.96875,
"learning_rate": 0.0002965315821241823,
"loss": 5.2319,
"step": 3465
},
{
"epoch": 1.5588499550763701,
"grad_norm": 3.875,
"learning_rate": 0.00029650796928804685,
"loss": 5.3169,
"step": 3470
},
{
"epoch": 1.5610961365678346,
"grad_norm": 3.03125,
"learning_rate": 0.0002964842773999005,
"loss": 5.2524,
"step": 3475
},
{
"epoch": 1.5633423180592994,
"grad_norm": 2.921875,
"learning_rate": 0.0002964605064739849,
"loss": 5.3455,
"step": 3480
},
{
"epoch": 1.5655884995507638,
"grad_norm": 3.015625,
"learning_rate": 0.0002964366565245892,
"loss": 5.3241,
"step": 3485
},
{
"epoch": 1.5678346810422283,
"grad_norm": 3.015625,
"learning_rate": 0.00029641272756605023,
"loss": 5.301,
"step": 3490
},
{
"epoch": 1.5700808625336928,
"grad_norm": 3.0,
"learning_rate": 0.0002963887196127519,
"loss": 5.2987,
"step": 3495
},
{
"epoch": 1.5723270440251573,
"grad_norm": 2.96875,
"learning_rate": 0.00029636463267912607,
"loss": 5.2262,
"step": 3500
},
{
"epoch": 1.5745732255166218,
"grad_norm": 2.90625,
"learning_rate": 0.00029634046677965174,
"loss": 5.2556,
"step": 3505
},
{
"epoch": 1.5768194070080863,
"grad_norm": 2.90625,
"learning_rate": 0.00029631622192885553,
"loss": 5.3328,
"step": 3510
},
{
"epoch": 1.5790655884995508,
"grad_norm": 3.078125,
"learning_rate": 0.00029629189814131155,
"loss": 5.3252,
"step": 3515
},
{
"epoch": 1.5813117699910153,
"grad_norm": 3.03125,
"learning_rate": 0.0002962674954316413,
"loss": 5.2871,
"step": 3520
},
{
"epoch": 1.5835579514824798,
"grad_norm": 2.890625,
"learning_rate": 0.0002962430138145137,
"loss": 5.2723,
"step": 3525
},
{
"epoch": 1.5858041329739443,
"grad_norm": 2.765625,
"learning_rate": 0.000296218453304645,
"loss": 5.2836,
"step": 3530
},
{
"epoch": 1.5880503144654088,
"grad_norm": 3.015625,
"learning_rate": 0.00029619381391679923,
"loss": 5.3014,
"step": 3535
},
{
"epoch": 1.5902964959568733,
"grad_norm": 2.890625,
"learning_rate": 0.00029616909566578746,
"loss": 5.2194,
"step": 3540
},
{
"epoch": 1.5925426774483378,
"grad_norm": 2.875,
"learning_rate": 0.0002961442985664684,
"loss": 5.3363,
"step": 3545
},
{
"epoch": 1.5947888589398023,
"grad_norm": 2.875,
"learning_rate": 0.000296119422633748,
"loss": 5.2192,
"step": 3550
},
{
"epoch": 1.5970350404312668,
"grad_norm": 3.109375,
"learning_rate": 0.0002960944678825797,
"loss": 5.2585,
"step": 3555
},
{
"epoch": 1.5992812219227313,
"grad_norm": 3.40625,
"learning_rate": 0.0002960694343279643,
"loss": 5.4105,
"step": 3560
},
{
"epoch": 1.6015274034141957,
"grad_norm": 2.953125,
"learning_rate": 0.0002960443219849499,
"loss": 5.2834,
"step": 3565
},
{
"epoch": 1.6037735849056602,
"grad_norm": 2.953125,
"learning_rate": 0.0002960191308686321,
"loss": 5.2917,
"step": 3570
},
{
"epoch": 1.6060197663971247,
"grad_norm": 2.953125,
"learning_rate": 0.0002959938609941537,
"loss": 5.3014,
"step": 3575
},
{
"epoch": 1.6082659478885895,
"grad_norm": 3.0625,
"learning_rate": 0.00029596851237670494,
"loss": 5.2469,
"step": 3580
},
{
"epoch": 1.610512129380054,
"grad_norm": 3.046875,
"learning_rate": 0.00029594308503152344,
"loss": 5.2651,
"step": 3585
},
{
"epoch": 1.6127583108715184,
"grad_norm": 2.9375,
"learning_rate": 0.00029591757897389403,
"loss": 5.2144,
"step": 3590
},
{
"epoch": 1.615004492362983,
"grad_norm": 3.015625,
"learning_rate": 0.00029589199421914885,
"loss": 5.2536,
"step": 3595
},
{
"epoch": 1.6172506738544474,
"grad_norm": 2.90625,
"learning_rate": 0.0002958663307826674,
"loss": 5.2291,
"step": 3600
},
{
"epoch": 1.619496855345912,
"grad_norm": 2.875,
"learning_rate": 0.00029584058867987656,
"loss": 5.2936,
"step": 3605
},
{
"epoch": 1.6217430368373764,
"grad_norm": 3.171875,
"learning_rate": 0.00029581476792625035,
"loss": 5.3135,
"step": 3610
},
{
"epoch": 1.6239892183288411,
"grad_norm": 3.078125,
"learning_rate": 0.0002957888685373101,
"loss": 5.2395,
"step": 3615
},
{
"epoch": 1.6262353998203056,
"grad_norm": 3.015625,
"learning_rate": 0.0002957628905286245,
"loss": 5.2269,
"step": 3620
},
{
"epoch": 1.6284815813117701,
"grad_norm": 2.953125,
"learning_rate": 0.00029573683391580946,
"loss": 5.2192,
"step": 3625
},
{
"epoch": 1.6307277628032346,
"grad_norm": 3.109375,
"learning_rate": 0.000295710698714528,
"loss": 5.2539,
"step": 3630
},
{
"epoch": 1.632973944294699,
"grad_norm": 3.03125,
"learning_rate": 0.0002956844849404906,
"loss": 5.2506,
"step": 3635
},
{
"epoch": 1.6352201257861636,
"grad_norm": 2.78125,
"learning_rate": 0.00029565819260945483,
"loss": 5.2739,
"step": 3640
},
{
"epoch": 1.637466307277628,
"grad_norm": 3.03125,
"learning_rate": 0.00029563182173722555,
"loss": 5.232,
"step": 3645
},
{
"epoch": 1.6397124887690926,
"grad_norm": 2.890625,
"learning_rate": 0.0002956053723396548,
"loss": 5.3054,
"step": 3650
},
{
"epoch": 1.641958670260557,
"grad_norm": 2.9375,
"learning_rate": 0.0002955788444326418,
"loss": 5.2955,
"step": 3655
},
{
"epoch": 1.6442048517520216,
"grad_norm": 3.0,
"learning_rate": 0.00029555223803213305,
"loss": 5.2577,
"step": 3660
},
{
"epoch": 1.646451033243486,
"grad_norm": 2.96875,
"learning_rate": 0.00029552555315412216,
"loss": 5.2796,
"step": 3665
},
{
"epoch": 1.6486972147349506,
"grad_norm": 3.75,
"learning_rate": 0.0002954987898146499,
"loss": 5.3159,
"step": 3670
},
{
"epoch": 1.650943396226415,
"grad_norm": 2.890625,
"learning_rate": 0.0002954719480298043,
"loss": 5.2639,
"step": 3675
},
{
"epoch": 1.6531895777178796,
"grad_norm": 2.875,
"learning_rate": 0.00029544502781572035,
"loss": 5.2906,
"step": 3680
},
{
"epoch": 1.655435759209344,
"grad_norm": 4.75,
"learning_rate": 0.0002954180291885804,
"loss": 5.299,
"step": 3685
},
{
"epoch": 1.6576819407008085,
"grad_norm": 3.046875,
"learning_rate": 0.00029539095216461395,
"loss": 5.2026,
"step": 3690
},
{
"epoch": 1.659928122192273,
"grad_norm": 2.859375,
"learning_rate": 0.0002953637967600974,
"loss": 5.2159,
"step": 3695
},
{
"epoch": 1.6621743036837375,
"grad_norm": 2.953125,
"learning_rate": 0.0002953365629913544,
"loss": 5.22,
"step": 3700
},
{
"epoch": 1.664420485175202,
"grad_norm": 3.015625,
"learning_rate": 0.0002953092508747557,
"loss": 5.1528,
"step": 3705
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.09375,
"learning_rate": 0.0002952818604267193,
"loss": 5.234,
"step": 3710
},
{
"epoch": 1.668912848158131,
"grad_norm": 3.421875,
"learning_rate": 0.0002952543916637099,
"loss": 5.263,
"step": 3715
},
{
"epoch": 1.6711590296495957,
"grad_norm": 2.984375,
"learning_rate": 0.00029522684460223965,
"loss": 5.2879,
"step": 3720
},
{
"epoch": 1.6734052111410602,
"grad_norm": 3.046875,
"learning_rate": 0.0002951992192588676,
"loss": 5.2081,
"step": 3725
},
{
"epoch": 1.6756513926325247,
"grad_norm": 2.953125,
"learning_rate": 0.0002951715156501999,
"loss": 5.2688,
"step": 3730
},
{
"epoch": 1.6778975741239892,
"grad_norm": 3.0,
"learning_rate": 0.00029514373379288967,
"loss": 5.2266,
"step": 3735
},
{
"epoch": 1.6801437556154537,
"grad_norm": 2.859375,
"learning_rate": 0.0002951158737036372,
"loss": 5.2542,
"step": 3740
},
{
"epoch": 1.6823899371069182,
"grad_norm": 2.984375,
"learning_rate": 0.0002950879353991897,
"loss": 5.2341,
"step": 3745
},
{
"epoch": 1.684636118598383,
"grad_norm": 3.171875,
"learning_rate": 0.0002950599188963414,
"loss": 5.2238,
"step": 3750
},
{
"epoch": 1.6868823000898474,
"grad_norm": 3.09375,
"learning_rate": 0.0002950318242119337,
"loss": 5.3397,
"step": 3755
},
{
"epoch": 1.689128481581312,
"grad_norm": 3.015625,
"learning_rate": 0.0002950036513628547,
"loss": 5.2441,
"step": 3760
},
{
"epoch": 1.6913746630727764,
"grad_norm": 2.859375,
"learning_rate": 0.0002949754003660397,
"loss": 5.3238,
"step": 3765
},
{
"epoch": 1.693620844564241,
"grad_norm": 3.390625,
"learning_rate": 0.00029494707123847095,
"loss": 5.3302,
"step": 3770
},
{
"epoch": 1.6958670260557054,
"grad_norm": 3.28125,
"learning_rate": 0.0002949186639971777,
"loss": 5.2831,
"step": 3775
},
{
"epoch": 1.6981132075471699,
"grad_norm": 3.078125,
"learning_rate": 0.00029489017865923597,
"loss": 5.2566,
"step": 3780
},
{
"epoch": 1.7003593890386344,
"grad_norm": 2.9375,
"learning_rate": 0.00029486161524176893,
"loss": 5.2631,
"step": 3785
},
{
"epoch": 1.7026055705300989,
"grad_norm": 3.046875,
"learning_rate": 0.0002948329737619466,
"loss": 5.2597,
"step": 3790
},
{
"epoch": 1.7048517520215634,
"grad_norm": 3.265625,
"learning_rate": 0.0002948042542369859,
"loss": 5.2838,
"step": 3795
},
{
"epoch": 1.7070979335130279,
"grad_norm": 2.9375,
"learning_rate": 0.0002947754566841508,
"loss": 5.2681,
"step": 3800
},
{
"epoch": 1.7093441150044923,
"grad_norm": 3.046875,
"learning_rate": 0.00029474658112075197,
"loss": 5.3089,
"step": 3805
},
{
"epoch": 1.7115902964959568,
"grad_norm": 3.03125,
"learning_rate": 0.00029471762756414703,
"loss": 5.2663,
"step": 3810
},
{
"epoch": 1.7138364779874213,
"grad_norm": 2.953125,
"learning_rate": 0.00029468859603174065,
"loss": 5.2597,
"step": 3815
},
{
"epoch": 1.7160826594788858,
"grad_norm": 3.046875,
"learning_rate": 0.00029465948654098427,
"loss": 5.2646,
"step": 3820
},
{
"epoch": 1.7183288409703503,
"grad_norm": 2.890625,
"learning_rate": 0.0002946302991093761,
"loss": 5.2662,
"step": 3825
},
{
"epoch": 1.7205750224618148,
"grad_norm": 2.890625,
"learning_rate": 0.00029460103375446116,
"loss": 5.2176,
"step": 3830
},
{
"epoch": 1.7228212039532793,
"grad_norm": 2.84375,
"learning_rate": 0.00029457169049383164,
"loss": 5.225,
"step": 3835
},
{
"epoch": 1.7250673854447438,
"grad_norm": 3.09375,
"learning_rate": 0.00029454226934512624,
"loss": 5.2631,
"step": 3840
},
{
"epoch": 1.7273135669362083,
"grad_norm": 2.8125,
"learning_rate": 0.00029451277032603064,
"loss": 5.2029,
"step": 3845
},
{
"epoch": 1.7295597484276728,
"grad_norm": 2.921875,
"learning_rate": 0.0002944831934542772,
"loss": 5.2321,
"step": 3850
},
{
"epoch": 1.7318059299191375,
"grad_norm": 3.03125,
"learning_rate": 0.00029445353874764526,
"loss": 5.2173,
"step": 3855
},
{
"epoch": 1.734052111410602,
"grad_norm": 2.90625,
"learning_rate": 0.00029442380622396073,
"loss": 5.2293,
"step": 3860
},
{
"epoch": 1.7362982929020665,
"grad_norm": 2.984375,
"learning_rate": 0.00029439399590109645,
"loss": 5.1509,
"step": 3865
},
{
"epoch": 1.738544474393531,
"grad_norm": 2.890625,
"learning_rate": 0.00029436410779697206,
"loss": 5.2911,
"step": 3870
},
{
"epoch": 1.7407906558849955,
"grad_norm": 3.03125,
"learning_rate": 0.00029433414192955377,
"loss": 5.1782,
"step": 3875
},
{
"epoch": 1.74303683737646,
"grad_norm": 3.0,
"learning_rate": 0.0002943040983168547,
"loss": 5.2294,
"step": 3880
},
{
"epoch": 1.7452830188679245,
"grad_norm": 3.171875,
"learning_rate": 0.0002942739769769347,
"loss": 5.2567,
"step": 3885
},
{
"epoch": 1.7475292003593892,
"grad_norm": 3.546875,
"learning_rate": 0.00029424377792790023,
"loss": 5.2894,
"step": 3890
},
{
"epoch": 1.7497753818508537,
"grad_norm": 2.953125,
"learning_rate": 0.0002942135011879046,
"loss": 5.3933,
"step": 3895
},
{
"epoch": 1.7520215633423182,
"grad_norm": 3.1875,
"learning_rate": 0.00029418314677514764,
"loss": 5.295,
"step": 3900
},
{
"epoch": 1.7542677448337827,
"grad_norm": 3.15625,
"learning_rate": 0.0002941527147078761,
"loss": 5.1949,
"step": 3905
},
{
"epoch": 1.7565139263252472,
"grad_norm": 2.96875,
"learning_rate": 0.00029412220500438317,
"loss": 5.1329,
"step": 3910
},
{
"epoch": 1.7587601078167117,
"grad_norm": 3.109375,
"learning_rate": 0.0002940916176830089,
"loss": 5.3141,
"step": 3915
},
{
"epoch": 1.7610062893081762,
"grad_norm": 3.109375,
"learning_rate": 0.0002940609527621399,
"loss": 5.2578,
"step": 3920
},
{
"epoch": 1.7632524707996406,
"grad_norm": 3.0,
"learning_rate": 0.00029403021026020955,
"loss": 5.2614,
"step": 3925
},
{
"epoch": 1.7654986522911051,
"grad_norm": 3.109375,
"learning_rate": 0.00029399939019569767,
"loss": 5.2955,
"step": 3930
},
{
"epoch": 1.7677448337825696,
"grad_norm": 2.9375,
"learning_rate": 0.00029396849258713084,
"loss": 5.2972,
"step": 3935
},
{
"epoch": 1.7699910152740341,
"grad_norm": 3.09375,
"learning_rate": 0.00029393751745308215,
"loss": 5.2714,
"step": 3940
},
{
"epoch": 1.7722371967654986,
"grad_norm": 3.234375,
"learning_rate": 0.0002939064648121714,
"loss": 5.2846,
"step": 3945
},
{
"epoch": 1.7744833782569631,
"grad_norm": 2.90625,
"learning_rate": 0.00029387533468306504,
"loss": 5.263,
"step": 3950
},
{
"epoch": 1.7767295597484276,
"grad_norm": 3.09375,
"learning_rate": 0.0002938441270844758,
"loss": 5.1442,
"step": 3955
},
{
"epoch": 1.778975741239892,
"grad_norm": 2.859375,
"learning_rate": 0.00029381284203516334,
"loss": 5.209,
"step": 3960
},
{
"epoch": 1.7812219227313566,
"grad_norm": 3.078125,
"learning_rate": 0.00029378147955393363,
"loss": 5.2285,
"step": 3965
},
{
"epoch": 1.783468104222821,
"grad_norm": 3.171875,
"learning_rate": 0.00029375003965963935,
"loss": 5.2605,
"step": 3970
},
{
"epoch": 1.7857142857142856,
"grad_norm": 2.921875,
"learning_rate": 0.00029371852237117957,
"loss": 5.2557,
"step": 3975
},
{
"epoch": 1.78796046720575,
"grad_norm": 2.96875,
"learning_rate": 0.00029368692770749994,
"loss": 5.1953,
"step": 3980
},
{
"epoch": 1.7902066486972146,
"grad_norm": 3.0,
"learning_rate": 0.00029365525568759266,
"loss": 5.2138,
"step": 3985
},
{
"epoch": 1.7924528301886793,
"grad_norm": 3.03125,
"learning_rate": 0.0002936235063304964,
"loss": 5.2362,
"step": 3990
},
{
"epoch": 1.7946990116801438,
"grad_norm": 3.703125,
"learning_rate": 0.0002935916796552963,
"loss": 5.238,
"step": 3995
},
{
"epoch": 1.7969451931716083,
"grad_norm": 3.03125,
"learning_rate": 0.00029355977568112403,
"loss": 5.2092,
"step": 4000
},
{
"epoch": 1.7969451931716083,
"eval_loss": 5.183039665222168,
"eval_runtime": 16.1808,
"eval_samples_per_second": 1916.649,
"eval_steps_per_second": 239.604,
"step": 4000
},
{
"epoch": 1.7991913746630728,
"grad_norm": 2.875,
"learning_rate": 0.00029352779442715765,
"loss": 5.2075,
"step": 4005
},
{
"epoch": 1.8014375561545373,
"grad_norm": 3.0,
"learning_rate": 0.0002934957359126218,
"loss": 5.1898,
"step": 4010
},
{
"epoch": 1.8036837376460018,
"grad_norm": 3.25,
"learning_rate": 0.0002934636001567873,
"loss": 5.2844,
"step": 4015
},
{
"epoch": 1.8059299191374663,
"grad_norm": 3.109375,
"learning_rate": 0.0002934313871789718,
"loss": 5.2941,
"step": 4020
},
{
"epoch": 1.808176100628931,
"grad_norm": 3.140625,
"learning_rate": 0.00029339909699853904,
"loss": 5.3192,
"step": 4025
},
{
"epoch": 1.8104222821203955,
"grad_norm": 3.015625,
"learning_rate": 0.00029336672963489925,
"loss": 5.1957,
"step": 4030
},
{
"epoch": 1.81266846361186,
"grad_norm": 2.890625,
"learning_rate": 0.0002933342851075092,
"loss": 5.2322,
"step": 4035
},
{
"epoch": 1.8149146451033245,
"grad_norm": 2.921875,
"learning_rate": 0.00029330176343587175,
"loss": 5.124,
"step": 4040
},
{
"epoch": 1.817160826594789,
"grad_norm": 2.921875,
"learning_rate": 0.00029326916463953646,
"loss": 5.195,
"step": 4045
},
{
"epoch": 1.8194070080862534,
"grad_norm": 3.03125,
"learning_rate": 0.0002932364887380991,
"loss": 5.2398,
"step": 4050
},
{
"epoch": 1.821653189577718,
"grad_norm": 3.03125,
"learning_rate": 0.00029320373575120174,
"loss": 5.1243,
"step": 4055
},
{
"epoch": 1.8238993710691824,
"grad_norm": 2.921875,
"learning_rate": 0.0002931709056985328,
"loss": 5.1875,
"step": 4060
},
{
"epoch": 1.826145552560647,
"grad_norm": 3.140625,
"learning_rate": 0.0002931379985998272,
"loss": 5.2679,
"step": 4065
},
{
"epoch": 1.8283917340521114,
"grad_norm": 3.109375,
"learning_rate": 0.0002931050144748659,
"loss": 5.1371,
"step": 4070
},
{
"epoch": 1.830637915543576,
"grad_norm": 2.921875,
"learning_rate": 0.0002930719533434764,
"loss": 5.2114,
"step": 4075
},
{
"epoch": 1.8328840970350404,
"grad_norm": 2.984375,
"learning_rate": 0.0002930388152255323,
"loss": 5.2132,
"step": 4080
},
{
"epoch": 1.835130278526505,
"grad_norm": 2.96875,
"learning_rate": 0.0002930056001409537,
"loss": 5.211,
"step": 4085
},
{
"epoch": 1.8373764600179694,
"grad_norm": 2.921875,
"learning_rate": 0.0002929723081097067,
"loss": 5.1184,
"step": 4090
},
{
"epoch": 1.8396226415094339,
"grad_norm": 2.796875,
"learning_rate": 0.00029293893915180387,
"loss": 5.1128,
"step": 4095
},
{
"epoch": 1.8418688230008984,
"grad_norm": 3.078125,
"learning_rate": 0.00029290549328730395,
"loss": 5.2356,
"step": 4100
},
{
"epoch": 1.8441150044923629,
"grad_norm": 3.140625,
"learning_rate": 0.0002928719705363118,
"loss": 5.1903,
"step": 4105
},
{
"epoch": 1.8463611859838274,
"grad_norm": 2.9375,
"learning_rate": 0.00029283837091897876,
"loss": 5.1552,
"step": 4110
},
{
"epoch": 1.8486073674752919,
"grad_norm": 3.015625,
"learning_rate": 0.00029280469445550213,
"loss": 5.1519,
"step": 4115
},
{
"epoch": 1.8508535489667564,
"grad_norm": 3.09375,
"learning_rate": 0.0002927709411661255,
"loss": 5.181,
"step": 4120
},
{
"epoch": 1.853099730458221,
"grad_norm": 3.15625,
"learning_rate": 0.00029273711107113856,
"loss": 5.1855,
"step": 4125
},
{
"epoch": 1.8553459119496856,
"grad_norm": 3.015625,
"learning_rate": 0.00029270320419087743,
"loss": 5.2248,
"step": 4130
},
{
"epoch": 1.85759209344115,
"grad_norm": 3.015625,
"learning_rate": 0.00029266922054572395,
"loss": 5.1783,
"step": 4135
},
{
"epoch": 1.8598382749326146,
"grad_norm": 2.890625,
"learning_rate": 0.00029263516015610655,
"loss": 5.2069,
"step": 4140
},
{
"epoch": 1.862084456424079,
"grad_norm": 3.078125,
"learning_rate": 0.0002926010230424995,
"loss": 5.1962,
"step": 4145
},
{
"epoch": 1.8643306379155435,
"grad_norm": 3.0625,
"learning_rate": 0.00029256680922542334,
"loss": 5.1803,
"step": 4150
},
{
"epoch": 1.866576819407008,
"grad_norm": 2.875,
"learning_rate": 0.0002925325187254446,
"loss": 5.2128,
"step": 4155
},
{
"epoch": 1.8688230008984728,
"grad_norm": 2.78125,
"learning_rate": 0.00029249815156317605,
"loss": 5.184,
"step": 4160
},
{
"epoch": 1.8710691823899372,
"grad_norm": 3.109375,
"learning_rate": 0.0002924637077592764,
"loss": 5.2263,
"step": 4165
},
{
"epoch": 1.8733153638814017,
"grad_norm": 3.15625,
"learning_rate": 0.0002924291873344505,
"loss": 5.1901,
"step": 4170
},
{
"epoch": 1.8755615453728662,
"grad_norm": 2.921875,
"learning_rate": 0.00029239459030944935,
"loss": 5.2521,
"step": 4175
},
{
"epoch": 1.8778077268643307,
"grad_norm": 2.9375,
"learning_rate": 0.0002923599167050697,
"loss": 5.167,
"step": 4180
},
{
"epoch": 1.8800539083557952,
"grad_norm": 2.9375,
"learning_rate": 0.0002923251665421547,
"loss": 5.1813,
"step": 4185
},
{
"epoch": 1.8823000898472597,
"grad_norm": 2.8125,
"learning_rate": 0.0002922903398415933,
"loss": 5.2392,
"step": 4190
},
{
"epoch": 1.8845462713387242,
"grad_norm": 3.0,
"learning_rate": 0.0002922554366243205,
"loss": 5.2032,
"step": 4195
},
{
"epoch": 1.8867924528301887,
"grad_norm": 3.421875,
"learning_rate": 0.00029222045691131737,
"loss": 5.1849,
"step": 4200
},
{
"epoch": 1.8890386343216532,
"grad_norm": 2.90625,
"learning_rate": 0.00029218540072361074,
"loss": 5.1958,
"step": 4205
},
{
"epoch": 1.8912848158131177,
"grad_norm": 2.921875,
"learning_rate": 0.0002921502680822738,
"loss": 5.174,
"step": 4210
},
{
"epoch": 1.8935309973045822,
"grad_norm": 3.25,
"learning_rate": 0.0002921150590084252,
"loss": 5.2986,
"step": 4215
},
{
"epoch": 1.8957771787960467,
"grad_norm": 3.125,
"learning_rate": 0.00029207977352323005,
"loss": 5.1103,
"step": 4220
},
{
"epoch": 1.8980233602875112,
"grad_norm": 2.796875,
"learning_rate": 0.000292044411647899,
"loss": 5.2693,
"step": 4225
},
{
"epoch": 1.9002695417789757,
"grad_norm": 3.046875,
"learning_rate": 0.00029200897340368883,
"loss": 5.219,
"step": 4230
},
{
"epoch": 1.9025157232704402,
"grad_norm": 2.921875,
"learning_rate": 0.0002919734588119021,
"loss": 5.1556,
"step": 4235
},
{
"epoch": 1.9047619047619047,
"grad_norm": 3.15625,
"learning_rate": 0.0002919378678938874,
"loss": 5.202,
"step": 4240
},
{
"epoch": 1.9070080862533692,
"grad_norm": 2.921875,
"learning_rate": 0.000291902200671039,
"loss": 5.1384,
"step": 4245
},
{
"epoch": 1.9092542677448336,
"grad_norm": 3.140625,
"learning_rate": 0.00029186645716479734,
"loss": 5.1446,
"step": 4250
},
{
"epoch": 1.9115004492362981,
"grad_norm": 3.3125,
"learning_rate": 0.0002918306373966484,
"loss": 5.3229,
"step": 4255
},
{
"epoch": 1.9137466307277629,
"grad_norm": 2.96875,
"learning_rate": 0.00029179474138812424,
"loss": 5.1863,
"step": 4260
},
{
"epoch": 1.9159928122192273,
"grad_norm": 3.046875,
"learning_rate": 0.0002917587691608026,
"loss": 5.1948,
"step": 4265
},
{
"epoch": 1.9182389937106918,
"grad_norm": 3.25,
"learning_rate": 0.00029172272073630707,
"loss": 5.1398,
"step": 4270
},
{
"epoch": 1.9204851752021563,
"grad_norm": 2.90625,
"learning_rate": 0.000291686596136307,
"loss": 5.2248,
"step": 4275
},
{
"epoch": 1.9227313566936208,
"grad_norm": 2.921875,
"learning_rate": 0.00029165039538251786,
"loss": 5.2137,
"step": 4280
},
{
"epoch": 1.9249775381850853,
"grad_norm": 3.046875,
"learning_rate": 0.00029161411849670034,
"loss": 5.2118,
"step": 4285
},
{
"epoch": 1.9272237196765498,
"grad_norm": 3.09375,
"learning_rate": 0.00029157776550066134,
"loss": 5.1821,
"step": 4290
},
{
"epoch": 1.9294699011680145,
"grad_norm": 2.890625,
"learning_rate": 0.0002915413364162533,
"loss": 5.1385,
"step": 4295
},
{
"epoch": 1.931716082659479,
"grad_norm": 2.9375,
"learning_rate": 0.00029150483126537445,
"loss": 5.1265,
"step": 4300
},
{
"epoch": 1.9339622641509435,
"grad_norm": 2.921875,
"learning_rate": 0.0002914682500699688,
"loss": 5.173,
"step": 4305
},
{
"epoch": 1.936208445642408,
"grad_norm": 3.25,
"learning_rate": 0.00029143159285202597,
"loss": 5.175,
"step": 4310
},
{
"epoch": 1.9384546271338725,
"grad_norm": 2.921875,
"learning_rate": 0.0002913948596335814,
"loss": 5.1925,
"step": 4315
},
{
"epoch": 1.940700808625337,
"grad_norm": 3.21875,
"learning_rate": 0.00029135805043671597,
"loss": 5.1982,
"step": 4320
},
{
"epoch": 1.9429469901168015,
"grad_norm": 3.015625,
"learning_rate": 0.0002913211652835567,
"loss": 5.1497,
"step": 4325
},
{
"epoch": 1.945193171608266,
"grad_norm": 2.890625,
"learning_rate": 0.00029128420419627566,
"loss": 5.151,
"step": 4330
},
{
"epoch": 1.9474393530997305,
"grad_norm": 3.015625,
"learning_rate": 0.00029124716719709114,
"loss": 5.1051,
"step": 4335
},
{
"epoch": 1.949685534591195,
"grad_norm": 2.9375,
"learning_rate": 0.0002912100543082666,
"loss": 5.1568,
"step": 4340
},
{
"epoch": 1.9519317160826595,
"grad_norm": 2.9375,
"learning_rate": 0.0002911728655521115,
"loss": 5.1824,
"step": 4345
},
{
"epoch": 1.954177897574124,
"grad_norm": 3.03125,
"learning_rate": 0.00029113560095098064,
"loss": 5.1908,
"step": 4350
},
{
"epoch": 1.9564240790655885,
"grad_norm": 3.046875,
"learning_rate": 0.0002910982605272745,
"loss": 5.1337,
"step": 4355
},
{
"epoch": 1.958670260557053,
"grad_norm": 2.953125,
"learning_rate": 0.0002910608443034391,
"loss": 5.2017,
"step": 4360
},
{
"epoch": 1.9609164420485174,
"grad_norm": 2.84375,
"learning_rate": 0.00029102335230196615,
"loss": 5.131,
"step": 4365
},
{
"epoch": 1.963162623539982,
"grad_norm": 2.875,
"learning_rate": 0.00029098578454539274,
"loss": 5.1247,
"step": 4370
},
{
"epoch": 1.9654088050314464,
"grad_norm": 3.046875,
"learning_rate": 0.0002909481410563017,
"loss": 5.1947,
"step": 4375
},
{
"epoch": 1.967654986522911,
"grad_norm": 2.9375,
"learning_rate": 0.0002909104218573211,
"loss": 5.162,
"step": 4380
},
{
"epoch": 1.9699011680143754,
"grad_norm": 2.9375,
"learning_rate": 0.00029087262697112494,
"loss": 5.1051,
"step": 4385
},
{
"epoch": 1.97214734950584,
"grad_norm": 2.9375,
"learning_rate": 0.00029083475642043216,
"loss": 5.1855,
"step": 4390
},
{
"epoch": 1.9743935309973046,
"grad_norm": 3.046875,
"learning_rate": 0.0002907968102280077,
"loss": 5.1933,
"step": 4395
},
{
"epoch": 1.9766397124887691,
"grad_norm": 3.234375,
"learning_rate": 0.0002907587884166616,
"loss": 5.1138,
"step": 4400
},
{
"epoch": 1.9788858939802336,
"grad_norm": 3.1875,
"learning_rate": 0.0002907206910092498,
"loss": 5.1579,
"step": 4405
},
{
"epoch": 1.9811320754716981,
"grad_norm": 2.96875,
"learning_rate": 0.000290682518028673,
"loss": 5.1163,
"step": 4410
},
{
"epoch": 1.9833782569631626,
"grad_norm": 2.921875,
"learning_rate": 0.00029064426949787807,
"loss": 5.1887,
"step": 4415
},
{
"epoch": 1.985624438454627,
"grad_norm": 2.984375,
"learning_rate": 0.0002906059454398567,
"loss": 5.2164,
"step": 4420
},
{
"epoch": 1.9878706199460916,
"grad_norm": 3.125,
"learning_rate": 0.0002905675458776464,
"loss": 5.0996,
"step": 4425
},
{
"epoch": 1.9901168014375563,
"grad_norm": 3.03125,
"learning_rate": 0.0002905290708343298,
"loss": 5.1728,
"step": 4430
},
{
"epoch": 1.9923629829290208,
"grad_norm": 3.0,
"learning_rate": 0.00029049052033303514,
"loss": 5.1126,
"step": 4435
},
{
"epoch": 1.9946091644204853,
"grad_norm": 3.03125,
"learning_rate": 0.00029045189439693564,
"loss": 5.1486,
"step": 4440
},
{
"epoch": 1.9968553459119498,
"grad_norm": 2.890625,
"learning_rate": 0.00029041319304925036,
"loss": 5.098,
"step": 4445
},
{
"epoch": 1.9991015274034143,
"grad_norm": 3.0,
"learning_rate": 0.0002903744163132432,
"loss": 5.1236,
"step": 4450
},
{
"epoch": 2.001347708894879,
"grad_norm": 3.171875,
"learning_rate": 0.00029033556421222383,
"loss": 5.1441,
"step": 4455
},
{
"epoch": 2.0035938903863433,
"grad_norm": 2.984375,
"learning_rate": 0.0002902966367695468,
"loss": 5.0451,
"step": 4460
},
{
"epoch": 2.0058400718778078,
"grad_norm": 2.859375,
"learning_rate": 0.00029025763400861236,
"loss": 5.104,
"step": 4465
},
{
"epoch": 2.0080862533692723,
"grad_norm": 2.9375,
"learning_rate": 0.00029021855595286574,
"loss": 5.0897,
"step": 4470
},
{
"epoch": 2.0103324348607368,
"grad_norm": 2.90625,
"learning_rate": 0.0002901794026257975,
"loss": 4.9517,
"step": 4475
},
{
"epoch": 2.0125786163522013,
"grad_norm": 2.859375,
"learning_rate": 0.0002901401740509435,
"loss": 4.9774,
"step": 4480
},
{
"epoch": 2.0148247978436657,
"grad_norm": 2.96875,
"learning_rate": 0.0002901008702518848,
"loss": 4.986,
"step": 4485
},
{
"epoch": 2.0170709793351302,
"grad_norm": 3.015625,
"learning_rate": 0.0002900614912522476,
"loss": 5.0134,
"step": 4490
},
{
"epoch": 2.0193171608265947,
"grad_norm": 3.3125,
"learning_rate": 0.0002900220370757035,
"loss": 5.0922,
"step": 4495
},
{
"epoch": 2.0215633423180592,
"grad_norm": 2.8125,
"learning_rate": 0.0002899825077459692,
"loss": 5.0198,
"step": 4500
},
{
"epoch": 2.0238095238095237,
"grad_norm": 3.203125,
"learning_rate": 0.0002899429032868064,
"loss": 5.1019,
"step": 4505
},
{
"epoch": 2.026055705300988,
"grad_norm": 3.078125,
"learning_rate": 0.0002899032237220223,
"loss": 5.0552,
"step": 4510
},
{
"epoch": 2.0283018867924527,
"grad_norm": 2.859375,
"learning_rate": 0.0002898634690754689,
"loss": 5.0344,
"step": 4515
},
{
"epoch": 2.030548068283917,
"grad_norm": 2.9375,
"learning_rate": 0.0002898236393710436,
"loss": 5.04,
"step": 4520
},
{
"epoch": 2.0327942497753817,
"grad_norm": 3.109375,
"learning_rate": 0.00028978373463268883,
"loss": 5.0868,
"step": 4525
},
{
"epoch": 2.035040431266846,
"grad_norm": 3.234375,
"learning_rate": 0.00028974375488439194,
"loss": 5.0977,
"step": 4530
},
{
"epoch": 2.0372866127583107,
"grad_norm": 2.96875,
"learning_rate": 0.0002897037001501857,
"loss": 5.0351,
"step": 4535
},
{
"epoch": 2.039532794249775,
"grad_norm": 3.5,
"learning_rate": 0.00028966357045414774,
"loss": 5.115,
"step": 4540
},
{
"epoch": 2.0417789757412397,
"grad_norm": 2.875,
"learning_rate": 0.00028962336582040086,
"loss": 5.137,
"step": 4545
},
{
"epoch": 2.0440251572327046,
"grad_norm": 3.15625,
"learning_rate": 0.0002895830862731127,
"loss": 5.0389,
"step": 4550
},
{
"epoch": 2.046271338724169,
"grad_norm": 2.921875,
"learning_rate": 0.0002895427318364963,
"loss": 5.045,
"step": 4555
},
{
"epoch": 2.0485175202156336,
"grad_norm": 3.0,
"learning_rate": 0.00028950230253480935,
"loss": 5.0665,
"step": 4560
},
{
"epoch": 2.050763701707098,
"grad_norm": 3.0,
"learning_rate": 0.00028946179839235475,
"loss": 4.9852,
"step": 4565
},
{
"epoch": 2.0530098831985626,
"grad_norm": 2.890625,
"learning_rate": 0.0002894212194334803,
"loss": 5.1119,
"step": 4570
},
{
"epoch": 2.055256064690027,
"grad_norm": 2.921875,
"learning_rate": 0.00028938056568257874,
"loss": 5.0799,
"step": 4575
},
{
"epoch": 2.0575022461814916,
"grad_norm": 3.125,
"learning_rate": 0.000289339837164088,
"loss": 5.0597,
"step": 4580
},
{
"epoch": 2.059748427672956,
"grad_norm": 2.859375,
"learning_rate": 0.0002892990339024907,
"loss": 5.0044,
"step": 4585
},
{
"epoch": 2.0619946091644206,
"grad_norm": 3.09375,
"learning_rate": 0.0002892581559223144,
"loss": 5.0103,
"step": 4590
},
{
"epoch": 2.064240790655885,
"grad_norm": 3.140625,
"learning_rate": 0.00028921720324813185,
"loss": 5.0157,
"step": 4595
},
{
"epoch": 2.0664869721473496,
"grad_norm": 2.875,
"learning_rate": 0.0002891761759045603,
"loss": 5.0655,
"step": 4600
},
{
"epoch": 2.068733153638814,
"grad_norm": 3.0,
"learning_rate": 0.0002891350739162622,
"loss": 5.1106,
"step": 4605
},
{
"epoch": 2.0709793351302785,
"grad_norm": 3.125,
"learning_rate": 0.0002890938973079447,
"loss": 5.129,
"step": 4610
},
{
"epoch": 2.073225516621743,
"grad_norm": 3.125,
"learning_rate": 0.00028905264610436,
"loss": 5.031,
"step": 4615
},
{
"epoch": 2.0754716981132075,
"grad_norm": 2.859375,
"learning_rate": 0.00028901132033030475,
"loss": 5.0716,
"step": 4620
},
{
"epoch": 2.077717879604672,
"grad_norm": 2.984375,
"learning_rate": 0.000288969920010621,
"loss": 5.0758,
"step": 4625
},
{
"epoch": 2.0799640610961365,
"grad_norm": 3.0625,
"learning_rate": 0.000288928445170195,
"loss": 5.0436,
"step": 4630
},
{
"epoch": 2.082210242587601,
"grad_norm": 2.84375,
"learning_rate": 0.00028888689583395826,
"loss": 5.0841,
"step": 4635
},
{
"epoch": 2.0844564240790655,
"grad_norm": 3.140625,
"learning_rate": 0.00028884527202688683,
"loss": 5.0446,
"step": 4640
},
{
"epoch": 2.08670260557053,
"grad_norm": 3.015625,
"learning_rate": 0.0002888035737740016,
"loss": 4.9765,
"step": 4645
},
{
"epoch": 2.0889487870619945,
"grad_norm": 2.96875,
"learning_rate": 0.00028876180110036823,
"loss": 5.1058,
"step": 4650
},
{
"epoch": 2.091194968553459,
"grad_norm": 2.953125,
"learning_rate": 0.0002887199540310971,
"loss": 5.0546,
"step": 4655
},
{
"epoch": 2.0934411500449235,
"grad_norm": 2.828125,
"learning_rate": 0.00028867803259134326,
"loss": 4.9612,
"step": 4660
},
{
"epoch": 2.095687331536388,
"grad_norm": 3.046875,
"learning_rate": 0.00028863603680630653,
"loss": 5.0064,
"step": 4665
},
{
"epoch": 2.0979335130278525,
"grad_norm": 2.984375,
"learning_rate": 0.00028859396670123135,
"loss": 5.0299,
"step": 4670
},
{
"epoch": 2.100179694519317,
"grad_norm": 3.171875,
"learning_rate": 0.000288551822301407,
"loss": 5.0889,
"step": 4675
},
{
"epoch": 2.1024258760107815,
"grad_norm": 3.0,
"learning_rate": 0.00028850960363216714,
"loss": 5.0944,
"step": 4680
},
{
"epoch": 2.1046720575022464,
"grad_norm": 2.953125,
"learning_rate": 0.0002884673107188904,
"loss": 4.9692,
"step": 4685
},
{
"epoch": 2.106918238993711,
"grad_norm": 3.140625,
"learning_rate": 0.00028842494358699973,
"loss": 4.9994,
"step": 4690
},
{
"epoch": 2.1091644204851754,
"grad_norm": 3.03125,
"learning_rate": 0.000288382502261963,
"loss": 5.0891,
"step": 4695
},
{
"epoch": 2.11141060197664,
"grad_norm": 3.125,
"learning_rate": 0.0002883399867692924,
"loss": 5.0812,
"step": 4700
},
{
"epoch": 2.1136567834681044,
"grad_norm": 3.1875,
"learning_rate": 0.00028829739713454483,
"loss": 5.0365,
"step": 4705
},
{
"epoch": 2.115902964959569,
"grad_norm": 3.0625,
"learning_rate": 0.0002882547333833218,
"loss": 5.0654,
"step": 4710
},
{
"epoch": 2.1181491464510334,
"grad_norm": 2.859375,
"learning_rate": 0.00028821199554126934,
"loss": 4.9854,
"step": 4715
},
{
"epoch": 2.120395327942498,
"grad_norm": 3.046875,
"learning_rate": 0.0002881691836340779,
"loss": 5.0865,
"step": 4720
},
{
"epoch": 2.1226415094339623,
"grad_norm": 2.9375,
"learning_rate": 0.00028812629768748267,
"loss": 5.045,
"step": 4725
},
{
"epoch": 2.124887690925427,
"grad_norm": 3.390625,
"learning_rate": 0.00028808333772726316,
"loss": 5.0897,
"step": 4730
},
{
"epoch": 2.1271338724168913,
"grad_norm": 3.265625,
"learning_rate": 0.00028804030377924345,
"loss": 5.0187,
"step": 4735
},
{
"epoch": 2.129380053908356,
"grad_norm": 2.9375,
"learning_rate": 0.0002879971958692921,
"loss": 5.0898,
"step": 4740
},
{
"epoch": 2.1316262353998203,
"grad_norm": 2.953125,
"learning_rate": 0.00028795401402332215,
"loss": 5.0058,
"step": 4745
},
{
"epoch": 2.133872416891285,
"grad_norm": 2.984375,
"learning_rate": 0.00028791075826729097,
"loss": 5.0468,
"step": 4750
},
{
"epoch": 2.1361185983827493,
"grad_norm": 3.109375,
"learning_rate": 0.00028786742862720055,
"loss": 5.0241,
"step": 4755
},
{
"epoch": 2.138364779874214,
"grad_norm": 3.0625,
"learning_rate": 0.0002878240251290971,
"loss": 5.1405,
"step": 4760
},
{
"epoch": 2.1406109613656783,
"grad_norm": 2.828125,
"learning_rate": 0.0002877805477990713,
"loss": 5.0095,
"step": 4765
},
{
"epoch": 2.142857142857143,
"grad_norm": 3.203125,
"learning_rate": 0.00028773699666325835,
"loss": 5.0425,
"step": 4770
},
{
"epoch": 2.1451033243486073,
"grad_norm": 3.078125,
"learning_rate": 0.00028769337174783754,
"loss": 5.0217,
"step": 4775
},
{
"epoch": 2.147349505840072,
"grad_norm": 3.078125,
"learning_rate": 0.0002876496730790327,
"loss": 5.0803,
"step": 4780
},
{
"epoch": 2.1495956873315363,
"grad_norm": 3.484375,
"learning_rate": 0.00028760590068311194,
"loss": 5.0487,
"step": 4785
},
{
"epoch": 2.1518418688230008,
"grad_norm": 3.0625,
"learning_rate": 0.00028756205458638776,
"loss": 5.0174,
"step": 4790
},
{
"epoch": 2.1540880503144653,
"grad_norm": 3.421875,
"learning_rate": 0.00028751813481521694,
"loss": 5.0855,
"step": 4795
},
{
"epoch": 2.1563342318059298,
"grad_norm": 3.140625,
"learning_rate": 0.00028747414139600034,
"loss": 5.0706,
"step": 4800
},
{
"epoch": 2.1585804132973943,
"grad_norm": 2.984375,
"learning_rate": 0.0002874300743551835,
"loss": 5.1177,
"step": 4805
},
{
"epoch": 2.1608265947888587,
"grad_norm": 3.328125,
"learning_rate": 0.0002873859337192558,
"loss": 5.0589,
"step": 4810
},
{
"epoch": 2.1630727762803232,
"grad_norm": 3.140625,
"learning_rate": 0.00028734171951475104,
"loss": 5.0959,
"step": 4815
},
{
"epoch": 2.165318957771788,
"grad_norm": 3.078125,
"learning_rate": 0.00028729743176824735,
"loss": 5.0754,
"step": 4820
},
{
"epoch": 2.1675651392632527,
"grad_norm": 3.03125,
"learning_rate": 0.0002872530705063669,
"loss": 5.0442,
"step": 4825
},
{
"epoch": 2.169811320754717,
"grad_norm": 3.421875,
"learning_rate": 0.00028720863575577615,
"loss": 4.9739,
"step": 4830
},
{
"epoch": 2.1720575022461817,
"grad_norm": 3.09375,
"learning_rate": 0.0002871641275431856,
"loss": 5.0175,
"step": 4835
},
{
"epoch": 2.174303683737646,
"grad_norm": 3.15625,
"learning_rate": 0.0002871195458953501,
"loss": 5.0096,
"step": 4840
},
{
"epoch": 2.1765498652291106,
"grad_norm": 3.125,
"learning_rate": 0.0002870748908390686,
"loss": 5.0525,
"step": 4845
},
{
"epoch": 2.178796046720575,
"grad_norm": 2.890625,
"learning_rate": 0.0002870301624011839,
"loss": 5.0469,
"step": 4850
},
{
"epoch": 2.1810422282120396,
"grad_norm": 3.0,
"learning_rate": 0.0002869853606085834,
"loss": 5.0679,
"step": 4855
},
{
"epoch": 2.183288409703504,
"grad_norm": 2.9375,
"learning_rate": 0.00028694048548819816,
"loss": 5.0369,
"step": 4860
},
{
"epoch": 2.1855345911949686,
"grad_norm": 3.078125,
"learning_rate": 0.00028689553706700356,
"loss": 5.0443,
"step": 4865
},
{
"epoch": 2.187780772686433,
"grad_norm": 3.0625,
"learning_rate": 0.000286850515372019,
"loss": 4.9984,
"step": 4870
},
{
"epoch": 2.1900269541778976,
"grad_norm": 2.9375,
"learning_rate": 0.00028680542043030787,
"loss": 4.9734,
"step": 4875
},
{
"epoch": 2.192273135669362,
"grad_norm": 2.953125,
"learning_rate": 0.0002867602522689776,
"loss": 5.0096,
"step": 4880
},
{
"epoch": 2.1945193171608266,
"grad_norm": 3.265625,
"learning_rate": 0.00028671501091517967,
"loss": 4.9606,
"step": 4885
},
{
"epoch": 2.196765498652291,
"grad_norm": 3.171875,
"learning_rate": 0.0002866696963961096,
"loss": 5.072,
"step": 4890
},
{
"epoch": 2.1990116801437556,
"grad_norm": 2.96875,
"learning_rate": 0.0002866243087390067,
"loss": 5.0319,
"step": 4895
},
{
"epoch": 2.20125786163522,
"grad_norm": 3.125,
"learning_rate": 0.0002865788479711545,
"loss": 5.0198,
"step": 4900
},
{
"epoch": 2.2035040431266846,
"grad_norm": 3.015625,
"learning_rate": 0.00028653331411988034,
"loss": 5.001,
"step": 4905
},
{
"epoch": 2.205750224618149,
"grad_norm": 2.890625,
"learning_rate": 0.00028648770721255543,
"loss": 5.0652,
"step": 4910
},
{
"epoch": 2.2079964061096136,
"grad_norm": 3.0625,
"learning_rate": 0.000286442027276595,
"loss": 4.9551,
"step": 4915
},
{
"epoch": 2.210242587601078,
"grad_norm": 3.09375,
"learning_rate": 0.0002863962743394583,
"loss": 5.0335,
"step": 4920
},
{
"epoch": 2.2124887690925426,
"grad_norm": 3.265625,
"learning_rate": 0.00028635044842864805,
"loss": 5.0267,
"step": 4925
},
{
"epoch": 2.214734950584007,
"grad_norm": 3.34375,
"learning_rate": 0.0002863045495717113,
"loss": 5.0602,
"step": 4930
},
{
"epoch": 2.2169811320754715,
"grad_norm": 3.09375,
"learning_rate": 0.0002862585777962387,
"loss": 5.0753,
"step": 4935
},
{
"epoch": 2.219227313566936,
"grad_norm": 3.09375,
"learning_rate": 0.0002862125331298648,
"loss": 5.0716,
"step": 4940
},
{
"epoch": 2.2214734950584005,
"grad_norm": 3.328125,
"learning_rate": 0.0002861664156002679,
"loss": 5.0408,
"step": 4945
},
{
"epoch": 2.223719676549865,
"grad_norm": 3.25,
"learning_rate": 0.00028612022523517015,
"loss": 5.0705,
"step": 4950
},
{
"epoch": 2.22596585804133,
"grad_norm": 2.921875,
"learning_rate": 0.0002860739620623375,
"loss": 5.06,
"step": 4955
},
{
"epoch": 2.2282120395327945,
"grad_norm": 2.953125,
"learning_rate": 0.00028602762610957966,
"loss": 5.0575,
"step": 4960
},
{
"epoch": 2.230458221024259,
"grad_norm": 2.90625,
"learning_rate": 0.0002859812174047501,
"loss": 5.0911,
"step": 4965
},
{
"epoch": 2.2327044025157234,
"grad_norm": 3.0625,
"learning_rate": 0.00028593473597574595,
"loss": 5.0714,
"step": 4970
},
{
"epoch": 2.234950584007188,
"grad_norm": 3.15625,
"learning_rate": 0.00028588818185050816,
"loss": 4.9425,
"step": 4975
},
{
"epoch": 2.2371967654986524,
"grad_norm": 3.359375,
"learning_rate": 0.00028584155505702124,
"loss": 5.0257,
"step": 4980
},
{
"epoch": 2.239442946990117,
"grad_norm": 3.015625,
"learning_rate": 0.00028579485562331354,
"loss": 4.9997,
"step": 4985
},
{
"epoch": 2.2416891284815814,
"grad_norm": 3.0,
"learning_rate": 0.00028574808357745697,
"loss": 5.136,
"step": 4990
},
{
"epoch": 2.243935309973046,
"grad_norm": 3.046875,
"learning_rate": 0.0002857012389475671,
"loss": 4.9934,
"step": 4995
},
{
"epoch": 2.2461814914645104,
"grad_norm": 3.203125,
"learning_rate": 0.0002856543217618033,
"loss": 5.0804,
"step": 5000
},
{
"epoch": 2.2461814914645104,
"eval_loss": 5.077792644500732,
"eval_runtime": 16.1311,
"eval_samples_per_second": 1922.556,
"eval_steps_per_second": 240.343,
"step": 5000
},
{
"epoch": 2.248427672955975,
"grad_norm": 3.21875,
"learning_rate": 0.00028560733204836814,
"loss": 5.0199,
"step": 5005
},
{
"epoch": 2.2506738544474394,
"grad_norm": 3.03125,
"learning_rate": 0.0002855602698355083,
"loss": 4.9319,
"step": 5010
},
{
"epoch": 2.252920035938904,
"grad_norm": 3.28125,
"learning_rate": 0.0002855131351515136,
"loss": 5.014,
"step": 5015
},
{
"epoch": 2.2551662174303684,
"grad_norm": 2.96875,
"learning_rate": 0.00028546592802471783,
"loss": 4.9945,
"step": 5020
},
{
"epoch": 2.257412398921833,
"grad_norm": 3.03125,
"learning_rate": 0.0002854186484834979,
"loss": 5.0318,
"step": 5025
},
{
"epoch": 2.2596585804132974,
"grad_norm": 3.015625,
"learning_rate": 0.0002853712965562747,
"loss": 4.9928,
"step": 5030
},
{
"epoch": 2.261904761904762,
"grad_norm": 3.25,
"learning_rate": 0.0002853238722715122,
"loss": 5.0388,
"step": 5035
},
{
"epoch": 2.2641509433962264,
"grad_norm": 3.1875,
"learning_rate": 0.0002852763756577181,
"loss": 5.0577,
"step": 5040
},
{
"epoch": 2.266397124887691,
"grad_norm": 2.984375,
"learning_rate": 0.0002852288067434437,
"loss": 5.0389,
"step": 5045
},
{
"epoch": 2.2686433063791553,
"grad_norm": 3.265625,
"learning_rate": 0.00028518116555728334,
"loss": 5.0881,
"step": 5050
},
{
"epoch": 2.27088948787062,
"grad_norm": 3.140625,
"learning_rate": 0.0002851334521278753,
"loss": 5.0352,
"step": 5055
},
{
"epoch": 2.2731356693620843,
"grad_norm": 2.921875,
"learning_rate": 0.0002850856664839009,
"loss": 5.0594,
"step": 5060
},
{
"epoch": 2.275381850853549,
"grad_norm": 3.078125,
"learning_rate": 0.0002850378086540852,
"loss": 5.0079,
"step": 5065
},
{
"epoch": 2.2776280323450133,
"grad_norm": 2.984375,
"learning_rate": 0.00028498987866719627,
"loss": 4.9529,
"step": 5070
},
{
"epoch": 2.279874213836478,
"grad_norm": 3.09375,
"learning_rate": 0.00028494187655204594,
"loss": 5.0234,
"step": 5075
},
{
"epoch": 2.2821203953279423,
"grad_norm": 3.640625,
"learning_rate": 0.00028489380233748913,
"loss": 4.9815,
"step": 5080
},
{
"epoch": 2.284366576819407,
"grad_norm": 3.03125,
"learning_rate": 0.0002848456560524242,
"loss": 5.0092,
"step": 5085
},
{
"epoch": 2.2866127583108717,
"grad_norm": 2.78125,
"learning_rate": 0.0002847974377257927,
"loss": 5.024,
"step": 5090
},
{
"epoch": 2.288858939802336,
"grad_norm": 3.078125,
"learning_rate": 0.0002847491473865799,
"loss": 4.9528,
"step": 5095
},
{
"epoch": 2.2911051212938007,
"grad_norm": 3.15625,
"learning_rate": 0.0002847007850638138,
"loss": 5.0185,
"step": 5100
},
{
"epoch": 2.2933513027852652,
"grad_norm": 3.078125,
"learning_rate": 0.00028465235078656607,
"loss": 5.066,
"step": 5105
},
{
"epoch": 2.2955974842767297,
"grad_norm": 3.109375,
"learning_rate": 0.00028460384458395147,
"loss": 5.0169,
"step": 5110
},
{
"epoch": 2.297843665768194,
"grad_norm": 3.015625,
"learning_rate": 0.000284555266485128,
"loss": 4.9659,
"step": 5115
},
{
"epoch": 2.3000898472596587,
"grad_norm": 3.3125,
"learning_rate": 0.00028450661651929695,
"loss": 4.9802,
"step": 5120
},
{
"epoch": 2.302336028751123,
"grad_norm": 3.09375,
"learning_rate": 0.00028445789471570273,
"loss": 5.035,
"step": 5125
},
{
"epoch": 2.3045822102425877,
"grad_norm": 2.9375,
"learning_rate": 0.00028440910110363296,
"loss": 5.0922,
"step": 5130
},
{
"epoch": 2.306828391734052,
"grad_norm": 3.046875,
"learning_rate": 0.00028436023571241855,
"loss": 5.0105,
"step": 5135
},
{
"epoch": 2.3090745732255167,
"grad_norm": 3.3125,
"learning_rate": 0.0002843112985714333,
"loss": 4.9729,
"step": 5140
},
{
"epoch": 2.311320754716981,
"grad_norm": 2.953125,
"learning_rate": 0.00028426228971009426,
"loss": 5.0841,
"step": 5145
},
{
"epoch": 2.3135669362084457,
"grad_norm": 3.265625,
"learning_rate": 0.0002842132091578618,
"loss": 5.0193,
"step": 5150
},
{
"epoch": 2.31581311769991,
"grad_norm": 3.03125,
"learning_rate": 0.000284164056944239,
"loss": 5.0195,
"step": 5155
},
{
"epoch": 2.3180592991913747,
"grad_norm": 2.90625,
"learning_rate": 0.00028411483309877234,
"loss": 4.9968,
"step": 5160
},
{
"epoch": 2.320305480682839,
"grad_norm": 3.015625,
"learning_rate": 0.0002840655376510512,
"loss": 5.0199,
"step": 5165
},
{
"epoch": 2.3225516621743036,
"grad_norm": 2.96875,
"learning_rate": 0.000284016170630708,
"loss": 5.0053,
"step": 5170
},
{
"epoch": 2.324797843665768,
"grad_norm": 3.078125,
"learning_rate": 0.00028396673206741827,
"loss": 5.0486,
"step": 5175
},
{
"epoch": 2.3270440251572326,
"grad_norm": 3.15625,
"learning_rate": 0.0002839172219909005,
"loss": 5.0429,
"step": 5180
},
{
"epoch": 2.329290206648697,
"grad_norm": 3.15625,
"learning_rate": 0.0002838676404309162,
"loss": 4.9361,
"step": 5185
},
{
"epoch": 2.3315363881401616,
"grad_norm": 2.921875,
"learning_rate": 0.00028381798741726965,
"loss": 4.9766,
"step": 5190
},
{
"epoch": 2.333782569631626,
"grad_norm": 3.21875,
"learning_rate": 0.0002837682629798084,
"loss": 4.9904,
"step": 5195
},
{
"epoch": 2.3360287511230906,
"grad_norm": 3.078125,
"learning_rate": 0.0002837184671484227,
"loss": 5.0596,
"step": 5200
},
{
"epoch": 2.338274932614555,
"grad_norm": 3.046875,
"learning_rate": 0.0002836685999530459,
"loss": 4.986,
"step": 5205
},
{
"epoch": 2.3405211141060196,
"grad_norm": 2.96875,
"learning_rate": 0.0002836186614236541,
"loss": 4.9947,
"step": 5210
},
{
"epoch": 2.342767295597484,
"grad_norm": 2.96875,
"learning_rate": 0.0002835686515902663,
"loss": 4.9349,
"step": 5215
},
{
"epoch": 2.3450134770889486,
"grad_norm": 3.109375,
"learning_rate": 0.0002835185704829443,
"loss": 4.9609,
"step": 5220
},
{
"epoch": 2.3472596585804135,
"grad_norm": 3.59375,
"learning_rate": 0.000283468418131793,
"loss": 5.0416,
"step": 5225
},
{
"epoch": 2.3495058400718776,
"grad_norm": 3.1875,
"learning_rate": 0.0002834181945669599,
"loss": 5.0325,
"step": 5230
},
{
"epoch": 2.3517520215633425,
"grad_norm": 3.0625,
"learning_rate": 0.0002833678998186354,
"loss": 5.0163,
"step": 5235
},
{
"epoch": 2.353998203054807,
"grad_norm": 3.0625,
"learning_rate": 0.0002833175339170525,
"loss": 4.949,
"step": 5240
},
{
"epoch": 2.3562443845462715,
"grad_norm": 3.140625,
"learning_rate": 0.0002832670968924873,
"loss": 4.976,
"step": 5245
},
{
"epoch": 2.358490566037736,
"grad_norm": 3.109375,
"learning_rate": 0.0002832165887752584,
"loss": 5.017,
"step": 5250
},
{
"epoch": 2.3607367475292005,
"grad_norm": 3.0625,
"learning_rate": 0.00028316600959572727,
"loss": 5.0021,
"step": 5255
},
{
"epoch": 2.362982929020665,
"grad_norm": 3.03125,
"learning_rate": 0.000283115359384298,
"loss": 5.0264,
"step": 5260
},
{
"epoch": 2.3652291105121295,
"grad_norm": 3.21875,
"learning_rate": 0.00028306463817141743,
"loss": 5.0308,
"step": 5265
},
{
"epoch": 2.367475292003594,
"grad_norm": 3.28125,
"learning_rate": 0.00028301384598757506,
"loss": 5.0511,
"step": 5270
},
{
"epoch": 2.3697214734950585,
"grad_norm": 2.8125,
"learning_rate": 0.00028296298286330305,
"loss": 5.0266,
"step": 5275
},
{
"epoch": 2.371967654986523,
"grad_norm": 3.0625,
"learning_rate": 0.0002829120488291763,
"loss": 4.9507,
"step": 5280
},
{
"epoch": 2.3742138364779874,
"grad_norm": 3.0625,
"learning_rate": 0.0002828610439158122,
"loss": 5.0018,
"step": 5285
},
{
"epoch": 2.376460017969452,
"grad_norm": 2.984375,
"learning_rate": 0.0002828099681538708,
"loss": 5.0241,
"step": 5290
},
{
"epoch": 2.3787061994609164,
"grad_norm": 3.109375,
"learning_rate": 0.0002827588215740547,
"loss": 5.0567,
"step": 5295
},
{
"epoch": 2.380952380952381,
"grad_norm": 3.0,
"learning_rate": 0.0002827076042071092,
"loss": 4.9711,
"step": 5300
},
{
"epoch": 2.3831985624438454,
"grad_norm": 3.078125,
"learning_rate": 0.000282656316083822,
"loss": 5.0117,
"step": 5305
},
{
"epoch": 2.38544474393531,
"grad_norm": 3.03125,
"learning_rate": 0.0002826049572350234,
"loss": 4.9413,
"step": 5310
},
{
"epoch": 2.3876909254267744,
"grad_norm": 3.234375,
"learning_rate": 0.00028255352769158623,
"loss": 5.0217,
"step": 5315
},
{
"epoch": 2.389937106918239,
"grad_norm": 3.203125,
"learning_rate": 0.0002825020274844257,
"loss": 4.9966,
"step": 5320
},
{
"epoch": 2.3921832884097034,
"grad_norm": 3.0625,
"learning_rate": 0.00028245045664449973,
"loss": 5.0136,
"step": 5325
},
{
"epoch": 2.394429469901168,
"grad_norm": 3.109375,
"learning_rate": 0.00028239881520280847,
"loss": 5.0281,
"step": 5330
},
{
"epoch": 2.3966756513926324,
"grad_norm": 3.609375,
"learning_rate": 0.00028234710319039466,
"loss": 5.0617,
"step": 5335
},
{
"epoch": 2.398921832884097,
"grad_norm": 3.109375,
"learning_rate": 0.00028229532063834336,
"loss": 4.941,
"step": 5340
},
{
"epoch": 2.4011680143755614,
"grad_norm": 3.171875,
"learning_rate": 0.00028224346757778205,
"loss": 5.0323,
"step": 5345
},
{
"epoch": 2.403414195867026,
"grad_norm": 3.0,
"learning_rate": 0.00028219154403988063,
"loss": 4.9451,
"step": 5350
},
{
"epoch": 2.4056603773584904,
"grad_norm": 2.859375,
"learning_rate": 0.0002821395500558515,
"loss": 5.037,
"step": 5355
},
{
"epoch": 2.4079065588499553,
"grad_norm": 3.046875,
"learning_rate": 0.000282087485656949,
"loss": 4.9873,
"step": 5360
},
{
"epoch": 2.4101527403414194,
"grad_norm": 2.921875,
"learning_rate": 0.00028203535087447025,
"loss": 5.0177,
"step": 5365
},
{
"epoch": 2.4123989218328843,
"grad_norm": 3.171875,
"learning_rate": 0.00028198314573975444,
"loss": 5.1103,
"step": 5370
},
{
"epoch": 2.414645103324349,
"grad_norm": 3.015625,
"learning_rate": 0.00028193087028418305,
"loss": 5.0471,
"step": 5375
},
{
"epoch": 2.4168912848158133,
"grad_norm": 3.3125,
"learning_rate": 0.00028187852453917994,
"loss": 5.021,
"step": 5380
},
{
"epoch": 2.4191374663072778,
"grad_norm": 2.9375,
"learning_rate": 0.0002818261085362111,
"loss": 4.9735,
"step": 5385
},
{
"epoch": 2.4213836477987423,
"grad_norm": 3.296875,
"learning_rate": 0.00028177362230678485,
"loss": 4.9797,
"step": 5390
},
{
"epoch": 2.4236298292902068,
"grad_norm": 3.0,
"learning_rate": 0.00028172106588245175,
"loss": 4.9648,
"step": 5395
},
{
"epoch": 2.4258760107816713,
"grad_norm": 3.0,
"learning_rate": 0.00028166843929480436,
"loss": 5.1115,
"step": 5400
},
{
"epoch": 2.4281221922731357,
"grad_norm": 5.5,
"learning_rate": 0.00028161574257547765,
"loss": 4.9531,
"step": 5405
},
{
"epoch": 2.4303683737646002,
"grad_norm": 2.984375,
"learning_rate": 0.00028156297575614864,
"loss": 4.9762,
"step": 5410
},
{
"epoch": 2.4326145552560647,
"grad_norm": 3.03125,
"learning_rate": 0.00028151013886853647,
"loss": 5.0298,
"step": 5415
},
{
"epoch": 2.4348607367475292,
"grad_norm": 2.921875,
"learning_rate": 0.0002814572319444024,
"loss": 5.0413,
"step": 5420
},
{
"epoch": 2.4371069182389937,
"grad_norm": 3.109375,
"learning_rate": 0.0002814042550155499,
"loss": 5.0045,
"step": 5425
},
{
"epoch": 2.439353099730458,
"grad_norm": 2.921875,
"learning_rate": 0.00028135120811382435,
"loss": 5.0008,
"step": 5430
},
{
"epoch": 2.4415992812219227,
"grad_norm": 3.15625,
"learning_rate": 0.0002812980912711133,
"loss": 5.0294,
"step": 5435
},
{
"epoch": 2.443845462713387,
"grad_norm": 3.359375,
"learning_rate": 0.00028124490451934635,
"loss": 5.0769,
"step": 5440
},
{
"epoch": 2.4460916442048517,
"grad_norm": 3.421875,
"learning_rate": 0.000281191647890495,
"loss": 5.0096,
"step": 5445
},
{
"epoch": 2.448337825696316,
"grad_norm": 3.03125,
"learning_rate": 0.0002811383214165731,
"loss": 4.9805,
"step": 5450
},
{
"epoch": 2.4505840071877807,
"grad_norm": 3.046875,
"learning_rate": 0.000281084925129636,
"loss": 4.949,
"step": 5455
},
{
"epoch": 2.452830188679245,
"grad_norm": 2.9375,
"learning_rate": 0.0002810314590617813,
"loss": 4.9011,
"step": 5460
},
{
"epoch": 2.4550763701707097,
"grad_norm": 2.953125,
"learning_rate": 0.00028097792324514853,
"loss": 4.9974,
"step": 5465
},
{
"epoch": 2.457322551662174,
"grad_norm": 3.234375,
"learning_rate": 0.0002809243177119191,
"loss": 4.9817,
"step": 5470
},
{
"epoch": 2.4595687331536387,
"grad_norm": 2.984375,
"learning_rate": 0.0002808706424943164,
"loss": 5.03,
"step": 5475
},
{
"epoch": 2.461814914645103,
"grad_norm": 2.890625,
"learning_rate": 0.00028081689762460553,
"loss": 5.0556,
"step": 5480
},
{
"epoch": 2.4640610961365677,
"grad_norm": 3.015625,
"learning_rate": 0.00028076308313509365,
"loss": 5.0748,
"step": 5485
},
{
"epoch": 2.466307277628032,
"grad_norm": 2.984375,
"learning_rate": 0.00028070919905812976,
"loss": 4.9664,
"step": 5490
},
{
"epoch": 2.468553459119497,
"grad_norm": 3.109375,
"learning_rate": 0.00028065524542610456,
"loss": 5.0278,
"step": 5495
},
{
"epoch": 2.470799640610961,
"grad_norm": 2.984375,
"learning_rate": 0.00028060122227145065,
"loss": 5.0414,
"step": 5500
},
{
"epoch": 2.473045822102426,
"grad_norm": 3.4375,
"learning_rate": 0.0002805471296266424,
"loss": 4.9741,
"step": 5505
},
{
"epoch": 2.4752920035938906,
"grad_norm": 2.96875,
"learning_rate": 0.00028049296752419593,
"loss": 4.9957,
"step": 5510
},
{
"epoch": 2.477538185085355,
"grad_norm": 2.90625,
"learning_rate": 0.00028043873599666925,
"loss": 5.0025,
"step": 5515
},
{
"epoch": 2.4797843665768196,
"grad_norm": 2.921875,
"learning_rate": 0.0002803844350766618,
"loss": 4.9335,
"step": 5520
},
{
"epoch": 2.482030548068284,
"grad_norm": 3.1875,
"learning_rate": 0.0002803300647968152,
"loss": 4.9839,
"step": 5525
},
{
"epoch": 2.4842767295597485,
"grad_norm": 3.25,
"learning_rate": 0.00028027562518981216,
"loss": 4.9595,
"step": 5530
},
{
"epoch": 2.486522911051213,
"grad_norm": 2.96875,
"learning_rate": 0.0002802211162883776,
"loss": 4.9742,
"step": 5535
},
{
"epoch": 2.4887690925426775,
"grad_norm": 3.390625,
"learning_rate": 0.0002801665381252779,
"loss": 5.0239,
"step": 5540
},
{
"epoch": 2.491015274034142,
"grad_norm": 2.890625,
"learning_rate": 0.0002801118907333209,
"loss": 4.9802,
"step": 5545
},
{
"epoch": 2.4932614555256065,
"grad_norm": 3.015625,
"learning_rate": 0.0002800571741453564,
"loss": 4.9646,
"step": 5550
},
{
"epoch": 2.495507637017071,
"grad_norm": 3.03125,
"learning_rate": 0.0002800023883942755,
"loss": 4.9662,
"step": 5555
},
{
"epoch": 2.4977538185085355,
"grad_norm": 2.890625,
"learning_rate": 0.000279947533513011,
"loss": 5.0099,
"step": 5560
},
{
"epoch": 2.5,
"grad_norm": 3.03125,
"learning_rate": 0.0002798926095345373,
"loss": 4.9691,
"step": 5565
},
{
"epoch": 2.5022461814914645,
"grad_norm": 2.9375,
"learning_rate": 0.00027983761649187015,
"loss": 5.0081,
"step": 5570
},
{
"epoch": 2.504492362982929,
"grad_norm": 3.0,
"learning_rate": 0.00027978255441806713,
"loss": 4.9875,
"step": 5575
},
{
"epoch": 2.5067385444743935,
"grad_norm": 2.890625,
"learning_rate": 0.00027972742334622696,
"loss": 5.0318,
"step": 5580
},
{
"epoch": 2.508984725965858,
"grad_norm": 2.984375,
"learning_rate": 0.00027967222330949006,
"loss": 4.9564,
"step": 5585
},
{
"epoch": 2.5112309074573225,
"grad_norm": 2.96875,
"learning_rate": 0.00027961695434103827,
"loss": 4.9256,
"step": 5590
},
{
"epoch": 2.513477088948787,
"grad_norm": 3.015625,
"learning_rate": 0.00027956161647409486,
"loss": 5.0247,
"step": 5595
},
{
"epoch": 2.5157232704402515,
"grad_norm": 3.234375,
"learning_rate": 0.00027950620974192446,
"loss": 5.0235,
"step": 5600
},
{
"epoch": 2.517969451931716,
"grad_norm": 3.125,
"learning_rate": 0.00027945073417783315,
"loss": 4.956,
"step": 5605
},
{
"epoch": 2.5202156334231804,
"grad_norm": 3.046875,
"learning_rate": 0.0002793951898151684,
"loss": 4.94,
"step": 5610
},
{
"epoch": 2.522461814914645,
"grad_norm": 3.125,
"learning_rate": 0.00027933957668731897,
"loss": 5.0343,
"step": 5615
},
{
"epoch": 2.52470799640611,
"grad_norm": 3.1875,
"learning_rate": 0.0002792838948277151,
"loss": 4.958,
"step": 5620
},
{
"epoch": 2.526954177897574,
"grad_norm": 3.078125,
"learning_rate": 0.0002792281442698281,
"loss": 4.9437,
"step": 5625
},
{
"epoch": 2.529200359389039,
"grad_norm": 3.25,
"learning_rate": 0.0002791723250471708,
"loss": 4.9659,
"step": 5630
},
{
"epoch": 2.531446540880503,
"grad_norm": 3.265625,
"learning_rate": 0.00027911643719329723,
"loss": 4.9834,
"step": 5635
},
{
"epoch": 2.533692722371968,
"grad_norm": 3.171875,
"learning_rate": 0.0002790604807418027,
"loss": 4.9261,
"step": 5640
},
{
"epoch": 2.535938903863432,
"grad_norm": 3.109375,
"learning_rate": 0.0002790044557263236,
"loss": 5.0249,
"step": 5645
},
{
"epoch": 2.538185085354897,
"grad_norm": 3.015625,
"learning_rate": 0.00027894836218053784,
"loss": 4.9651,
"step": 5650
},
{
"epoch": 2.5404312668463613,
"grad_norm": 3.1875,
"learning_rate": 0.00027889220013816416,
"loss": 5.0094,
"step": 5655
},
{
"epoch": 2.542677448337826,
"grad_norm": 3.421875,
"learning_rate": 0.0002788359696329628,
"loss": 4.9669,
"step": 5660
},
{
"epoch": 2.5449236298292903,
"grad_norm": 3.0625,
"learning_rate": 0.00027877967069873494,
"loss": 4.9674,
"step": 5665
},
{
"epoch": 2.547169811320755,
"grad_norm": 3.25,
"learning_rate": 0.0002787233033693231,
"loss": 4.9891,
"step": 5670
},
{
"epoch": 2.5494159928122193,
"grad_norm": 3.0625,
"learning_rate": 0.0002786668676786106,
"loss": 4.913,
"step": 5675
},
{
"epoch": 2.551662174303684,
"grad_norm": 2.84375,
"learning_rate": 0.00027861036366052215,
"loss": 4.9285,
"step": 5680
},
{
"epoch": 2.5539083557951483,
"grad_norm": 3.0,
"learning_rate": 0.0002785537913490233,
"loss": 4.9889,
"step": 5685
},
{
"epoch": 2.556154537286613,
"grad_norm": 3.265625,
"learning_rate": 0.000278497150778121,
"loss": 4.9526,
"step": 5690
},
{
"epoch": 2.5584007187780773,
"grad_norm": 3.109375,
"learning_rate": 0.00027844044198186275,
"loss": 5.052,
"step": 5695
},
{
"epoch": 2.560646900269542,
"grad_norm": 3.375,
"learning_rate": 0.00027838366499433753,
"loss": 4.9283,
"step": 5700
},
{
"epoch": 2.5628930817610063,
"grad_norm": 3.171875,
"learning_rate": 0.00027832681984967493,
"loss": 5.0854,
"step": 5705
},
{
"epoch": 2.5651392632524708,
"grad_norm": 3.3125,
"learning_rate": 0.00027826990658204575,
"loss": 4.8997,
"step": 5710
},
{
"epoch": 2.5673854447439353,
"grad_norm": 3.015625,
"learning_rate": 0.0002782129252256617,
"loss": 5.0075,
"step": 5715
},
{
"epoch": 2.5696316262353998,
"grad_norm": 2.90625,
"learning_rate": 0.0002781558758147754,
"loss": 4.9988,
"step": 5720
},
{
"epoch": 2.5718778077268643,
"grad_norm": 2.90625,
"learning_rate": 0.0002780987583836802,
"loss": 5.0213,
"step": 5725
},
{
"epoch": 2.5741239892183287,
"grad_norm": 3.046875,
"learning_rate": 0.0002780415729667107,
"loss": 4.9287,
"step": 5730
},
{
"epoch": 2.5763701707097932,
"grad_norm": 2.9375,
"learning_rate": 0.0002779843195982421,
"loss": 4.9767,
"step": 5735
},
{
"epoch": 2.5786163522012577,
"grad_norm": 3.140625,
"learning_rate": 0.00027792699831269044,
"loss": 4.9909,
"step": 5740
},
{
"epoch": 2.5808625336927222,
"grad_norm": 3.390625,
"learning_rate": 0.00027786960914451286,
"loss": 5.0782,
"step": 5745
},
{
"epoch": 2.5831087151841867,
"grad_norm": 3.3125,
"learning_rate": 0.00027781215212820684,
"loss": 4.9401,
"step": 5750
},
{
"epoch": 2.5853548966756517,
"grad_norm": 3.03125,
"learning_rate": 0.0002777546272983112,
"loss": 4.973,
"step": 5755
},
{
"epoch": 2.5876010781671157,
"grad_norm": 2.875,
"learning_rate": 0.000277697034689405,
"loss": 4.9916,
"step": 5760
},
{
"epoch": 2.5898472596585806,
"grad_norm": 3.265625,
"learning_rate": 0.00027763937433610843,
"loss": 4.9979,
"step": 5765
},
{
"epoch": 2.5920934411500447,
"grad_norm": 2.984375,
"learning_rate": 0.00027758164627308225,
"loss": 4.9277,
"step": 5770
},
{
"epoch": 2.5943396226415096,
"grad_norm": 3.453125,
"learning_rate": 0.00027752385053502783,
"loss": 5.0059,
"step": 5775
},
{
"epoch": 2.5965858041329737,
"grad_norm": 3.15625,
"learning_rate": 0.0002774659871566874,
"loss": 4.9416,
"step": 5780
},
{
"epoch": 2.5988319856244386,
"grad_norm": 3.046875,
"learning_rate": 0.00027740805617284376,
"loss": 4.9635,
"step": 5785
},
{
"epoch": 2.601078167115903,
"grad_norm": 3.1875,
"learning_rate": 0.0002773500576183203,
"loss": 5.0296,
"step": 5790
},
{
"epoch": 2.6033243486073676,
"grad_norm": 2.9375,
"learning_rate": 0.0002772919915279812,
"loss": 4.9442,
"step": 5795
},
{
"epoch": 2.605570530098832,
"grad_norm": 3.125,
"learning_rate": 0.000277233857936731,
"loss": 4.9411,
"step": 5800
},
{
"epoch": 2.6078167115902966,
"grad_norm": 3.328125,
"learning_rate": 0.000277175656879515,
"loss": 5.0361,
"step": 5805
},
{
"epoch": 2.610062893081761,
"grad_norm": 3.0,
"learning_rate": 0.00027711738839131895,
"loss": 4.9689,
"step": 5810
},
{
"epoch": 2.6123090745732256,
"grad_norm": 3.09375,
"learning_rate": 0.00027705905250716926,
"loss": 4.9799,
"step": 5815
},
{
"epoch": 2.61455525606469,
"grad_norm": 3.015625,
"learning_rate": 0.0002770006492621327,
"loss": 5.0151,
"step": 5820
},
{
"epoch": 2.6168014375561546,
"grad_norm": 2.984375,
"learning_rate": 0.0002769421786913166,
"loss": 4.9397,
"step": 5825
},
{
"epoch": 2.619047619047619,
"grad_norm": 3.171875,
"learning_rate": 0.0002768836408298688,
"loss": 5.0281,
"step": 5830
},
{
"epoch": 2.6212938005390836,
"grad_norm": 3.078125,
"learning_rate": 0.0002768250357129775,
"loss": 4.9577,
"step": 5835
},
{
"epoch": 2.623539982030548,
"grad_norm": 2.890625,
"learning_rate": 0.00027676636337587145,
"loss": 4.9567,
"step": 5840
},
{
"epoch": 2.6257861635220126,
"grad_norm": 3.140625,
"learning_rate": 0.00027670762385381974,
"loss": 4.9665,
"step": 5845
},
{
"epoch": 2.628032345013477,
"grad_norm": 3.25,
"learning_rate": 0.00027664881718213175,
"loss": 4.9683,
"step": 5850
},
{
"epoch": 2.6302785265049415,
"grad_norm": 3.0,
"learning_rate": 0.0002765899433961574,
"loss": 4.9659,
"step": 5855
},
{
"epoch": 2.632524707996406,
"grad_norm": 3.265625,
"learning_rate": 0.00027653100253128687,
"loss": 4.9306,
"step": 5860
},
{
"epoch": 2.6347708894878705,
"grad_norm": 3.53125,
"learning_rate": 0.00027647199462295065,
"loss": 4.9186,
"step": 5865
},
{
"epoch": 2.637017070979335,
"grad_norm": 3.28125,
"learning_rate": 0.00027641291970661953,
"loss": 4.9603,
"step": 5870
},
{
"epoch": 2.6392632524707995,
"grad_norm": 2.953125,
"learning_rate": 0.00027635377781780465,
"loss": 4.9935,
"step": 5875
},
{
"epoch": 2.641509433962264,
"grad_norm": 3.015625,
"learning_rate": 0.00027629456899205725,
"loss": 5.0406,
"step": 5880
},
{
"epoch": 2.6437556154537285,
"grad_norm": 3.203125,
"learning_rate": 0.00027623529326496906,
"loss": 4.9832,
"step": 5885
},
{
"epoch": 2.6460017969451934,
"grad_norm": 3.609375,
"learning_rate": 0.0002761759506721717,
"loss": 4.9561,
"step": 5890
},
{
"epoch": 2.6482479784366575,
"grad_norm": 2.921875,
"learning_rate": 0.0002761165412493373,
"loss": 4.9534,
"step": 5895
},
{
"epoch": 2.6504941599281224,
"grad_norm": 3.015625,
"learning_rate": 0.00027605706503217806,
"loss": 4.9841,
"step": 5900
},
{
"epoch": 2.6527403414195865,
"grad_norm": 3.234375,
"learning_rate": 0.0002759975220564462,
"loss": 5.1202,
"step": 5905
},
{
"epoch": 2.6549865229110514,
"grad_norm": 3.171875,
"learning_rate": 0.0002759379123579341,
"loss": 4.9232,
"step": 5910
},
{
"epoch": 2.6572327044025155,
"grad_norm": 3.140625,
"learning_rate": 0.0002758782359724745,
"loss": 4.923,
"step": 5915
},
{
"epoch": 2.6594788858939804,
"grad_norm": 3.375,
"learning_rate": 0.00027581849293593994,
"loss": 4.9812,
"step": 5920
},
{
"epoch": 2.661725067385445,
"grad_norm": 3.046875,
"learning_rate": 0.00027575868328424307,
"loss": 5.078,
"step": 5925
},
{
"epoch": 2.6639712488769094,
"grad_norm": 3.28125,
"learning_rate": 0.00027569880705333676,
"loss": 4.9466,
"step": 5930
},
{
"epoch": 2.666217430368374,
"grad_norm": 2.984375,
"learning_rate": 0.00027563886427921377,
"loss": 4.9025,
"step": 5935
},
{
"epoch": 2.6684636118598384,
"grad_norm": 3.015625,
"learning_rate": 0.00027557885499790674,
"loss": 4.9652,
"step": 5940
},
{
"epoch": 2.670709793351303,
"grad_norm": 3.0,
"learning_rate": 0.00027551877924548854,
"loss": 5.0297,
"step": 5945
},
{
"epoch": 2.6729559748427674,
"grad_norm": 3.171875,
"learning_rate": 0.0002754586370580719,
"loss": 4.9552,
"step": 5950
},
{
"epoch": 2.675202156334232,
"grad_norm": 3.328125,
"learning_rate": 0.00027539842847180935,
"loss": 5.0043,
"step": 5955
},
{
"epoch": 2.6774483378256964,
"grad_norm": 2.90625,
"learning_rate": 0.00027533815352289353,
"loss": 4.9195,
"step": 5960
},
{
"epoch": 2.679694519317161,
"grad_norm": 3.015625,
"learning_rate": 0.00027527781224755696,
"loss": 4.9867,
"step": 5965
},
{
"epoch": 2.6819407008086253,
"grad_norm": 3.015625,
"learning_rate": 0.0002752174046820718,
"loss": 4.9602,
"step": 5970
},
{
"epoch": 2.68418688230009,
"grad_norm": 3.03125,
"learning_rate": 0.00027515693086275025,
"loss": 4.9846,
"step": 5975
},
{
"epoch": 2.6864330637915543,
"grad_norm": 3.0,
"learning_rate": 0.0002750963908259445,
"loss": 4.9414,
"step": 5980
},
{
"epoch": 2.688679245283019,
"grad_norm": 3.0625,
"learning_rate": 0.00027503578460804604,
"loss": 4.9944,
"step": 5985
},
{
"epoch": 2.6909254267744833,
"grad_norm": 2.96875,
"learning_rate": 0.00027497511224548667,
"loss": 5.0515,
"step": 5990
},
{
"epoch": 2.693171608265948,
"grad_norm": 3.484375,
"learning_rate": 0.0002749143737747377,
"loss": 4.9846,
"step": 5995
},
{
"epoch": 2.6954177897574123,
"grad_norm": 3.984375,
"learning_rate": 0.00027485356923231014,
"loss": 4.9318,
"step": 6000
},
{
"epoch": 2.6954177897574123,
"eval_loss": 5.004312992095947,
"eval_runtime": 16.1624,
"eval_samples_per_second": 1918.841,
"eval_steps_per_second": 239.878,
"step": 6000
},
{
"epoch": 2.697663971248877,
"grad_norm": 3.078125,
"learning_rate": 0.00027479269865475487,
"loss": 4.9818,
"step": 6005
},
{
"epoch": 2.6999101527403413,
"grad_norm": 3.0,
"learning_rate": 0.0002747317620786623,
"loss": 4.9563,
"step": 6010
},
{
"epoch": 2.702156334231806,
"grad_norm": 3.53125,
"learning_rate": 0.0002746707595406627,
"loss": 4.9565,
"step": 6015
},
{
"epoch": 2.7044025157232703,
"grad_norm": 2.890625,
"learning_rate": 0.0002746096910774258,
"loss": 4.955,
"step": 6020
},
{
"epoch": 2.706648697214735,
"grad_norm": 2.890625,
"learning_rate": 0.00027454855672566107,
"loss": 4.948,
"step": 6025
},
{
"epoch": 2.7088948787061993,
"grad_norm": 3.4375,
"learning_rate": 0.0002744873565221176,
"loss": 4.9657,
"step": 6030
},
{
"epoch": 2.711141060197664,
"grad_norm": 2.953125,
"learning_rate": 0.000274426090503584,
"loss": 4.9173,
"step": 6035
},
{
"epoch": 2.7133872416891283,
"grad_norm": 3.265625,
"learning_rate": 0.00027436475870688847,
"loss": 4.9704,
"step": 6040
},
{
"epoch": 2.715633423180593,
"grad_norm": 2.96875,
"learning_rate": 0.00027430336116889876,
"loss": 4.9755,
"step": 6045
},
{
"epoch": 2.7178796046720572,
"grad_norm": 3.1875,
"learning_rate": 0.00027424189792652214,
"loss": 4.9371,
"step": 6050
},
{
"epoch": 2.720125786163522,
"grad_norm": 2.90625,
"learning_rate": 0.00027418036901670533,
"loss": 4.9885,
"step": 6055
},
{
"epoch": 2.7223719676549867,
"grad_norm": 3.0625,
"learning_rate": 0.00027411877447643454,
"loss": 4.8649,
"step": 6060
},
{
"epoch": 2.724618149146451,
"grad_norm": 3.203125,
"learning_rate": 0.0002740571143427356,
"loss": 4.9875,
"step": 6065
},
{
"epoch": 2.7268643306379157,
"grad_norm": 3.078125,
"learning_rate": 0.00027399538865267343,
"loss": 4.9599,
"step": 6070
},
{
"epoch": 2.72911051212938,
"grad_norm": 3.03125,
"learning_rate": 0.0002739335974433527,
"loss": 4.9258,
"step": 6075
},
{
"epoch": 2.7313566936208447,
"grad_norm": 3.1875,
"learning_rate": 0.0002738717407519172,
"loss": 4.9696,
"step": 6080
},
{
"epoch": 2.733602875112309,
"grad_norm": 3.6875,
"learning_rate": 0.00027380981861555026,
"loss": 4.9673,
"step": 6085
},
{
"epoch": 2.7358490566037736,
"grad_norm": 3.09375,
"learning_rate": 0.00027374783107147446,
"loss": 5.0333,
"step": 6090
},
{
"epoch": 2.738095238095238,
"grad_norm": 3.03125,
"learning_rate": 0.00027368577815695176,
"loss": 4.9061,
"step": 6095
},
{
"epoch": 2.7403414195867026,
"grad_norm": 3.171875,
"learning_rate": 0.0002736236599092833,
"loss": 4.8905,
"step": 6100
},
{
"epoch": 2.742587601078167,
"grad_norm": 3.09375,
"learning_rate": 0.0002735614763658097,
"loss": 4.9118,
"step": 6105
},
{
"epoch": 2.7448337825696316,
"grad_norm": 3.4375,
"learning_rate": 0.0002734992275639106,
"loss": 5.0166,
"step": 6110
},
{
"epoch": 2.747079964061096,
"grad_norm": 3.03125,
"learning_rate": 0.000273436913541005,
"loss": 4.9696,
"step": 6115
},
{
"epoch": 2.7493261455525606,
"grad_norm": 3.109375,
"learning_rate": 0.0002733745343345511,
"loss": 4.9343,
"step": 6120
},
{
"epoch": 2.751572327044025,
"grad_norm": 3.046875,
"learning_rate": 0.00027331208998204623,
"loss": 4.9587,
"step": 6125
},
{
"epoch": 2.7538185085354896,
"grad_norm": 3.015625,
"learning_rate": 0.00027324958052102696,
"loss": 4.8604,
"step": 6130
},
{
"epoch": 2.756064690026954,
"grad_norm": 3.140625,
"learning_rate": 0.00027318700598906887,
"loss": 4.8835,
"step": 6135
},
{
"epoch": 2.7583108715184186,
"grad_norm": 3.0,
"learning_rate": 0.0002731243664237868,
"loss": 4.9459,
"step": 6140
},
{
"epoch": 2.760557053009883,
"grad_norm": 3.09375,
"learning_rate": 0.00027306166186283457,
"loss": 4.912,
"step": 6145
},
{
"epoch": 2.7628032345013476,
"grad_norm": 3.109375,
"learning_rate": 0.00027299889234390514,
"loss": 4.962,
"step": 6150
},
{
"epoch": 2.765049415992812,
"grad_norm": 3.296875,
"learning_rate": 0.0002729360579047305,
"loss": 4.8934,
"step": 6155
},
{
"epoch": 2.767295597484277,
"grad_norm": 3.15625,
"learning_rate": 0.00027287315858308164,
"loss": 4.9474,
"step": 6160
},
{
"epoch": 2.769541778975741,
"grad_norm": 3.09375,
"learning_rate": 0.00027281019441676856,
"loss": 4.9378,
"step": 6165
},
{
"epoch": 2.771787960467206,
"grad_norm": 2.984375,
"learning_rate": 0.00027274716544364034,
"loss": 4.9604,
"step": 6170
},
{
"epoch": 2.77403414195867,
"grad_norm": 3.09375,
"learning_rate": 0.00027268407170158486,
"loss": 4.9024,
"step": 6175
},
{
"epoch": 2.776280323450135,
"grad_norm": 2.859375,
"learning_rate": 0.00027262091322852893,
"loss": 4.9575,
"step": 6180
},
{
"epoch": 2.778526504941599,
"grad_norm": 2.984375,
"learning_rate": 0.00027255769006243855,
"loss": 4.9526,
"step": 6185
},
{
"epoch": 2.780772686433064,
"grad_norm": 2.875,
"learning_rate": 0.00027249440224131813,
"loss": 4.9385,
"step": 6190
},
{
"epoch": 2.7830188679245285,
"grad_norm": 3.09375,
"learning_rate": 0.0002724310498032115,
"loss": 4.9669,
"step": 6195
},
{
"epoch": 2.785265049415993,
"grad_norm": 3.0,
"learning_rate": 0.0002723676327862008,
"loss": 4.9392,
"step": 6200
},
{
"epoch": 2.7875112309074574,
"grad_norm": 3.125,
"learning_rate": 0.00027230415122840736,
"loss": 4.873,
"step": 6205
},
{
"epoch": 2.789757412398922,
"grad_norm": 3.390625,
"learning_rate": 0.0002722406051679912,
"loss": 4.9445,
"step": 6210
},
{
"epoch": 2.7920035938903864,
"grad_norm": 3.25,
"learning_rate": 0.00027217699464315105,
"loss": 4.9907,
"step": 6215
},
{
"epoch": 2.794249775381851,
"grad_norm": 3.171875,
"learning_rate": 0.00027211331969212443,
"loss": 5.0226,
"step": 6220
},
{
"epoch": 2.7964959568733154,
"grad_norm": 3.125,
"learning_rate": 0.00027204958035318766,
"loss": 4.9335,
"step": 6225
},
{
"epoch": 2.79874213836478,
"grad_norm": 3.203125,
"learning_rate": 0.00027198577666465574,
"loss": 4.9036,
"step": 6230
},
{
"epoch": 2.8009883198562444,
"grad_norm": 3.125,
"learning_rate": 0.0002719219086648821,
"loss": 4.9858,
"step": 6235
},
{
"epoch": 2.803234501347709,
"grad_norm": 3.484375,
"learning_rate": 0.0002718579763922593,
"loss": 4.9541,
"step": 6240
},
{
"epoch": 2.8054806828391734,
"grad_norm": 3.703125,
"learning_rate": 0.0002717939798852181,
"loss": 4.918,
"step": 6245
},
{
"epoch": 2.807726864330638,
"grad_norm": 3.09375,
"learning_rate": 0.0002717299191822281,
"loss": 4.9336,
"step": 6250
},
{
"epoch": 2.8099730458221024,
"grad_norm": 3.109375,
"learning_rate": 0.0002716657943217975,
"loss": 4.9163,
"step": 6255
},
{
"epoch": 2.812219227313567,
"grad_norm": 3.4375,
"learning_rate": 0.000271601605342473,
"loss": 4.8734,
"step": 6260
},
{
"epoch": 2.8144654088050314,
"grad_norm": 3.265625,
"learning_rate": 0.00027153735228283975,
"loss": 4.9175,
"step": 6265
},
{
"epoch": 2.816711590296496,
"grad_norm": 3.21875,
"learning_rate": 0.0002714730351815216,
"loss": 5.0152,
"step": 6270
},
{
"epoch": 2.8189577717879604,
"grad_norm": 3.03125,
"learning_rate": 0.0002714086540771808,
"loss": 4.9391,
"step": 6275
},
{
"epoch": 2.821203953279425,
"grad_norm": 3.03125,
"learning_rate": 0.0002713442090085181,
"loss": 4.9086,
"step": 6280
},
{
"epoch": 2.8234501347708894,
"grad_norm": 3.109375,
"learning_rate": 0.0002712797000142727,
"loss": 4.9808,
"step": 6285
},
{
"epoch": 2.825696316262354,
"grad_norm": 3.453125,
"learning_rate": 0.0002712151271332222,
"loss": 4.9397,
"step": 6290
},
{
"epoch": 2.827942497753819,
"grad_norm": 3.203125,
"learning_rate": 0.00027115049040418254,
"loss": 4.8799,
"step": 6295
},
{
"epoch": 2.830188679245283,
"grad_norm": 2.9375,
"learning_rate": 0.0002710857898660082,
"loss": 4.9463,
"step": 6300
},
{
"epoch": 2.8324348607367478,
"grad_norm": 3.09375,
"learning_rate": 0.00027102102555759205,
"loss": 4.9161,
"step": 6305
},
{
"epoch": 2.834681042228212,
"grad_norm": 2.828125,
"learning_rate": 0.000270956197517865,
"loss": 4.9685,
"step": 6310
},
{
"epoch": 2.8369272237196768,
"grad_norm": 2.96875,
"learning_rate": 0.0002708913057857965,
"loss": 4.9146,
"step": 6315
},
{
"epoch": 2.839173405211141,
"grad_norm": 2.921875,
"learning_rate": 0.00027082635040039435,
"loss": 4.9201,
"step": 6320
},
{
"epoch": 2.8414195867026057,
"grad_norm": 3.0,
"learning_rate": 0.0002707613314007044,
"loss": 4.9169,
"step": 6325
},
{
"epoch": 2.8436657681940702,
"grad_norm": 3.109375,
"learning_rate": 0.00027069624882581077,
"loss": 4.9624,
"step": 6330
},
{
"epoch": 2.8459119496855347,
"grad_norm": 3.078125,
"learning_rate": 0.000270631102714836,
"loss": 4.9702,
"step": 6335
},
{
"epoch": 2.8481581311769992,
"grad_norm": 3.015625,
"learning_rate": 0.0002705658931069406,
"loss": 4.9867,
"step": 6340
},
{
"epoch": 2.8504043126684637,
"grad_norm": 2.90625,
"learning_rate": 0.0002705006200413235,
"loss": 4.9874,
"step": 6345
},
{
"epoch": 2.852650494159928,
"grad_norm": 2.921875,
"learning_rate": 0.00027043528355722135,
"loss": 4.935,
"step": 6350
},
{
"epoch": 2.8548966756513927,
"grad_norm": 3.03125,
"learning_rate": 0.00027036988369390946,
"loss": 4.8973,
"step": 6355
},
{
"epoch": 2.857142857142857,
"grad_norm": 2.9375,
"learning_rate": 0.00027030442049070076,
"loss": 4.8817,
"step": 6360
},
{
"epoch": 2.8593890386343217,
"grad_norm": 3.140625,
"learning_rate": 0.0002702388939869466,
"loss": 4.9394,
"step": 6365
},
{
"epoch": 2.861635220125786,
"grad_norm": 3.125,
"learning_rate": 0.00027017330422203614,
"loss": 4.844,
"step": 6370
},
{
"epoch": 2.8638814016172507,
"grad_norm": 3.015625,
"learning_rate": 0.0002701076512353968,
"loss": 4.8938,
"step": 6375
},
{
"epoch": 2.866127583108715,
"grad_norm": 2.84375,
"learning_rate": 0.00027004193506649374,
"loss": 4.9167,
"step": 6380
},
{
"epoch": 2.8683737646001797,
"grad_norm": 3.03125,
"learning_rate": 0.00026997615575483026,
"loss": 4.9192,
"step": 6385
},
{
"epoch": 2.870619946091644,
"grad_norm": 3.109375,
"learning_rate": 0.0002699103133399476,
"loss": 4.9162,
"step": 6390
},
{
"epoch": 2.8728661275831087,
"grad_norm": 3.015625,
"learning_rate": 0.00026984440786142496,
"loss": 4.9291,
"step": 6395
},
{
"epoch": 2.875112309074573,
"grad_norm": 3.28125,
"learning_rate": 0.0002697784393588794,
"loss": 5.0111,
"step": 6400
},
{
"epoch": 2.8773584905660377,
"grad_norm": 3.15625,
"learning_rate": 0.0002697124078719659,
"loss": 5.0144,
"step": 6405
},
{
"epoch": 2.879604672057502,
"grad_norm": 2.921875,
"learning_rate": 0.00026964631344037713,
"loss": 4.9051,
"step": 6410
},
{
"epoch": 2.8818508535489666,
"grad_norm": 3.25,
"learning_rate": 0.00026958015610384394,
"loss": 4.9883,
"step": 6415
},
{
"epoch": 2.884097035040431,
"grad_norm": 3.078125,
"learning_rate": 0.00026951393590213474,
"loss": 5.031,
"step": 6420
},
{
"epoch": 2.8863432165318956,
"grad_norm": 3.75,
"learning_rate": 0.0002694476528750557,
"loss": 4.9772,
"step": 6425
},
{
"epoch": 2.88858939802336,
"grad_norm": 3.1875,
"learning_rate": 0.0002693813070624509,
"loss": 4.989,
"step": 6430
},
{
"epoch": 2.8908355795148246,
"grad_norm": 3.109375,
"learning_rate": 0.00026931489850420213,
"loss": 4.9268,
"step": 6435
},
{
"epoch": 2.8930817610062896,
"grad_norm": 3.03125,
"learning_rate": 0.0002692484272402288,
"loss": 4.9483,
"step": 6440
},
{
"epoch": 2.8953279424977536,
"grad_norm": 3.15625,
"learning_rate": 0.00026918189331048825,
"loss": 4.9406,
"step": 6445
},
{
"epoch": 2.8975741239892185,
"grad_norm": 2.9375,
"learning_rate": 0.00026911529675497514,
"loss": 4.9445,
"step": 6450
},
{
"epoch": 2.8998203054806826,
"grad_norm": 3.296875,
"learning_rate": 0.00026904863761372205,
"loss": 4.8945,
"step": 6455
},
{
"epoch": 2.9020664869721475,
"grad_norm": 3.171875,
"learning_rate": 0.0002689819159267991,
"loss": 4.944,
"step": 6460
},
{
"epoch": 2.904312668463612,
"grad_norm": 3.0625,
"learning_rate": 0.00026891513173431394,
"loss": 4.8718,
"step": 6465
},
{
"epoch": 2.9065588499550765,
"grad_norm": 3.328125,
"learning_rate": 0.0002688482850764119,
"loss": 4.9186,
"step": 6470
},
{
"epoch": 2.908805031446541,
"grad_norm": 3.140625,
"learning_rate": 0.0002687813759932758,
"loss": 4.9278,
"step": 6475
},
{
"epoch": 2.9110512129380055,
"grad_norm": 3.734375,
"learning_rate": 0.000268714404525126,
"loss": 4.9514,
"step": 6480
},
{
"epoch": 2.91329739442947,
"grad_norm": 3.015625,
"learning_rate": 0.0002686473707122204,
"loss": 4.8925,
"step": 6485
},
{
"epoch": 2.9155435759209345,
"grad_norm": 3.0,
"learning_rate": 0.00026858027459485427,
"loss": 4.864,
"step": 6490
},
{
"epoch": 2.917789757412399,
"grad_norm": 3.125,
"learning_rate": 0.0002685131162133604,
"loss": 4.9311,
"step": 6495
},
{
"epoch": 2.9200359389038635,
"grad_norm": 3.09375,
"learning_rate": 0.0002684458956081091,
"loss": 4.9183,
"step": 6500
},
{
"epoch": 2.922282120395328,
"grad_norm": 3.296875,
"learning_rate": 0.00026837861281950786,
"loss": 5.0522,
"step": 6505
},
{
"epoch": 2.9245283018867925,
"grad_norm": 3.1875,
"learning_rate": 0.00026831126788800174,
"loss": 4.8712,
"step": 6510
},
{
"epoch": 2.926774483378257,
"grad_norm": 3.125,
"learning_rate": 0.00026824386085407307,
"loss": 4.9477,
"step": 6515
},
{
"epoch": 2.9290206648697215,
"grad_norm": 3.03125,
"learning_rate": 0.0002681763917582416,
"loss": 4.8396,
"step": 6520
},
{
"epoch": 2.931266846361186,
"grad_norm": 3.53125,
"learning_rate": 0.00026810886064106425,
"loss": 5.0069,
"step": 6525
},
{
"epoch": 2.9335130278526504,
"grad_norm": 3.328125,
"learning_rate": 0.00026804126754313533,
"loss": 4.9952,
"step": 6530
},
{
"epoch": 2.935759209344115,
"grad_norm": 3.078125,
"learning_rate": 0.00026797361250508644,
"loss": 4.8484,
"step": 6535
},
{
"epoch": 2.9380053908355794,
"grad_norm": 3.890625,
"learning_rate": 0.0002679058955675862,
"loss": 5.0126,
"step": 6540
},
{
"epoch": 2.940251572327044,
"grad_norm": 3.015625,
"learning_rate": 0.00026783811677134065,
"loss": 4.9527,
"step": 6545
},
{
"epoch": 2.9424977538185084,
"grad_norm": 2.890625,
"learning_rate": 0.00026777027615709304,
"loss": 4.9737,
"step": 6550
},
{
"epoch": 2.944743935309973,
"grad_norm": 3.796875,
"learning_rate": 0.0002677023737656235,
"loss": 4.9099,
"step": 6555
},
{
"epoch": 2.9469901168014374,
"grad_norm": 2.984375,
"learning_rate": 0.00026763440963774966,
"loss": 4.8881,
"step": 6560
},
{
"epoch": 2.949236298292902,
"grad_norm": 3.25,
"learning_rate": 0.00026756638381432603,
"loss": 4.9634,
"step": 6565
},
{
"epoch": 2.9514824797843664,
"grad_norm": 3.015625,
"learning_rate": 0.0002674982963362442,
"loss": 4.8719,
"step": 6570
},
{
"epoch": 2.9537286612758313,
"grad_norm": 3.125,
"learning_rate": 0.00026743014724443293,
"loss": 4.969,
"step": 6575
},
{
"epoch": 2.9559748427672954,
"grad_norm": 3.03125,
"learning_rate": 0.000267361936579858,
"loss": 4.917,
"step": 6580
},
{
"epoch": 2.9582210242587603,
"grad_norm": 3.109375,
"learning_rate": 0.00026729366438352215,
"loss": 4.9,
"step": 6585
},
{
"epoch": 2.9604672057502244,
"grad_norm": 3.015625,
"learning_rate": 0.0002672253306964651,
"loss": 4.9521,
"step": 6590
},
{
"epoch": 2.9627133872416893,
"grad_norm": 3.328125,
"learning_rate": 0.0002671569355597637,
"loss": 4.9743,
"step": 6595
},
{
"epoch": 2.964959568733154,
"grad_norm": 3.09375,
"learning_rate": 0.0002670884790145314,
"loss": 4.9766,
"step": 6600
},
{
"epoch": 2.9672057502246183,
"grad_norm": 3.109375,
"learning_rate": 0.0002670199611019189,
"loss": 4.96,
"step": 6605
},
{
"epoch": 2.969451931716083,
"grad_norm": 3.046875,
"learning_rate": 0.00026695138186311364,
"loss": 4.8694,
"step": 6610
},
{
"epoch": 2.9716981132075473,
"grad_norm": 3.15625,
"learning_rate": 0.0002668827413393399,
"loss": 4.8839,
"step": 6615
},
{
"epoch": 2.973944294699012,
"grad_norm": 3.09375,
"learning_rate": 0.0002668140395718588,
"loss": 4.8949,
"step": 6620
},
{
"epoch": 2.9761904761904763,
"grad_norm": 3.0625,
"learning_rate": 0.0002667452766019685,
"loss": 4.8834,
"step": 6625
},
{
"epoch": 2.9784366576819408,
"grad_norm": 3.0625,
"learning_rate": 0.00026667645247100357,
"loss": 4.9984,
"step": 6630
},
{
"epoch": 2.9806828391734053,
"grad_norm": 3.015625,
"learning_rate": 0.0002666075672203356,
"loss": 4.8534,
"step": 6635
},
{
"epoch": 2.9829290206648698,
"grad_norm": 3.171875,
"learning_rate": 0.00026653862089137296,
"loss": 4.9614,
"step": 6640
},
{
"epoch": 2.9851752021563343,
"grad_norm": 3.09375,
"learning_rate": 0.0002664696135255605,
"loss": 4.8943,
"step": 6645
},
{
"epoch": 2.9874213836477987,
"grad_norm": 2.859375,
"learning_rate": 0.00026640054516437997,
"loss": 4.8697,
"step": 6650
},
{
"epoch": 2.9896675651392632,
"grad_norm": 3.46875,
"learning_rate": 0.0002663314158493496,
"loss": 4.9618,
"step": 6655
},
{
"epoch": 2.9919137466307277,
"grad_norm": 3.09375,
"learning_rate": 0.00026626222562202456,
"loss": 4.8952,
"step": 6660
},
{
"epoch": 2.9941599281221922,
"grad_norm": 3.140625,
"learning_rate": 0.00026619297452399633,
"loss": 4.9478,
"step": 6665
},
{
"epoch": 2.9964061096136567,
"grad_norm": 3.03125,
"learning_rate": 0.0002661236625968931,
"loss": 4.9124,
"step": 6670
},
{
"epoch": 2.998652291105121,
"grad_norm": 3.328125,
"learning_rate": 0.00026605428988237965,
"loss": 4.9819,
"step": 6675
},
{
"epoch": 3.0008984725965857,
"grad_norm": 3.375,
"learning_rate": 0.0002659848564221573,
"loss": 4.8854,
"step": 6680
},
{
"epoch": 3.00314465408805,
"grad_norm": 3.296875,
"learning_rate": 0.0002659153622579638,
"loss": 4.8016,
"step": 6685
},
{
"epoch": 3.0053908355795147,
"grad_norm": 3.859375,
"learning_rate": 0.0002658458074315735,
"loss": 4.8727,
"step": 6690
},
{
"epoch": 3.007637017070979,
"grad_norm": 3.046875,
"learning_rate": 0.0002657761919847971,
"loss": 4.824,
"step": 6695
},
{
"epoch": 3.0098831985624437,
"grad_norm": 3.015625,
"learning_rate": 0.0002657065159594819,
"loss": 4.8335,
"step": 6700
},
{
"epoch": 3.012129380053908,
"grad_norm": 3.0,
"learning_rate": 0.00026563677939751146,
"loss": 4.8298,
"step": 6705
},
{
"epoch": 3.0143755615453727,
"grad_norm": 3.125,
"learning_rate": 0.00026556698234080577,
"loss": 4.8667,
"step": 6710
},
{
"epoch": 3.016621743036837,
"grad_norm": 3.328125,
"learning_rate": 0.0002654971248313213,
"loss": 4.8908,
"step": 6715
},
{
"epoch": 3.018867924528302,
"grad_norm": 3.453125,
"learning_rate": 0.0002654272069110507,
"loss": 4.7931,
"step": 6720
},
{
"epoch": 3.0211141060197666,
"grad_norm": 3.296875,
"learning_rate": 0.0002653572286220229,
"loss": 4.7856,
"step": 6725
},
{
"epoch": 3.023360287511231,
"grad_norm": 3.078125,
"learning_rate": 0.0002652871900063034,
"loss": 4.7742,
"step": 6730
},
{
"epoch": 3.0256064690026956,
"grad_norm": 3.203125,
"learning_rate": 0.0002652170911059937,
"loss": 4.8128,
"step": 6735
},
{
"epoch": 3.02785265049416,
"grad_norm": 3.1875,
"learning_rate": 0.0002651469319632316,
"loss": 4.8296,
"step": 6740
},
{
"epoch": 3.0300988319856246,
"grad_norm": 3.46875,
"learning_rate": 0.00026507671262019115,
"loss": 4.8438,
"step": 6745
},
{
"epoch": 3.032345013477089,
"grad_norm": 3.078125,
"learning_rate": 0.00026500643311908257,
"loss": 4.7799,
"step": 6750
},
{
"epoch": 3.0345911949685536,
"grad_norm": 3.171875,
"learning_rate": 0.0002649360935021522,
"loss": 4.845,
"step": 6755
},
{
"epoch": 3.036837376460018,
"grad_norm": 3.28125,
"learning_rate": 0.00026486569381168267,
"loss": 4.8419,
"step": 6760
},
{
"epoch": 3.0390835579514826,
"grad_norm": 3.265625,
"learning_rate": 0.0002647952340899925,
"loss": 4.8683,
"step": 6765
},
{
"epoch": 3.041329739442947,
"grad_norm": 3.5,
"learning_rate": 0.0002647247143794365,
"loss": 4.8123,
"step": 6770
},
{
"epoch": 3.0435759209344115,
"grad_norm": 3.015625,
"learning_rate": 0.00026465413472240534,
"loss": 4.8202,
"step": 6775
},
{
"epoch": 3.045822102425876,
"grad_norm": 3.0625,
"learning_rate": 0.0002645834951613259,
"loss": 4.8717,
"step": 6780
},
{
"epoch": 3.0480682839173405,
"grad_norm": 3.0625,
"learning_rate": 0.00026451279573866095,
"loss": 4.7503,
"step": 6785
},
{
"epoch": 3.050314465408805,
"grad_norm": 3.140625,
"learning_rate": 0.0002644420364969094,
"loss": 4.8023,
"step": 6790
},
{
"epoch": 3.0525606469002695,
"grad_norm": 3.25,
"learning_rate": 0.0002643712174786059,
"loss": 4.8349,
"step": 6795
},
{
"epoch": 3.054806828391734,
"grad_norm": 3.109375,
"learning_rate": 0.00026430033872632116,
"loss": 4.7862,
"step": 6800
},
{
"epoch": 3.0570530098831985,
"grad_norm": 4.0,
"learning_rate": 0.00026422940028266183,
"loss": 4.8704,
"step": 6805
},
{
"epoch": 3.059299191374663,
"grad_norm": 3.40625,
"learning_rate": 0.0002641584021902704,
"loss": 4.8366,
"step": 6810
},
{
"epoch": 3.0615453728661275,
"grad_norm": 3.296875,
"learning_rate": 0.0002640873444918252,
"loss": 4.8354,
"step": 6815
},
{
"epoch": 3.063791554357592,
"grad_norm": 3.234375,
"learning_rate": 0.00026401622723004034,
"loss": 4.8597,
"step": 6820
},
{
"epoch": 3.0660377358490565,
"grad_norm": 3.03125,
"learning_rate": 0.00026394505044766587,
"loss": 4.8656,
"step": 6825
},
{
"epoch": 3.068283917340521,
"grad_norm": 3.203125,
"learning_rate": 0.0002638738141874876,
"loss": 4.8846,
"step": 6830
},
{
"epoch": 3.0705300988319855,
"grad_norm": 3.140625,
"learning_rate": 0.00026380251849232687,
"loss": 4.8764,
"step": 6835
},
{
"epoch": 3.07277628032345,
"grad_norm": 3.046875,
"learning_rate": 0.00026373116340504103,
"loss": 4.7835,
"step": 6840
},
{
"epoch": 3.0750224618149145,
"grad_norm": 3.15625,
"learning_rate": 0.00026365974896852296,
"loss": 4.8515,
"step": 6845
},
{
"epoch": 3.077268643306379,
"grad_norm": 3.234375,
"learning_rate": 0.0002635882752257013,
"loss": 4.8444,
"step": 6850
},
{
"epoch": 3.079514824797844,
"grad_norm": 3.046875,
"learning_rate": 0.00026351674221954043,
"loss": 4.7379,
"step": 6855
},
{
"epoch": 3.0817610062893084,
"grad_norm": 3.359375,
"learning_rate": 0.0002634451499930401,
"loss": 4.8479,
"step": 6860
},
{
"epoch": 3.084007187780773,
"grad_norm": 3.203125,
"learning_rate": 0.0002633734985892358,
"loss": 4.7955,
"step": 6865
},
{
"epoch": 3.0862533692722374,
"grad_norm": 2.953125,
"learning_rate": 0.00026330178805119853,
"loss": 4.8404,
"step": 6870
},
{
"epoch": 3.088499550763702,
"grad_norm": 3.34375,
"learning_rate": 0.00026323001842203504,
"loss": 4.8335,
"step": 6875
},
{
"epoch": 3.0907457322551664,
"grad_norm": 3.1875,
"learning_rate": 0.00026315818974488744,
"loss": 4.8428,
"step": 6880
},
{
"epoch": 3.092991913746631,
"grad_norm": 3.21875,
"learning_rate": 0.00026308630206293325,
"loss": 4.7151,
"step": 6885
},
{
"epoch": 3.0952380952380953,
"grad_norm": 3.046875,
"learning_rate": 0.0002630143554193857,
"loss": 4.8407,
"step": 6890
},
{
"epoch": 3.09748427672956,
"grad_norm": 3.078125,
"learning_rate": 0.00026294234985749313,
"loss": 4.7312,
"step": 6895
},
{
"epoch": 3.0997304582210243,
"grad_norm": 3.25,
"learning_rate": 0.00026287028542053975,
"loss": 4.7925,
"step": 6900
},
{
"epoch": 3.101976639712489,
"grad_norm": 3.203125,
"learning_rate": 0.0002627981621518447,
"loss": 4.8265,
"step": 6905
},
{
"epoch": 3.1042228212039533,
"grad_norm": 3.03125,
"learning_rate": 0.0002627259800947627,
"loss": 4.8757,
"step": 6910
},
{
"epoch": 3.106469002695418,
"grad_norm": 3.015625,
"learning_rate": 0.00026265373929268383,
"loss": 4.8218,
"step": 6915
},
{
"epoch": 3.1087151841868823,
"grad_norm": 3.046875,
"learning_rate": 0.00026258143978903354,
"loss": 4.8604,
"step": 6920
},
{
"epoch": 3.110961365678347,
"grad_norm": 3.546875,
"learning_rate": 0.00026250908162727234,
"loss": 4.8454,
"step": 6925
},
{
"epoch": 3.1132075471698113,
"grad_norm": 3.125,
"learning_rate": 0.0002624366648508962,
"loss": 4.8521,
"step": 6930
},
{
"epoch": 3.115453728661276,
"grad_norm": 3.1875,
"learning_rate": 0.00026236418950343623,
"loss": 4.7329,
"step": 6935
},
{
"epoch": 3.1176999101527403,
"grad_norm": 3.15625,
"learning_rate": 0.0002622916556284588,
"loss": 4.7403,
"step": 6940
},
{
"epoch": 3.1199460916442048,
"grad_norm": 3.15625,
"learning_rate": 0.0002622190632695655,
"loss": 4.7682,
"step": 6945
},
{
"epoch": 3.1221922731356693,
"grad_norm": 3.21875,
"learning_rate": 0.0002621464124703929,
"loss": 4.8178,
"step": 6950
},
{
"epoch": 3.1244384546271338,
"grad_norm": 3.125,
"learning_rate": 0.00026207370327461284,
"loss": 4.8774,
"step": 6955
},
{
"epoch": 3.1266846361185983,
"grad_norm": 3.578125,
"learning_rate": 0.0002620009357259323,
"loss": 4.8435,
"step": 6960
},
{
"epoch": 3.1289308176100628,
"grad_norm": 3.109375,
"learning_rate": 0.0002619281098680932,
"loss": 4.8077,
"step": 6965
},
{
"epoch": 3.1311769991015272,
"grad_norm": 3.296875,
"learning_rate": 0.0002618552257448727,
"loss": 4.7614,
"step": 6970
},
{
"epoch": 3.1334231805929917,
"grad_norm": 3.21875,
"learning_rate": 0.00026178228340008276,
"loss": 4.8246,
"step": 6975
},
{
"epoch": 3.1356693620844562,
"grad_norm": 3.546875,
"learning_rate": 0.0002617092828775705,
"loss": 4.8138,
"step": 6980
},
{
"epoch": 3.1379155435759207,
"grad_norm": 3.046875,
"learning_rate": 0.0002616362242212179,
"loss": 4.8909,
"step": 6985
},
{
"epoch": 3.1401617250673857,
"grad_norm": 3.390625,
"learning_rate": 0.00026156310747494206,
"loss": 4.826,
"step": 6990
},
{
"epoch": 3.14240790655885,
"grad_norm": 3.140625,
"learning_rate": 0.0002614899326826948,
"loss": 4.7744,
"step": 6995
},
{
"epoch": 3.1446540880503147,
"grad_norm": 3.296875,
"learning_rate": 0.00026141669988846293,
"loss": 4.9305,
"step": 7000
},
{
"epoch": 3.1446540880503147,
"eval_loss": 4.942409038543701,
"eval_runtime": 16.1167,
"eval_samples_per_second": 1924.273,
"eval_steps_per_second": 240.557,
"step": 7000
},
{
"epoch": 3.146900269541779,
"grad_norm": 3.03125,
"learning_rate": 0.00026134340913626814,
"loss": 4.8665,
"step": 7005
},
{
"epoch": 3.1491464510332436,
"grad_norm": 3.328125,
"learning_rate": 0.00026127006047016693,
"loss": 4.8994,
"step": 7010
},
{
"epoch": 3.151392632524708,
"grad_norm": 3.25,
"learning_rate": 0.0002611966539342506,
"loss": 4.8005,
"step": 7015
},
{
"epoch": 3.1536388140161726,
"grad_norm": 3.203125,
"learning_rate": 0.0002611231895726453,
"loss": 4.9289,
"step": 7020
},
{
"epoch": 3.155884995507637,
"grad_norm": 3.359375,
"learning_rate": 0.0002610496674295118,
"loss": 4.7866,
"step": 7025
},
{
"epoch": 3.1581311769991016,
"grad_norm": 3.015625,
"learning_rate": 0.0002609760875490457,
"loss": 4.791,
"step": 7030
},
{
"epoch": 3.160377358490566,
"grad_norm": 3.0625,
"learning_rate": 0.00026090244997547743,
"loss": 4.7871,
"step": 7035
},
{
"epoch": 3.1626235399820306,
"grad_norm": 3.015625,
"learning_rate": 0.00026082875475307184,
"loss": 4.7937,
"step": 7040
},
{
"epoch": 3.164869721473495,
"grad_norm": 2.953125,
"learning_rate": 0.0002607550019261287,
"loss": 4.794,
"step": 7045
},
{
"epoch": 3.1671159029649596,
"grad_norm": 3.3125,
"learning_rate": 0.0002606811915389822,
"loss": 4.8237,
"step": 7050
},
{
"epoch": 3.169362084456424,
"grad_norm": 2.921875,
"learning_rate": 0.00026060732363600113,
"loss": 4.8981,
"step": 7055
},
{
"epoch": 3.1716082659478886,
"grad_norm": 3.296875,
"learning_rate": 0.00026053339826158904,
"loss": 4.8026,
"step": 7060
},
{
"epoch": 3.173854447439353,
"grad_norm": 3.296875,
"learning_rate": 0.0002604594154601839,
"loss": 4.8203,
"step": 7065
},
{
"epoch": 3.1761006289308176,
"grad_norm": 3.3125,
"learning_rate": 0.00026038537527625817,
"loss": 4.8191,
"step": 7070
},
{
"epoch": 3.178346810422282,
"grad_norm": 3.1875,
"learning_rate": 0.00026031127775431894,
"loss": 4.8258,
"step": 7075
},
{
"epoch": 3.1805929919137466,
"grad_norm": 3.109375,
"learning_rate": 0.0002602371229389076,
"loss": 4.8744,
"step": 7080
},
{
"epoch": 3.182839173405211,
"grad_norm": 3.296875,
"learning_rate": 0.0002601629108746001,
"loss": 4.8279,
"step": 7085
},
{
"epoch": 3.1850853548966755,
"grad_norm": 3.390625,
"learning_rate": 0.0002600886416060068,
"loss": 4.7797,
"step": 7090
},
{
"epoch": 3.18733153638814,
"grad_norm": 4.0625,
"learning_rate": 0.00026001431517777226,
"loss": 4.8642,
"step": 7095
},
{
"epoch": 3.1895777178796045,
"grad_norm": 3.265625,
"learning_rate": 0.0002599399316345757,
"loss": 4.7916,
"step": 7100
},
{
"epoch": 3.191823899371069,
"grad_norm": 3.171875,
"learning_rate": 0.0002598654910211304,
"loss": 4.779,
"step": 7105
},
{
"epoch": 3.1940700808625335,
"grad_norm": 3.21875,
"learning_rate": 0.0002597909933821842,
"loss": 4.8629,
"step": 7110
},
{
"epoch": 3.196316262353998,
"grad_norm": 3.21875,
"learning_rate": 0.000259716438762519,
"loss": 4.7861,
"step": 7115
},
{
"epoch": 3.1985624438454625,
"grad_norm": 3.25,
"learning_rate": 0.0002596418272069511,
"loss": 4.8307,
"step": 7120
},
{
"epoch": 3.2008086253369274,
"grad_norm": 3.15625,
"learning_rate": 0.0002595671587603309,
"loss": 4.7688,
"step": 7125
},
{
"epoch": 3.2030548068283915,
"grad_norm": 3.125,
"learning_rate": 0.00025949243346754306,
"loss": 4.8044,
"step": 7130
},
{
"epoch": 3.2053009883198564,
"grad_norm": 3.21875,
"learning_rate": 0.00025941765137350647,
"loss": 4.8947,
"step": 7135
},
{
"epoch": 3.207547169811321,
"grad_norm": 3.28125,
"learning_rate": 0.0002593428125231741,
"loss": 4.8465,
"step": 7140
},
{
"epoch": 3.2097933513027854,
"grad_norm": 3.171875,
"learning_rate": 0.000259267916961533,
"loss": 4.7989,
"step": 7145
},
{
"epoch": 3.21203953279425,
"grad_norm": 3.203125,
"learning_rate": 0.0002591929647336044,
"loss": 4.8914,
"step": 7150
},
{
"epoch": 3.2142857142857144,
"grad_norm": 3.125,
"learning_rate": 0.00025911795588444354,
"loss": 4.861,
"step": 7155
},
{
"epoch": 3.216531895777179,
"grad_norm": 3.28125,
"learning_rate": 0.00025904289045913966,
"loss": 4.8461,
"step": 7160
},
{
"epoch": 3.2187780772686434,
"grad_norm": 3.21875,
"learning_rate": 0.0002589677685028161,
"loss": 4.8025,
"step": 7165
},
{
"epoch": 3.221024258760108,
"grad_norm": 3.265625,
"learning_rate": 0.0002588925900606301,
"loss": 4.7946,
"step": 7170
},
{
"epoch": 3.2232704402515724,
"grad_norm": 3.296875,
"learning_rate": 0.000258817355177773,
"loss": 4.8217,
"step": 7175
},
{
"epoch": 3.225516621743037,
"grad_norm": 3.3125,
"learning_rate": 0.0002587420638994698,
"loss": 4.7985,
"step": 7180
},
{
"epoch": 3.2277628032345014,
"grad_norm": 3.328125,
"learning_rate": 0.0002586667162709797,
"loss": 4.7482,
"step": 7185
},
{
"epoch": 3.230008984725966,
"grad_norm": 3.03125,
"learning_rate": 0.0002585913123375956,
"loss": 4.7843,
"step": 7190
},
{
"epoch": 3.2322551662174304,
"grad_norm": 3.203125,
"learning_rate": 0.00025851585214464414,
"loss": 4.8181,
"step": 7195
},
{
"epoch": 3.234501347708895,
"grad_norm": 3.234375,
"learning_rate": 0.0002584403357374861,
"loss": 4.8006,
"step": 7200
},
{
"epoch": 3.2367475292003594,
"grad_norm": 3.3125,
"learning_rate": 0.0002583647631615158,
"loss": 4.9063,
"step": 7205
},
{
"epoch": 3.238993710691824,
"grad_norm": 3.125,
"learning_rate": 0.00025828913446216133,
"loss": 4.8141,
"step": 7210
},
{
"epoch": 3.2412398921832883,
"grad_norm": 3.140625,
"learning_rate": 0.0002582134496848847,
"loss": 4.8757,
"step": 7215
},
{
"epoch": 3.243486073674753,
"grad_norm": 3.09375,
"learning_rate": 0.0002581377088751814,
"loss": 4.802,
"step": 7220
},
{
"epoch": 3.2457322551662173,
"grad_norm": 3.125,
"learning_rate": 0.00025806191207858076,
"loss": 4.8018,
"step": 7225
},
{
"epoch": 3.247978436657682,
"grad_norm": 3.390625,
"learning_rate": 0.0002579860593406457,
"loss": 4.8861,
"step": 7230
},
{
"epoch": 3.2502246181491463,
"grad_norm": 3.1875,
"learning_rate": 0.0002579101507069728,
"loss": 4.8369,
"step": 7235
},
{
"epoch": 3.252470799640611,
"grad_norm": 3.0625,
"learning_rate": 0.0002578341862231922,
"loss": 4.823,
"step": 7240
},
{
"epoch": 3.2547169811320753,
"grad_norm": 3.203125,
"learning_rate": 0.0002577581659349677,
"loss": 4.8676,
"step": 7245
},
{
"epoch": 3.25696316262354,
"grad_norm": 3.3125,
"learning_rate": 0.0002576820898879965,
"loss": 4.8252,
"step": 7250
},
{
"epoch": 3.2592093441150043,
"grad_norm": 3.046875,
"learning_rate": 0.0002576059581280095,
"loss": 4.7799,
"step": 7255
},
{
"epoch": 3.2614555256064692,
"grad_norm": 3.125,
"learning_rate": 0.0002575297707007709,
"loss": 4.8234,
"step": 7260
},
{
"epoch": 3.2637017070979333,
"grad_norm": 3.1875,
"learning_rate": 0.00025745352765207843,
"loss": 4.7695,
"step": 7265
},
{
"epoch": 3.265947888589398,
"grad_norm": 3.359375,
"learning_rate": 0.0002573772290277633,
"loss": 4.8183,
"step": 7270
},
{
"epoch": 3.2681940700808627,
"grad_norm": 3.15625,
"learning_rate": 0.0002573008748736902,
"loss": 4.8566,
"step": 7275
},
{
"epoch": 3.270440251572327,
"grad_norm": 3.125,
"learning_rate": 0.00025722446523575705,
"loss": 4.7541,
"step": 7280
},
{
"epoch": 3.2726864330637917,
"grad_norm": 3.046875,
"learning_rate": 0.00025714800015989506,
"loss": 4.7738,
"step": 7285
},
{
"epoch": 3.274932614555256,
"grad_norm": 3.359375,
"learning_rate": 0.00025707147969206904,
"loss": 4.8893,
"step": 7290
},
{
"epoch": 3.2771787960467207,
"grad_norm": 3.421875,
"learning_rate": 0.0002569949038782769,
"loss": 4.7991,
"step": 7295
},
{
"epoch": 3.279424977538185,
"grad_norm": 3.265625,
"learning_rate": 0.0002569182727645498,
"loss": 4.7758,
"step": 7300
},
{
"epoch": 3.2816711590296497,
"grad_norm": 3.171875,
"learning_rate": 0.0002568415863969522,
"loss": 4.7917,
"step": 7305
},
{
"epoch": 3.283917340521114,
"grad_norm": 3.390625,
"learning_rate": 0.00025676484482158187,
"loss": 4.7623,
"step": 7310
},
{
"epoch": 3.2861635220125787,
"grad_norm": 3.265625,
"learning_rate": 0.0002566880480845696,
"loss": 4.7615,
"step": 7315
},
{
"epoch": 3.288409703504043,
"grad_norm": 3.4375,
"learning_rate": 0.00025661119623207943,
"loss": 4.7924,
"step": 7320
},
{
"epoch": 3.2906558849955077,
"grad_norm": 3.125,
"learning_rate": 0.00025653428931030856,
"loss": 4.8251,
"step": 7325
},
{
"epoch": 3.292902066486972,
"grad_norm": 3.25,
"learning_rate": 0.00025645732736548707,
"loss": 4.7862,
"step": 7330
},
{
"epoch": 3.2951482479784366,
"grad_norm": 3.296875,
"learning_rate": 0.0002563803104438785,
"loss": 4.8408,
"step": 7335
},
{
"epoch": 3.297394429469901,
"grad_norm": 3.453125,
"learning_rate": 0.0002563032385917791,
"loss": 4.7965,
"step": 7340
},
{
"epoch": 3.2996406109613656,
"grad_norm": 3.1875,
"learning_rate": 0.00025622611185551825,
"loss": 4.8009,
"step": 7345
},
{
"epoch": 3.30188679245283,
"grad_norm": 3.03125,
"learning_rate": 0.0002561489302814585,
"loss": 4.7463,
"step": 7350
},
{
"epoch": 3.3041329739442946,
"grad_norm": 3.296875,
"learning_rate": 0.000256071693915995,
"loss": 4.8728,
"step": 7355
},
{
"epoch": 3.306379155435759,
"grad_norm": 3.640625,
"learning_rate": 0.00025599440280555616,
"loss": 4.8311,
"step": 7360
},
{
"epoch": 3.3086253369272236,
"grad_norm": 3.171875,
"learning_rate": 0.00025591705699660317,
"loss": 4.8349,
"step": 7365
},
{
"epoch": 3.310871518418688,
"grad_norm": 3.03125,
"learning_rate": 0.00025583965653563006,
"loss": 4.8007,
"step": 7370
},
{
"epoch": 3.3131176999101526,
"grad_norm": 3.125,
"learning_rate": 0.00025576220146916376,
"loss": 4.8239,
"step": 7375
},
{
"epoch": 3.315363881401617,
"grad_norm": 3.125,
"learning_rate": 0.0002556846918437641,
"loss": 4.7837,
"step": 7380
},
{
"epoch": 3.3176100628930816,
"grad_norm": 3.1875,
"learning_rate": 0.0002556071277060236,
"loss": 4.8485,
"step": 7385
},
{
"epoch": 3.319856244384546,
"grad_norm": 3.1875,
"learning_rate": 0.0002555295091025675,
"loss": 4.8199,
"step": 7390
},
{
"epoch": 3.322102425876011,
"grad_norm": 3.203125,
"learning_rate": 0.00025545183608005395,
"loss": 4.7623,
"step": 7395
},
{
"epoch": 3.324348607367475,
"grad_norm": 3.265625,
"learning_rate": 0.0002553741086851737,
"loss": 4.8978,
"step": 7400
},
{
"epoch": 3.32659478885894,
"grad_norm": 3.25,
"learning_rate": 0.0002552963269646502,
"loss": 4.7921,
"step": 7405
},
{
"epoch": 3.3288409703504045,
"grad_norm": 3.21875,
"learning_rate": 0.0002552184909652396,
"loss": 4.7919,
"step": 7410
},
{
"epoch": 3.331087151841869,
"grad_norm": 3.203125,
"learning_rate": 0.0002551406007337305,
"loss": 4.8001,
"step": 7415
},
{
"epoch": 3.3333333333333335,
"grad_norm": 3.296875,
"learning_rate": 0.0002550626563169444,
"loss": 4.7865,
"step": 7420
},
{
"epoch": 3.335579514824798,
"grad_norm": 3.015625,
"learning_rate": 0.0002549846577617352,
"loss": 4.7541,
"step": 7425
},
{
"epoch": 3.3378256963162625,
"grad_norm": 3.234375,
"learning_rate": 0.00025490660511498926,
"loss": 4.8102,
"step": 7430
},
{
"epoch": 3.340071877807727,
"grad_norm": 3.03125,
"learning_rate": 0.0002548284984236256,
"loss": 4.7369,
"step": 7435
},
{
"epoch": 3.3423180592991915,
"grad_norm": 3.234375,
"learning_rate": 0.0002547503377345957,
"loss": 4.8052,
"step": 7440
},
{
"epoch": 3.344564240790656,
"grad_norm": 3.078125,
"learning_rate": 0.00025467212309488347,
"loss": 4.8815,
"step": 7445
},
{
"epoch": 3.3468104222821204,
"grad_norm": 3.3125,
"learning_rate": 0.0002545938545515052,
"loss": 4.8297,
"step": 7450
},
{
"epoch": 3.349056603773585,
"grad_norm": 3.375,
"learning_rate": 0.00025451553215150973,
"loss": 4.8577,
"step": 7455
},
{
"epoch": 3.3513027852650494,
"grad_norm": 3.109375,
"learning_rate": 0.0002544371559419781,
"loss": 4.8335,
"step": 7460
},
{
"epoch": 3.353548966756514,
"grad_norm": 3.109375,
"learning_rate": 0.0002543587259700239,
"loss": 4.8204,
"step": 7465
},
{
"epoch": 3.3557951482479784,
"grad_norm": 3.15625,
"learning_rate": 0.0002542802422827928,
"loss": 4.8149,
"step": 7470
},
{
"epoch": 3.358041329739443,
"grad_norm": 3.234375,
"learning_rate": 0.00025420170492746293,
"loss": 4.7721,
"step": 7475
},
{
"epoch": 3.3602875112309074,
"grad_norm": 3.3125,
"learning_rate": 0.0002541231139512447,
"loss": 4.7729,
"step": 7480
},
{
"epoch": 3.362533692722372,
"grad_norm": 3.125,
"learning_rate": 0.0002540444694013805,
"loss": 4.8291,
"step": 7485
},
{
"epoch": 3.3647798742138364,
"grad_norm": 3.515625,
"learning_rate": 0.00025396577132514523,
"loss": 4.8063,
"step": 7490
},
{
"epoch": 3.367026055705301,
"grad_norm": 3.234375,
"learning_rate": 0.00025388701976984587,
"loss": 4.7306,
"step": 7495
},
{
"epoch": 3.3692722371967654,
"grad_norm": 3.125,
"learning_rate": 0.0002538082147828214,
"loss": 4.7863,
"step": 7500
},
{
"epoch": 3.37151841868823,
"grad_norm": 2.96875,
"learning_rate": 0.0002537293564114432,
"loss": 4.8825,
"step": 7505
},
{
"epoch": 3.3737646001796944,
"grad_norm": 3.0625,
"learning_rate": 0.00025365044470311446,
"loss": 4.8224,
"step": 7510
},
{
"epoch": 3.376010781671159,
"grad_norm": 3.25,
"learning_rate": 0.0002535714797052706,
"loss": 4.8422,
"step": 7515
},
{
"epoch": 3.3782569631626234,
"grad_norm": 3.265625,
"learning_rate": 0.000253492461465379,
"loss": 4.7746,
"step": 7520
},
{
"epoch": 3.380503144654088,
"grad_norm": 3.640625,
"learning_rate": 0.00025341339003093905,
"loss": 4.8838,
"step": 7525
},
{
"epoch": 3.382749326145553,
"grad_norm": 3.9375,
"learning_rate": 0.00025333426544948214,
"loss": 4.7781,
"step": 7530
},
{
"epoch": 3.384995507637017,
"grad_norm": 3.3125,
"learning_rate": 0.0002532550877685716,
"loss": 4.808,
"step": 7535
},
{
"epoch": 3.387241689128482,
"grad_norm": 3.09375,
"learning_rate": 0.0002531758570358028,
"loss": 4.8098,
"step": 7540
},
{
"epoch": 3.3894878706199463,
"grad_norm": 3.1875,
"learning_rate": 0.0002530965732988027,
"loss": 4.7755,
"step": 7545
},
{
"epoch": 3.3917340521114108,
"grad_norm": 3.15625,
"learning_rate": 0.00025301723660523044,
"loss": 4.7746,
"step": 7550
},
{
"epoch": 3.3939802336028753,
"grad_norm": 3.0,
"learning_rate": 0.00025293784700277673,
"loss": 4.7915,
"step": 7555
},
{
"epoch": 3.3962264150943398,
"grad_norm": 3.09375,
"learning_rate": 0.0002528584045391644,
"loss": 4.7881,
"step": 7560
},
{
"epoch": 3.3984725965858043,
"grad_norm": 3.265625,
"learning_rate": 0.00025277890926214767,
"loss": 4.8263,
"step": 7565
},
{
"epoch": 3.4007187780772687,
"grad_norm": 3.203125,
"learning_rate": 0.0002526993612195128,
"loss": 4.7642,
"step": 7570
},
{
"epoch": 3.4029649595687332,
"grad_norm": 3.03125,
"learning_rate": 0.0002526197604590777,
"loss": 4.8737,
"step": 7575
},
{
"epoch": 3.4052111410601977,
"grad_norm": 3.203125,
"learning_rate": 0.00025254010702869194,
"loss": 4.7828,
"step": 7580
},
{
"epoch": 3.4074573225516622,
"grad_norm": 3.03125,
"learning_rate": 0.0002524604009762366,
"loss": 4.8156,
"step": 7585
},
{
"epoch": 3.4097035040431267,
"grad_norm": 3.21875,
"learning_rate": 0.00025238064234962474,
"loss": 4.8054,
"step": 7590
},
{
"epoch": 3.411949685534591,
"grad_norm": 3.09375,
"learning_rate": 0.00025230083119680074,
"loss": 4.8162,
"step": 7595
},
{
"epoch": 3.4141958670260557,
"grad_norm": 3.0,
"learning_rate": 0.0002522209675657407,
"loss": 4.8375,
"step": 7600
},
{
"epoch": 3.41644204851752,
"grad_norm": 3.359375,
"learning_rate": 0.0002521410515044522,
"loss": 4.7701,
"step": 7605
},
{
"epoch": 3.4186882300089847,
"grad_norm": 3.328125,
"learning_rate": 0.0002520610830609742,
"loss": 4.7296,
"step": 7610
},
{
"epoch": 3.420934411500449,
"grad_norm": 3.078125,
"learning_rate": 0.0002519810622833775,
"loss": 4.858,
"step": 7615
},
{
"epoch": 3.4231805929919137,
"grad_norm": 3.28125,
"learning_rate": 0.00025190098921976404,
"loss": 4.852,
"step": 7620
},
{
"epoch": 3.425426774483378,
"grad_norm": 3.234375,
"learning_rate": 0.00025182086391826726,
"loss": 4.7896,
"step": 7625
},
{
"epoch": 3.4276729559748427,
"grad_norm": 3.125,
"learning_rate": 0.0002517406864270522,
"loss": 4.8046,
"step": 7630
},
{
"epoch": 3.429919137466307,
"grad_norm": 3.109375,
"learning_rate": 0.000251660456794315,
"loss": 4.8123,
"step": 7635
},
{
"epoch": 3.4321653189577717,
"grad_norm": 3.265625,
"learning_rate": 0.0002515801750682833,
"loss": 4.7836,
"step": 7640
},
{
"epoch": 3.434411500449236,
"grad_norm": 3.265625,
"learning_rate": 0.000251499841297216,
"loss": 4.8299,
"step": 7645
},
{
"epoch": 3.4366576819407006,
"grad_norm": 3.15625,
"learning_rate": 0.0002514194555294033,
"loss": 4.7713,
"step": 7650
},
{
"epoch": 3.438903863432165,
"grad_norm": 3.109375,
"learning_rate": 0.00025133901781316663,
"loss": 4.7489,
"step": 7655
},
{
"epoch": 3.4411500449236296,
"grad_norm": 3.046875,
"learning_rate": 0.0002512585281968588,
"loss": 4.8084,
"step": 7660
},
{
"epoch": 3.4433962264150946,
"grad_norm": 3.234375,
"learning_rate": 0.00025117798672886354,
"loss": 4.7632,
"step": 7665
},
{
"epoch": 3.4456424079065586,
"grad_norm": 3.640625,
"learning_rate": 0.0002510973934575959,
"loss": 4.7962,
"step": 7670
},
{
"epoch": 3.4478885893980236,
"grad_norm": 3.203125,
"learning_rate": 0.0002510167484315022,
"loss": 4.7781,
"step": 7675
},
{
"epoch": 3.450134770889488,
"grad_norm": 3.1875,
"learning_rate": 0.0002509360516990597,
"loss": 4.7245,
"step": 7680
},
{
"epoch": 3.4523809523809526,
"grad_norm": 3.28125,
"learning_rate": 0.00025085530330877666,
"loss": 4.8373,
"step": 7685
},
{
"epoch": 3.454627133872417,
"grad_norm": 3.28125,
"learning_rate": 0.0002507745033091927,
"loss": 4.7834,
"step": 7690
},
{
"epoch": 3.4568733153638815,
"grad_norm": 3.140625,
"learning_rate": 0.00025069365174887814,
"loss": 4.8153,
"step": 7695
},
{
"epoch": 3.459119496855346,
"grad_norm": 3.265625,
"learning_rate": 0.0002506127486764345,
"loss": 4.7421,
"step": 7700
},
{
"epoch": 3.4613656783468105,
"grad_norm": 3.1875,
"learning_rate": 0.00025053179414049416,
"loss": 4.8132,
"step": 7705
},
{
"epoch": 3.463611859838275,
"grad_norm": 3.046875,
"learning_rate": 0.00025045078818972046,
"loss": 4.7787,
"step": 7710
},
{
"epoch": 3.4658580413297395,
"grad_norm": 3.5,
"learning_rate": 0.0002503697308728077,
"loss": 4.8161,
"step": 7715
},
{
"epoch": 3.468104222821204,
"grad_norm": 3.34375,
"learning_rate": 0.0002502886222384811,
"loss": 4.7623,
"step": 7720
},
{
"epoch": 3.4703504043126685,
"grad_norm": 3.15625,
"learning_rate": 0.0002502074623354965,
"loss": 4.9089,
"step": 7725
},
{
"epoch": 3.472596585804133,
"grad_norm": 3.0625,
"learning_rate": 0.0002501262512126408,
"loss": 4.8818,
"step": 7730
},
{
"epoch": 3.4748427672955975,
"grad_norm": 3.375,
"learning_rate": 0.00025004498891873146,
"loss": 4.8681,
"step": 7735
},
{
"epoch": 3.477088948787062,
"grad_norm": 3.046875,
"learning_rate": 0.000249963675502617,
"loss": 4.7931,
"step": 7740
},
{
"epoch": 3.4793351302785265,
"grad_norm": 3.109375,
"learning_rate": 0.00024988231101317647,
"loss": 4.7794,
"step": 7745
},
{
"epoch": 3.481581311769991,
"grad_norm": 3.140625,
"learning_rate": 0.00024980089549931955,
"loss": 4.7498,
"step": 7750
},
{
"epoch": 3.4838274932614555,
"grad_norm": 3.046875,
"learning_rate": 0.0002497194290099868,
"loss": 4.8458,
"step": 7755
},
{
"epoch": 3.48607367475292,
"grad_norm": 3.34375,
"learning_rate": 0.00024963791159414927,
"loss": 4.8934,
"step": 7760
},
{
"epoch": 3.4883198562443845,
"grad_norm": 3.375,
"learning_rate": 0.00024955634330080863,
"loss": 4.7986,
"step": 7765
},
{
"epoch": 3.490566037735849,
"grad_norm": 3.0625,
"learning_rate": 0.00024947472417899733,
"loss": 4.7661,
"step": 7770
},
{
"epoch": 3.4928122192273134,
"grad_norm": 3.296875,
"learning_rate": 0.000249393054277778,
"loss": 4.8551,
"step": 7775
},
{
"epoch": 3.495058400718778,
"grad_norm": 3.078125,
"learning_rate": 0.0002493113336462442,
"loss": 4.8479,
"step": 7780
},
{
"epoch": 3.4973045822102424,
"grad_norm": 3.25,
"learning_rate": 0.00024922956233351976,
"loss": 4.8853,
"step": 7785
},
{
"epoch": 3.499550763701707,
"grad_norm": 3.171875,
"learning_rate": 0.00024914774038875895,
"loss": 4.7687,
"step": 7790
},
{
"epoch": 3.5017969451931714,
"grad_norm": 3.296875,
"learning_rate": 0.0002490658678611466,
"loss": 4.7617,
"step": 7795
},
{
"epoch": 3.5040431266846364,
"grad_norm": 3.078125,
"learning_rate": 0.00024898394479989786,
"loss": 4.7722,
"step": 7800
},
{
"epoch": 3.5062893081761004,
"grad_norm": 3.109375,
"learning_rate": 0.0002489019712542583,
"loss": 4.8146,
"step": 7805
},
{
"epoch": 3.5085354896675653,
"grad_norm": 3.15625,
"learning_rate": 0.00024881994727350373,
"loss": 4.8087,
"step": 7810
},
{
"epoch": 3.5107816711590294,
"grad_norm": 3.125,
"learning_rate": 0.0002487378729069405,
"loss": 4.8572,
"step": 7815
},
{
"epoch": 3.5130278526504943,
"grad_norm": 3.171875,
"learning_rate": 0.0002486557482039051,
"loss": 4.7661,
"step": 7820
},
{
"epoch": 3.515274034141959,
"grad_norm": 3.09375,
"learning_rate": 0.0002485735732137642,
"loss": 4.8137,
"step": 7825
},
{
"epoch": 3.5175202156334233,
"grad_norm": 3.125,
"learning_rate": 0.00024849134798591487,
"loss": 4.8203,
"step": 7830
},
{
"epoch": 3.519766397124888,
"grad_norm": 3.140625,
"learning_rate": 0.00024840907256978433,
"loss": 4.7541,
"step": 7835
},
{
"epoch": 3.5220125786163523,
"grad_norm": 3.03125,
"learning_rate": 0.0002483267470148298,
"loss": 4.7931,
"step": 7840
},
{
"epoch": 3.524258760107817,
"grad_norm": 3.59375,
"learning_rate": 0.0002482443713705389,
"loss": 4.8011,
"step": 7845
},
{
"epoch": 3.5265049415992813,
"grad_norm": 3.296875,
"learning_rate": 0.0002481619456864293,
"loss": 4.8371,
"step": 7850
},
{
"epoch": 3.528751123090746,
"grad_norm": 3.265625,
"learning_rate": 0.0002480794700120485,
"loss": 4.7765,
"step": 7855
},
{
"epoch": 3.5309973045822103,
"grad_norm": 3.4375,
"learning_rate": 0.00024799694439697436,
"loss": 4.7728,
"step": 7860
},
{
"epoch": 3.5332434860736748,
"grad_norm": 3.125,
"learning_rate": 0.00024791436889081466,
"loss": 4.82,
"step": 7865
},
{
"epoch": 3.5354896675651393,
"grad_norm": 3.28125,
"learning_rate": 0.0002478317435432071,
"loss": 4.8269,
"step": 7870
},
{
"epoch": 3.5377358490566038,
"grad_norm": 3.1875,
"learning_rate": 0.00024774906840381935,
"loss": 4.8323,
"step": 7875
},
{
"epoch": 3.5399820305480683,
"grad_norm": 3.1875,
"learning_rate": 0.0002476663435223492,
"loss": 4.769,
"step": 7880
},
{
"epoch": 3.5422282120395328,
"grad_norm": 3.296875,
"learning_rate": 0.00024758356894852404,
"loss": 4.7889,
"step": 7885
},
{
"epoch": 3.5444743935309972,
"grad_norm": 3.21875,
"learning_rate": 0.00024750074473210134,
"loss": 4.7562,
"step": 7890
},
{
"epoch": 3.5467205750224617,
"grad_norm": 3.203125,
"learning_rate": 0.0002474178709228684,
"loss": 4.8241,
"step": 7895
},
{
"epoch": 3.5489667565139262,
"grad_norm": 3.0,
"learning_rate": 0.0002473349475706422,
"loss": 4.7784,
"step": 7900
},
{
"epoch": 3.5512129380053907,
"grad_norm": 2.984375,
"learning_rate": 0.0002472519747252697,
"loss": 4.7175,
"step": 7905
},
{
"epoch": 3.5534591194968552,
"grad_norm": 3.15625,
"learning_rate": 0.00024716895243662737,
"loss": 4.7571,
"step": 7910
},
{
"epoch": 3.5557053009883197,
"grad_norm": 3.234375,
"learning_rate": 0.00024708588075462166,
"loss": 4.7624,
"step": 7915
},
{
"epoch": 3.557951482479784,
"grad_norm": 3.3125,
"learning_rate": 0.0002470027597291885,
"loss": 4.7763,
"step": 7920
},
{
"epoch": 3.560197663971249,
"grad_norm": 3.140625,
"learning_rate": 0.0002469195894102935,
"loss": 4.8054,
"step": 7925
},
{
"epoch": 3.562443845462713,
"grad_norm": 3.15625,
"learning_rate": 0.0002468363698479321,
"loss": 4.7957,
"step": 7930
},
{
"epoch": 3.564690026954178,
"grad_norm": 3.390625,
"learning_rate": 0.0002467531010921292,
"loss": 4.7889,
"step": 7935
},
{
"epoch": 3.566936208445642,
"grad_norm": 3.15625,
"learning_rate": 0.00024666978319293914,
"loss": 4.7675,
"step": 7940
},
{
"epoch": 3.569182389937107,
"grad_norm": 3.21875,
"learning_rate": 0.00024658641620044604,
"loss": 4.843,
"step": 7945
},
{
"epoch": 3.571428571428571,
"grad_norm": 3.1875,
"learning_rate": 0.0002465030001647634,
"loss": 4.7993,
"step": 7950
},
{
"epoch": 3.573674752920036,
"grad_norm": 3.3125,
"learning_rate": 0.0002464195351360343,
"loss": 4.8091,
"step": 7955
},
{
"epoch": 3.5759209344115006,
"grad_norm": 3.21875,
"learning_rate": 0.0002463360211644311,
"loss": 4.7122,
"step": 7960
},
{
"epoch": 3.578167115902965,
"grad_norm": 3.046875,
"learning_rate": 0.0002462524583001557,
"loss": 4.8386,
"step": 7965
},
{
"epoch": 3.5804132973944296,
"grad_norm": 3.203125,
"learning_rate": 0.0002461688465934395,
"loss": 4.752,
"step": 7970
},
{
"epoch": 3.582659478885894,
"grad_norm": 3.125,
"learning_rate": 0.00024608518609454293,
"loss": 4.7621,
"step": 7975
},
{
"epoch": 3.5849056603773586,
"grad_norm": 3.390625,
"learning_rate": 0.0002460014768537561,
"loss": 4.7538,
"step": 7980
},
{
"epoch": 3.587151841868823,
"grad_norm": 3.625,
"learning_rate": 0.00024591771892139817,
"loss": 4.8875,
"step": 7985
},
{
"epoch": 3.5893980233602876,
"grad_norm": 3.125,
"learning_rate": 0.0002458339123478178,
"loss": 4.8174,
"step": 7990
},
{
"epoch": 3.591644204851752,
"grad_norm": 3.046875,
"learning_rate": 0.00024575005718339255,
"loss": 4.7648,
"step": 7995
},
{
"epoch": 3.5938903863432166,
"grad_norm": 3.15625,
"learning_rate": 0.00024566615347852965,
"loss": 4.8448,
"step": 8000
},
{
"epoch": 3.5938903863432166,
"eval_loss": 4.903536796569824,
"eval_runtime": 16.0594,
"eval_samples_per_second": 1931.145,
"eval_steps_per_second": 241.416,
"step": 8000
},
{
"epoch": 3.596136567834681,
"grad_norm": 3.265625,
"learning_rate": 0.0002455822012836651,
"loss": 4.8178,
"step": 8005
},
{
"epoch": 3.5983827493261455,
"grad_norm": 3.015625,
"learning_rate": 0.0002454982006492642,
"loss": 4.7372,
"step": 8010
},
{
"epoch": 3.60062893081761,
"grad_norm": 3.25,
"learning_rate": 0.00024541415162582144,
"loss": 4.8245,
"step": 8015
},
{
"epoch": 3.6028751123090745,
"grad_norm": 3.421875,
"learning_rate": 0.00024533005426386026,
"loss": 4.8042,
"step": 8020
},
{
"epoch": 3.605121293800539,
"grad_norm": 3.453125,
"learning_rate": 0.0002452459086139333,
"loss": 4.7305,
"step": 8025
},
{
"epoch": 3.6073674752920035,
"grad_norm": 3.28125,
"learning_rate": 0.0002451617147266221,
"loss": 4.7429,
"step": 8030
},
{
"epoch": 3.609613656783468,
"grad_norm": 2.96875,
"learning_rate": 0.00024507747265253735,
"loss": 4.8285,
"step": 8035
},
{
"epoch": 3.6118598382749325,
"grad_norm": 3.234375,
"learning_rate": 0.00024499318244231846,
"loss": 4.7211,
"step": 8040
},
{
"epoch": 3.614106019766397,
"grad_norm": 3.140625,
"learning_rate": 0.00024490884414663406,
"loss": 4.8138,
"step": 8045
},
{
"epoch": 3.6163522012578615,
"grad_norm": 3.25,
"learning_rate": 0.00024482445781618144,
"loss": 4.782,
"step": 8050
},
{
"epoch": 3.618598382749326,
"grad_norm": 3.46875,
"learning_rate": 0.0002447400235016869,
"loss": 4.823,
"step": 8055
},
{
"epoch": 3.620844564240791,
"grad_norm": 3.5,
"learning_rate": 0.00024465554125390566,
"loss": 4.7987,
"step": 8060
},
{
"epoch": 3.623090745732255,
"grad_norm": 3.09375,
"learning_rate": 0.00024457101112362146,
"loss": 4.8458,
"step": 8065
},
{
"epoch": 3.62533692722372,
"grad_norm": 3.171875,
"learning_rate": 0.00024448643316164715,
"loss": 4.8168,
"step": 8070
},
{
"epoch": 3.627583108715184,
"grad_norm": 3.265625,
"learning_rate": 0.0002444018074188242,
"loss": 4.819,
"step": 8075
},
{
"epoch": 3.629829290206649,
"grad_norm": 3.203125,
"learning_rate": 0.00024431713394602276,
"loss": 4.8063,
"step": 8080
},
{
"epoch": 3.632075471698113,
"grad_norm": 3.34375,
"learning_rate": 0.0002442324127941417,
"loss": 4.7975,
"step": 8085
},
{
"epoch": 3.634321653189578,
"grad_norm": 3.25,
"learning_rate": 0.00024414764401410854,
"loss": 4.7946,
"step": 8090
},
{
"epoch": 3.6365678346810424,
"grad_norm": 3.234375,
"learning_rate": 0.00024406282765687952,
"loss": 4.8146,
"step": 8095
},
{
"epoch": 3.638814016172507,
"grad_norm": 3.3125,
"learning_rate": 0.00024397796377343938,
"loss": 4.8036,
"step": 8100
},
{
"epoch": 3.6410601976639714,
"grad_norm": 3.25,
"learning_rate": 0.00024389305241480144,
"loss": 4.8005,
"step": 8105
},
{
"epoch": 3.643306379155436,
"grad_norm": 3.28125,
"learning_rate": 0.00024380809363200756,
"loss": 4.83,
"step": 8110
},
{
"epoch": 3.6455525606469004,
"grad_norm": 3.1875,
"learning_rate": 0.0002437230874761282,
"loss": 4.7698,
"step": 8115
},
{
"epoch": 3.647798742138365,
"grad_norm": 3.328125,
"learning_rate": 0.00024363803399826217,
"loss": 4.7716,
"step": 8120
},
{
"epoch": 3.6500449236298294,
"grad_norm": 3.171875,
"learning_rate": 0.0002435529332495368,
"loss": 4.7791,
"step": 8125
},
{
"epoch": 3.652291105121294,
"grad_norm": 3.234375,
"learning_rate": 0.0002434677852811078,
"loss": 4.8309,
"step": 8130
},
{
"epoch": 3.6545372866127583,
"grad_norm": 3.4375,
"learning_rate": 0.00024338259014415923,
"loss": 4.8274,
"step": 8135
},
{
"epoch": 3.656783468104223,
"grad_norm": 3.265625,
"learning_rate": 0.00024329734788990366,
"loss": 4.7547,
"step": 8140
},
{
"epoch": 3.6590296495956873,
"grad_norm": 3.265625,
"learning_rate": 0.00024321205856958178,
"loss": 4.7754,
"step": 8145
},
{
"epoch": 3.661275831087152,
"grad_norm": 3.171875,
"learning_rate": 0.00024312672223446272,
"loss": 4.765,
"step": 8150
},
{
"epoch": 3.6635220125786163,
"grad_norm": 3.1875,
"learning_rate": 0.0002430413389358438,
"loss": 4.7664,
"step": 8155
},
{
"epoch": 3.665768194070081,
"grad_norm": 3.203125,
"learning_rate": 0.00024295590872505055,
"loss": 4.756,
"step": 8160
},
{
"epoch": 3.6680143755615453,
"grad_norm": 3.328125,
"learning_rate": 0.0002428704316534368,
"loss": 4.7967,
"step": 8165
},
{
"epoch": 3.67026055705301,
"grad_norm": 3.421875,
"learning_rate": 0.00024278490777238448,
"loss": 4.7841,
"step": 8170
},
{
"epoch": 3.6725067385444743,
"grad_norm": 3.140625,
"learning_rate": 0.0002426993371333037,
"loss": 4.7319,
"step": 8175
},
{
"epoch": 3.674752920035939,
"grad_norm": 3.296875,
"learning_rate": 0.0002426137197876325,
"loss": 4.8211,
"step": 8180
},
{
"epoch": 3.6769991015274033,
"grad_norm": 3.09375,
"learning_rate": 0.00024252805578683733,
"loss": 4.7469,
"step": 8185
},
{
"epoch": 3.6792452830188678,
"grad_norm": 3.28125,
"learning_rate": 0.00024244234518241235,
"loss": 4.7779,
"step": 8190
},
{
"epoch": 3.6814914645103327,
"grad_norm": 3.296875,
"learning_rate": 0.00024235658802587996,
"loss": 4.7694,
"step": 8195
},
{
"epoch": 3.6837376460017968,
"grad_norm": 3.171875,
"learning_rate": 0.00024227078436879043,
"loss": 4.8198,
"step": 8200
},
{
"epoch": 3.6859838274932617,
"grad_norm": 3.875,
"learning_rate": 0.00024218493426272203,
"loss": 4.8039,
"step": 8205
},
{
"epoch": 3.6882300089847257,
"grad_norm": 3.375,
"learning_rate": 0.00024209903775928093,
"loss": 4.758,
"step": 8210
},
{
"epoch": 3.6904761904761907,
"grad_norm": 3.03125,
"learning_rate": 0.0002420130949101012,
"loss": 4.7523,
"step": 8215
},
{
"epoch": 3.6927223719676547,
"grad_norm": 3.34375,
"learning_rate": 0.00024192710576684476,
"loss": 4.7552,
"step": 8220
},
{
"epoch": 3.6949685534591197,
"grad_norm": 3.125,
"learning_rate": 0.00024184107038120137,
"loss": 4.8155,
"step": 8225
},
{
"epoch": 3.697214734950584,
"grad_norm": 3.046875,
"learning_rate": 0.00024175498880488856,
"loss": 4.7569,
"step": 8230
},
{
"epoch": 3.6994609164420487,
"grad_norm": 2.9375,
"learning_rate": 0.00024166886108965168,
"loss": 4.7675,
"step": 8235
},
{
"epoch": 3.701707097933513,
"grad_norm": 3.8125,
"learning_rate": 0.00024158268728726375,
"loss": 4.7861,
"step": 8240
},
{
"epoch": 3.7039532794249777,
"grad_norm": 3.3125,
"learning_rate": 0.0002414964674495256,
"loss": 4.8087,
"step": 8245
},
{
"epoch": 3.706199460916442,
"grad_norm": 4.71875,
"learning_rate": 0.00024141020162826558,
"loss": 4.8768,
"step": 8250
},
{
"epoch": 3.7084456424079066,
"grad_norm": 3.359375,
"learning_rate": 0.0002413238898753398,
"loss": 4.812,
"step": 8255
},
{
"epoch": 3.710691823899371,
"grad_norm": 3.46875,
"learning_rate": 0.00024123753224263193,
"loss": 4.8085,
"step": 8260
},
{
"epoch": 3.7129380053908356,
"grad_norm": 3.0625,
"learning_rate": 0.00024115112878205321,
"loss": 4.7944,
"step": 8265
},
{
"epoch": 3.7151841868823,
"grad_norm": 3.21875,
"learning_rate": 0.00024106467954554254,
"loss": 4.7821,
"step": 8270
},
{
"epoch": 3.7174303683737646,
"grad_norm": 3.140625,
"learning_rate": 0.0002409781845850661,
"loss": 4.7904,
"step": 8275
},
{
"epoch": 3.719676549865229,
"grad_norm": 3.015625,
"learning_rate": 0.00024089164395261784,
"loss": 4.7672,
"step": 8280
},
{
"epoch": 3.7219227313566936,
"grad_norm": 3.078125,
"learning_rate": 0.0002408050577002189,
"loss": 4.7801,
"step": 8285
},
{
"epoch": 3.724168912848158,
"grad_norm": 3.125,
"learning_rate": 0.00024071842587991806,
"loss": 4.8116,
"step": 8290
},
{
"epoch": 3.7264150943396226,
"grad_norm": 3.125,
"learning_rate": 0.00024063174854379145,
"loss": 4.8041,
"step": 8295
},
{
"epoch": 3.728661275831087,
"grad_norm": 3.34375,
"learning_rate": 0.00024054502574394235,
"loss": 4.8149,
"step": 8300
},
{
"epoch": 3.7309074573225516,
"grad_norm": 3.15625,
"learning_rate": 0.0002404582575325016,
"loss": 4.7656,
"step": 8305
},
{
"epoch": 3.733153638814016,
"grad_norm": 3.046875,
"learning_rate": 0.00024037144396162733,
"loss": 4.8151,
"step": 8310
},
{
"epoch": 3.7353998203054806,
"grad_norm": 3.390625,
"learning_rate": 0.00024028458508350484,
"loss": 4.836,
"step": 8315
},
{
"epoch": 3.737646001796945,
"grad_norm": 3.28125,
"learning_rate": 0.00024019768095034664,
"loss": 4.7813,
"step": 8320
},
{
"epoch": 3.7398921832884096,
"grad_norm": 3.234375,
"learning_rate": 0.00024011073161439255,
"loss": 4.8202,
"step": 8325
},
{
"epoch": 3.742138364779874,
"grad_norm": 3.375,
"learning_rate": 0.00024002373712790956,
"loss": 4.7586,
"step": 8330
},
{
"epoch": 3.7443845462713385,
"grad_norm": 3.296875,
"learning_rate": 0.0002399366975431917,
"loss": 4.7871,
"step": 8335
},
{
"epoch": 3.7466307277628035,
"grad_norm": 3.28125,
"learning_rate": 0.00023984961291256018,
"loss": 4.7348,
"step": 8340
},
{
"epoch": 3.7488769092542675,
"grad_norm": 3.171875,
"learning_rate": 0.00023976248328836327,
"loss": 4.7715,
"step": 8345
},
{
"epoch": 3.7511230907457325,
"grad_norm": 3.421875,
"learning_rate": 0.00023967530872297623,
"loss": 4.76,
"step": 8350
},
{
"epoch": 3.7533692722371965,
"grad_norm": 3.15625,
"learning_rate": 0.0002395880892688015,
"loss": 4.7845,
"step": 8355
},
{
"epoch": 3.7556154537286615,
"grad_norm": 3.203125,
"learning_rate": 0.00023950082497826842,
"loss": 4.8077,
"step": 8360
},
{
"epoch": 3.757861635220126,
"grad_norm": 3.265625,
"learning_rate": 0.00023941351590383314,
"loss": 4.7349,
"step": 8365
},
{
"epoch": 3.7601078167115904,
"grad_norm": 3.859375,
"learning_rate": 0.0002393261620979789,
"loss": 4.7692,
"step": 8370
},
{
"epoch": 3.762353998203055,
"grad_norm": 3.171875,
"learning_rate": 0.00023923876361321583,
"loss": 4.7812,
"step": 8375
},
{
"epoch": 3.7646001796945194,
"grad_norm": 3.1875,
"learning_rate": 0.0002391513205020808,
"loss": 4.786,
"step": 8380
},
{
"epoch": 3.766846361185984,
"grad_norm": 3.671875,
"learning_rate": 0.00023906383281713757,
"loss": 4.8124,
"step": 8385
},
{
"epoch": 3.7690925426774484,
"grad_norm": 3.171875,
"learning_rate": 0.00023897630061097677,
"loss": 4.8414,
"step": 8390
},
{
"epoch": 3.771338724168913,
"grad_norm": 3.1875,
"learning_rate": 0.00023888872393621564,
"loss": 4.7914,
"step": 8395
},
{
"epoch": 3.7735849056603774,
"grad_norm": 3.40625,
"learning_rate": 0.00023880110284549828,
"loss": 4.8036,
"step": 8400
},
{
"epoch": 3.775831087151842,
"grad_norm": 3.171875,
"learning_rate": 0.0002387134373914954,
"loss": 4.7247,
"step": 8405
},
{
"epoch": 3.7780772686433064,
"grad_norm": 3.28125,
"learning_rate": 0.00023862572762690452,
"loss": 4.8149,
"step": 8410
},
{
"epoch": 3.780323450134771,
"grad_norm": 3.28125,
"learning_rate": 0.0002385379736044496,
"loss": 4.7492,
"step": 8415
},
{
"epoch": 3.7825696316262354,
"grad_norm": 3.46875,
"learning_rate": 0.00023845017537688125,
"loss": 4.763,
"step": 8420
},
{
"epoch": 3.7848158131177,
"grad_norm": 3.15625,
"learning_rate": 0.00023836233299697685,
"loss": 4.7334,
"step": 8425
},
{
"epoch": 3.7870619946091644,
"grad_norm": 3.484375,
"learning_rate": 0.00023827444651754005,
"loss": 4.7934,
"step": 8430
},
{
"epoch": 3.789308176100629,
"grad_norm": 3.34375,
"learning_rate": 0.00023818651599140115,
"loss": 4.8119,
"step": 8435
},
{
"epoch": 3.7915543575920934,
"grad_norm": 3.453125,
"learning_rate": 0.00023809854147141695,
"loss": 4.7902,
"step": 8440
},
{
"epoch": 3.793800539083558,
"grad_norm": 3.65625,
"learning_rate": 0.00023801052301047063,
"loss": 4.8311,
"step": 8445
},
{
"epoch": 3.7960467205750223,
"grad_norm": 3.390625,
"learning_rate": 0.00023792246066147186,
"loss": 4.7616,
"step": 8450
},
{
"epoch": 3.798292902066487,
"grad_norm": 3.03125,
"learning_rate": 0.00023783435447735657,
"loss": 4.7668,
"step": 8455
},
{
"epoch": 3.8005390835579513,
"grad_norm": 3.21875,
"learning_rate": 0.00023774620451108707,
"loss": 4.7531,
"step": 8460
},
{
"epoch": 3.802785265049416,
"grad_norm": 3.203125,
"learning_rate": 0.00023765801081565213,
"loss": 4.8713,
"step": 8465
},
{
"epoch": 3.8050314465408803,
"grad_norm": 3.140625,
"learning_rate": 0.00023756977344406663,
"loss": 4.878,
"step": 8470
},
{
"epoch": 3.8072776280323453,
"grad_norm": 3.40625,
"learning_rate": 0.00023748149244937186,
"loss": 4.7309,
"step": 8475
},
{
"epoch": 3.8095238095238093,
"grad_norm": 3.109375,
"learning_rate": 0.00023739316788463517,
"loss": 4.7774,
"step": 8480
},
{
"epoch": 3.8117699910152743,
"grad_norm": 3.109375,
"learning_rate": 0.00023730479980295022,
"loss": 4.7595,
"step": 8485
},
{
"epoch": 3.8140161725067383,
"grad_norm": 3.296875,
"learning_rate": 0.0002372163882574368,
"loss": 4.7536,
"step": 8490
},
{
"epoch": 3.8162623539982032,
"grad_norm": 3.3125,
"learning_rate": 0.00023712793330124077,
"loss": 4.7914,
"step": 8495
},
{
"epoch": 3.8185085354896673,
"grad_norm": 3.3125,
"learning_rate": 0.00023703943498753417,
"loss": 4.7724,
"step": 8500
},
{
"epoch": 3.8207547169811322,
"grad_norm": 3.03125,
"learning_rate": 0.00023695089336951507,
"loss": 4.7454,
"step": 8505
},
{
"epoch": 3.8230008984725967,
"grad_norm": 3.21875,
"learning_rate": 0.00023686230850040758,
"loss": 4.7626,
"step": 8510
},
{
"epoch": 3.825247079964061,
"grad_norm": 3.296875,
"learning_rate": 0.00023677368043346174,
"loss": 4.773,
"step": 8515
},
{
"epoch": 3.8274932614555257,
"grad_norm": 3.1875,
"learning_rate": 0.0002366850092219537,
"loss": 4.7775,
"step": 8520
},
{
"epoch": 3.82973944294699,
"grad_norm": 3.09375,
"learning_rate": 0.00023659629491918534,
"loss": 4.7524,
"step": 8525
},
{
"epoch": 3.8319856244384547,
"grad_norm": 3.15625,
"learning_rate": 0.0002365075375784847,
"loss": 4.783,
"step": 8530
},
{
"epoch": 3.834231805929919,
"grad_norm": 3.28125,
"learning_rate": 0.00023641873725320544,
"loss": 4.7749,
"step": 8535
},
{
"epoch": 3.8364779874213837,
"grad_norm": 3.21875,
"learning_rate": 0.0002363298939967272,
"loss": 4.7647,
"step": 8540
},
{
"epoch": 3.838724168912848,
"grad_norm": 3.40625,
"learning_rate": 0.00023624100786245547,
"loss": 4.7626,
"step": 8545
},
{
"epoch": 3.8409703504043127,
"grad_norm": 3.140625,
"learning_rate": 0.0002361520789038213,
"loss": 4.7869,
"step": 8550
},
{
"epoch": 3.843216531895777,
"grad_norm": 3.34375,
"learning_rate": 0.00023606310717428177,
"loss": 4.8144,
"step": 8555
},
{
"epoch": 3.8454627133872417,
"grad_norm": 3.015625,
"learning_rate": 0.00023597409272731946,
"loss": 4.791,
"step": 8560
},
{
"epoch": 3.847708894878706,
"grad_norm": 3.0625,
"learning_rate": 0.00023588503561644268,
"loss": 4.86,
"step": 8565
},
{
"epoch": 3.8499550763701706,
"grad_norm": 3.046875,
"learning_rate": 0.0002357959358951854,
"loss": 4.7741,
"step": 8570
},
{
"epoch": 3.852201257861635,
"grad_norm": 3.234375,
"learning_rate": 0.00023570679361710728,
"loss": 4.7514,
"step": 8575
},
{
"epoch": 3.8544474393530996,
"grad_norm": 3.296875,
"learning_rate": 0.0002356176088357934,
"loss": 4.7896,
"step": 8580
},
{
"epoch": 3.856693620844564,
"grad_norm": 3.171875,
"learning_rate": 0.00023552838160485453,
"loss": 4.7116,
"step": 8585
},
{
"epoch": 3.8589398023360286,
"grad_norm": 3.6875,
"learning_rate": 0.00023543911197792682,
"loss": 4.7938,
"step": 8590
},
{
"epoch": 3.861185983827493,
"grad_norm": 3.296875,
"learning_rate": 0.0002353498000086721,
"loss": 4.7324,
"step": 8595
},
{
"epoch": 3.8634321653189576,
"grad_norm": 3.234375,
"learning_rate": 0.00023526044575077743,
"loss": 4.7512,
"step": 8600
},
{
"epoch": 3.865678346810422,
"grad_norm": 3.484375,
"learning_rate": 0.0002351710492579555,
"loss": 4.7148,
"step": 8605
},
{
"epoch": 3.867924528301887,
"grad_norm": 3.09375,
"learning_rate": 0.00023508161058394424,
"loss": 4.7609,
"step": 8610
},
{
"epoch": 3.870170709793351,
"grad_norm": 3.40625,
"learning_rate": 0.00023499212978250696,
"loss": 4.8106,
"step": 8615
},
{
"epoch": 3.872416891284816,
"grad_norm": 3.234375,
"learning_rate": 0.00023490260690743235,
"loss": 4.8064,
"step": 8620
},
{
"epoch": 3.87466307277628,
"grad_norm": 3.34375,
"learning_rate": 0.00023481304201253438,
"loss": 4.8099,
"step": 8625
},
{
"epoch": 3.876909254267745,
"grad_norm": 3.46875,
"learning_rate": 0.00023472343515165223,
"loss": 4.8328,
"step": 8630
},
{
"epoch": 3.879155435759209,
"grad_norm": 3.109375,
"learning_rate": 0.00023463378637865036,
"loss": 4.8231,
"step": 8635
},
{
"epoch": 3.881401617250674,
"grad_norm": 3.125,
"learning_rate": 0.00023454409574741843,
"loss": 4.7911,
"step": 8640
},
{
"epoch": 3.8836477987421385,
"grad_norm": 3.078125,
"learning_rate": 0.00023445436331187108,
"loss": 4.7646,
"step": 8645
},
{
"epoch": 3.885893980233603,
"grad_norm": 3.21875,
"learning_rate": 0.0002343645891259484,
"loss": 4.8198,
"step": 8650
},
{
"epoch": 3.8881401617250675,
"grad_norm": 3.375,
"learning_rate": 0.00023427477324361532,
"loss": 4.7684,
"step": 8655
},
{
"epoch": 3.890386343216532,
"grad_norm": 3.21875,
"learning_rate": 0.00023418491571886198,
"loss": 4.7267,
"step": 8660
},
{
"epoch": 3.8926325247079965,
"grad_norm": 3.203125,
"learning_rate": 0.0002340950166057034,
"loss": 4.8222,
"step": 8665
},
{
"epoch": 3.894878706199461,
"grad_norm": 3.359375,
"learning_rate": 0.0002340050759581798,
"loss": 4.8394,
"step": 8670
},
{
"epoch": 3.8971248876909255,
"grad_norm": 2.9375,
"learning_rate": 0.00023391509383035618,
"loss": 4.7634,
"step": 8675
},
{
"epoch": 3.89937106918239,
"grad_norm": 3.25,
"learning_rate": 0.00023382507027632264,
"loss": 4.6996,
"step": 8680
},
{
"epoch": 3.9016172506738545,
"grad_norm": 3.0,
"learning_rate": 0.00023373500535019403,
"loss": 4.8458,
"step": 8685
},
{
"epoch": 3.903863432165319,
"grad_norm": 3.25,
"learning_rate": 0.00023364489910611018,
"loss": 4.7772,
"step": 8690
},
{
"epoch": 3.9061096136567834,
"grad_norm": 3.15625,
"learning_rate": 0.00023355475159823568,
"loss": 4.8331,
"step": 8695
},
{
"epoch": 3.908355795148248,
"grad_norm": 3.1875,
"learning_rate": 0.00023346456288075995,
"loss": 4.8063,
"step": 8700
},
{
"epoch": 3.9106019766397124,
"grad_norm": 3.59375,
"learning_rate": 0.00023337433300789725,
"loss": 4.7402,
"step": 8705
},
{
"epoch": 3.912848158131177,
"grad_norm": 3.046875,
"learning_rate": 0.00023328406203388646,
"loss": 4.7966,
"step": 8710
},
{
"epoch": 3.9150943396226414,
"grad_norm": 3.5,
"learning_rate": 0.00023319375001299125,
"loss": 4.7583,
"step": 8715
},
{
"epoch": 3.917340521114106,
"grad_norm": 3.15625,
"learning_rate": 0.00023310339699949995,
"loss": 4.8278,
"step": 8720
},
{
"epoch": 3.9195867026055704,
"grad_norm": 3.359375,
"learning_rate": 0.0002330130030477255,
"loss": 4.7303,
"step": 8725
},
{
"epoch": 3.921832884097035,
"grad_norm": 3.109375,
"learning_rate": 0.00023292256821200546,
"loss": 4.8432,
"step": 8730
},
{
"epoch": 3.9240790655884994,
"grad_norm": 3.1875,
"learning_rate": 0.00023283209254670203,
"loss": 4.7292,
"step": 8735
},
{
"epoch": 3.926325247079964,
"grad_norm": 3.265625,
"learning_rate": 0.00023274157610620187,
"loss": 4.7701,
"step": 8740
},
{
"epoch": 3.928571428571429,
"grad_norm": 3.28125,
"learning_rate": 0.00023265101894491623,
"loss": 4.7612,
"step": 8745
},
{
"epoch": 3.930817610062893,
"grad_norm": 4.0,
"learning_rate": 0.0002325604211172807,
"loss": 4.8229,
"step": 8750
},
{
"epoch": 3.933063791554358,
"grad_norm": 3.21875,
"learning_rate": 0.00023246978267775546,
"loss": 4.7351,
"step": 8755
},
{
"epoch": 3.935309973045822,
"grad_norm": 3.203125,
"learning_rate": 0.00023237910368082503,
"loss": 4.8045,
"step": 8760
},
{
"epoch": 3.937556154537287,
"grad_norm": 3.40625,
"learning_rate": 0.0002322883841809983,
"loss": 4.8242,
"step": 8765
},
{
"epoch": 3.939802336028751,
"grad_norm": 3.234375,
"learning_rate": 0.00023219762423280863,
"loss": 4.7605,
"step": 8770
},
{
"epoch": 3.942048517520216,
"grad_norm": 3.15625,
"learning_rate": 0.00023210682389081355,
"loss": 4.7575,
"step": 8775
},
{
"epoch": 3.9442946990116803,
"grad_norm": 3.15625,
"learning_rate": 0.00023201598320959487,
"loss": 4.7075,
"step": 8780
},
{
"epoch": 3.9465408805031448,
"grad_norm": 3.46875,
"learning_rate": 0.00023192510224375875,
"loss": 4.7283,
"step": 8785
},
{
"epoch": 3.9487870619946093,
"grad_norm": 3.203125,
"learning_rate": 0.00023183418104793548,
"loss": 4.7323,
"step": 8790
},
{
"epoch": 3.9510332434860738,
"grad_norm": 3.21875,
"learning_rate": 0.00023174321967677958,
"loss": 4.7524,
"step": 8795
},
{
"epoch": 3.9532794249775383,
"grad_norm": 3.265625,
"learning_rate": 0.00023165221818496976,
"loss": 4.7401,
"step": 8800
},
{
"epoch": 3.9555256064690028,
"grad_norm": 3.421875,
"learning_rate": 0.00023156117662720876,
"loss": 4.8213,
"step": 8805
},
{
"epoch": 3.9577717879604672,
"grad_norm": 3.375,
"learning_rate": 0.0002314700950582234,
"loss": 4.778,
"step": 8810
},
{
"epoch": 3.9600179694519317,
"grad_norm": 3.3125,
"learning_rate": 0.00023137897353276468,
"loss": 4.7286,
"step": 8815
},
{
"epoch": 3.9622641509433962,
"grad_norm": 3.296875,
"learning_rate": 0.0002312878121056074,
"loss": 4.7604,
"step": 8820
},
{
"epoch": 3.9645103324348607,
"grad_norm": 3.578125,
"learning_rate": 0.00023119661083155057,
"loss": 4.7712,
"step": 8825
},
{
"epoch": 3.9667565139263252,
"grad_norm": 3.546875,
"learning_rate": 0.0002311053697654171,
"loss": 4.7624,
"step": 8830
},
{
"epoch": 3.9690026954177897,
"grad_norm": 3.109375,
"learning_rate": 0.00023101408896205366,
"loss": 4.7509,
"step": 8835
},
{
"epoch": 3.971248876909254,
"grad_norm": 3.015625,
"learning_rate": 0.00023092276847633101,
"loss": 4.8025,
"step": 8840
},
{
"epoch": 3.9734950584007187,
"grad_norm": 3.234375,
"learning_rate": 0.00023083140836314367,
"loss": 4.8212,
"step": 8845
},
{
"epoch": 3.975741239892183,
"grad_norm": 3.203125,
"learning_rate": 0.00023074000867740995,
"loss": 4.6859,
"step": 8850
},
{
"epoch": 3.9779874213836477,
"grad_norm": 3.390625,
"learning_rate": 0.000230648569474072,
"loss": 4.8425,
"step": 8855
},
{
"epoch": 3.980233602875112,
"grad_norm": 3.375,
"learning_rate": 0.0002305570908080957,
"loss": 4.7836,
"step": 8860
},
{
"epoch": 3.9824797843665767,
"grad_norm": 3.453125,
"learning_rate": 0.00023046557273447075,
"loss": 4.8095,
"step": 8865
},
{
"epoch": 3.984725965858041,
"grad_norm": 3.296875,
"learning_rate": 0.00023037401530821042,
"loss": 4.772,
"step": 8870
},
{
"epoch": 3.9869721473495057,
"grad_norm": 3.484375,
"learning_rate": 0.00023028241858435154,
"loss": 4.7742,
"step": 8875
},
{
"epoch": 3.9892183288409706,
"grad_norm": 3.375,
"learning_rate": 0.0002301907826179548,
"loss": 4.7964,
"step": 8880
},
{
"epoch": 3.9914645103324347,
"grad_norm": 3.25,
"learning_rate": 0.00023009910746410442,
"loss": 4.7904,
"step": 8885
},
{
"epoch": 3.9937106918238996,
"grad_norm": 3.015625,
"learning_rate": 0.00023000739317790805,
"loss": 4.8029,
"step": 8890
},
{
"epoch": 3.9959568733153636,
"grad_norm": 3.421875,
"learning_rate": 0.00022991563981449693,
"loss": 4.721,
"step": 8895
},
{
"epoch": 3.9982030548068286,
"grad_norm": 3.109375,
"learning_rate": 0.00022982384742902586,
"loss": 4.7919,
"step": 8900
},
{
"epoch": 4.000449236298293,
"grad_norm": 3.296875,
"learning_rate": 0.00022973201607667297,
"loss": 4.8092,
"step": 8905
},
{
"epoch": 4.002695417789758,
"grad_norm": 3.28125,
"learning_rate": 0.00022964014581263993,
"loss": 4.6842,
"step": 8910
},
{
"epoch": 4.004941599281222,
"grad_norm": 3.28125,
"learning_rate": 0.0002295482366921517,
"loss": 4.7022,
"step": 8915
},
{
"epoch": 4.007187780772687,
"grad_norm": 3.203125,
"learning_rate": 0.00022945628877045675,
"loss": 4.6657,
"step": 8920
},
{
"epoch": 4.009433962264151,
"grad_norm": 3.21875,
"learning_rate": 0.00022936430210282674,
"loss": 4.6306,
"step": 8925
},
{
"epoch": 4.0116801437556155,
"grad_norm": 3.3125,
"learning_rate": 0.00022927227674455653,
"loss": 4.6586,
"step": 8930
},
{
"epoch": 4.01392632524708,
"grad_norm": 3.265625,
"learning_rate": 0.0002291802127509645,
"loss": 4.7236,
"step": 8935
},
{
"epoch": 4.0161725067385445,
"grad_norm": 3.296875,
"learning_rate": 0.0002290881101773921,
"loss": 4.7126,
"step": 8940
},
{
"epoch": 4.018418688230009,
"grad_norm": 3.25,
"learning_rate": 0.00022899596907920389,
"loss": 4.7159,
"step": 8945
},
{
"epoch": 4.0206648697214735,
"grad_norm": 3.46875,
"learning_rate": 0.0002289037895117878,
"loss": 4.7184,
"step": 8950
},
{
"epoch": 4.022911051212938,
"grad_norm": 3.109375,
"learning_rate": 0.0002288115715305547,
"loss": 4.6531,
"step": 8955
},
{
"epoch": 4.0251572327044025,
"grad_norm": 3.34375,
"learning_rate": 0.00022871931519093867,
"loss": 4.6687,
"step": 8960
},
{
"epoch": 4.0274034141958674,
"grad_norm": 3.21875,
"learning_rate": 0.00022862702054839674,
"loss": 4.6754,
"step": 8965
},
{
"epoch": 4.0296495956873315,
"grad_norm": 3.265625,
"learning_rate": 0.00022853468765840907,
"loss": 4.7094,
"step": 8970
},
{
"epoch": 4.031895777178796,
"grad_norm": 3.25,
"learning_rate": 0.00022844231657647874,
"loss": 4.6216,
"step": 8975
},
{
"epoch": 4.0341419586702605,
"grad_norm": 3.109375,
"learning_rate": 0.00022834990735813186,
"loss": 4.677,
"step": 8980
},
{
"epoch": 4.036388140161725,
"grad_norm": 3.40625,
"learning_rate": 0.0002282574600589174,
"loss": 4.6951,
"step": 8985
},
{
"epoch": 4.0386343216531895,
"grad_norm": 3.15625,
"learning_rate": 0.00022816497473440717,
"loss": 4.7113,
"step": 8990
},
{
"epoch": 4.040880503144654,
"grad_norm": 3.4375,
"learning_rate": 0.00022807245144019594,
"loss": 4.6925,
"step": 8995
},
{
"epoch": 4.0431266846361185,
"grad_norm": 3.328125,
"learning_rate": 0.00022797989023190133,
"loss": 4.6086,
"step": 9000
},
{
"epoch": 4.0431266846361185,
"eval_loss": 4.870049476623535,
"eval_runtime": 16.2198,
"eval_samples_per_second": 1912.043,
"eval_steps_per_second": 239.028,
"step": 9000
},
{
"epoch": 4.045372866127583,
"grad_norm": 3.71875,
"learning_rate": 0.00022788729116516364,
"loss": 4.732,
"step": 9005
},
{
"epoch": 4.0476190476190474,
"grad_norm": 3.4375,
"learning_rate": 0.000227794654295646,
"loss": 4.6506,
"step": 9010
},
{
"epoch": 4.049865229110512,
"grad_norm": 3.171875,
"learning_rate": 0.0002277019796790342,
"loss": 4.6555,
"step": 9015
},
{
"epoch": 4.052111410601976,
"grad_norm": 3.46875,
"learning_rate": 0.00022760926737103683,
"loss": 4.6926,
"step": 9020
},
{
"epoch": 4.054357592093441,
"grad_norm": 3.28125,
"learning_rate": 0.00022751651742738502,
"loss": 4.7167,
"step": 9025
},
{
"epoch": 4.056603773584905,
"grad_norm": 3.421875,
"learning_rate": 0.00022742372990383261,
"loss": 4.6789,
"step": 9030
},
{
"epoch": 4.05884995507637,
"grad_norm": 3.3125,
"learning_rate": 0.00022733090485615594,
"loss": 4.693,
"step": 9035
},
{
"epoch": 4.061096136567834,
"grad_norm": 3.140625,
"learning_rate": 0.00022723804234015403,
"loss": 4.6121,
"step": 9040
},
{
"epoch": 4.063342318059299,
"grad_norm": 3.15625,
"learning_rate": 0.00022714514241164825,
"loss": 4.6792,
"step": 9045
},
{
"epoch": 4.065588499550763,
"grad_norm": 3.3125,
"learning_rate": 0.00022705220512648266,
"loss": 4.7157,
"step": 9050
},
{
"epoch": 4.067834681042228,
"grad_norm": 3.203125,
"learning_rate": 0.0002269592305405237,
"loss": 4.6604,
"step": 9055
},
{
"epoch": 4.070080862533692,
"grad_norm": 3.46875,
"learning_rate": 0.00022686621870966013,
"loss": 4.7952,
"step": 9060
},
{
"epoch": 4.072327044025157,
"grad_norm": 3.25,
"learning_rate": 0.0002267731696898032,
"loss": 4.6736,
"step": 9065
},
{
"epoch": 4.074573225516621,
"grad_norm": 3.09375,
"learning_rate": 0.0002266800835368865,
"loss": 4.6698,
"step": 9070
},
{
"epoch": 4.076819407008086,
"grad_norm": 3.515625,
"learning_rate": 0.00022658696030686598,
"loss": 4.7083,
"step": 9075
},
{
"epoch": 4.07906558849955,
"grad_norm": 3.3125,
"learning_rate": 0.00022649380005571975,
"loss": 4.6677,
"step": 9080
},
{
"epoch": 4.081311769991015,
"grad_norm": 3.375,
"learning_rate": 0.0002264006028394483,
"loss": 4.6811,
"step": 9085
},
{
"epoch": 4.083557951482479,
"grad_norm": 3.1875,
"learning_rate": 0.00022630736871407436,
"loss": 4.7013,
"step": 9090
},
{
"epoch": 4.085804132973944,
"grad_norm": 3.265625,
"learning_rate": 0.00022621409773564269,
"loss": 4.6296,
"step": 9095
},
{
"epoch": 4.088050314465409,
"grad_norm": 3.453125,
"learning_rate": 0.00022612078996022032,
"loss": 4.7159,
"step": 9100
},
{
"epoch": 4.090296495956873,
"grad_norm": 3.1875,
"learning_rate": 0.0002260274454438964,
"loss": 4.6755,
"step": 9105
},
{
"epoch": 4.092542677448338,
"grad_norm": 3.328125,
"learning_rate": 0.00022593406424278214,
"loss": 4.6946,
"step": 9110
},
{
"epoch": 4.094788858939802,
"grad_norm": 3.5625,
"learning_rate": 0.0002258406464130108,
"loss": 4.7235,
"step": 9115
},
{
"epoch": 4.097035040431267,
"grad_norm": 3.1875,
"learning_rate": 0.00022574719201073765,
"loss": 4.6733,
"step": 9120
},
{
"epoch": 4.099281221922731,
"grad_norm": 3.34375,
"learning_rate": 0.00022565370109214,
"loss": 4.6833,
"step": 9125
},
{
"epoch": 4.101527403414196,
"grad_norm": 3.578125,
"learning_rate": 0.00022556017371341703,
"loss": 4.6202,
"step": 9130
},
{
"epoch": 4.10377358490566,
"grad_norm": 3.265625,
"learning_rate": 0.0002254666099307899,
"loss": 4.7795,
"step": 9135
},
{
"epoch": 4.106019766397125,
"grad_norm": 3.3125,
"learning_rate": 0.00022537300980050157,
"loss": 4.6459,
"step": 9140
},
{
"epoch": 4.108265947888589,
"grad_norm": 3.265625,
"learning_rate": 0.00022527937337881698,
"loss": 4.7103,
"step": 9145
},
{
"epoch": 4.110512129380054,
"grad_norm": 3.25,
"learning_rate": 0.0002251857007220228,
"loss": 4.6682,
"step": 9150
},
{
"epoch": 4.112758310871518,
"grad_norm": 3.34375,
"learning_rate": 0.00022509199188642747,
"loss": 4.7415,
"step": 9155
},
{
"epoch": 4.115004492362983,
"grad_norm": 3.140625,
"learning_rate": 0.00022499824692836124,
"loss": 4.688,
"step": 9160
},
{
"epoch": 4.117250673854447,
"grad_norm": 3.28125,
"learning_rate": 0.00022490446590417594,
"loss": 4.654,
"step": 9165
},
{
"epoch": 4.119496855345912,
"grad_norm": 3.265625,
"learning_rate": 0.0002248106488702453,
"loss": 4.7146,
"step": 9170
},
{
"epoch": 4.121743036837376,
"grad_norm": 3.296875,
"learning_rate": 0.00022471679588296456,
"loss": 4.6695,
"step": 9175
},
{
"epoch": 4.123989218328841,
"grad_norm": 3.234375,
"learning_rate": 0.00022462290699875044,
"loss": 4.712,
"step": 9180
},
{
"epoch": 4.126235399820305,
"grad_norm": 3.140625,
"learning_rate": 0.00022452898227404158,
"loss": 4.6607,
"step": 9185
},
{
"epoch": 4.12848158131177,
"grad_norm": 3.46875,
"learning_rate": 0.00022443502176529783,
"loss": 4.5974,
"step": 9190
},
{
"epoch": 4.130727762803234,
"grad_norm": 3.3125,
"learning_rate": 0.00022434102552900073,
"loss": 4.6807,
"step": 9195
},
{
"epoch": 4.132973944294699,
"grad_norm": 3.421875,
"learning_rate": 0.0002242469936216533,
"loss": 4.63,
"step": 9200
},
{
"epoch": 4.135220125786163,
"grad_norm": 3.3125,
"learning_rate": 0.00022415292609977988,
"loss": 4.6643,
"step": 9205
},
{
"epoch": 4.137466307277628,
"grad_norm": 3.375,
"learning_rate": 0.00022405882301992637,
"loss": 4.6353,
"step": 9210
},
{
"epoch": 4.139712488769092,
"grad_norm": 3.265625,
"learning_rate": 0.00022396468443865994,
"loss": 4.6658,
"step": 9215
},
{
"epoch": 4.141958670260557,
"grad_norm": 3.28125,
"learning_rate": 0.00022387051041256907,
"loss": 4.6706,
"step": 9220
},
{
"epoch": 4.144204851752021,
"grad_norm": 3.125,
"learning_rate": 0.00022377630099826366,
"loss": 4.7247,
"step": 9225
},
{
"epoch": 4.146451033243486,
"grad_norm": 3.1875,
"learning_rate": 0.0002236820562523749,
"loss": 4.6981,
"step": 9230
},
{
"epoch": 4.148697214734951,
"grad_norm": 3.3125,
"learning_rate": 0.00022358777623155505,
"loss": 4.6588,
"step": 9235
},
{
"epoch": 4.150943396226415,
"grad_norm": 3.15625,
"learning_rate": 0.00022349346099247768,
"loss": 4.7104,
"step": 9240
},
{
"epoch": 4.15318957771788,
"grad_norm": 3.34375,
"learning_rate": 0.00022339911059183763,
"loss": 4.6564,
"step": 9245
},
{
"epoch": 4.155435759209344,
"grad_norm": 3.34375,
"learning_rate": 0.00022330472508635062,
"loss": 4.6547,
"step": 9250
},
{
"epoch": 4.157681940700809,
"grad_norm": 3.359375,
"learning_rate": 0.0002232103045327537,
"loss": 4.7364,
"step": 9255
},
{
"epoch": 4.159928122192273,
"grad_norm": 3.25,
"learning_rate": 0.00022311584898780494,
"loss": 4.6378,
"step": 9260
},
{
"epoch": 4.162174303683738,
"grad_norm": 3.25,
"learning_rate": 0.00022302135850828337,
"loss": 4.6988,
"step": 9265
},
{
"epoch": 4.164420485175202,
"grad_norm": 3.25,
"learning_rate": 0.00022292683315098904,
"loss": 4.6526,
"step": 9270
},
{
"epoch": 4.166666666666667,
"grad_norm": 3.484375,
"learning_rate": 0.00022283227297274305,
"loss": 4.6805,
"step": 9275
},
{
"epoch": 4.168912848158131,
"grad_norm": 3.703125,
"learning_rate": 0.00022273767803038727,
"loss": 4.6883,
"step": 9280
},
{
"epoch": 4.171159029649596,
"grad_norm": 3.390625,
"learning_rate": 0.00022264304838078475,
"loss": 4.6406,
"step": 9285
},
{
"epoch": 4.17340521114106,
"grad_norm": 3.28125,
"learning_rate": 0.00022254838408081908,
"loss": 4.7056,
"step": 9290
},
{
"epoch": 4.175651392632525,
"grad_norm": 3.515625,
"learning_rate": 0.0002224536851873948,
"loss": 4.7173,
"step": 9295
},
{
"epoch": 4.177897574123989,
"grad_norm": 3.234375,
"learning_rate": 0.00022235895175743743,
"loss": 4.6716,
"step": 9300
},
{
"epoch": 4.180143755615454,
"grad_norm": 3.53125,
"learning_rate": 0.00022226418384789284,
"loss": 4.6478,
"step": 9305
},
{
"epoch": 4.182389937106918,
"grad_norm": 3.34375,
"learning_rate": 0.00022216938151572814,
"loss": 4.6902,
"step": 9310
},
{
"epoch": 4.184636118598383,
"grad_norm": 3.46875,
"learning_rate": 0.00022207454481793063,
"loss": 4.694,
"step": 9315
},
{
"epoch": 4.186882300089847,
"grad_norm": 3.21875,
"learning_rate": 0.00022197967381150867,
"loss": 4.6173,
"step": 9320
},
{
"epoch": 4.189128481581312,
"grad_norm": 3.28125,
"learning_rate": 0.00022188476855349102,
"loss": 4.6479,
"step": 9325
},
{
"epoch": 4.191374663072776,
"grad_norm": 3.53125,
"learning_rate": 0.0002217898291009271,
"loss": 4.7526,
"step": 9330
},
{
"epoch": 4.193620844564241,
"grad_norm": 3.40625,
"learning_rate": 0.00022169485551088678,
"loss": 4.6498,
"step": 9335
},
{
"epoch": 4.195867026055705,
"grad_norm": 3.640625,
"learning_rate": 0.00022159984784046063,
"loss": 4.6994,
"step": 9340
},
{
"epoch": 4.19811320754717,
"grad_norm": 3.46875,
"learning_rate": 0.00022150480614675962,
"loss": 4.674,
"step": 9345
},
{
"epoch": 4.200359389038634,
"grad_norm": 3.375,
"learning_rate": 0.00022140973048691512,
"loss": 4.6204,
"step": 9350
},
{
"epoch": 4.202605570530099,
"grad_norm": 3.203125,
"learning_rate": 0.00022131462091807904,
"loss": 4.6888,
"step": 9355
},
{
"epoch": 4.204851752021563,
"grad_norm": 3.328125,
"learning_rate": 0.00022121947749742353,
"loss": 4.7396,
"step": 9360
},
{
"epoch": 4.207097933513028,
"grad_norm": 3.25,
"learning_rate": 0.0002211243002821412,
"loss": 4.7202,
"step": 9365
},
{
"epoch": 4.209344115004493,
"grad_norm": 3.421875,
"learning_rate": 0.00022102908932944488,
"loss": 4.6249,
"step": 9370
},
{
"epoch": 4.211590296495957,
"grad_norm": 3.140625,
"learning_rate": 0.00022093384469656785,
"loss": 4.6602,
"step": 9375
},
{
"epoch": 4.213836477987422,
"grad_norm": 3.234375,
"learning_rate": 0.00022083856644076338,
"loss": 4.6307,
"step": 9380
},
{
"epoch": 4.216082659478886,
"grad_norm": 3.40625,
"learning_rate": 0.00022074325461930524,
"loss": 4.678,
"step": 9385
},
{
"epoch": 4.218328840970351,
"grad_norm": 3.0625,
"learning_rate": 0.00022064790928948708,
"loss": 4.6617,
"step": 9390
},
{
"epoch": 4.220575022461815,
"grad_norm": 3.0625,
"learning_rate": 0.00022055253050862295,
"loss": 4.6534,
"step": 9395
},
{
"epoch": 4.22282120395328,
"grad_norm": 3.265625,
"learning_rate": 0.00022045711833404682,
"loss": 4.6576,
"step": 9400
},
{
"epoch": 4.225067385444744,
"grad_norm": 3.328125,
"learning_rate": 0.0002203616728231129,
"loss": 4.683,
"step": 9405
},
{
"epoch": 4.227313566936209,
"grad_norm": 3.25,
"learning_rate": 0.0002202661940331953,
"loss": 4.7134,
"step": 9410
},
{
"epoch": 4.229559748427673,
"grad_norm": 3.5,
"learning_rate": 0.00022017068202168818,
"loss": 4.6617,
"step": 9415
},
{
"epoch": 4.231805929919138,
"grad_norm": 3.34375,
"learning_rate": 0.0002200751368460057,
"loss": 4.6808,
"step": 9420
},
{
"epoch": 4.234052111410602,
"grad_norm": 3.265625,
"learning_rate": 0.00021997955856358184,
"loss": 4.6932,
"step": 9425
},
{
"epoch": 4.236298292902067,
"grad_norm": 3.25,
"learning_rate": 0.00021988394723187075,
"loss": 4.6907,
"step": 9430
},
{
"epoch": 4.238544474393531,
"grad_norm": 3.359375,
"learning_rate": 0.00021978830290834614,
"loss": 4.7321,
"step": 9435
},
{
"epoch": 4.240790655884996,
"grad_norm": 3.453125,
"learning_rate": 0.0002196926256505017,
"loss": 4.714,
"step": 9440
},
{
"epoch": 4.24303683737646,
"grad_norm": 3.28125,
"learning_rate": 0.00021959691551585097,
"loss": 4.7027,
"step": 9445
},
{
"epoch": 4.245283018867925,
"grad_norm": 3.578125,
"learning_rate": 0.0002195011725619271,
"loss": 4.5976,
"step": 9450
},
{
"epoch": 4.247529200359389,
"grad_norm": 3.234375,
"learning_rate": 0.00021940539684628307,
"loss": 4.629,
"step": 9455
},
{
"epoch": 4.249775381850854,
"grad_norm": 3.546875,
"learning_rate": 0.00021930958842649156,
"loss": 4.6977,
"step": 9460
},
{
"epoch": 4.252021563342318,
"grad_norm": 3.25,
"learning_rate": 0.00021921374736014488,
"loss": 4.6177,
"step": 9465
},
{
"epoch": 4.254267744833783,
"grad_norm": 3.359375,
"learning_rate": 0.00021911787370485497,
"loss": 4.7463,
"step": 9470
},
{
"epoch": 4.256513926325247,
"grad_norm": 4.34375,
"learning_rate": 0.00021902196751825333,
"loss": 4.6008,
"step": 9475
},
{
"epoch": 4.258760107816712,
"grad_norm": 3.46875,
"learning_rate": 0.0002189260288579911,
"loss": 4.6715,
"step": 9480
},
{
"epoch": 4.261006289308176,
"grad_norm": 3.109375,
"learning_rate": 0.00021883005778173878,
"loss": 4.692,
"step": 9485
},
{
"epoch": 4.263252470799641,
"grad_norm": 3.265625,
"learning_rate": 0.00021873405434718655,
"loss": 4.7109,
"step": 9490
},
{
"epoch": 4.265498652291106,
"grad_norm": 3.234375,
"learning_rate": 0.00021863801861204393,
"loss": 4.7958,
"step": 9495
},
{
"epoch": 4.26774483378257,
"grad_norm": 3.484375,
"learning_rate": 0.00021854195063403988,
"loss": 4.682,
"step": 9500
},
{
"epoch": 4.269991015274034,
"grad_norm": 3.3125,
"learning_rate": 0.00021844585047092274,
"loss": 4.6555,
"step": 9505
},
{
"epoch": 4.272237196765499,
"grad_norm": 3.515625,
"learning_rate": 0.00021834971818046018,
"loss": 4.6723,
"step": 9510
},
{
"epoch": 4.274483378256964,
"grad_norm": 3.53125,
"learning_rate": 0.00021825355382043917,
"loss": 4.688,
"step": 9515
},
{
"epoch": 4.276729559748428,
"grad_norm": 3.25,
"learning_rate": 0.0002181573574486661,
"loss": 4.7326,
"step": 9520
},
{
"epoch": 4.2789757412398925,
"grad_norm": 3.25,
"learning_rate": 0.00021806112912296633,
"loss": 4.6849,
"step": 9525
},
{
"epoch": 4.281221922731357,
"grad_norm": 3.421875,
"learning_rate": 0.00021796486890118474,
"loss": 4.6588,
"step": 9530
},
{
"epoch": 4.2834681042228215,
"grad_norm": 3.40625,
"learning_rate": 0.00021786857684118514,
"loss": 4.7288,
"step": 9535
},
{
"epoch": 4.285714285714286,
"grad_norm": 3.21875,
"learning_rate": 0.00021777225300085055,
"loss": 4.749,
"step": 9540
},
{
"epoch": 4.2879604672057505,
"grad_norm": 3.359375,
"learning_rate": 0.0002176758974380832,
"loss": 4.7648,
"step": 9545
},
{
"epoch": 4.290206648697215,
"grad_norm": 3.59375,
"learning_rate": 0.00021757951021080424,
"loss": 4.7049,
"step": 9550
},
{
"epoch": 4.2924528301886795,
"grad_norm": 3.25,
"learning_rate": 0.00021748309137695394,
"loss": 4.6978,
"step": 9555
},
{
"epoch": 4.294699011680144,
"grad_norm": 3.4375,
"learning_rate": 0.00021738664099449158,
"loss": 4.7332,
"step": 9560
},
{
"epoch": 4.2969451931716085,
"grad_norm": 3.25,
"learning_rate": 0.0002172901591213953,
"loss": 4.6581,
"step": 9565
},
{
"epoch": 4.2991913746630726,
"grad_norm": 3.46875,
"learning_rate": 0.00021719364581566225,
"loss": 4.5986,
"step": 9570
},
{
"epoch": 4.3014375561545375,
"grad_norm": 3.328125,
"learning_rate": 0.00021709710113530851,
"loss": 4.6496,
"step": 9575
},
{
"epoch": 4.3036837376460015,
"grad_norm": 3.296875,
"learning_rate": 0.00021700052513836892,
"loss": 4.599,
"step": 9580
},
{
"epoch": 4.3059299191374665,
"grad_norm": 3.59375,
"learning_rate": 0.00021690391788289725,
"loss": 4.6833,
"step": 9585
},
{
"epoch": 4.3081761006289305,
"grad_norm": 3.4375,
"learning_rate": 0.00021680727942696595,
"loss": 4.6969,
"step": 9590
},
{
"epoch": 4.3104222821203955,
"grad_norm": 3.515625,
"learning_rate": 0.00021671060982866638,
"loss": 4.6736,
"step": 9595
},
{
"epoch": 4.3126684636118595,
"grad_norm": 3.140625,
"learning_rate": 0.00021661390914610846,
"loss": 4.7603,
"step": 9600
},
{
"epoch": 4.3149146451033245,
"grad_norm": 3.28125,
"learning_rate": 0.00021651717743742082,
"loss": 4.6373,
"step": 9605
},
{
"epoch": 4.3171608265947885,
"grad_norm": 3.40625,
"learning_rate": 0.00021642041476075088,
"loss": 4.6946,
"step": 9610
},
{
"epoch": 4.319407008086253,
"grad_norm": 3.546875,
"learning_rate": 0.0002163236211742645,
"loss": 4.6837,
"step": 9615
},
{
"epoch": 4.3216531895777175,
"grad_norm": 3.25,
"learning_rate": 0.00021622679673614621,
"loss": 4.7555,
"step": 9620
},
{
"epoch": 4.323899371069182,
"grad_norm": 3.3125,
"learning_rate": 0.0002161299415045991,
"loss": 4.7089,
"step": 9625
},
{
"epoch": 4.3261455525606465,
"grad_norm": 3.40625,
"learning_rate": 0.00021603305553784472,
"loss": 4.7033,
"step": 9630
},
{
"epoch": 4.328391734052111,
"grad_norm": 3.171875,
"learning_rate": 0.00021593613889412313,
"loss": 4.6401,
"step": 9635
},
{
"epoch": 4.330637915543576,
"grad_norm": 3.4375,
"learning_rate": 0.00021583919163169286,
"loss": 4.6932,
"step": 9640
},
{
"epoch": 4.33288409703504,
"grad_norm": 3.25,
"learning_rate": 0.00021574221380883072,
"loss": 4.6643,
"step": 9645
},
{
"epoch": 4.335130278526505,
"grad_norm": 3.484375,
"learning_rate": 0.000215645205483832,
"loss": 4.685,
"step": 9650
},
{
"epoch": 4.337376460017969,
"grad_norm": 3.4375,
"learning_rate": 0.00021554816671501034,
"loss": 4.6756,
"step": 9655
},
{
"epoch": 4.339622641509434,
"grad_norm": 3.5,
"learning_rate": 0.0002154510975606976,
"loss": 4.6344,
"step": 9660
},
{
"epoch": 4.341868823000898,
"grad_norm": 3.296875,
"learning_rate": 0.00021535399807924398,
"loss": 4.6881,
"step": 9665
},
{
"epoch": 4.344115004492363,
"grad_norm": 3.390625,
"learning_rate": 0.0002152568683290178,
"loss": 4.6898,
"step": 9670
},
{
"epoch": 4.346361185983827,
"grad_norm": 3.109375,
"learning_rate": 0.0002151597083684058,
"loss": 4.7361,
"step": 9675
},
{
"epoch": 4.348607367475292,
"grad_norm": 3.359375,
"learning_rate": 0.00021506251825581255,
"loss": 4.6747,
"step": 9680
},
{
"epoch": 4.350853548966756,
"grad_norm": 3.34375,
"learning_rate": 0.00021496529804966103,
"loss": 4.7717,
"step": 9685
},
{
"epoch": 4.353099730458221,
"grad_norm": 3.203125,
"learning_rate": 0.00021486804780839226,
"loss": 4.6896,
"step": 9690
},
{
"epoch": 4.355345911949685,
"grad_norm": 3.78125,
"learning_rate": 0.00021477076759046513,
"loss": 4.621,
"step": 9695
},
{
"epoch": 4.35759209344115,
"grad_norm": 3.5,
"learning_rate": 0.00021467345745435678,
"loss": 4.7051,
"step": 9700
},
{
"epoch": 4.359838274932614,
"grad_norm": 3.203125,
"learning_rate": 0.0002145761174585622,
"loss": 4.6858,
"step": 9705
},
{
"epoch": 4.362084456424079,
"grad_norm": 3.515625,
"learning_rate": 0.00021447874766159433,
"loss": 4.7533,
"step": 9710
},
{
"epoch": 4.364330637915543,
"grad_norm": 3.265625,
"learning_rate": 0.00021438134812198415,
"loss": 4.7265,
"step": 9715
},
{
"epoch": 4.366576819407008,
"grad_norm": 3.265625,
"learning_rate": 0.00021428391889828034,
"loss": 4.6811,
"step": 9720
},
{
"epoch": 4.368823000898472,
"grad_norm": 3.453125,
"learning_rate": 0.00021418646004904953,
"loss": 4.6191,
"step": 9725
},
{
"epoch": 4.371069182389937,
"grad_norm": 3.640625,
"learning_rate": 0.00021408897163287615,
"loss": 4.7698,
"step": 9730
},
{
"epoch": 4.373315363881401,
"grad_norm": 3.296875,
"learning_rate": 0.00021399145370836238,
"loss": 4.7045,
"step": 9735
},
{
"epoch": 4.375561545372866,
"grad_norm": 3.203125,
"learning_rate": 0.0002138939063341282,
"loss": 4.6745,
"step": 9740
},
{
"epoch": 4.37780772686433,
"grad_norm": 3.5,
"learning_rate": 0.00021379632956881116,
"loss": 4.6972,
"step": 9745
},
{
"epoch": 4.380053908355795,
"grad_norm": 3.296875,
"learning_rate": 0.00021369872347106662,
"loss": 4.6778,
"step": 9750
},
{
"epoch": 4.382300089847259,
"grad_norm": 3.578125,
"learning_rate": 0.00021360108809956752,
"loss": 4.7863,
"step": 9755
},
{
"epoch": 4.384546271338724,
"grad_norm": 3.171875,
"learning_rate": 0.00021350342351300438,
"loss": 4.6412,
"step": 9760
},
{
"epoch": 4.386792452830189,
"grad_norm": 3.296875,
"learning_rate": 0.00021340572977008524,
"loss": 4.6175,
"step": 9765
},
{
"epoch": 4.389038634321653,
"grad_norm": 3.09375,
"learning_rate": 0.0002133080069295358,
"loss": 4.7325,
"step": 9770
},
{
"epoch": 4.391284815813117,
"grad_norm": 3.296875,
"learning_rate": 0.0002132102550500991,
"loss": 4.6518,
"step": 9775
},
{
"epoch": 4.393530997304582,
"grad_norm": 3.328125,
"learning_rate": 0.00021311247419053574,
"loss": 4.701,
"step": 9780
},
{
"epoch": 4.395777178796047,
"grad_norm": 3.21875,
"learning_rate": 0.0002130146644096237,
"loss": 4.6722,
"step": 9785
},
{
"epoch": 4.398023360287511,
"grad_norm": 3.40625,
"learning_rate": 0.00021291682576615837,
"loss": 4.6529,
"step": 9790
},
{
"epoch": 4.400269541778976,
"grad_norm": 3.25,
"learning_rate": 0.00021281895831895247,
"loss": 4.6846,
"step": 9795
},
{
"epoch": 4.40251572327044,
"grad_norm": 3.34375,
"learning_rate": 0.00021272106212683598,
"loss": 4.674,
"step": 9800
},
{
"epoch": 4.404761904761905,
"grad_norm": 3.34375,
"learning_rate": 0.00021262313724865626,
"loss": 4.6378,
"step": 9805
},
{
"epoch": 4.407008086253369,
"grad_norm": 3.34375,
"learning_rate": 0.0002125251837432779,
"loss": 4.7018,
"step": 9810
},
{
"epoch": 4.409254267744834,
"grad_norm": 3.265625,
"learning_rate": 0.00021242720166958257,
"loss": 4.68,
"step": 9815
},
{
"epoch": 4.411500449236298,
"grad_norm": 3.515625,
"learning_rate": 0.00021232919108646933,
"loss": 4.6918,
"step": 9820
},
{
"epoch": 4.413746630727763,
"grad_norm": 3.75,
"learning_rate": 0.00021223115205285418,
"loss": 4.6849,
"step": 9825
},
{
"epoch": 4.415992812219227,
"grad_norm": 3.25,
"learning_rate": 0.00021213308462767025,
"loss": 4.6931,
"step": 9830
},
{
"epoch": 4.418238993710692,
"grad_norm": 3.453125,
"learning_rate": 0.00021203498886986793,
"loss": 4.6482,
"step": 9835
},
{
"epoch": 4.420485175202156,
"grad_norm": 3.34375,
"learning_rate": 0.00021193686483841437,
"loss": 4.6818,
"step": 9840
},
{
"epoch": 4.422731356693621,
"grad_norm": 3.1875,
"learning_rate": 0.00021183871259229393,
"loss": 4.6446,
"step": 9845
},
{
"epoch": 4.424977538185085,
"grad_norm": 3.453125,
"learning_rate": 0.00021174053219050778,
"loss": 4.6766,
"step": 9850
},
{
"epoch": 4.42722371967655,
"grad_norm": 3.3125,
"learning_rate": 0.0002116423236920741,
"loss": 4.6678,
"step": 9855
},
{
"epoch": 4.429469901168014,
"grad_norm": 3.390625,
"learning_rate": 0.00021154408715602795,
"loss": 4.7295,
"step": 9860
},
{
"epoch": 4.431716082659479,
"grad_norm": 3.171875,
"learning_rate": 0.00021144582264142123,
"loss": 4.7037,
"step": 9865
},
{
"epoch": 4.433962264150943,
"grad_norm": 3.4375,
"learning_rate": 0.00021134753020732265,
"loss": 4.6139,
"step": 9870
},
{
"epoch": 4.436208445642408,
"grad_norm": 3.5625,
"learning_rate": 0.00021124920991281778,
"loss": 4.6233,
"step": 9875
},
{
"epoch": 4.438454627133872,
"grad_norm": 3.359375,
"learning_rate": 0.00021115086181700877,
"loss": 4.6462,
"step": 9880
},
{
"epoch": 4.440700808625337,
"grad_norm": 3.234375,
"learning_rate": 0.00021105248597901456,
"loss": 4.692,
"step": 9885
},
{
"epoch": 4.442946990116801,
"grad_norm": 4.03125,
"learning_rate": 0.00021095408245797094,
"loss": 4.7333,
"step": 9890
},
{
"epoch": 4.445193171608266,
"grad_norm": 3.390625,
"learning_rate": 0.00021085565131303004,
"loss": 4.7001,
"step": 9895
},
{
"epoch": 4.44743935309973,
"grad_norm": 3.515625,
"learning_rate": 0.00021075719260336086,
"loss": 4.6733,
"step": 9900
},
{
"epoch": 4.449685534591195,
"grad_norm": 3.375,
"learning_rate": 0.00021065870638814875,
"loss": 4.6761,
"step": 9905
},
{
"epoch": 4.45193171608266,
"grad_norm": 3.65625,
"learning_rate": 0.0002105601927265958,
"loss": 4.7403,
"step": 9910
},
{
"epoch": 4.454177897574124,
"grad_norm": 3.390625,
"learning_rate": 0.0002104616516779204,
"loss": 4.6371,
"step": 9915
},
{
"epoch": 4.456424079065589,
"grad_norm": 3.296875,
"learning_rate": 0.00021036308330135752,
"loss": 4.6903,
"step": 9920
},
{
"epoch": 4.458670260557053,
"grad_norm": 3.078125,
"learning_rate": 0.00021026448765615866,
"loss": 4.6965,
"step": 9925
},
{
"epoch": 4.460916442048518,
"grad_norm": 3.375,
"learning_rate": 0.00021016586480159145,
"loss": 4.7419,
"step": 9930
},
{
"epoch": 4.463162623539982,
"grad_norm": 3.46875,
"learning_rate": 0.0002100672147969401,
"loss": 4.7129,
"step": 9935
},
{
"epoch": 4.465408805031447,
"grad_norm": 3.3125,
"learning_rate": 0.00020996853770150495,
"loss": 4.6758,
"step": 9940
},
{
"epoch": 4.467654986522911,
"grad_norm": 3.171875,
"learning_rate": 0.00020986983357460282,
"loss": 4.6629,
"step": 9945
},
{
"epoch": 4.469901168014376,
"grad_norm": 3.3125,
"learning_rate": 0.00020977110247556667,
"loss": 4.7698,
"step": 9950
},
{
"epoch": 4.47214734950584,
"grad_norm": 3.21875,
"learning_rate": 0.00020967234446374572,
"loss": 4.7114,
"step": 9955
},
{
"epoch": 4.474393530997305,
"grad_norm": 3.453125,
"learning_rate": 0.0002095735595985053,
"loss": 4.7192,
"step": 9960
},
{
"epoch": 4.476639712488769,
"grad_norm": 3.296875,
"learning_rate": 0.00020947474793922699,
"loss": 4.7341,
"step": 9965
},
{
"epoch": 4.478885893980234,
"grad_norm": 3.453125,
"learning_rate": 0.00020937590954530827,
"loss": 4.6937,
"step": 9970
},
{
"epoch": 4.481132075471698,
"grad_norm": 3.515625,
"learning_rate": 0.00020927704447616291,
"loss": 4.6864,
"step": 9975
},
{
"epoch": 4.483378256963163,
"grad_norm": 3.6875,
"learning_rate": 0.0002091781527912207,
"loss": 4.7076,
"step": 9980
},
{
"epoch": 4.485624438454627,
"grad_norm": 3.375,
"learning_rate": 0.00020907923454992729,
"loss": 4.6991,
"step": 9985
},
{
"epoch": 4.487870619946092,
"grad_norm": 3.1875,
"learning_rate": 0.0002089802898117444,
"loss": 4.64,
"step": 9990
},
{
"epoch": 4.490116801437556,
"grad_norm": 3.265625,
"learning_rate": 0.0002088813186361496,
"loss": 4.656,
"step": 9995
},
{
"epoch": 4.492362982929021,
"grad_norm": 3.578125,
"learning_rate": 0.00020878232108263647,
"loss": 4.7397,
"step": 10000
},
{
"epoch": 4.492362982929021,
"eval_loss": 4.845594882965088,
"eval_runtime": 16.0517,
"eval_samples_per_second": 1932.072,
"eval_steps_per_second": 241.532,
"step": 10000
}
],
"logging_steps": 5,
"max_steps": 22260,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.71597460168448e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}