CocoRoF's picture
Training in progress, step 9521, checkpoint
b32154b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9999491282051282,
"eval_steps": 2500,
"global_step": 9521,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010502564102564103,
"grad_norm": 83.8125,
"learning_rate": 9.999979487179486e-07,
"loss": 137.2689,
"step": 10
},
{
"epoch": 0.0021005128205128206,
"grad_norm": 73.875,
"learning_rate": 9.999958974358973e-07,
"loss": 137.7469,
"step": 20
},
{
"epoch": 0.003150769230769231,
"grad_norm": 76.0,
"learning_rate": 9.99993846153846e-07,
"loss": 138.4526,
"step": 30
},
{
"epoch": 0.004201025641025641,
"grad_norm": 85.9375,
"learning_rate": 9.99991794871795e-07,
"loss": 138.0835,
"step": 40
},
{
"epoch": 0.005251282051282051,
"grad_norm": 76.8125,
"learning_rate": 9.999897435897434e-07,
"loss": 137.577,
"step": 50
},
{
"epoch": 0.006301538461538462,
"grad_norm": 81.75,
"learning_rate": 9.999876923076923e-07,
"loss": 136.94,
"step": 60
},
{
"epoch": 0.007351794871794872,
"grad_norm": 72.75,
"learning_rate": 9.99985641025641e-07,
"loss": 136.7488,
"step": 70
},
{
"epoch": 0.008402051282051282,
"grad_norm": 76.0,
"learning_rate": 9.999835897435897e-07,
"loss": 136.7595,
"step": 80
},
{
"epoch": 0.009452307692307692,
"grad_norm": 76.625,
"learning_rate": 9.999815384615384e-07,
"loss": 136.5558,
"step": 90
},
{
"epoch": 0.010502564102564102,
"grad_norm": 75.3125,
"learning_rate": 9.99979487179487e-07,
"loss": 136.2622,
"step": 100
},
{
"epoch": 0.011552820512820514,
"grad_norm": 70.5625,
"learning_rate": 9.999774358974358e-07,
"loss": 137.3947,
"step": 110
},
{
"epoch": 0.012603076923076923,
"grad_norm": 75.375,
"learning_rate": 9.999753846153845e-07,
"loss": 136.5051,
"step": 120
},
{
"epoch": 0.013653333333333333,
"grad_norm": 73.1875,
"learning_rate": 9.999733333333334e-07,
"loss": 137.4362,
"step": 130
},
{
"epoch": 0.014703589743589743,
"grad_norm": 72.75,
"learning_rate": 9.99971282051282e-07,
"loss": 137.3079,
"step": 140
},
{
"epoch": 0.015753846153846153,
"grad_norm": 80.25,
"learning_rate": 9.999692307692306e-07,
"loss": 136.6685,
"step": 150
},
{
"epoch": 0.016804102564102565,
"grad_norm": 72.3125,
"learning_rate": 9.999671794871795e-07,
"loss": 135.9851,
"step": 160
},
{
"epoch": 0.017854358974358973,
"grad_norm": 77.1875,
"learning_rate": 9.999651282051282e-07,
"loss": 135.917,
"step": 170
},
{
"epoch": 0.018904615384615384,
"grad_norm": 88.3125,
"learning_rate": 9.999630769230769e-07,
"loss": 138.2422,
"step": 180
},
{
"epoch": 0.019954871794871796,
"grad_norm": 73.25,
"learning_rate": 9.999610256410256e-07,
"loss": 137.2377,
"step": 190
},
{
"epoch": 0.021005128205128204,
"grad_norm": 72.5,
"learning_rate": 9.999589743589743e-07,
"loss": 135.6885,
"step": 200
},
{
"epoch": 0.022055384615384616,
"grad_norm": 74.25,
"learning_rate": 9.99956923076923e-07,
"loss": 136.6409,
"step": 210
},
{
"epoch": 0.023105641025641027,
"grad_norm": 73.625,
"learning_rate": 9.999548717948716e-07,
"loss": 136.0549,
"step": 220
},
{
"epoch": 0.024155897435897435,
"grad_norm": 73.5,
"learning_rate": 9.999528205128205e-07,
"loss": 137.4658,
"step": 230
},
{
"epoch": 0.025206153846153847,
"grad_norm": 80.6875,
"learning_rate": 9.999507692307692e-07,
"loss": 136.3624,
"step": 240
},
{
"epoch": 0.026256410256410255,
"grad_norm": 76.4375,
"learning_rate": 9.99948717948718e-07,
"loss": 136.9343,
"step": 250
},
{
"epoch": 0.027306666666666667,
"grad_norm": 85.25,
"learning_rate": 9.999466666666666e-07,
"loss": 137.7632,
"step": 260
},
{
"epoch": 0.028356923076923078,
"grad_norm": 75.375,
"learning_rate": 9.999446153846153e-07,
"loss": 137.4173,
"step": 270
},
{
"epoch": 0.029407179487179486,
"grad_norm": 77.0,
"learning_rate": 9.99942564102564e-07,
"loss": 136.4367,
"step": 280
},
{
"epoch": 0.030457435897435898,
"grad_norm": 78.75,
"learning_rate": 9.999405128205127e-07,
"loss": 136.3395,
"step": 290
},
{
"epoch": 0.031507692307692306,
"grad_norm": 75.3125,
"learning_rate": 9.999384615384614e-07,
"loss": 136.1427,
"step": 300
},
{
"epoch": 0.03255794871794872,
"grad_norm": 75.5625,
"learning_rate": 9.9993641025641e-07,
"loss": 135.8248,
"step": 310
},
{
"epoch": 0.03360820512820513,
"grad_norm": 76.6875,
"learning_rate": 9.99934358974359e-07,
"loss": 136.6485,
"step": 320
},
{
"epoch": 0.03465846153846154,
"grad_norm": 74.25,
"learning_rate": 9.999323076923077e-07,
"loss": 137.1976,
"step": 330
},
{
"epoch": 0.035708717948717945,
"grad_norm": 76.0625,
"learning_rate": 9.999302564102564e-07,
"loss": 135.8058,
"step": 340
},
{
"epoch": 0.03675897435897436,
"grad_norm": 81.625,
"learning_rate": 9.99928205128205e-07,
"loss": 136.5466,
"step": 350
},
{
"epoch": 0.03780923076923077,
"grad_norm": 76.125,
"learning_rate": 9.999261538461538e-07,
"loss": 135.6967,
"step": 360
},
{
"epoch": 0.03885948717948718,
"grad_norm": 75.0625,
"learning_rate": 9.999241025641025e-07,
"loss": 136.8226,
"step": 370
},
{
"epoch": 0.03990974358974359,
"grad_norm": 78.0,
"learning_rate": 9.999220512820512e-07,
"loss": 136.4603,
"step": 380
},
{
"epoch": 0.04096,
"grad_norm": 74.375,
"learning_rate": 9.9992e-07,
"loss": 136.3817,
"step": 390
},
{
"epoch": 0.04201025641025641,
"grad_norm": 74.9375,
"learning_rate": 9.999179487179486e-07,
"loss": 135.7093,
"step": 400
},
{
"epoch": 0.04306051282051282,
"grad_norm": 75.1875,
"learning_rate": 9.999158974358975e-07,
"loss": 137.9199,
"step": 410
},
{
"epoch": 0.04411076923076923,
"grad_norm": 74.4375,
"learning_rate": 9.999138461538462e-07,
"loss": 137.6895,
"step": 420
},
{
"epoch": 0.04516102564102564,
"grad_norm": 76.375,
"learning_rate": 9.999117948717949e-07,
"loss": 137.1656,
"step": 430
},
{
"epoch": 0.046211282051282054,
"grad_norm": 78.8125,
"learning_rate": 9.999097435897435e-07,
"loss": 136.766,
"step": 440
},
{
"epoch": 0.04726153846153846,
"grad_norm": 77.8125,
"learning_rate": 9.999076923076922e-07,
"loss": 136.1063,
"step": 450
},
{
"epoch": 0.04831179487179487,
"grad_norm": 76.25,
"learning_rate": 9.99905641025641e-07,
"loss": 137.0769,
"step": 460
},
{
"epoch": 0.04936205128205128,
"grad_norm": 75.3125,
"learning_rate": 9.999035897435896e-07,
"loss": 136.7605,
"step": 470
},
{
"epoch": 0.050412307692307694,
"grad_norm": 71.625,
"learning_rate": 9.999015384615385e-07,
"loss": 136.8585,
"step": 480
},
{
"epoch": 0.051462564102564105,
"grad_norm": 81.5625,
"learning_rate": 9.998994871794872e-07,
"loss": 136.7847,
"step": 490
},
{
"epoch": 0.05251282051282051,
"grad_norm": 78.5,
"learning_rate": 9.998974358974357e-07,
"loss": 135.8417,
"step": 500
},
{
"epoch": 0.05356307692307692,
"grad_norm": 79.0625,
"learning_rate": 9.998953846153846e-07,
"loss": 136.4017,
"step": 510
},
{
"epoch": 0.05461333333333333,
"grad_norm": 73.0,
"learning_rate": 9.998933333333333e-07,
"loss": 138.0991,
"step": 520
},
{
"epoch": 0.055663589743589745,
"grad_norm": 72.5,
"learning_rate": 9.99891282051282e-07,
"loss": 137.349,
"step": 530
},
{
"epoch": 0.056713846153846156,
"grad_norm": 74.0625,
"learning_rate": 9.998892307692307e-07,
"loss": 136.6539,
"step": 540
},
{
"epoch": 0.05776410256410256,
"grad_norm": 80.375,
"learning_rate": 9.998871794871794e-07,
"loss": 135.9581,
"step": 550
},
{
"epoch": 0.05881435897435897,
"grad_norm": 76.1875,
"learning_rate": 9.99885128205128e-07,
"loss": 137.2837,
"step": 560
},
{
"epoch": 0.059864615384615384,
"grad_norm": 83.5,
"learning_rate": 9.998830769230768e-07,
"loss": 135.8109,
"step": 570
},
{
"epoch": 0.060914871794871796,
"grad_norm": 81.5,
"learning_rate": 9.998810256410257e-07,
"loss": 136.6003,
"step": 580
},
{
"epoch": 0.06196512820512821,
"grad_norm": 78.1875,
"learning_rate": 9.998789743589744e-07,
"loss": 136.3486,
"step": 590
},
{
"epoch": 0.06301538461538461,
"grad_norm": 74.1875,
"learning_rate": 9.99876923076923e-07,
"loss": 136.5433,
"step": 600
},
{
"epoch": 0.06406564102564102,
"grad_norm": 77.9375,
"learning_rate": 9.998748717948718e-07,
"loss": 137.5628,
"step": 610
},
{
"epoch": 0.06511589743589744,
"grad_norm": 77.5,
"learning_rate": 9.998728205128205e-07,
"loss": 136.4774,
"step": 620
},
{
"epoch": 0.06616615384615385,
"grad_norm": 82.1875,
"learning_rate": 9.998707692307692e-07,
"loss": 136.5914,
"step": 630
},
{
"epoch": 0.06721641025641026,
"grad_norm": 75.75,
"learning_rate": 9.998687179487178e-07,
"loss": 136.7258,
"step": 640
},
{
"epoch": 0.06826666666666667,
"grad_norm": 77.4375,
"learning_rate": 9.998666666666665e-07,
"loss": 137.3747,
"step": 650
},
{
"epoch": 0.06931692307692308,
"grad_norm": 80.6875,
"learning_rate": 9.998646153846152e-07,
"loss": 136.8755,
"step": 660
},
{
"epoch": 0.0703671794871795,
"grad_norm": 77.8125,
"learning_rate": 9.998625641025641e-07,
"loss": 136.6606,
"step": 670
},
{
"epoch": 0.07141743589743589,
"grad_norm": 74.8125,
"learning_rate": 9.998605128205128e-07,
"loss": 136.7844,
"step": 680
},
{
"epoch": 0.0724676923076923,
"grad_norm": 75.5625,
"learning_rate": 9.998584615384615e-07,
"loss": 136.1632,
"step": 690
},
{
"epoch": 0.07351794871794871,
"grad_norm": 70.6875,
"learning_rate": 9.998564102564102e-07,
"loss": 136.7524,
"step": 700
},
{
"epoch": 0.07456820512820513,
"grad_norm": 69.6875,
"learning_rate": 9.99854358974359e-07,
"loss": 136.8704,
"step": 710
},
{
"epoch": 0.07561846153846154,
"grad_norm": 73.25,
"learning_rate": 9.998523076923076e-07,
"loss": 135.607,
"step": 720
},
{
"epoch": 0.07666871794871795,
"grad_norm": 79.0,
"learning_rate": 9.998502564102563e-07,
"loss": 135.7957,
"step": 730
},
{
"epoch": 0.07771897435897436,
"grad_norm": 74.5,
"learning_rate": 9.998482051282052e-07,
"loss": 137.2365,
"step": 740
},
{
"epoch": 0.07876923076923077,
"grad_norm": 72.25,
"learning_rate": 9.998461538461537e-07,
"loss": 136.9944,
"step": 750
},
{
"epoch": 0.07981948717948718,
"grad_norm": 80.0625,
"learning_rate": 9.998441025641026e-07,
"loss": 138.0186,
"step": 760
},
{
"epoch": 0.0808697435897436,
"grad_norm": 73.125,
"learning_rate": 9.998420512820513e-07,
"loss": 136.6754,
"step": 770
},
{
"epoch": 0.08192,
"grad_norm": 79.0,
"learning_rate": 9.9984e-07,
"loss": 136.0845,
"step": 780
},
{
"epoch": 0.0829702564102564,
"grad_norm": 77.4375,
"learning_rate": 9.998379487179487e-07,
"loss": 135.9881,
"step": 790
},
{
"epoch": 0.08402051282051282,
"grad_norm": 81.8125,
"learning_rate": 9.998358974358974e-07,
"loss": 137.3697,
"step": 800
},
{
"epoch": 0.08507076923076923,
"grad_norm": 77.375,
"learning_rate": 9.99833846153846e-07,
"loss": 136.4123,
"step": 810
},
{
"epoch": 0.08612102564102564,
"grad_norm": 76.5625,
"learning_rate": 9.998317948717948e-07,
"loss": 136.5667,
"step": 820
},
{
"epoch": 0.08717128205128205,
"grad_norm": 75.875,
"learning_rate": 9.998297435897437e-07,
"loss": 137.2428,
"step": 830
},
{
"epoch": 0.08822153846153846,
"grad_norm": 80.4375,
"learning_rate": 9.998276923076924e-07,
"loss": 135.8229,
"step": 840
},
{
"epoch": 0.08927179487179487,
"grad_norm": 75.4375,
"learning_rate": 9.998256410256408e-07,
"loss": 135.0417,
"step": 850
},
{
"epoch": 0.09032205128205129,
"grad_norm": 89.0625,
"learning_rate": 9.998235897435897e-07,
"loss": 136.6309,
"step": 860
},
{
"epoch": 0.0913723076923077,
"grad_norm": 74.0,
"learning_rate": 9.998215384615384e-07,
"loss": 136.2141,
"step": 870
},
{
"epoch": 0.09242256410256411,
"grad_norm": 78.875,
"learning_rate": 9.998194871794871e-07,
"loss": 135.1106,
"step": 880
},
{
"epoch": 0.0934728205128205,
"grad_norm": 79.8125,
"learning_rate": 9.998174358974358e-07,
"loss": 136.1402,
"step": 890
},
{
"epoch": 0.09452307692307692,
"grad_norm": 83.1875,
"learning_rate": 9.998153846153845e-07,
"loss": 135.6284,
"step": 900
},
{
"epoch": 0.09557333333333333,
"grad_norm": 78.1875,
"learning_rate": 9.998133333333332e-07,
"loss": 135.9521,
"step": 910
},
{
"epoch": 0.09662358974358974,
"grad_norm": 78.0625,
"learning_rate": 9.99811282051282e-07,
"loss": 136.0459,
"step": 920
},
{
"epoch": 0.09767384615384615,
"grad_norm": 75.1875,
"learning_rate": 9.998092307692308e-07,
"loss": 135.8785,
"step": 930
},
{
"epoch": 0.09872410256410256,
"grad_norm": 75.0,
"learning_rate": 9.998071794871795e-07,
"loss": 135.5974,
"step": 940
},
{
"epoch": 0.09977435897435898,
"grad_norm": 73.5625,
"learning_rate": 9.998051282051282e-07,
"loss": 135.9134,
"step": 950
},
{
"epoch": 0.10082461538461539,
"grad_norm": 83.875,
"learning_rate": 9.99803076923077e-07,
"loss": 136.6835,
"step": 960
},
{
"epoch": 0.1018748717948718,
"grad_norm": 74.9375,
"learning_rate": 9.998010256410256e-07,
"loss": 136.0822,
"step": 970
},
{
"epoch": 0.10292512820512821,
"grad_norm": 78.8125,
"learning_rate": 9.997989743589743e-07,
"loss": 135.76,
"step": 980
},
{
"epoch": 0.10397538461538462,
"grad_norm": 81.5,
"learning_rate": 9.99796923076923e-07,
"loss": 137.3108,
"step": 990
},
{
"epoch": 0.10502564102564102,
"grad_norm": 74.6875,
"learning_rate": 9.997948717948717e-07,
"loss": 136.5909,
"step": 1000
},
{
"epoch": 0.10607589743589743,
"grad_norm": 76.9375,
"learning_rate": 9.997928205128204e-07,
"loss": 136.463,
"step": 1010
},
{
"epoch": 0.10712615384615384,
"grad_norm": 76.5,
"learning_rate": 9.997907692307693e-07,
"loss": 135.7026,
"step": 1020
},
{
"epoch": 0.10817641025641025,
"grad_norm": 78.0,
"learning_rate": 9.99788717948718e-07,
"loss": 136.5197,
"step": 1030
},
{
"epoch": 0.10922666666666667,
"grad_norm": 77.4375,
"learning_rate": 9.997866666666667e-07,
"loss": 135.3555,
"step": 1040
},
{
"epoch": 0.11027692307692308,
"grad_norm": 76.0625,
"learning_rate": 9.997846153846154e-07,
"loss": 135.3746,
"step": 1050
},
{
"epoch": 0.11132717948717949,
"grad_norm": 76.4375,
"learning_rate": 9.99782564102564e-07,
"loss": 136.8601,
"step": 1060
},
{
"epoch": 0.1123774358974359,
"grad_norm": 74.4375,
"learning_rate": 9.997805128205127e-07,
"loss": 137.0016,
"step": 1070
},
{
"epoch": 0.11342769230769231,
"grad_norm": 75.875,
"learning_rate": 9.997784615384614e-07,
"loss": 136.985,
"step": 1080
},
{
"epoch": 0.11447794871794872,
"grad_norm": 75.3125,
"learning_rate": 9.997764102564103e-07,
"loss": 136.9973,
"step": 1090
},
{
"epoch": 0.11552820512820512,
"grad_norm": 74.875,
"learning_rate": 9.997743589743588e-07,
"loss": 137.1771,
"step": 1100
},
{
"epoch": 0.11657846153846153,
"grad_norm": 76.0,
"learning_rate": 9.997723076923077e-07,
"loss": 136.5904,
"step": 1110
},
{
"epoch": 0.11762871794871795,
"grad_norm": 80.0,
"learning_rate": 9.997702564102564e-07,
"loss": 137.0198,
"step": 1120
},
{
"epoch": 0.11867897435897436,
"grad_norm": 78.3125,
"learning_rate": 9.997682051282051e-07,
"loss": 136.515,
"step": 1130
},
{
"epoch": 0.11972923076923077,
"grad_norm": 77.0625,
"learning_rate": 9.997661538461538e-07,
"loss": 136.2788,
"step": 1140
},
{
"epoch": 0.12077948717948718,
"grad_norm": 76.625,
"learning_rate": 9.997641025641025e-07,
"loss": 135.2233,
"step": 1150
},
{
"epoch": 0.12182974358974359,
"grad_norm": 77.5625,
"learning_rate": 9.997620512820512e-07,
"loss": 136.8247,
"step": 1160
},
{
"epoch": 0.12288,
"grad_norm": 79.4375,
"learning_rate": 9.9976e-07,
"loss": 135.9922,
"step": 1170
},
{
"epoch": 0.12393025641025641,
"grad_norm": 74.9375,
"learning_rate": 9.997579487179488e-07,
"loss": 135.9835,
"step": 1180
},
{
"epoch": 0.12498051282051283,
"grad_norm": 78.4375,
"learning_rate": 9.997558974358975e-07,
"loss": 137.149,
"step": 1190
},
{
"epoch": 0.12603076923076922,
"grad_norm": 87.0,
"learning_rate": 9.99753846153846e-07,
"loss": 135.9062,
"step": 1200
},
{
"epoch": 0.12708102564102564,
"grad_norm": 90.75,
"learning_rate": 9.997517948717949e-07,
"loss": 137.0315,
"step": 1210
},
{
"epoch": 0.12813128205128205,
"grad_norm": 74.1875,
"learning_rate": 9.997497435897436e-07,
"loss": 134.5245,
"step": 1220
},
{
"epoch": 0.12918153846153846,
"grad_norm": 77.4375,
"learning_rate": 9.997476923076923e-07,
"loss": 136.1781,
"step": 1230
},
{
"epoch": 0.13023179487179487,
"grad_norm": 76.1875,
"learning_rate": 9.99745641025641e-07,
"loss": 135.0808,
"step": 1240
},
{
"epoch": 0.13128205128205128,
"grad_norm": 88.1875,
"learning_rate": 9.997435897435897e-07,
"loss": 137.6019,
"step": 1250
},
{
"epoch": 0.1323323076923077,
"grad_norm": 77.75,
"learning_rate": 9.997415384615384e-07,
"loss": 136.8665,
"step": 1260
},
{
"epoch": 0.1333825641025641,
"grad_norm": 74.625,
"learning_rate": 9.99739487179487e-07,
"loss": 135.1396,
"step": 1270
},
{
"epoch": 0.13443282051282052,
"grad_norm": 77.125,
"learning_rate": 9.99737435897436e-07,
"loss": 136.1739,
"step": 1280
},
{
"epoch": 0.13548307692307693,
"grad_norm": 86.375,
"learning_rate": 9.997353846153844e-07,
"loss": 135.8782,
"step": 1290
},
{
"epoch": 0.13653333333333334,
"grad_norm": 80.8125,
"learning_rate": 9.997333333333333e-07,
"loss": 135.7326,
"step": 1300
},
{
"epoch": 0.13758358974358975,
"grad_norm": 76.0625,
"learning_rate": 9.99731282051282e-07,
"loss": 135.3882,
"step": 1310
},
{
"epoch": 0.13863384615384616,
"grad_norm": 81.4375,
"learning_rate": 9.997292307692307e-07,
"loss": 136.0269,
"step": 1320
},
{
"epoch": 0.13968410256410257,
"grad_norm": 75.125,
"learning_rate": 9.997271794871794e-07,
"loss": 135.8283,
"step": 1330
},
{
"epoch": 0.140734358974359,
"grad_norm": 76.3125,
"learning_rate": 9.997251282051281e-07,
"loss": 135.8927,
"step": 1340
},
{
"epoch": 0.1417846153846154,
"grad_norm": 81.375,
"learning_rate": 9.997230769230768e-07,
"loss": 136.4391,
"step": 1350
},
{
"epoch": 0.14283487179487178,
"grad_norm": 76.8125,
"learning_rate": 9.997210256410255e-07,
"loss": 136.1003,
"step": 1360
},
{
"epoch": 0.1438851282051282,
"grad_norm": 77.0625,
"learning_rate": 9.997189743589744e-07,
"loss": 136.084,
"step": 1370
},
{
"epoch": 0.1449353846153846,
"grad_norm": 77.9375,
"learning_rate": 9.99716923076923e-07,
"loss": 136.8443,
"step": 1380
},
{
"epoch": 0.14598564102564102,
"grad_norm": 78.875,
"learning_rate": 9.997148717948718e-07,
"loss": 137.2401,
"step": 1390
},
{
"epoch": 0.14703589743589743,
"grad_norm": 77.75,
"learning_rate": 9.997128205128205e-07,
"loss": 135.3477,
"step": 1400
},
{
"epoch": 0.14808615384615384,
"grad_norm": 75.0625,
"learning_rate": 9.997107692307692e-07,
"loss": 136.3265,
"step": 1410
},
{
"epoch": 0.14913641025641025,
"grad_norm": 77.0625,
"learning_rate": 9.997087179487179e-07,
"loss": 135.3777,
"step": 1420
},
{
"epoch": 0.15018666666666666,
"grad_norm": 83.125,
"learning_rate": 9.997066666666666e-07,
"loss": 136.6043,
"step": 1430
},
{
"epoch": 0.15123692307692307,
"grad_norm": 75.5,
"learning_rate": 9.997046153846153e-07,
"loss": 134.7866,
"step": 1440
},
{
"epoch": 0.15228717948717949,
"grad_norm": 80.0625,
"learning_rate": 9.99702564102564e-07,
"loss": 136.6343,
"step": 1450
},
{
"epoch": 0.1533374358974359,
"grad_norm": 77.1875,
"learning_rate": 9.997005128205129e-07,
"loss": 135.3757,
"step": 1460
},
{
"epoch": 0.1543876923076923,
"grad_norm": 76.1875,
"learning_rate": 9.996984615384616e-07,
"loss": 137.085,
"step": 1470
},
{
"epoch": 0.15543794871794872,
"grad_norm": 82.9375,
"learning_rate": 9.996964102564103e-07,
"loss": 135.0811,
"step": 1480
},
{
"epoch": 0.15648820512820513,
"grad_norm": 82.1875,
"learning_rate": 9.99694358974359e-07,
"loss": 137.3096,
"step": 1490
},
{
"epoch": 0.15753846153846154,
"grad_norm": 86.875,
"learning_rate": 9.996923076923076e-07,
"loss": 137.6569,
"step": 1500
},
{
"epoch": 0.15858871794871796,
"grad_norm": 82.8125,
"learning_rate": 9.996902564102563e-07,
"loss": 135.1526,
"step": 1510
},
{
"epoch": 0.15963897435897437,
"grad_norm": 76.125,
"learning_rate": 9.99688205128205e-07,
"loss": 136.4004,
"step": 1520
},
{
"epoch": 0.16068923076923078,
"grad_norm": 77.25,
"learning_rate": 9.99686153846154e-07,
"loss": 135.9153,
"step": 1530
},
{
"epoch": 0.1617394871794872,
"grad_norm": 79.5625,
"learning_rate": 9.996841025641024e-07,
"loss": 135.5955,
"step": 1540
},
{
"epoch": 0.1627897435897436,
"grad_norm": 73.5,
"learning_rate": 9.996820512820511e-07,
"loss": 135.8393,
"step": 1550
},
{
"epoch": 0.16384,
"grad_norm": 79.625,
"learning_rate": 9.9968e-07,
"loss": 134.5212,
"step": 1560
},
{
"epoch": 0.1648902564102564,
"grad_norm": 77.0625,
"learning_rate": 9.996779487179487e-07,
"loss": 134.8009,
"step": 1570
},
{
"epoch": 0.1659405128205128,
"grad_norm": 75.3125,
"learning_rate": 9.996758974358974e-07,
"loss": 136.2163,
"step": 1580
},
{
"epoch": 0.16699076923076922,
"grad_norm": 76.25,
"learning_rate": 9.99673846153846e-07,
"loss": 134.558,
"step": 1590
},
{
"epoch": 0.16804102564102563,
"grad_norm": 80.5,
"learning_rate": 9.996717948717948e-07,
"loss": 137.3439,
"step": 1600
},
{
"epoch": 0.16909128205128204,
"grad_norm": 79.5,
"learning_rate": 9.996697435897435e-07,
"loss": 135.4167,
"step": 1610
},
{
"epoch": 0.17014153846153846,
"grad_norm": 84.375,
"learning_rate": 9.996676923076922e-07,
"loss": 135.6234,
"step": 1620
},
{
"epoch": 0.17119179487179487,
"grad_norm": 77.125,
"learning_rate": 9.99665641025641e-07,
"loss": 136.2828,
"step": 1630
},
{
"epoch": 0.17224205128205128,
"grad_norm": 80.0625,
"learning_rate": 9.996635897435896e-07,
"loss": 136.7889,
"step": 1640
},
{
"epoch": 0.1732923076923077,
"grad_norm": 85.1875,
"learning_rate": 9.996615384615385e-07,
"loss": 135.2274,
"step": 1650
},
{
"epoch": 0.1743425641025641,
"grad_norm": 76.0625,
"learning_rate": 9.996594871794872e-07,
"loss": 134.4018,
"step": 1660
},
{
"epoch": 0.1753928205128205,
"grad_norm": 72.5,
"learning_rate": 9.996574358974359e-07,
"loss": 136.2152,
"step": 1670
},
{
"epoch": 0.17644307692307692,
"grad_norm": 80.125,
"learning_rate": 9.996553846153846e-07,
"loss": 137.071,
"step": 1680
},
{
"epoch": 0.17749333333333334,
"grad_norm": 78.375,
"learning_rate": 9.996533333333332e-07,
"loss": 138.2829,
"step": 1690
},
{
"epoch": 0.17854358974358975,
"grad_norm": 80.5625,
"learning_rate": 9.99651282051282e-07,
"loss": 138.097,
"step": 1700
},
{
"epoch": 0.17959384615384616,
"grad_norm": 75.4375,
"learning_rate": 9.996492307692306e-07,
"loss": 135.6503,
"step": 1710
},
{
"epoch": 0.18064410256410257,
"grad_norm": 72.3125,
"learning_rate": 9.996471794871795e-07,
"loss": 135.8609,
"step": 1720
},
{
"epoch": 0.18169435897435898,
"grad_norm": 76.5,
"learning_rate": 9.996451282051282e-07,
"loss": 135.2807,
"step": 1730
},
{
"epoch": 0.1827446153846154,
"grad_norm": 77.375,
"learning_rate": 9.99643076923077e-07,
"loss": 137.0498,
"step": 1740
},
{
"epoch": 0.1837948717948718,
"grad_norm": 79.125,
"learning_rate": 9.996410256410256e-07,
"loss": 135.6374,
"step": 1750
},
{
"epoch": 0.18484512820512822,
"grad_norm": 76.4375,
"learning_rate": 9.996389743589743e-07,
"loss": 135.5604,
"step": 1760
},
{
"epoch": 0.18589538461538463,
"grad_norm": 77.1875,
"learning_rate": 9.99636923076923e-07,
"loss": 136.8207,
"step": 1770
},
{
"epoch": 0.186945641025641,
"grad_norm": 73.75,
"learning_rate": 9.996348717948717e-07,
"loss": 134.608,
"step": 1780
},
{
"epoch": 0.18799589743589742,
"grad_norm": 76.75,
"learning_rate": 9.996328205128204e-07,
"loss": 134.2615,
"step": 1790
},
{
"epoch": 0.18904615384615384,
"grad_norm": 71.0,
"learning_rate": 9.99630769230769e-07,
"loss": 135.2525,
"step": 1800
},
{
"epoch": 0.19009641025641025,
"grad_norm": 73.8125,
"learning_rate": 9.99628717948718e-07,
"loss": 136.1974,
"step": 1810
},
{
"epoch": 0.19114666666666666,
"grad_norm": 75.8125,
"learning_rate": 9.996266666666667e-07,
"loss": 135.5419,
"step": 1820
},
{
"epoch": 0.19219692307692307,
"grad_norm": 80.75,
"learning_rate": 9.996246153846154e-07,
"loss": 137.3305,
"step": 1830
},
{
"epoch": 0.19324717948717948,
"grad_norm": 71.25,
"learning_rate": 9.99622564102564e-07,
"loss": 137.0593,
"step": 1840
},
{
"epoch": 0.1942974358974359,
"grad_norm": 74.75,
"learning_rate": 9.996205128205128e-07,
"loss": 134.3344,
"step": 1850
},
{
"epoch": 0.1953476923076923,
"grad_norm": 78.875,
"learning_rate": 9.996184615384615e-07,
"loss": 135.5054,
"step": 1860
},
{
"epoch": 0.19639794871794872,
"grad_norm": 86.9375,
"learning_rate": 9.996164102564102e-07,
"loss": 135.8128,
"step": 1870
},
{
"epoch": 0.19744820512820513,
"grad_norm": 77.375,
"learning_rate": 9.99614358974359e-07,
"loss": 136.683,
"step": 1880
},
{
"epoch": 0.19849846153846154,
"grad_norm": 74.625,
"learning_rate": 9.996123076923075e-07,
"loss": 135.5866,
"step": 1890
},
{
"epoch": 0.19954871794871795,
"grad_norm": 81.9375,
"learning_rate": 9.996102564102562e-07,
"loss": 136.3391,
"step": 1900
},
{
"epoch": 0.20059897435897436,
"grad_norm": 72.3125,
"learning_rate": 9.996082051282051e-07,
"loss": 134.9728,
"step": 1910
},
{
"epoch": 0.20164923076923078,
"grad_norm": 76.0,
"learning_rate": 9.996061538461538e-07,
"loss": 136.9715,
"step": 1920
},
{
"epoch": 0.2026994871794872,
"grad_norm": 75.875,
"learning_rate": 9.996041025641025e-07,
"loss": 136.9253,
"step": 1930
},
{
"epoch": 0.2037497435897436,
"grad_norm": 72.5625,
"learning_rate": 9.996020512820512e-07,
"loss": 136.5684,
"step": 1940
},
{
"epoch": 0.2048,
"grad_norm": 79.1875,
"learning_rate": 9.996e-07,
"loss": 137.1642,
"step": 1950
},
{
"epoch": 0.20585025641025642,
"grad_norm": 73.25,
"learning_rate": 9.995979487179486e-07,
"loss": 136.117,
"step": 1960
},
{
"epoch": 0.20690051282051283,
"grad_norm": 75.5625,
"learning_rate": 9.995958974358973e-07,
"loss": 134.5405,
"step": 1970
},
{
"epoch": 0.20795076923076924,
"grad_norm": 83.3125,
"learning_rate": 9.995938461538462e-07,
"loss": 137.0504,
"step": 1980
},
{
"epoch": 0.20900102564102563,
"grad_norm": 79.875,
"learning_rate": 9.995917948717947e-07,
"loss": 136.2677,
"step": 1990
},
{
"epoch": 0.21005128205128204,
"grad_norm": 79.125,
"learning_rate": 9.995897435897436e-07,
"loss": 135.2774,
"step": 2000
},
{
"epoch": 0.21110153846153845,
"grad_norm": 76.75,
"learning_rate": 9.995876923076923e-07,
"loss": 136.594,
"step": 2010
},
{
"epoch": 0.21215179487179486,
"grad_norm": 83.25,
"learning_rate": 9.99585641025641e-07,
"loss": 134.4644,
"step": 2020
},
{
"epoch": 0.21320205128205127,
"grad_norm": 73.75,
"learning_rate": 9.995835897435897e-07,
"loss": 136.3149,
"step": 2030
},
{
"epoch": 0.2142523076923077,
"grad_norm": 77.1875,
"learning_rate": 9.995815384615384e-07,
"loss": 135.3595,
"step": 2040
},
{
"epoch": 0.2153025641025641,
"grad_norm": 72.875,
"learning_rate": 9.99579487179487e-07,
"loss": 133.5256,
"step": 2050
},
{
"epoch": 0.2163528205128205,
"grad_norm": 79.0,
"learning_rate": 9.995774358974358e-07,
"loss": 135.2664,
"step": 2060
},
{
"epoch": 0.21740307692307692,
"grad_norm": 73.1875,
"learning_rate": 9.995753846153847e-07,
"loss": 136.2204,
"step": 2070
},
{
"epoch": 0.21845333333333333,
"grad_norm": 75.5625,
"learning_rate": 9.995733333333334e-07,
"loss": 137.547,
"step": 2080
},
{
"epoch": 0.21950358974358974,
"grad_norm": 75.3125,
"learning_rate": 9.99571282051282e-07,
"loss": 135.3881,
"step": 2090
},
{
"epoch": 0.22055384615384616,
"grad_norm": 76.0625,
"learning_rate": 9.995692307692308e-07,
"loss": 133.5891,
"step": 2100
},
{
"epoch": 0.22160410256410257,
"grad_norm": 79.25,
"learning_rate": 9.995671794871795e-07,
"loss": 135.3257,
"step": 2110
},
{
"epoch": 0.22265435897435898,
"grad_norm": 72.1875,
"learning_rate": 9.995651282051281e-07,
"loss": 136.8712,
"step": 2120
},
{
"epoch": 0.2237046153846154,
"grad_norm": 75.0625,
"learning_rate": 9.995630769230768e-07,
"loss": 136.354,
"step": 2130
},
{
"epoch": 0.2247548717948718,
"grad_norm": 77.9375,
"learning_rate": 9.995610256410255e-07,
"loss": 136.7022,
"step": 2140
},
{
"epoch": 0.2258051282051282,
"grad_norm": 79.25,
"learning_rate": 9.995589743589742e-07,
"loss": 135.4528,
"step": 2150
},
{
"epoch": 0.22685538461538463,
"grad_norm": 72.5625,
"learning_rate": 9.995569230769231e-07,
"loss": 134.8882,
"step": 2160
},
{
"epoch": 0.22790564102564104,
"grad_norm": 77.3125,
"learning_rate": 9.995548717948718e-07,
"loss": 136.6945,
"step": 2170
},
{
"epoch": 0.22895589743589745,
"grad_norm": 77.5625,
"learning_rate": 9.995528205128205e-07,
"loss": 135.1974,
"step": 2180
},
{
"epoch": 0.23000615384615383,
"grad_norm": 78.375,
"learning_rate": 9.995507692307692e-07,
"loss": 134.4525,
"step": 2190
},
{
"epoch": 0.23105641025641024,
"grad_norm": 74.375,
"learning_rate": 9.99548717948718e-07,
"loss": 136.5888,
"step": 2200
},
{
"epoch": 0.23210666666666666,
"grad_norm": 76.25,
"learning_rate": 9.995466666666666e-07,
"loss": 134.7819,
"step": 2210
},
{
"epoch": 0.23315692307692307,
"grad_norm": 77.5625,
"learning_rate": 9.995446153846153e-07,
"loss": 136.178,
"step": 2220
},
{
"epoch": 0.23420717948717948,
"grad_norm": 73.0625,
"learning_rate": 9.995425641025642e-07,
"loss": 134.5108,
"step": 2230
},
{
"epoch": 0.2352574358974359,
"grad_norm": 74.5,
"learning_rate": 9.995405128205127e-07,
"loss": 133.9853,
"step": 2240
},
{
"epoch": 0.2363076923076923,
"grad_norm": 78.125,
"learning_rate": 9.995384615384614e-07,
"loss": 135.3976,
"step": 2250
},
{
"epoch": 0.2373579487179487,
"grad_norm": 77.0625,
"learning_rate": 9.995364102564103e-07,
"loss": 134.6315,
"step": 2260
},
{
"epoch": 0.23840820512820513,
"grad_norm": 76.375,
"learning_rate": 9.99534358974359e-07,
"loss": 135.5964,
"step": 2270
},
{
"epoch": 0.23945846153846154,
"grad_norm": 79.0,
"learning_rate": 9.995323076923077e-07,
"loss": 134.7914,
"step": 2280
},
{
"epoch": 0.24050871794871795,
"grad_norm": 72.75,
"learning_rate": 9.995302564102564e-07,
"loss": 136.3084,
"step": 2290
},
{
"epoch": 0.24155897435897436,
"grad_norm": 80.0,
"learning_rate": 9.99528205128205e-07,
"loss": 135.3856,
"step": 2300
},
{
"epoch": 0.24260923076923077,
"grad_norm": 74.375,
"learning_rate": 9.995261538461538e-07,
"loss": 135.1752,
"step": 2310
},
{
"epoch": 0.24365948717948718,
"grad_norm": 78.4375,
"learning_rate": 9.995241025641024e-07,
"loss": 135.734,
"step": 2320
},
{
"epoch": 0.2447097435897436,
"grad_norm": 73.0625,
"learning_rate": 9.995220512820514e-07,
"loss": 138.4359,
"step": 2330
},
{
"epoch": 0.24576,
"grad_norm": 75.6875,
"learning_rate": 9.995199999999998e-07,
"loss": 134.4686,
"step": 2340
},
{
"epoch": 0.24681025641025642,
"grad_norm": 80.1875,
"learning_rate": 9.995179487179487e-07,
"loss": 134.8197,
"step": 2350
},
{
"epoch": 0.24786051282051283,
"grad_norm": 72.625,
"learning_rate": 9.995158974358974e-07,
"loss": 133.9546,
"step": 2360
},
{
"epoch": 0.24891076923076924,
"grad_norm": 78.6875,
"learning_rate": 9.995138461538461e-07,
"loss": 136.5728,
"step": 2370
},
{
"epoch": 0.24996102564102565,
"grad_norm": 75.1875,
"learning_rate": 9.995117948717948e-07,
"loss": 134.8723,
"step": 2380
},
{
"epoch": 0.25101128205128204,
"grad_norm": 80.0625,
"learning_rate": 9.995097435897435e-07,
"loss": 135.4755,
"step": 2390
},
{
"epoch": 0.25206153846153845,
"grad_norm": 79.375,
"learning_rate": 9.995076923076922e-07,
"loss": 135.7919,
"step": 2400
},
{
"epoch": 0.25311179487179486,
"grad_norm": 77.9375,
"learning_rate": 9.99505641025641e-07,
"loss": 134.9586,
"step": 2410
},
{
"epoch": 0.25416205128205127,
"grad_norm": 83.8125,
"learning_rate": 9.995035897435898e-07,
"loss": 135.5097,
"step": 2420
},
{
"epoch": 0.2552123076923077,
"grad_norm": 75.125,
"learning_rate": 9.995015384615383e-07,
"loss": 135.1367,
"step": 2430
},
{
"epoch": 0.2562625641025641,
"grad_norm": 82.75,
"learning_rate": 9.994994871794872e-07,
"loss": 134.9296,
"step": 2440
},
{
"epoch": 0.2573128205128205,
"grad_norm": 79.125,
"learning_rate": 9.994974358974359e-07,
"loss": 135.2879,
"step": 2450
},
{
"epoch": 0.2583630769230769,
"grad_norm": 75.25,
"learning_rate": 9.994953846153846e-07,
"loss": 137.2041,
"step": 2460
},
{
"epoch": 0.25941333333333333,
"grad_norm": 73.125,
"learning_rate": 9.994933333333333e-07,
"loss": 134.5497,
"step": 2470
},
{
"epoch": 0.26046358974358974,
"grad_norm": 76.3125,
"learning_rate": 9.99491282051282e-07,
"loss": 133.5379,
"step": 2480
},
{
"epoch": 0.26151384615384615,
"grad_norm": 79.3125,
"learning_rate": 9.994892307692307e-07,
"loss": 135.711,
"step": 2490
},
{
"epoch": 0.26256410256410256,
"grad_norm": 75.1875,
"learning_rate": 9.994871794871794e-07,
"loss": 135.4191,
"step": 2500
},
{
"epoch": 0.26256410256410256,
"eval_loss": 2.1188364028930664,
"eval_runtime": 323.2666,
"eval_samples_per_second": 1546.714,
"eval_steps_per_second": 48.338,
"step": 2500
},
{
"epoch": 0.263614358974359,
"grad_norm": 79.25,
"learning_rate": 9.994851282051283e-07,
"loss": 135.2211,
"step": 2510
},
{
"epoch": 0.2646646153846154,
"grad_norm": 79.25,
"learning_rate": 9.99483076923077e-07,
"loss": 136.2887,
"step": 2520
},
{
"epoch": 0.2657148717948718,
"grad_norm": 74.875,
"learning_rate": 9.994810256410254e-07,
"loss": 135.4725,
"step": 2530
},
{
"epoch": 0.2667651282051282,
"grad_norm": 77.125,
"learning_rate": 9.994789743589743e-07,
"loss": 134.7815,
"step": 2540
},
{
"epoch": 0.2678153846153846,
"grad_norm": 73.0625,
"learning_rate": 9.99476923076923e-07,
"loss": 136.2688,
"step": 2550
},
{
"epoch": 0.26886564102564103,
"grad_norm": 75.0625,
"learning_rate": 9.994748717948717e-07,
"loss": 135.9708,
"step": 2560
},
{
"epoch": 0.26991589743589744,
"grad_norm": 76.375,
"learning_rate": 9.994728205128204e-07,
"loss": 135.3358,
"step": 2570
},
{
"epoch": 0.27096615384615386,
"grad_norm": 78.1875,
"learning_rate": 9.994707692307691e-07,
"loss": 133.8587,
"step": 2580
},
{
"epoch": 0.27201641025641027,
"grad_norm": 81.5625,
"learning_rate": 9.994687179487178e-07,
"loss": 134.9151,
"step": 2590
},
{
"epoch": 0.2730666666666667,
"grad_norm": 78.9375,
"learning_rate": 9.994666666666665e-07,
"loss": 136.3942,
"step": 2600
},
{
"epoch": 0.2741169230769231,
"grad_norm": 73.75,
"learning_rate": 9.994646153846154e-07,
"loss": 136.1266,
"step": 2610
},
{
"epoch": 0.2751671794871795,
"grad_norm": 77.4375,
"learning_rate": 9.994625641025641e-07,
"loss": 133.3652,
"step": 2620
},
{
"epoch": 0.2762174358974359,
"grad_norm": 77.8125,
"learning_rate": 9.994605128205128e-07,
"loss": 134.6492,
"step": 2630
},
{
"epoch": 0.2772676923076923,
"grad_norm": 85.1875,
"learning_rate": 9.994584615384615e-07,
"loss": 135.2869,
"step": 2640
},
{
"epoch": 0.27831794871794874,
"grad_norm": 79.3125,
"learning_rate": 9.994564102564102e-07,
"loss": 134.8688,
"step": 2650
},
{
"epoch": 0.27936820512820515,
"grad_norm": 74.875,
"learning_rate": 9.994543589743589e-07,
"loss": 135.1861,
"step": 2660
},
{
"epoch": 0.28041846153846156,
"grad_norm": 78.9375,
"learning_rate": 9.994523076923076e-07,
"loss": 135.177,
"step": 2670
},
{
"epoch": 0.281468717948718,
"grad_norm": 76.5,
"learning_rate": 9.994502564102563e-07,
"loss": 135.4743,
"step": 2680
},
{
"epoch": 0.2825189743589744,
"grad_norm": 81.4375,
"learning_rate": 9.99448205128205e-07,
"loss": 135.5451,
"step": 2690
},
{
"epoch": 0.2835692307692308,
"grad_norm": 79.3125,
"learning_rate": 9.994461538461539e-07,
"loss": 134.3136,
"step": 2700
},
{
"epoch": 0.2846194871794872,
"grad_norm": 77.5,
"learning_rate": 9.994441025641026e-07,
"loss": 134.4667,
"step": 2710
},
{
"epoch": 0.28566974358974356,
"grad_norm": 73.625,
"learning_rate": 9.994420512820513e-07,
"loss": 134.8625,
"step": 2720
},
{
"epoch": 0.28672,
"grad_norm": 73.25,
"learning_rate": 9.9944e-07,
"loss": 137.0244,
"step": 2730
},
{
"epoch": 0.2877702564102564,
"grad_norm": 73.75,
"learning_rate": 9.994379487179486e-07,
"loss": 134.9446,
"step": 2740
},
{
"epoch": 0.2888205128205128,
"grad_norm": 77.625,
"learning_rate": 9.994358974358973e-07,
"loss": 135.4492,
"step": 2750
},
{
"epoch": 0.2898707692307692,
"grad_norm": 75.9375,
"learning_rate": 9.99433846153846e-07,
"loss": 136.541,
"step": 2760
},
{
"epoch": 0.2909210256410256,
"grad_norm": 78.0625,
"learning_rate": 9.99431794871795e-07,
"loss": 134.317,
"step": 2770
},
{
"epoch": 0.29197128205128203,
"grad_norm": 73.0,
"learning_rate": 9.994297435897434e-07,
"loss": 135.7358,
"step": 2780
},
{
"epoch": 0.29302153846153844,
"grad_norm": 79.9375,
"learning_rate": 9.994276923076923e-07,
"loss": 137.0936,
"step": 2790
},
{
"epoch": 0.29407179487179486,
"grad_norm": 76.125,
"learning_rate": 9.99425641025641e-07,
"loss": 135.2308,
"step": 2800
},
{
"epoch": 0.29512205128205127,
"grad_norm": 72.3125,
"learning_rate": 9.994235897435897e-07,
"loss": 135.2886,
"step": 2810
},
{
"epoch": 0.2961723076923077,
"grad_norm": 74.0,
"learning_rate": 9.994215384615384e-07,
"loss": 136.1337,
"step": 2820
},
{
"epoch": 0.2972225641025641,
"grad_norm": 74.375,
"learning_rate": 9.99419487179487e-07,
"loss": 135.8501,
"step": 2830
},
{
"epoch": 0.2982728205128205,
"grad_norm": 81.5625,
"learning_rate": 9.994174358974358e-07,
"loss": 135.7207,
"step": 2840
},
{
"epoch": 0.2993230769230769,
"grad_norm": 74.4375,
"learning_rate": 9.994153846153845e-07,
"loss": 135.9827,
"step": 2850
},
{
"epoch": 0.3003733333333333,
"grad_norm": 72.625,
"learning_rate": 9.994133333333334e-07,
"loss": 134.6337,
"step": 2860
},
{
"epoch": 0.30142358974358974,
"grad_norm": 70.375,
"learning_rate": 9.99411282051282e-07,
"loss": 134.3101,
"step": 2870
},
{
"epoch": 0.30247384615384615,
"grad_norm": 80.1875,
"learning_rate": 9.994092307692306e-07,
"loss": 137.0535,
"step": 2880
},
{
"epoch": 0.30352410256410256,
"grad_norm": 76.375,
"learning_rate": 9.994071794871795e-07,
"loss": 135.9274,
"step": 2890
},
{
"epoch": 0.30457435897435897,
"grad_norm": 72.8125,
"learning_rate": 9.994051282051282e-07,
"loss": 132.9079,
"step": 2900
},
{
"epoch": 0.3056246153846154,
"grad_norm": 75.125,
"learning_rate": 9.994030769230769e-07,
"loss": 135.1428,
"step": 2910
},
{
"epoch": 0.3066748717948718,
"grad_norm": 74.625,
"learning_rate": 9.994010256410256e-07,
"loss": 134.4849,
"step": 2920
},
{
"epoch": 0.3077251282051282,
"grad_norm": 73.75,
"learning_rate": 9.993989743589743e-07,
"loss": 135.9804,
"step": 2930
},
{
"epoch": 0.3087753846153846,
"grad_norm": 78.625,
"learning_rate": 9.99396923076923e-07,
"loss": 136.6684,
"step": 2940
},
{
"epoch": 0.30982564102564103,
"grad_norm": 71.875,
"learning_rate": 9.993948717948716e-07,
"loss": 135.7181,
"step": 2950
},
{
"epoch": 0.31087589743589744,
"grad_norm": 78.375,
"learning_rate": 9.993928205128206e-07,
"loss": 135.7046,
"step": 2960
},
{
"epoch": 0.31192615384615385,
"grad_norm": 74.125,
"learning_rate": 9.993907692307692e-07,
"loss": 137.1845,
"step": 2970
},
{
"epoch": 0.31297641025641026,
"grad_norm": 85.1875,
"learning_rate": 9.99388717948718e-07,
"loss": 135.0767,
"step": 2980
},
{
"epoch": 0.3140266666666667,
"grad_norm": 77.25,
"learning_rate": 9.993866666666666e-07,
"loss": 136.31,
"step": 2990
},
{
"epoch": 0.3150769230769231,
"grad_norm": 75.625,
"learning_rate": 9.993846153846153e-07,
"loss": 136.1574,
"step": 3000
},
{
"epoch": 0.3161271794871795,
"grad_norm": 75.25,
"learning_rate": 9.99382564102564e-07,
"loss": 137.0583,
"step": 3010
},
{
"epoch": 0.3171774358974359,
"grad_norm": 83.4375,
"learning_rate": 9.993805128205127e-07,
"loss": 135.9799,
"step": 3020
},
{
"epoch": 0.3182276923076923,
"grad_norm": 72.0625,
"learning_rate": 9.993784615384614e-07,
"loss": 134.9051,
"step": 3030
},
{
"epoch": 0.31927794871794873,
"grad_norm": 82.1875,
"learning_rate": 9.9937641025641e-07,
"loss": 135.2081,
"step": 3040
},
{
"epoch": 0.32032820512820515,
"grad_norm": 79.6875,
"learning_rate": 9.99374358974359e-07,
"loss": 136.1164,
"step": 3050
},
{
"epoch": 0.32137846153846156,
"grad_norm": 78.0,
"learning_rate": 9.993723076923077e-07,
"loss": 134.9097,
"step": 3060
},
{
"epoch": 0.32242871794871797,
"grad_norm": 76.4375,
"learning_rate": 9.993702564102564e-07,
"loss": 133.515,
"step": 3070
},
{
"epoch": 0.3234789743589744,
"grad_norm": 76.0625,
"learning_rate": 9.99368205128205e-07,
"loss": 133.6614,
"step": 3080
},
{
"epoch": 0.3245292307692308,
"grad_norm": 77.9375,
"learning_rate": 9.993661538461538e-07,
"loss": 135.41,
"step": 3090
},
{
"epoch": 0.3255794871794872,
"grad_norm": 79.875,
"learning_rate": 9.993641025641025e-07,
"loss": 134.63,
"step": 3100
},
{
"epoch": 0.3266297435897436,
"grad_norm": 84.0,
"learning_rate": 9.993620512820512e-07,
"loss": 134.7932,
"step": 3110
},
{
"epoch": 0.32768,
"grad_norm": 76.25,
"learning_rate": 9.9936e-07,
"loss": 136.1248,
"step": 3120
},
{
"epoch": 0.3287302564102564,
"grad_norm": 77.625,
"learning_rate": 9.993579487179486e-07,
"loss": 136.2906,
"step": 3130
},
{
"epoch": 0.3297805128205128,
"grad_norm": 73.875,
"learning_rate": 9.993558974358975e-07,
"loss": 135.0763,
"step": 3140
},
{
"epoch": 0.3308307692307692,
"grad_norm": 76.0,
"learning_rate": 9.993538461538462e-07,
"loss": 135.5835,
"step": 3150
},
{
"epoch": 0.3318810256410256,
"grad_norm": 75.0,
"learning_rate": 9.993517948717949e-07,
"loss": 134.8059,
"step": 3160
},
{
"epoch": 0.33293128205128203,
"grad_norm": 75.5625,
"learning_rate": 9.993497435897435e-07,
"loss": 133.6129,
"step": 3170
},
{
"epoch": 0.33398153846153844,
"grad_norm": 80.3125,
"learning_rate": 9.993476923076922e-07,
"loss": 134.7108,
"step": 3180
},
{
"epoch": 0.33503179487179485,
"grad_norm": 75.8125,
"learning_rate": 9.99345641025641e-07,
"loss": 134.7491,
"step": 3190
},
{
"epoch": 0.33608205128205126,
"grad_norm": 81.8125,
"learning_rate": 9.993435897435896e-07,
"loss": 136.0053,
"step": 3200
},
{
"epoch": 0.3371323076923077,
"grad_norm": 80.5,
"learning_rate": 9.993415384615385e-07,
"loss": 135.721,
"step": 3210
},
{
"epoch": 0.3381825641025641,
"grad_norm": 81.0625,
"learning_rate": 9.993394871794872e-07,
"loss": 134.6836,
"step": 3220
},
{
"epoch": 0.3392328205128205,
"grad_norm": 72.9375,
"learning_rate": 9.993374358974357e-07,
"loss": 135.0893,
"step": 3230
},
{
"epoch": 0.3402830769230769,
"grad_norm": 71.75,
"learning_rate": 9.993353846153846e-07,
"loss": 134.1155,
"step": 3240
},
{
"epoch": 0.3413333333333333,
"grad_norm": 80.25,
"learning_rate": 9.993333333333333e-07,
"loss": 135.7648,
"step": 3250
},
{
"epoch": 0.34238358974358973,
"grad_norm": 80.5625,
"learning_rate": 9.99331282051282e-07,
"loss": 137.1672,
"step": 3260
},
{
"epoch": 0.34343384615384615,
"grad_norm": 72.4375,
"learning_rate": 9.993292307692307e-07,
"loss": 135.3809,
"step": 3270
},
{
"epoch": 0.34448410256410256,
"grad_norm": 85.625,
"learning_rate": 9.993271794871794e-07,
"loss": 135.0371,
"step": 3280
},
{
"epoch": 0.34553435897435897,
"grad_norm": 75.75,
"learning_rate": 9.99325128205128e-07,
"loss": 136.3321,
"step": 3290
},
{
"epoch": 0.3465846153846154,
"grad_norm": 74.4375,
"learning_rate": 9.993230769230768e-07,
"loss": 135.4693,
"step": 3300
},
{
"epoch": 0.3476348717948718,
"grad_norm": 76.9375,
"learning_rate": 9.993210256410257e-07,
"loss": 136.1733,
"step": 3310
},
{
"epoch": 0.3486851282051282,
"grad_norm": 74.875,
"learning_rate": 9.993189743589744e-07,
"loss": 136.2052,
"step": 3320
},
{
"epoch": 0.3497353846153846,
"grad_norm": 74.25,
"learning_rate": 9.99316923076923e-07,
"loss": 135.3316,
"step": 3330
},
{
"epoch": 0.350785641025641,
"grad_norm": 75.375,
"learning_rate": 9.993148717948718e-07,
"loss": 134.3749,
"step": 3340
},
{
"epoch": 0.35183589743589744,
"grad_norm": 75.3125,
"learning_rate": 9.993128205128205e-07,
"loss": 135.7341,
"step": 3350
},
{
"epoch": 0.35288615384615385,
"grad_norm": 79.25,
"learning_rate": 9.993107692307692e-07,
"loss": 133.1281,
"step": 3360
},
{
"epoch": 0.35393641025641026,
"grad_norm": 78.5625,
"learning_rate": 9.993087179487178e-07,
"loss": 135.4264,
"step": 3370
},
{
"epoch": 0.3549866666666667,
"grad_norm": 77.125,
"learning_rate": 9.993066666666665e-07,
"loss": 134.1795,
"step": 3380
},
{
"epoch": 0.3560369230769231,
"grad_norm": 76.875,
"learning_rate": 9.993046153846152e-07,
"loss": 135.5148,
"step": 3390
},
{
"epoch": 0.3570871794871795,
"grad_norm": 73.1875,
"learning_rate": 9.993025641025641e-07,
"loss": 133.5614,
"step": 3400
},
{
"epoch": 0.3581374358974359,
"grad_norm": 77.6875,
"learning_rate": 9.993005128205128e-07,
"loss": 136.9069,
"step": 3410
},
{
"epoch": 0.3591876923076923,
"grad_norm": 74.4375,
"learning_rate": 9.992984615384615e-07,
"loss": 134.5801,
"step": 3420
},
{
"epoch": 0.36023794871794873,
"grad_norm": 84.8125,
"learning_rate": 9.992964102564102e-07,
"loss": 135.537,
"step": 3430
},
{
"epoch": 0.36128820512820514,
"grad_norm": 77.6875,
"learning_rate": 9.99294358974359e-07,
"loss": 136.1516,
"step": 3440
},
{
"epoch": 0.36233846153846155,
"grad_norm": 75.75,
"learning_rate": 9.992923076923076e-07,
"loss": 135.1764,
"step": 3450
},
{
"epoch": 0.36338871794871797,
"grad_norm": 77.3125,
"learning_rate": 9.992902564102563e-07,
"loss": 135.4487,
"step": 3460
},
{
"epoch": 0.3644389743589744,
"grad_norm": 79.25,
"learning_rate": 9.992882051282052e-07,
"loss": 135.1645,
"step": 3470
},
{
"epoch": 0.3654892307692308,
"grad_norm": 70.8125,
"learning_rate": 9.992861538461537e-07,
"loss": 135.1935,
"step": 3480
},
{
"epoch": 0.3665394871794872,
"grad_norm": 75.625,
"learning_rate": 9.992841025641026e-07,
"loss": 136.0637,
"step": 3490
},
{
"epoch": 0.3675897435897436,
"grad_norm": 76.625,
"learning_rate": 9.992820512820513e-07,
"loss": 134.5354,
"step": 3500
},
{
"epoch": 0.36864,
"grad_norm": 77.625,
"learning_rate": 9.9928e-07,
"loss": 135.7018,
"step": 3510
},
{
"epoch": 0.36969025641025643,
"grad_norm": 75.1875,
"learning_rate": 9.992779487179487e-07,
"loss": 134.9154,
"step": 3520
},
{
"epoch": 0.37074051282051285,
"grad_norm": 73.5625,
"learning_rate": 9.992758974358974e-07,
"loss": 133.1253,
"step": 3530
},
{
"epoch": 0.37179076923076926,
"grad_norm": 72.125,
"learning_rate": 9.99273846153846e-07,
"loss": 135.5619,
"step": 3540
},
{
"epoch": 0.3728410256410256,
"grad_norm": 78.5,
"learning_rate": 9.992717948717948e-07,
"loss": 136.4245,
"step": 3550
},
{
"epoch": 0.373891282051282,
"grad_norm": 76.625,
"learning_rate": 9.992697435897437e-07,
"loss": 134.4015,
"step": 3560
},
{
"epoch": 0.37494153846153844,
"grad_norm": 73.625,
"learning_rate": 9.992676923076924e-07,
"loss": 133.8719,
"step": 3570
},
{
"epoch": 0.37599179487179485,
"grad_norm": 78.75,
"learning_rate": 9.992656410256408e-07,
"loss": 135.8428,
"step": 3580
},
{
"epoch": 0.37704205128205126,
"grad_norm": 77.25,
"learning_rate": 9.992635897435897e-07,
"loss": 135.6345,
"step": 3590
},
{
"epoch": 0.37809230769230767,
"grad_norm": 77.8125,
"learning_rate": 9.992615384615384e-07,
"loss": 135.7983,
"step": 3600
},
{
"epoch": 0.3791425641025641,
"grad_norm": 85.0,
"learning_rate": 9.992594871794871e-07,
"loss": 136.1515,
"step": 3610
},
{
"epoch": 0.3801928205128205,
"grad_norm": 76.4375,
"learning_rate": 9.992574358974358e-07,
"loss": 135.6257,
"step": 3620
},
{
"epoch": 0.3812430769230769,
"grad_norm": 73.75,
"learning_rate": 9.992553846153845e-07,
"loss": 133.979,
"step": 3630
},
{
"epoch": 0.3822933333333333,
"grad_norm": 76.9375,
"learning_rate": 9.992533333333332e-07,
"loss": 136.2324,
"step": 3640
},
{
"epoch": 0.38334358974358973,
"grad_norm": 77.5625,
"learning_rate": 9.99251282051282e-07,
"loss": 134.3718,
"step": 3650
},
{
"epoch": 0.38439384615384614,
"grad_norm": 79.8125,
"learning_rate": 9.992492307692308e-07,
"loss": 135.6694,
"step": 3660
},
{
"epoch": 0.38544410256410255,
"grad_norm": 75.1875,
"learning_rate": 9.992471794871793e-07,
"loss": 134.8646,
"step": 3670
},
{
"epoch": 0.38649435897435896,
"grad_norm": 76.4375,
"learning_rate": 9.992451282051282e-07,
"loss": 134.7257,
"step": 3680
},
{
"epoch": 0.3875446153846154,
"grad_norm": 81.3125,
"learning_rate": 9.99243076923077e-07,
"loss": 134.3707,
"step": 3690
},
{
"epoch": 0.3885948717948718,
"grad_norm": 84.5625,
"learning_rate": 9.992410256410256e-07,
"loss": 134.4454,
"step": 3700
},
{
"epoch": 0.3896451282051282,
"grad_norm": 74.0625,
"learning_rate": 9.992389743589743e-07,
"loss": 135.4043,
"step": 3710
},
{
"epoch": 0.3906953846153846,
"grad_norm": 75.0,
"learning_rate": 9.99236923076923e-07,
"loss": 135.5324,
"step": 3720
},
{
"epoch": 0.391745641025641,
"grad_norm": 76.75,
"learning_rate": 9.992348717948717e-07,
"loss": 133.5802,
"step": 3730
},
{
"epoch": 0.39279589743589743,
"grad_norm": 80.5,
"learning_rate": 9.992328205128204e-07,
"loss": 134.3153,
"step": 3740
},
{
"epoch": 0.39384615384615385,
"grad_norm": 73.5625,
"learning_rate": 9.992307692307693e-07,
"loss": 135.3091,
"step": 3750
},
{
"epoch": 0.39489641025641026,
"grad_norm": 80.625,
"learning_rate": 9.99228717948718e-07,
"loss": 135.558,
"step": 3760
},
{
"epoch": 0.39594666666666667,
"grad_norm": 92.1875,
"learning_rate": 9.992266666666667e-07,
"loss": 134.8342,
"step": 3770
},
{
"epoch": 0.3969969230769231,
"grad_norm": 76.375,
"learning_rate": 9.992246153846154e-07,
"loss": 133.2689,
"step": 3780
},
{
"epoch": 0.3980471794871795,
"grad_norm": 75.9375,
"learning_rate": 9.99222564102564e-07,
"loss": 134.2165,
"step": 3790
},
{
"epoch": 0.3990974358974359,
"grad_norm": 79.0,
"learning_rate": 9.992205128205127e-07,
"loss": 133.4279,
"step": 3800
},
{
"epoch": 0.4001476923076923,
"grad_norm": 79.5,
"learning_rate": 9.992184615384614e-07,
"loss": 135.7965,
"step": 3810
},
{
"epoch": 0.4011979487179487,
"grad_norm": 80.0625,
"learning_rate": 9.992164102564101e-07,
"loss": 135.0,
"step": 3820
},
{
"epoch": 0.40224820512820514,
"grad_norm": 80.375,
"learning_rate": 9.992143589743588e-07,
"loss": 134.7765,
"step": 3830
},
{
"epoch": 0.40329846153846155,
"grad_norm": 73.75,
"learning_rate": 9.992123076923077e-07,
"loss": 134.9427,
"step": 3840
},
{
"epoch": 0.40434871794871796,
"grad_norm": 79.5625,
"learning_rate": 9.992102564102564e-07,
"loss": 136.5997,
"step": 3850
},
{
"epoch": 0.4053989743589744,
"grad_norm": 76.375,
"learning_rate": 9.992082051282051e-07,
"loss": 135.9788,
"step": 3860
},
{
"epoch": 0.4064492307692308,
"grad_norm": 77.4375,
"learning_rate": 9.992061538461538e-07,
"loss": 135.3422,
"step": 3870
},
{
"epoch": 0.4074994871794872,
"grad_norm": 87.1875,
"learning_rate": 9.992041025641025e-07,
"loss": 136.0771,
"step": 3880
},
{
"epoch": 0.4085497435897436,
"grad_norm": 80.5,
"learning_rate": 9.992020512820512e-07,
"loss": 135.1932,
"step": 3890
},
{
"epoch": 0.4096,
"grad_norm": 80.0,
"learning_rate": 9.992e-07,
"loss": 135.4803,
"step": 3900
},
{
"epoch": 0.41065025641025643,
"grad_norm": 78.9375,
"learning_rate": 9.991979487179488e-07,
"loss": 136.9885,
"step": 3910
},
{
"epoch": 0.41170051282051284,
"grad_norm": 75.1875,
"learning_rate": 9.991958974358973e-07,
"loss": 134.2177,
"step": 3920
},
{
"epoch": 0.41275076923076925,
"grad_norm": 76.0625,
"learning_rate": 9.99193846153846e-07,
"loss": 135.0054,
"step": 3930
},
{
"epoch": 0.41380102564102567,
"grad_norm": 73.25,
"learning_rate": 9.991917948717949e-07,
"loss": 135.2807,
"step": 3940
},
{
"epoch": 0.4148512820512821,
"grad_norm": 76.25,
"learning_rate": 9.991897435897436e-07,
"loss": 134.7263,
"step": 3950
},
{
"epoch": 0.4159015384615385,
"grad_norm": 76.6875,
"learning_rate": 9.991876923076923e-07,
"loss": 134.8251,
"step": 3960
},
{
"epoch": 0.41695179487179485,
"grad_norm": 73.4375,
"learning_rate": 9.99185641025641e-07,
"loss": 135.8926,
"step": 3970
},
{
"epoch": 0.41800205128205126,
"grad_norm": 81.25,
"learning_rate": 9.991835897435897e-07,
"loss": 134.2271,
"step": 3980
},
{
"epoch": 0.41905230769230767,
"grad_norm": 75.5625,
"learning_rate": 9.991815384615384e-07,
"loss": 135.0995,
"step": 3990
},
{
"epoch": 0.4201025641025641,
"grad_norm": 80.75,
"learning_rate": 9.99179487179487e-07,
"loss": 135.0728,
"step": 4000
},
{
"epoch": 0.4211528205128205,
"grad_norm": 82.6875,
"learning_rate": 9.99177435897436e-07,
"loss": 134.6969,
"step": 4010
},
{
"epoch": 0.4222030769230769,
"grad_norm": 80.625,
"learning_rate": 9.991753846153844e-07,
"loss": 135.1022,
"step": 4020
},
{
"epoch": 0.4232533333333333,
"grad_norm": 83.0,
"learning_rate": 9.991733333333333e-07,
"loss": 133.988,
"step": 4030
},
{
"epoch": 0.4243035897435897,
"grad_norm": 82.75,
"learning_rate": 9.99171282051282e-07,
"loss": 134.9216,
"step": 4040
},
{
"epoch": 0.42535384615384614,
"grad_norm": 78.75,
"learning_rate": 9.991692307692307e-07,
"loss": 135.8505,
"step": 4050
},
{
"epoch": 0.42640410256410255,
"grad_norm": 79.5,
"learning_rate": 9.991671794871794e-07,
"loss": 134.4515,
"step": 4060
},
{
"epoch": 0.42745435897435896,
"grad_norm": 75.625,
"learning_rate": 9.991651282051281e-07,
"loss": 133.4118,
"step": 4070
},
{
"epoch": 0.4285046153846154,
"grad_norm": 78.5,
"learning_rate": 9.991630769230768e-07,
"loss": 134.5181,
"step": 4080
},
{
"epoch": 0.4295548717948718,
"grad_norm": 77.5625,
"learning_rate": 9.991610256410255e-07,
"loss": 134.244,
"step": 4090
},
{
"epoch": 0.4306051282051282,
"grad_norm": 76.1875,
"learning_rate": 9.991589743589744e-07,
"loss": 134.0188,
"step": 4100
},
{
"epoch": 0.4316553846153846,
"grad_norm": 76.5625,
"learning_rate": 9.99156923076923e-07,
"loss": 134.7784,
"step": 4110
},
{
"epoch": 0.432705641025641,
"grad_norm": 78.4375,
"learning_rate": 9.991548717948718e-07,
"loss": 134.985,
"step": 4120
},
{
"epoch": 0.43375589743589743,
"grad_norm": 70.125,
"learning_rate": 9.991528205128205e-07,
"loss": 135.8493,
"step": 4130
},
{
"epoch": 0.43480615384615384,
"grad_norm": 72.0,
"learning_rate": 9.991507692307692e-07,
"loss": 134.0036,
"step": 4140
},
{
"epoch": 0.43585641025641025,
"grad_norm": 73.3125,
"learning_rate": 9.991487179487179e-07,
"loss": 135.3329,
"step": 4150
},
{
"epoch": 0.43690666666666667,
"grad_norm": 89.3125,
"learning_rate": 9.991466666666666e-07,
"loss": 135.4847,
"step": 4160
},
{
"epoch": 0.4379569230769231,
"grad_norm": 79.625,
"learning_rate": 9.991446153846153e-07,
"loss": 135.6277,
"step": 4170
},
{
"epoch": 0.4390071794871795,
"grad_norm": 77.375,
"learning_rate": 9.99142564102564e-07,
"loss": 134.1732,
"step": 4180
},
{
"epoch": 0.4400574358974359,
"grad_norm": 77.5625,
"learning_rate": 9.991405128205129e-07,
"loss": 134.5374,
"step": 4190
},
{
"epoch": 0.4411076923076923,
"grad_norm": 75.625,
"learning_rate": 9.991384615384616e-07,
"loss": 133.4375,
"step": 4200
},
{
"epoch": 0.4421579487179487,
"grad_norm": 77.0625,
"learning_rate": 9.991364102564103e-07,
"loss": 135.5672,
"step": 4210
},
{
"epoch": 0.44320820512820513,
"grad_norm": 79.5625,
"learning_rate": 9.99134358974359e-07,
"loss": 133.6737,
"step": 4220
},
{
"epoch": 0.44425846153846155,
"grad_norm": 77.875,
"learning_rate": 9.991323076923076e-07,
"loss": 133.9747,
"step": 4230
},
{
"epoch": 0.44530871794871796,
"grad_norm": 79.9375,
"learning_rate": 9.991302564102563e-07,
"loss": 135.8439,
"step": 4240
},
{
"epoch": 0.44635897435897437,
"grad_norm": 76.1875,
"learning_rate": 9.99128205128205e-07,
"loss": 135.6554,
"step": 4250
},
{
"epoch": 0.4474092307692308,
"grad_norm": 81.5,
"learning_rate": 9.99126153846154e-07,
"loss": 135.8364,
"step": 4260
},
{
"epoch": 0.4484594871794872,
"grad_norm": 137.375,
"learning_rate": 9.991241025641024e-07,
"loss": 133.487,
"step": 4270
},
{
"epoch": 0.4495097435897436,
"grad_norm": 78.8125,
"learning_rate": 9.991220512820511e-07,
"loss": 134.1286,
"step": 4280
},
{
"epoch": 0.45056,
"grad_norm": 81.5,
"learning_rate": 9.9912e-07,
"loss": 133.8978,
"step": 4290
},
{
"epoch": 0.4516102564102564,
"grad_norm": 90.6875,
"learning_rate": 9.991179487179487e-07,
"loss": 135.2246,
"step": 4300
},
{
"epoch": 0.45266051282051284,
"grad_norm": 74.75,
"learning_rate": 9.991158974358974e-07,
"loss": 134.1289,
"step": 4310
},
{
"epoch": 0.45371076923076925,
"grad_norm": 72.625,
"learning_rate": 9.99113846153846e-07,
"loss": 135.7046,
"step": 4320
},
{
"epoch": 0.45476102564102566,
"grad_norm": 75.0,
"learning_rate": 9.991117948717948e-07,
"loss": 134.6371,
"step": 4330
},
{
"epoch": 0.4558112820512821,
"grad_norm": 73.125,
"learning_rate": 9.991097435897435e-07,
"loss": 134.274,
"step": 4340
},
{
"epoch": 0.4568615384615385,
"grad_norm": 73.25,
"learning_rate": 9.991076923076922e-07,
"loss": 134.0306,
"step": 4350
},
{
"epoch": 0.4579117948717949,
"grad_norm": 79.3125,
"learning_rate": 9.99105641025641e-07,
"loss": 135.0842,
"step": 4360
},
{
"epoch": 0.4589620512820513,
"grad_norm": 78.375,
"learning_rate": 9.991035897435896e-07,
"loss": 134.0684,
"step": 4370
},
{
"epoch": 0.46001230769230766,
"grad_norm": 77.375,
"learning_rate": 9.991015384615385e-07,
"loss": 135.4514,
"step": 4380
},
{
"epoch": 0.4610625641025641,
"grad_norm": 78.125,
"learning_rate": 9.990994871794872e-07,
"loss": 135.0359,
"step": 4390
},
{
"epoch": 0.4621128205128205,
"grad_norm": 71.4375,
"learning_rate": 9.990974358974359e-07,
"loss": 135.9999,
"step": 4400
},
{
"epoch": 0.4631630769230769,
"grad_norm": 76.125,
"learning_rate": 9.990953846153846e-07,
"loss": 135.3524,
"step": 4410
},
{
"epoch": 0.4642133333333333,
"grad_norm": 72.375,
"learning_rate": 9.990933333333332e-07,
"loss": 134.5182,
"step": 4420
},
{
"epoch": 0.4652635897435897,
"grad_norm": 75.6875,
"learning_rate": 9.99091282051282e-07,
"loss": 135.2036,
"step": 4430
},
{
"epoch": 0.46631384615384613,
"grad_norm": 74.0,
"learning_rate": 9.990892307692306e-07,
"loss": 135.2458,
"step": 4440
},
{
"epoch": 0.46736410256410255,
"grad_norm": 78.5625,
"learning_rate": 9.990871794871795e-07,
"loss": 135.9651,
"step": 4450
},
{
"epoch": 0.46841435897435896,
"grad_norm": 74.875,
"learning_rate": 9.990851282051282e-07,
"loss": 135.4157,
"step": 4460
},
{
"epoch": 0.46946461538461537,
"grad_norm": 80.125,
"learning_rate": 9.99083076923077e-07,
"loss": 134.8523,
"step": 4470
},
{
"epoch": 0.4705148717948718,
"grad_norm": 79.1875,
"learning_rate": 9.990810256410256e-07,
"loss": 134.8162,
"step": 4480
},
{
"epoch": 0.4715651282051282,
"grad_norm": 77.375,
"learning_rate": 9.990789743589743e-07,
"loss": 135.253,
"step": 4490
},
{
"epoch": 0.4726153846153846,
"grad_norm": 76.125,
"learning_rate": 9.99076923076923e-07,
"loss": 134.1781,
"step": 4500
},
{
"epoch": 0.473665641025641,
"grad_norm": 75.375,
"learning_rate": 9.990748717948717e-07,
"loss": 133.6803,
"step": 4510
},
{
"epoch": 0.4747158974358974,
"grad_norm": 75.0,
"learning_rate": 9.990728205128204e-07,
"loss": 134.4917,
"step": 4520
},
{
"epoch": 0.47576615384615384,
"grad_norm": 74.625,
"learning_rate": 9.99070769230769e-07,
"loss": 134.4515,
"step": 4530
},
{
"epoch": 0.47681641025641025,
"grad_norm": 73.25,
"learning_rate": 9.99068717948718e-07,
"loss": 134.1556,
"step": 4540
},
{
"epoch": 0.47786666666666666,
"grad_norm": 77.5,
"learning_rate": 9.990666666666667e-07,
"loss": 135.3948,
"step": 4550
},
{
"epoch": 0.4789169230769231,
"grad_norm": 83.5,
"learning_rate": 9.990646153846154e-07,
"loss": 135.5987,
"step": 4560
},
{
"epoch": 0.4799671794871795,
"grad_norm": 75.0625,
"learning_rate": 9.99062564102564e-07,
"loss": 135.1735,
"step": 4570
},
{
"epoch": 0.4810174358974359,
"grad_norm": 77.5625,
"learning_rate": 9.990605128205128e-07,
"loss": 134.6337,
"step": 4580
},
{
"epoch": 0.4820676923076923,
"grad_norm": 77.8125,
"learning_rate": 9.990584615384615e-07,
"loss": 136.2858,
"step": 4590
},
{
"epoch": 0.4831179487179487,
"grad_norm": 80.4375,
"learning_rate": 9.990564102564102e-07,
"loss": 135.1227,
"step": 4600
},
{
"epoch": 0.48416820512820513,
"grad_norm": 75.5625,
"learning_rate": 9.99054358974359e-07,
"loss": 134.9417,
"step": 4610
},
{
"epoch": 0.48521846153846154,
"grad_norm": 77.8125,
"learning_rate": 9.990523076923075e-07,
"loss": 133.6081,
"step": 4620
},
{
"epoch": 0.48626871794871795,
"grad_norm": 79.25,
"learning_rate": 9.990502564102565e-07,
"loss": 134.3238,
"step": 4630
},
{
"epoch": 0.48731897435897437,
"grad_norm": 73.4375,
"learning_rate": 9.990482051282051e-07,
"loss": 133.9954,
"step": 4640
},
{
"epoch": 0.4883692307692308,
"grad_norm": 73.4375,
"learning_rate": 9.990461538461538e-07,
"loss": 134.8811,
"step": 4650
},
{
"epoch": 0.4894194871794872,
"grad_norm": 76.5625,
"learning_rate": 9.990441025641025e-07,
"loss": 134.8447,
"step": 4660
},
{
"epoch": 0.4904697435897436,
"grad_norm": 76.3125,
"learning_rate": 9.990420512820512e-07,
"loss": 132.7166,
"step": 4670
},
{
"epoch": 0.49152,
"grad_norm": 75.5625,
"learning_rate": 9.9904e-07,
"loss": 134.4517,
"step": 4680
},
{
"epoch": 0.4925702564102564,
"grad_norm": 73.8125,
"learning_rate": 9.990379487179486e-07,
"loss": 136.0681,
"step": 4690
},
{
"epoch": 0.49362051282051284,
"grad_norm": 78.9375,
"learning_rate": 9.990358974358975e-07,
"loss": 134.9556,
"step": 4700
},
{
"epoch": 0.49467076923076925,
"grad_norm": 68.75,
"learning_rate": 9.990338461538462e-07,
"loss": 136.2311,
"step": 4710
},
{
"epoch": 0.49572102564102566,
"grad_norm": 75.4375,
"learning_rate": 9.990317948717947e-07,
"loss": 135.2467,
"step": 4720
},
{
"epoch": 0.49677128205128207,
"grad_norm": 83.5625,
"learning_rate": 9.990297435897436e-07,
"loss": 133.9345,
"step": 4730
},
{
"epoch": 0.4978215384615385,
"grad_norm": 75.625,
"learning_rate": 9.990276923076923e-07,
"loss": 133.6037,
"step": 4740
},
{
"epoch": 0.4988717948717949,
"grad_norm": 72.875,
"learning_rate": 9.99025641025641e-07,
"loss": 135.1181,
"step": 4750
},
{
"epoch": 0.4999220512820513,
"grad_norm": 76.6875,
"learning_rate": 9.990235897435897e-07,
"loss": 135.0438,
"step": 4760
},
{
"epoch": 0.5009723076923077,
"grad_norm": 75.625,
"learning_rate": 9.990215384615384e-07,
"loss": 135.5069,
"step": 4770
},
{
"epoch": 0.5020225641025641,
"grad_norm": 79.875,
"learning_rate": 9.99019487179487e-07,
"loss": 135.4686,
"step": 4780
},
{
"epoch": 0.5030728205128205,
"grad_norm": 77.1875,
"learning_rate": 9.990174358974358e-07,
"loss": 132.4513,
"step": 4790
},
{
"epoch": 0.5041230769230769,
"grad_norm": 72.0625,
"learning_rate": 9.990153846153847e-07,
"loss": 133.8345,
"step": 4800
},
{
"epoch": 0.5051733333333334,
"grad_norm": 80.8125,
"learning_rate": 9.990133333333334e-07,
"loss": 134.3062,
"step": 4810
},
{
"epoch": 0.5062235897435897,
"grad_norm": 76.9375,
"learning_rate": 9.99011282051282e-07,
"loss": 134.9275,
"step": 4820
},
{
"epoch": 0.5072738461538462,
"grad_norm": 77.4375,
"learning_rate": 9.990092307692308e-07,
"loss": 133.0396,
"step": 4830
},
{
"epoch": 0.5083241025641025,
"grad_norm": 80.5,
"learning_rate": 9.990071794871795e-07,
"loss": 133.6458,
"step": 4840
},
{
"epoch": 0.509374358974359,
"grad_norm": 80.9375,
"learning_rate": 9.990051282051281e-07,
"loss": 134.5248,
"step": 4850
},
{
"epoch": 0.5104246153846154,
"grad_norm": 78.625,
"learning_rate": 9.990030769230768e-07,
"loss": 134.9512,
"step": 4860
},
{
"epoch": 0.5114748717948718,
"grad_norm": 75.9375,
"learning_rate": 9.990010256410255e-07,
"loss": 135.7238,
"step": 4870
},
{
"epoch": 0.5125251282051282,
"grad_norm": 75.1875,
"learning_rate": 9.989989743589742e-07,
"loss": 133.1803,
"step": 4880
},
{
"epoch": 0.5135753846153847,
"grad_norm": 76.1875,
"learning_rate": 9.989969230769231e-07,
"loss": 133.4545,
"step": 4890
},
{
"epoch": 0.514625641025641,
"grad_norm": 75.25,
"learning_rate": 9.989948717948718e-07,
"loss": 134.8201,
"step": 4900
},
{
"epoch": 0.5156758974358975,
"grad_norm": 73.9375,
"learning_rate": 9.989928205128205e-07,
"loss": 135.7624,
"step": 4910
},
{
"epoch": 0.5167261538461538,
"grad_norm": 75.0625,
"learning_rate": 9.989907692307692e-07,
"loss": 133.1574,
"step": 4920
},
{
"epoch": 0.5177764102564103,
"grad_norm": 73.6875,
"learning_rate": 9.98988717948718e-07,
"loss": 135.8609,
"step": 4930
},
{
"epoch": 0.5188266666666667,
"grad_norm": 70.6875,
"learning_rate": 9.989866666666666e-07,
"loss": 135.0993,
"step": 4940
},
{
"epoch": 0.5198769230769231,
"grad_norm": 74.0,
"learning_rate": 9.989846153846153e-07,
"loss": 134.2167,
"step": 4950
},
{
"epoch": 0.5209271794871795,
"grad_norm": 70.875,
"learning_rate": 9.989825641025642e-07,
"loss": 134.5762,
"step": 4960
},
{
"epoch": 0.521977435897436,
"grad_norm": 81.0625,
"learning_rate": 9.989805128205127e-07,
"loss": 133.4322,
"step": 4970
},
{
"epoch": 0.5230276923076923,
"grad_norm": 80.0,
"learning_rate": 9.989784615384616e-07,
"loss": 134.8409,
"step": 4980
},
{
"epoch": 0.5240779487179488,
"grad_norm": 77.5,
"learning_rate": 9.989764102564103e-07,
"loss": 133.8979,
"step": 4990
},
{
"epoch": 0.5251282051282051,
"grad_norm": 77.625,
"learning_rate": 9.98974358974359e-07,
"loss": 135.3786,
"step": 5000
},
{
"epoch": 0.5251282051282051,
"eval_loss": 2.1084959506988525,
"eval_runtime": 323.1466,
"eval_samples_per_second": 1547.288,
"eval_steps_per_second": 48.356,
"step": 5000
},
{
"epoch": 0.5261784615384615,
"grad_norm": 77.9375,
"learning_rate": 9.989723076923077e-07,
"loss": 135.7908,
"step": 5010
},
{
"epoch": 0.527228717948718,
"grad_norm": 76.875,
"learning_rate": 9.989702564102564e-07,
"loss": 133.9965,
"step": 5020
},
{
"epoch": 0.5282789743589743,
"grad_norm": 76.1875,
"learning_rate": 9.98968205128205e-07,
"loss": 136.395,
"step": 5030
},
{
"epoch": 0.5293292307692308,
"grad_norm": 80.4375,
"learning_rate": 9.989661538461538e-07,
"loss": 137.1353,
"step": 5040
},
{
"epoch": 0.5303794871794871,
"grad_norm": 79.6875,
"learning_rate": 9.989641025641027e-07,
"loss": 135.522,
"step": 5050
},
{
"epoch": 0.5314297435897436,
"grad_norm": 79.125,
"learning_rate": 9.989620512820511e-07,
"loss": 135.3318,
"step": 5060
},
{
"epoch": 0.53248,
"grad_norm": 79.4375,
"learning_rate": 9.989599999999998e-07,
"loss": 133.8391,
"step": 5070
},
{
"epoch": 0.5335302564102564,
"grad_norm": 80.8125,
"learning_rate": 9.989579487179487e-07,
"loss": 134.4684,
"step": 5080
},
{
"epoch": 0.5345805128205128,
"grad_norm": 73.375,
"learning_rate": 9.989558974358974e-07,
"loss": 135.565,
"step": 5090
},
{
"epoch": 0.5356307692307692,
"grad_norm": 77.0,
"learning_rate": 9.989538461538461e-07,
"loss": 134.9499,
"step": 5100
},
{
"epoch": 0.5366810256410256,
"grad_norm": 72.875,
"learning_rate": 9.989517948717948e-07,
"loss": 135.5963,
"step": 5110
},
{
"epoch": 0.5377312820512821,
"grad_norm": 80.4375,
"learning_rate": 9.989497435897435e-07,
"loss": 134.9717,
"step": 5120
},
{
"epoch": 0.5387815384615384,
"grad_norm": 76.9375,
"learning_rate": 9.989476923076922e-07,
"loss": 133.5198,
"step": 5130
},
{
"epoch": 0.5398317948717949,
"grad_norm": 79.125,
"learning_rate": 9.98945641025641e-07,
"loss": 134.2271,
"step": 5140
},
{
"epoch": 0.5408820512820512,
"grad_norm": 78.4375,
"learning_rate": 9.989435897435898e-07,
"loss": 135.2163,
"step": 5150
},
{
"epoch": 0.5419323076923077,
"grad_norm": 82.75,
"learning_rate": 9.989415384615383e-07,
"loss": 134.3486,
"step": 5160
},
{
"epoch": 0.5429825641025641,
"grad_norm": 75.5625,
"learning_rate": 9.989394871794872e-07,
"loss": 134.6154,
"step": 5170
},
{
"epoch": 0.5440328205128205,
"grad_norm": 76.8125,
"learning_rate": 9.989374358974359e-07,
"loss": 134.4962,
"step": 5180
},
{
"epoch": 0.5450830769230769,
"grad_norm": 76.3125,
"learning_rate": 9.989353846153846e-07,
"loss": 134.8321,
"step": 5190
},
{
"epoch": 0.5461333333333334,
"grad_norm": 76.125,
"learning_rate": 9.989333333333333e-07,
"loss": 134.5848,
"step": 5200
},
{
"epoch": 0.5471835897435897,
"grad_norm": 82.9375,
"learning_rate": 9.98931282051282e-07,
"loss": 135.8918,
"step": 5210
},
{
"epoch": 0.5482338461538462,
"grad_norm": 79.75,
"learning_rate": 9.989292307692307e-07,
"loss": 134.9434,
"step": 5220
},
{
"epoch": 0.5492841025641025,
"grad_norm": 79.0625,
"learning_rate": 9.989271794871794e-07,
"loss": 136.0459,
"step": 5230
},
{
"epoch": 0.550334358974359,
"grad_norm": 80.5625,
"learning_rate": 9.989251282051283e-07,
"loss": 134.0239,
"step": 5240
},
{
"epoch": 0.5513846153846154,
"grad_norm": 82.5625,
"learning_rate": 9.98923076923077e-07,
"loss": 135.3833,
"step": 5250
},
{
"epoch": 0.5524348717948718,
"grad_norm": 79.125,
"learning_rate": 9.989210256410257e-07,
"loss": 135.0751,
"step": 5260
},
{
"epoch": 0.5534851282051282,
"grad_norm": 91.125,
"learning_rate": 9.989189743589743e-07,
"loss": 134.6919,
"step": 5270
},
{
"epoch": 0.5545353846153847,
"grad_norm": 79.375,
"learning_rate": 9.98916923076923e-07,
"loss": 134.0143,
"step": 5280
},
{
"epoch": 0.555585641025641,
"grad_norm": 79.125,
"learning_rate": 9.989148717948717e-07,
"loss": 134.374,
"step": 5290
},
{
"epoch": 0.5566358974358975,
"grad_norm": 77.75,
"learning_rate": 9.989128205128204e-07,
"loss": 134.8326,
"step": 5300
},
{
"epoch": 0.5576861538461538,
"grad_norm": 79.25,
"learning_rate": 9.989107692307691e-07,
"loss": 134.68,
"step": 5310
},
{
"epoch": 0.5587364102564103,
"grad_norm": 82.1875,
"learning_rate": 9.989087179487178e-07,
"loss": 134.3108,
"step": 5320
},
{
"epoch": 0.5597866666666667,
"grad_norm": 74.0,
"learning_rate": 9.989066666666667e-07,
"loss": 134.6612,
"step": 5330
},
{
"epoch": 0.5608369230769231,
"grad_norm": 80.0,
"learning_rate": 9.989046153846154e-07,
"loss": 135.2691,
"step": 5340
},
{
"epoch": 0.5618871794871795,
"grad_norm": 73.875,
"learning_rate": 9.989025641025641e-07,
"loss": 134.7519,
"step": 5350
},
{
"epoch": 0.562937435897436,
"grad_norm": 75.3125,
"learning_rate": 9.989005128205128e-07,
"loss": 134.7679,
"step": 5360
},
{
"epoch": 0.5639876923076923,
"grad_norm": 82.3125,
"learning_rate": 9.988984615384615e-07,
"loss": 135.0176,
"step": 5370
},
{
"epoch": 0.5650379487179488,
"grad_norm": 78.4375,
"learning_rate": 9.988964102564102e-07,
"loss": 135.313,
"step": 5380
},
{
"epoch": 0.5660882051282051,
"grad_norm": 74.5,
"learning_rate": 9.988943589743589e-07,
"loss": 134.0978,
"step": 5390
},
{
"epoch": 0.5671384615384616,
"grad_norm": 71.375,
"learning_rate": 9.988923076923078e-07,
"loss": 134.1742,
"step": 5400
},
{
"epoch": 0.568188717948718,
"grad_norm": 74.75,
"learning_rate": 9.988902564102563e-07,
"loss": 134.1676,
"step": 5410
},
{
"epoch": 0.5692389743589744,
"grad_norm": 80.0,
"learning_rate": 9.98888205128205e-07,
"loss": 136.1296,
"step": 5420
},
{
"epoch": 0.5702892307692308,
"grad_norm": 72.25,
"learning_rate": 9.988861538461539e-07,
"loss": 135.4083,
"step": 5430
},
{
"epoch": 0.5713394871794871,
"grad_norm": 74.4375,
"learning_rate": 9.988841025641026e-07,
"loss": 136.1724,
"step": 5440
},
{
"epoch": 0.5723897435897436,
"grad_norm": 80.25,
"learning_rate": 9.988820512820513e-07,
"loss": 134.1989,
"step": 5450
},
{
"epoch": 0.57344,
"grad_norm": 83.0,
"learning_rate": 9.9888e-07,
"loss": 134.7482,
"step": 5460
},
{
"epoch": 0.5744902564102564,
"grad_norm": 75.75,
"learning_rate": 9.988779487179486e-07,
"loss": 134.8441,
"step": 5470
},
{
"epoch": 0.5755405128205128,
"grad_norm": 73.6875,
"learning_rate": 9.988758974358973e-07,
"loss": 133.2782,
"step": 5480
},
{
"epoch": 0.5765907692307692,
"grad_norm": 76.5625,
"learning_rate": 9.98873846153846e-07,
"loss": 132.6737,
"step": 5490
},
{
"epoch": 0.5776410256410256,
"grad_norm": 76.875,
"learning_rate": 9.98871794871795e-07,
"loss": 133.4861,
"step": 5500
},
{
"epoch": 0.5786912820512821,
"grad_norm": 77.625,
"learning_rate": 9.988697435897434e-07,
"loss": 135.5047,
"step": 5510
},
{
"epoch": 0.5797415384615384,
"grad_norm": 76.4375,
"learning_rate": 9.988676923076923e-07,
"loss": 135.0375,
"step": 5520
},
{
"epoch": 0.5807917948717949,
"grad_norm": 72.0,
"learning_rate": 9.98865641025641e-07,
"loss": 135.1532,
"step": 5530
},
{
"epoch": 0.5818420512820512,
"grad_norm": 76.8125,
"learning_rate": 9.988635897435897e-07,
"loss": 133.7135,
"step": 5540
},
{
"epoch": 0.5828923076923077,
"grad_norm": 77.625,
"learning_rate": 9.988615384615384e-07,
"loss": 134.7512,
"step": 5550
},
{
"epoch": 0.5839425641025641,
"grad_norm": 76.8125,
"learning_rate": 9.988594871794871e-07,
"loss": 133.1693,
"step": 5560
},
{
"epoch": 0.5849928205128205,
"grad_norm": 73.8125,
"learning_rate": 9.988574358974358e-07,
"loss": 134.1779,
"step": 5570
},
{
"epoch": 0.5860430769230769,
"grad_norm": 73.4375,
"learning_rate": 9.988553846153845e-07,
"loss": 134.0802,
"step": 5580
},
{
"epoch": 0.5870933333333334,
"grad_norm": 80.25,
"learning_rate": 9.988533333333334e-07,
"loss": 133.4755,
"step": 5590
},
{
"epoch": 0.5881435897435897,
"grad_norm": 75.5,
"learning_rate": 9.98851282051282e-07,
"loss": 133.0621,
"step": 5600
},
{
"epoch": 0.5891938461538462,
"grad_norm": 76.75,
"learning_rate": 9.988492307692308e-07,
"loss": 134.8084,
"step": 5610
},
{
"epoch": 0.5902441025641025,
"grad_norm": 80.5,
"learning_rate": 9.988471794871795e-07,
"loss": 134.011,
"step": 5620
},
{
"epoch": 0.591294358974359,
"grad_norm": 79.25,
"learning_rate": 9.988451282051282e-07,
"loss": 134.1596,
"step": 5630
},
{
"epoch": 0.5923446153846154,
"grad_norm": 79.1875,
"learning_rate": 9.988430769230769e-07,
"loss": 133.8143,
"step": 5640
},
{
"epoch": 0.5933948717948718,
"grad_norm": 78.1875,
"learning_rate": 9.988410256410256e-07,
"loss": 132.8301,
"step": 5650
},
{
"epoch": 0.5944451282051282,
"grad_norm": 81.4375,
"learning_rate": 9.988389743589743e-07,
"loss": 134.9465,
"step": 5660
},
{
"epoch": 0.5954953846153846,
"grad_norm": 75.8125,
"learning_rate": 9.98836923076923e-07,
"loss": 133.7755,
"step": 5670
},
{
"epoch": 0.596545641025641,
"grad_norm": 77.375,
"learning_rate": 9.988348717948719e-07,
"loss": 135.0217,
"step": 5680
},
{
"epoch": 0.5975958974358975,
"grad_norm": 78.625,
"learning_rate": 9.988328205128206e-07,
"loss": 133.1542,
"step": 5690
},
{
"epoch": 0.5986461538461538,
"grad_norm": 75.9375,
"learning_rate": 9.988307692307692e-07,
"loss": 133.7185,
"step": 5700
},
{
"epoch": 0.5996964102564103,
"grad_norm": 76.625,
"learning_rate": 9.98828717948718e-07,
"loss": 134.098,
"step": 5710
},
{
"epoch": 0.6007466666666667,
"grad_norm": 80.0,
"learning_rate": 9.988266666666666e-07,
"loss": 135.2549,
"step": 5720
},
{
"epoch": 0.6017969230769231,
"grad_norm": 74.375,
"learning_rate": 9.988246153846153e-07,
"loss": 133.9132,
"step": 5730
},
{
"epoch": 0.6028471794871795,
"grad_norm": 72.75,
"learning_rate": 9.98822564102564e-07,
"loss": 133.688,
"step": 5740
},
{
"epoch": 0.6038974358974359,
"grad_norm": 74.4375,
"learning_rate": 9.98820512820513e-07,
"loss": 134.2703,
"step": 5750
},
{
"epoch": 0.6049476923076923,
"grad_norm": 84.625,
"learning_rate": 9.988184615384614e-07,
"loss": 136.125,
"step": 5760
},
{
"epoch": 0.6059979487179488,
"grad_norm": 76.8125,
"learning_rate": 9.9881641025641e-07,
"loss": 134.1665,
"step": 5770
},
{
"epoch": 0.6070482051282051,
"grad_norm": 76.625,
"learning_rate": 9.98814358974359e-07,
"loss": 134.8555,
"step": 5780
},
{
"epoch": 0.6080984615384616,
"grad_norm": 76.625,
"learning_rate": 9.988123076923077e-07,
"loss": 133.6014,
"step": 5790
},
{
"epoch": 0.6091487179487179,
"grad_norm": 74.25,
"learning_rate": 9.988102564102564e-07,
"loss": 133.9827,
"step": 5800
},
{
"epoch": 0.6101989743589744,
"grad_norm": 77.3125,
"learning_rate": 9.98808205128205e-07,
"loss": 133.2115,
"step": 5810
},
{
"epoch": 0.6112492307692308,
"grad_norm": 73.9375,
"learning_rate": 9.988061538461538e-07,
"loss": 133.0385,
"step": 5820
},
{
"epoch": 0.6122994871794872,
"grad_norm": 79.625,
"learning_rate": 9.988041025641025e-07,
"loss": 132.0571,
"step": 5830
},
{
"epoch": 0.6133497435897436,
"grad_norm": 73.9375,
"learning_rate": 9.988020512820512e-07,
"loss": 133.794,
"step": 5840
},
{
"epoch": 0.6144,
"grad_norm": 79.125,
"learning_rate": 9.988e-07,
"loss": 132.8695,
"step": 5850
},
{
"epoch": 0.6154502564102564,
"grad_norm": 77.25,
"learning_rate": 9.987979487179486e-07,
"loss": 133.7304,
"step": 5860
},
{
"epoch": 0.6165005128205128,
"grad_norm": 79.5,
"learning_rate": 9.987958974358975e-07,
"loss": 133.9512,
"step": 5870
},
{
"epoch": 0.6175507692307692,
"grad_norm": 75.9375,
"learning_rate": 9.987938461538462e-07,
"loss": 135.2929,
"step": 5880
},
{
"epoch": 0.6186010256410256,
"grad_norm": 83.3125,
"learning_rate": 9.987917948717949e-07,
"loss": 135.2723,
"step": 5890
},
{
"epoch": 0.6196512820512821,
"grad_norm": 74.0625,
"learning_rate": 9.987897435897435e-07,
"loss": 135.1879,
"step": 5900
},
{
"epoch": 0.6207015384615384,
"grad_norm": 76.75,
"learning_rate": 9.987876923076922e-07,
"loss": 134.8009,
"step": 5910
},
{
"epoch": 0.6217517948717949,
"grad_norm": 82.5,
"learning_rate": 9.98785641025641e-07,
"loss": 135.7849,
"step": 5920
},
{
"epoch": 0.6228020512820512,
"grad_norm": 74.4375,
"learning_rate": 9.987835897435896e-07,
"loss": 134.5044,
"step": 5930
},
{
"epoch": 0.6238523076923077,
"grad_norm": 80.0,
"learning_rate": 9.987815384615385e-07,
"loss": 133.4429,
"step": 5940
},
{
"epoch": 0.6249025641025641,
"grad_norm": 85.625,
"learning_rate": 9.987794871794872e-07,
"loss": 133.1182,
"step": 5950
},
{
"epoch": 0.6259528205128205,
"grad_norm": 77.0625,
"learning_rate": 9.98777435897436e-07,
"loss": 133.511,
"step": 5960
},
{
"epoch": 0.6270030769230769,
"grad_norm": 80.125,
"learning_rate": 9.987753846153846e-07,
"loss": 134.8845,
"step": 5970
},
{
"epoch": 0.6280533333333334,
"grad_norm": 69.9375,
"learning_rate": 9.987733333333333e-07,
"loss": 133.8227,
"step": 5980
},
{
"epoch": 0.6291035897435897,
"grad_norm": 75.5625,
"learning_rate": 9.98771282051282e-07,
"loss": 134.4892,
"step": 5990
},
{
"epoch": 0.6301538461538462,
"grad_norm": 72.125,
"learning_rate": 9.987692307692307e-07,
"loss": 135.4582,
"step": 6000
},
{
"epoch": 0.6312041025641025,
"grad_norm": 75.625,
"learning_rate": 9.987671794871794e-07,
"loss": 135.2013,
"step": 6010
},
{
"epoch": 0.632254358974359,
"grad_norm": 74.0625,
"learning_rate": 9.98765128205128e-07,
"loss": 134.8731,
"step": 6020
},
{
"epoch": 0.6333046153846154,
"grad_norm": 82.6875,
"learning_rate": 9.98763076923077e-07,
"loss": 135.0607,
"step": 6030
},
{
"epoch": 0.6343548717948718,
"grad_norm": 79.75,
"learning_rate": 9.987610256410257e-07,
"loss": 134.0427,
"step": 6040
},
{
"epoch": 0.6354051282051282,
"grad_norm": 75.4375,
"learning_rate": 9.987589743589742e-07,
"loss": 133.6469,
"step": 6050
},
{
"epoch": 0.6364553846153846,
"grad_norm": 77.6875,
"learning_rate": 9.98756923076923e-07,
"loss": 133.951,
"step": 6060
},
{
"epoch": 0.637505641025641,
"grad_norm": 74.1875,
"learning_rate": 9.987548717948718e-07,
"loss": 134.3955,
"step": 6070
},
{
"epoch": 0.6385558974358975,
"grad_norm": 80.3125,
"learning_rate": 9.987528205128205e-07,
"loss": 133.7433,
"step": 6080
},
{
"epoch": 0.6396061538461538,
"grad_norm": 75.8125,
"learning_rate": 9.987507692307692e-07,
"loss": 132.4955,
"step": 6090
},
{
"epoch": 0.6406564102564103,
"grad_norm": 80.125,
"learning_rate": 9.98748717948718e-07,
"loss": 133.3074,
"step": 6100
},
{
"epoch": 0.6417066666666666,
"grad_norm": 75.75,
"learning_rate": 9.987466666666665e-07,
"loss": 134.3473,
"step": 6110
},
{
"epoch": 0.6427569230769231,
"grad_norm": 77.625,
"learning_rate": 9.987446153846152e-07,
"loss": 134.2209,
"step": 6120
},
{
"epoch": 0.6438071794871795,
"grad_norm": 75.375,
"learning_rate": 9.987425641025641e-07,
"loss": 136.051,
"step": 6130
},
{
"epoch": 0.6448574358974359,
"grad_norm": 78.625,
"learning_rate": 9.987405128205128e-07,
"loss": 133.6452,
"step": 6140
},
{
"epoch": 0.6459076923076923,
"grad_norm": 72.875,
"learning_rate": 9.987384615384615e-07,
"loss": 135.9148,
"step": 6150
},
{
"epoch": 0.6469579487179488,
"grad_norm": 79.9375,
"learning_rate": 9.987364102564102e-07,
"loss": 133.9573,
"step": 6160
},
{
"epoch": 0.6480082051282051,
"grad_norm": 77.375,
"learning_rate": 9.98734358974359e-07,
"loss": 134.187,
"step": 6170
},
{
"epoch": 0.6490584615384616,
"grad_norm": 77.6875,
"learning_rate": 9.987323076923076e-07,
"loss": 135.4981,
"step": 6180
},
{
"epoch": 0.6501087179487179,
"grad_norm": 76.375,
"learning_rate": 9.987302564102563e-07,
"loss": 134.0596,
"step": 6190
},
{
"epoch": 0.6511589743589744,
"grad_norm": 68.75,
"learning_rate": 9.98728205128205e-07,
"loss": 133.4401,
"step": 6200
},
{
"epoch": 0.6522092307692308,
"grad_norm": 88.0,
"learning_rate": 9.987261538461537e-07,
"loss": 133.9623,
"step": 6210
},
{
"epoch": 0.6532594871794872,
"grad_norm": 73.125,
"learning_rate": 9.987241025641026e-07,
"loss": 134.9918,
"step": 6220
},
{
"epoch": 0.6543097435897436,
"grad_norm": 79.6875,
"learning_rate": 9.987220512820513e-07,
"loss": 134.2293,
"step": 6230
},
{
"epoch": 0.65536,
"grad_norm": 79.125,
"learning_rate": 9.9872e-07,
"loss": 134.9116,
"step": 6240
},
{
"epoch": 0.6564102564102564,
"grad_norm": 74.0625,
"learning_rate": 9.987179487179487e-07,
"loss": 133.4889,
"step": 6250
},
{
"epoch": 0.6574605128205128,
"grad_norm": 74.0,
"learning_rate": 9.987158974358974e-07,
"loss": 133.3706,
"step": 6260
},
{
"epoch": 0.6585107692307692,
"grad_norm": 73.5625,
"learning_rate": 9.98713846153846e-07,
"loss": 134.6084,
"step": 6270
},
{
"epoch": 0.6595610256410256,
"grad_norm": 76.8125,
"learning_rate": 9.987117948717948e-07,
"loss": 133.7456,
"step": 6280
},
{
"epoch": 0.6606112820512821,
"grad_norm": 77.625,
"learning_rate": 9.987097435897437e-07,
"loss": 133.8633,
"step": 6290
},
{
"epoch": 0.6616615384615384,
"grad_norm": 76.625,
"learning_rate": 9.987076923076921e-07,
"loss": 133.3514,
"step": 6300
},
{
"epoch": 0.6627117948717949,
"grad_norm": 78.6875,
"learning_rate": 9.98705641025641e-07,
"loss": 133.0192,
"step": 6310
},
{
"epoch": 0.6637620512820512,
"grad_norm": 76.375,
"learning_rate": 9.987035897435897e-07,
"loss": 135.2725,
"step": 6320
},
{
"epoch": 0.6648123076923077,
"grad_norm": 75.25,
"learning_rate": 9.987015384615384e-07,
"loss": 133.7453,
"step": 6330
},
{
"epoch": 0.6658625641025641,
"grad_norm": 76.0625,
"learning_rate": 9.986994871794871e-07,
"loss": 134.4162,
"step": 6340
},
{
"epoch": 0.6669128205128205,
"grad_norm": 77.3125,
"learning_rate": 9.986974358974358e-07,
"loss": 133.5715,
"step": 6350
},
{
"epoch": 0.6679630769230769,
"grad_norm": 79.375,
"learning_rate": 9.986953846153845e-07,
"loss": 133.915,
"step": 6360
},
{
"epoch": 0.6690133333333333,
"grad_norm": 76.0,
"learning_rate": 9.986933333333332e-07,
"loss": 134.2913,
"step": 6370
},
{
"epoch": 0.6700635897435897,
"grad_norm": 80.0,
"learning_rate": 9.986912820512821e-07,
"loss": 135.7478,
"step": 6380
},
{
"epoch": 0.6711138461538462,
"grad_norm": 81.0625,
"learning_rate": 9.986892307692308e-07,
"loss": 135.2542,
"step": 6390
},
{
"epoch": 0.6721641025641025,
"grad_norm": 73.3125,
"learning_rate": 9.986871794871793e-07,
"loss": 133.8043,
"step": 6400
},
{
"epoch": 0.673214358974359,
"grad_norm": 74.9375,
"learning_rate": 9.986851282051282e-07,
"loss": 132.8474,
"step": 6410
},
{
"epoch": 0.6742646153846154,
"grad_norm": 78.5625,
"learning_rate": 9.98683076923077e-07,
"loss": 133.1841,
"step": 6420
},
{
"epoch": 0.6753148717948718,
"grad_norm": 81.8125,
"learning_rate": 9.986810256410256e-07,
"loss": 132.1895,
"step": 6430
},
{
"epoch": 0.6763651282051282,
"grad_norm": 79.6875,
"learning_rate": 9.986789743589743e-07,
"loss": 133.3178,
"step": 6440
},
{
"epoch": 0.6774153846153846,
"grad_norm": 77.9375,
"learning_rate": 9.98676923076923e-07,
"loss": 134.5587,
"step": 6450
},
{
"epoch": 0.678465641025641,
"grad_norm": 76.75,
"learning_rate": 9.986748717948717e-07,
"loss": 133.5905,
"step": 6460
},
{
"epoch": 0.6795158974358975,
"grad_norm": 74.0,
"learning_rate": 9.986728205128204e-07,
"loss": 133.0102,
"step": 6470
},
{
"epoch": 0.6805661538461538,
"grad_norm": 85.0,
"learning_rate": 9.986707692307693e-07,
"loss": 135.4808,
"step": 6480
},
{
"epoch": 0.6816164102564103,
"grad_norm": 82.0625,
"learning_rate": 9.98668717948718e-07,
"loss": 133.2434,
"step": 6490
},
{
"epoch": 0.6826666666666666,
"grad_norm": 73.1875,
"learning_rate": 9.986666666666667e-07,
"loss": 134.3713,
"step": 6500
},
{
"epoch": 0.6837169230769231,
"grad_norm": 75.9375,
"learning_rate": 9.986646153846154e-07,
"loss": 134.012,
"step": 6510
},
{
"epoch": 0.6847671794871795,
"grad_norm": 77.5,
"learning_rate": 9.98662564102564e-07,
"loss": 134.6316,
"step": 6520
},
{
"epoch": 0.6858174358974359,
"grad_norm": 79.9375,
"learning_rate": 9.986605128205127e-07,
"loss": 134.4724,
"step": 6530
},
{
"epoch": 0.6868676923076923,
"grad_norm": 73.0,
"learning_rate": 9.986584615384614e-07,
"loss": 133.8849,
"step": 6540
},
{
"epoch": 0.6879179487179488,
"grad_norm": 74.3125,
"learning_rate": 9.986564102564101e-07,
"loss": 135.4998,
"step": 6550
},
{
"epoch": 0.6889682051282051,
"grad_norm": 82.0,
"learning_rate": 9.986543589743588e-07,
"loss": 134.5724,
"step": 6560
},
{
"epoch": 0.6900184615384616,
"grad_norm": 77.625,
"learning_rate": 9.986523076923077e-07,
"loss": 134.0957,
"step": 6570
},
{
"epoch": 0.6910687179487179,
"grad_norm": 73.5,
"learning_rate": 9.986502564102564e-07,
"loss": 133.3827,
"step": 6580
},
{
"epoch": 0.6921189743589744,
"grad_norm": 73.625,
"learning_rate": 9.986482051282051e-07,
"loss": 134.7083,
"step": 6590
},
{
"epoch": 0.6931692307692308,
"grad_norm": 81.1875,
"learning_rate": 9.986461538461538e-07,
"loss": 134.4949,
"step": 6600
},
{
"epoch": 0.6942194871794872,
"grad_norm": 74.8125,
"learning_rate": 9.986441025641025e-07,
"loss": 133.9215,
"step": 6610
},
{
"epoch": 0.6952697435897436,
"grad_norm": 76.5,
"learning_rate": 9.986420512820512e-07,
"loss": 134.7131,
"step": 6620
},
{
"epoch": 0.69632,
"grad_norm": 74.1875,
"learning_rate": 9.9864e-07,
"loss": 132.6291,
"step": 6630
},
{
"epoch": 0.6973702564102564,
"grad_norm": 76.375,
"learning_rate": 9.986379487179488e-07,
"loss": 133.4663,
"step": 6640
},
{
"epoch": 0.6984205128205129,
"grad_norm": 76.6875,
"learning_rate": 9.986358974358973e-07,
"loss": 133.2238,
"step": 6650
},
{
"epoch": 0.6994707692307692,
"grad_norm": 75.4375,
"learning_rate": 9.986338461538462e-07,
"loss": 135.6267,
"step": 6660
},
{
"epoch": 0.7005210256410257,
"grad_norm": 76.5625,
"learning_rate": 9.986317948717949e-07,
"loss": 133.9723,
"step": 6670
},
{
"epoch": 0.701571282051282,
"grad_norm": 75.5,
"learning_rate": 9.986297435897436e-07,
"loss": 132.1382,
"step": 6680
},
{
"epoch": 0.7026215384615384,
"grad_norm": 75.375,
"learning_rate": 9.986276923076923e-07,
"loss": 132.8579,
"step": 6690
},
{
"epoch": 0.7036717948717949,
"grad_norm": 76.3125,
"learning_rate": 9.98625641025641e-07,
"loss": 133.7719,
"step": 6700
},
{
"epoch": 0.7047220512820512,
"grad_norm": 81.0625,
"learning_rate": 9.986235897435897e-07,
"loss": 135.3735,
"step": 6710
},
{
"epoch": 0.7057723076923077,
"grad_norm": 75.75,
"learning_rate": 9.986215384615384e-07,
"loss": 132.8083,
"step": 6720
},
{
"epoch": 0.706822564102564,
"grad_norm": 74.8125,
"learning_rate": 9.986194871794873e-07,
"loss": 133.2499,
"step": 6730
},
{
"epoch": 0.7078728205128205,
"grad_norm": 74.375,
"learning_rate": 9.98617435897436e-07,
"loss": 133.904,
"step": 6740
},
{
"epoch": 0.7089230769230769,
"grad_norm": 71.25,
"learning_rate": 9.986153846153844e-07,
"loss": 134.7248,
"step": 6750
},
{
"epoch": 0.7099733333333333,
"grad_norm": 78.4375,
"learning_rate": 9.986133333333333e-07,
"loss": 134.4564,
"step": 6760
},
{
"epoch": 0.7110235897435897,
"grad_norm": 87.3125,
"learning_rate": 9.98611282051282e-07,
"loss": 132.3151,
"step": 6770
},
{
"epoch": 0.7120738461538462,
"grad_norm": 73.0625,
"learning_rate": 9.986092307692307e-07,
"loss": 133.7481,
"step": 6780
},
{
"epoch": 0.7131241025641025,
"grad_norm": 73.0,
"learning_rate": 9.986071794871794e-07,
"loss": 133.2306,
"step": 6790
},
{
"epoch": 0.714174358974359,
"grad_norm": 74.6875,
"learning_rate": 9.986051282051281e-07,
"loss": 133.5443,
"step": 6800
},
{
"epoch": 0.7152246153846153,
"grad_norm": 73.4375,
"learning_rate": 9.986030769230768e-07,
"loss": 133.3841,
"step": 6810
},
{
"epoch": 0.7162748717948718,
"grad_norm": 73.9375,
"learning_rate": 9.986010256410255e-07,
"loss": 135.036,
"step": 6820
},
{
"epoch": 0.7173251282051282,
"grad_norm": 83.9375,
"learning_rate": 9.985989743589744e-07,
"loss": 134.1337,
"step": 6830
},
{
"epoch": 0.7183753846153846,
"grad_norm": 78.1875,
"learning_rate": 9.98596923076923e-07,
"loss": 133.3089,
"step": 6840
},
{
"epoch": 0.719425641025641,
"grad_norm": 76.875,
"learning_rate": 9.985948717948718e-07,
"loss": 133.6665,
"step": 6850
},
{
"epoch": 0.7204758974358975,
"grad_norm": 74.125,
"learning_rate": 9.985928205128205e-07,
"loss": 133.7026,
"step": 6860
},
{
"epoch": 0.7215261538461538,
"grad_norm": 78.4375,
"learning_rate": 9.985907692307692e-07,
"loss": 133.7467,
"step": 6870
},
{
"epoch": 0.7225764102564103,
"grad_norm": 73.1875,
"learning_rate": 9.985887179487179e-07,
"loss": 133.6408,
"step": 6880
},
{
"epoch": 0.7236266666666666,
"grad_norm": 77.0625,
"learning_rate": 9.985866666666666e-07,
"loss": 132.6118,
"step": 6890
},
{
"epoch": 0.7246769230769231,
"grad_norm": 76.0625,
"learning_rate": 9.985846153846153e-07,
"loss": 132.8741,
"step": 6900
},
{
"epoch": 0.7257271794871795,
"grad_norm": 73.5625,
"learning_rate": 9.98582564102564e-07,
"loss": 134.1753,
"step": 6910
},
{
"epoch": 0.7267774358974359,
"grad_norm": 76.875,
"learning_rate": 9.985805128205129e-07,
"loss": 132.842,
"step": 6920
},
{
"epoch": 0.7278276923076923,
"grad_norm": 70.0,
"learning_rate": 9.985784615384616e-07,
"loss": 134.3394,
"step": 6930
},
{
"epoch": 0.7288779487179488,
"grad_norm": 74.0625,
"learning_rate": 9.985764102564103e-07,
"loss": 135.2059,
"step": 6940
},
{
"epoch": 0.7299282051282051,
"grad_norm": 78.625,
"learning_rate": 9.98574358974359e-07,
"loss": 134.0309,
"step": 6950
},
{
"epoch": 0.7309784615384616,
"grad_norm": 77.75,
"learning_rate": 9.985723076923076e-07,
"loss": 134.4309,
"step": 6960
},
{
"epoch": 0.7320287179487179,
"grad_norm": 74.6875,
"learning_rate": 9.985702564102563e-07,
"loss": 134.0655,
"step": 6970
},
{
"epoch": 0.7330789743589744,
"grad_norm": 71.1875,
"learning_rate": 9.98568205128205e-07,
"loss": 134.798,
"step": 6980
},
{
"epoch": 0.7341292307692308,
"grad_norm": 80.25,
"learning_rate": 9.98566153846154e-07,
"loss": 133.176,
"step": 6990
},
{
"epoch": 0.7351794871794872,
"grad_norm": 77.3125,
"learning_rate": 9.985641025641024e-07,
"loss": 133.7738,
"step": 7000
},
{
"epoch": 0.7362297435897436,
"grad_norm": 73.4375,
"learning_rate": 9.985620512820513e-07,
"loss": 133.5852,
"step": 7010
},
{
"epoch": 0.73728,
"grad_norm": 82.125,
"learning_rate": 9.9856e-07,
"loss": 133.2783,
"step": 7020
},
{
"epoch": 0.7383302564102564,
"grad_norm": 78.0625,
"learning_rate": 9.985579487179487e-07,
"loss": 133.2677,
"step": 7030
},
{
"epoch": 0.7393805128205129,
"grad_norm": 78.5,
"learning_rate": 9.985558974358974e-07,
"loss": 133.9121,
"step": 7040
},
{
"epoch": 0.7404307692307692,
"grad_norm": 78.875,
"learning_rate": 9.98553846153846e-07,
"loss": 133.3367,
"step": 7050
},
{
"epoch": 0.7414810256410257,
"grad_norm": 77.8125,
"learning_rate": 9.985517948717948e-07,
"loss": 132.6513,
"step": 7060
},
{
"epoch": 0.742531282051282,
"grad_norm": 73.0,
"learning_rate": 9.985497435897435e-07,
"loss": 135.524,
"step": 7070
},
{
"epoch": 0.7435815384615385,
"grad_norm": 74.6875,
"learning_rate": 9.985476923076924e-07,
"loss": 132.8569,
"step": 7080
},
{
"epoch": 0.7446317948717949,
"grad_norm": 71.25,
"learning_rate": 9.98545641025641e-07,
"loss": 132.9906,
"step": 7090
},
{
"epoch": 0.7456820512820512,
"grad_norm": 75.4375,
"learning_rate": 9.985435897435896e-07,
"loss": 134.611,
"step": 7100
},
{
"epoch": 0.7467323076923077,
"grad_norm": 76.0625,
"learning_rate": 9.985415384615385e-07,
"loss": 135.1841,
"step": 7110
},
{
"epoch": 0.747782564102564,
"grad_norm": 80.25,
"learning_rate": 9.985394871794872e-07,
"loss": 132.8851,
"step": 7120
},
{
"epoch": 0.7488328205128205,
"grad_norm": 77.875,
"learning_rate": 9.985374358974359e-07,
"loss": 132.9889,
"step": 7130
},
{
"epoch": 0.7498830769230769,
"grad_norm": 74.375,
"learning_rate": 9.985353846153846e-07,
"loss": 134.75,
"step": 7140
},
{
"epoch": 0.7509333333333333,
"grad_norm": 77.6875,
"learning_rate": 9.985333333333332e-07,
"loss": 131.8883,
"step": 7150
},
{
"epoch": 0.7519835897435897,
"grad_norm": 71.5,
"learning_rate": 9.98531282051282e-07,
"loss": 132.9914,
"step": 7160
},
{
"epoch": 0.7530338461538462,
"grad_norm": 77.4375,
"learning_rate": 9.985292307692306e-07,
"loss": 133.2398,
"step": 7170
},
{
"epoch": 0.7540841025641025,
"grad_norm": 79.1875,
"learning_rate": 9.985271794871795e-07,
"loss": 133.4467,
"step": 7180
},
{
"epoch": 0.755134358974359,
"grad_norm": 79.375,
"learning_rate": 9.985251282051282e-07,
"loss": 134.8063,
"step": 7190
},
{
"epoch": 0.7561846153846153,
"grad_norm": 75.3125,
"learning_rate": 9.98523076923077e-07,
"loss": 133.1698,
"step": 7200
},
{
"epoch": 0.7572348717948718,
"grad_norm": 73.5625,
"learning_rate": 9.985210256410256e-07,
"loss": 133.0102,
"step": 7210
},
{
"epoch": 0.7582851282051282,
"grad_norm": 71.75,
"learning_rate": 9.985189743589743e-07,
"loss": 134.511,
"step": 7220
},
{
"epoch": 0.7593353846153846,
"grad_norm": 85.5,
"learning_rate": 9.98516923076923e-07,
"loss": 134.3958,
"step": 7230
},
{
"epoch": 0.760385641025641,
"grad_norm": 87.5625,
"learning_rate": 9.985148717948717e-07,
"loss": 134.2493,
"step": 7240
},
{
"epoch": 0.7614358974358975,
"grad_norm": 82.25,
"learning_rate": 9.985128205128204e-07,
"loss": 133.0641,
"step": 7250
},
{
"epoch": 0.7624861538461538,
"grad_norm": 82.25,
"learning_rate": 9.98510769230769e-07,
"loss": 134.3485,
"step": 7260
},
{
"epoch": 0.7635364102564103,
"grad_norm": 79.1875,
"learning_rate": 9.98508717948718e-07,
"loss": 134.2047,
"step": 7270
},
{
"epoch": 0.7645866666666666,
"grad_norm": 84.0625,
"learning_rate": 9.985066666666667e-07,
"loss": 133.9074,
"step": 7280
},
{
"epoch": 0.7656369230769231,
"grad_norm": 75.875,
"learning_rate": 9.985046153846154e-07,
"loss": 132.4027,
"step": 7290
},
{
"epoch": 0.7666871794871795,
"grad_norm": 79.6875,
"learning_rate": 9.98502564102564e-07,
"loss": 132.4265,
"step": 7300
},
{
"epoch": 0.7677374358974359,
"grad_norm": 75.6875,
"learning_rate": 9.985005128205128e-07,
"loss": 132.4591,
"step": 7310
},
{
"epoch": 0.7687876923076923,
"grad_norm": 70.75,
"learning_rate": 9.984984615384615e-07,
"loss": 133.4718,
"step": 7320
},
{
"epoch": 0.7698379487179488,
"grad_norm": 74.3125,
"learning_rate": 9.984964102564102e-07,
"loss": 132.798,
"step": 7330
},
{
"epoch": 0.7708882051282051,
"grad_norm": 76.4375,
"learning_rate": 9.98494358974359e-07,
"loss": 133.6705,
"step": 7340
},
{
"epoch": 0.7719384615384616,
"grad_norm": 81.125,
"learning_rate": 9.984923076923076e-07,
"loss": 132.7228,
"step": 7350
},
{
"epoch": 0.7729887179487179,
"grad_norm": 75.0,
"learning_rate": 9.984902564102565e-07,
"loss": 133.0821,
"step": 7360
},
{
"epoch": 0.7740389743589744,
"grad_norm": 80.625,
"learning_rate": 9.984882051282051e-07,
"loss": 132.362,
"step": 7370
},
{
"epoch": 0.7750892307692308,
"grad_norm": 74.6875,
"learning_rate": 9.984861538461538e-07,
"loss": 133.2498,
"step": 7380
},
{
"epoch": 0.7761394871794872,
"grad_norm": 78.5,
"learning_rate": 9.984841025641025e-07,
"loss": 134.545,
"step": 7390
},
{
"epoch": 0.7771897435897436,
"grad_norm": 82.625,
"learning_rate": 9.984820512820512e-07,
"loss": 135.3461,
"step": 7400
},
{
"epoch": 0.77824,
"grad_norm": 80.8125,
"learning_rate": 9.9848e-07,
"loss": 133.5678,
"step": 7410
},
{
"epoch": 0.7792902564102564,
"grad_norm": 77.875,
"learning_rate": 9.984779487179486e-07,
"loss": 133.22,
"step": 7420
},
{
"epoch": 0.7803405128205129,
"grad_norm": 81.3125,
"learning_rate": 9.984758974358975e-07,
"loss": 133.2538,
"step": 7430
},
{
"epoch": 0.7813907692307692,
"grad_norm": 76.125,
"learning_rate": 9.98473846153846e-07,
"loss": 134.0912,
"step": 7440
},
{
"epoch": 0.7824410256410257,
"grad_norm": 77.375,
"learning_rate": 9.984717948717947e-07,
"loss": 133.252,
"step": 7450
},
{
"epoch": 0.783491282051282,
"grad_norm": 82.0,
"learning_rate": 9.984697435897436e-07,
"loss": 131.4886,
"step": 7460
},
{
"epoch": 0.7845415384615385,
"grad_norm": 73.375,
"learning_rate": 9.984676923076923e-07,
"loss": 133.4359,
"step": 7470
},
{
"epoch": 0.7855917948717949,
"grad_norm": 74.375,
"learning_rate": 9.98465641025641e-07,
"loss": 134.0868,
"step": 7480
},
{
"epoch": 0.7866420512820513,
"grad_norm": 83.4375,
"learning_rate": 9.984635897435897e-07,
"loss": 132.8313,
"step": 7490
},
{
"epoch": 0.7876923076923077,
"grad_norm": 76.9375,
"learning_rate": 9.984615384615384e-07,
"loss": 134.246,
"step": 7500
},
{
"epoch": 0.7876923076923077,
"eval_loss": 2.086611270904541,
"eval_runtime": 327.2333,
"eval_samples_per_second": 1527.965,
"eval_steps_per_second": 47.752,
"step": 7500
},
{
"epoch": 0.788742564102564,
"grad_norm": 78.0625,
"learning_rate": 9.98459487179487e-07,
"loss": 132.7844,
"step": 7510
},
{
"epoch": 0.7897928205128205,
"grad_norm": 76.1875,
"learning_rate": 9.984574358974358e-07,
"loss": 132.6412,
"step": 7520
},
{
"epoch": 0.7908430769230769,
"grad_norm": 79.4375,
"learning_rate": 9.984553846153847e-07,
"loss": 133.3601,
"step": 7530
},
{
"epoch": 0.7918933333333333,
"grad_norm": 74.9375,
"learning_rate": 9.984533333333332e-07,
"loss": 133.7195,
"step": 7540
},
{
"epoch": 0.7929435897435897,
"grad_norm": 76.1875,
"learning_rate": 9.98451282051282e-07,
"loss": 133.1729,
"step": 7550
},
{
"epoch": 0.7939938461538462,
"grad_norm": 79.125,
"learning_rate": 9.984492307692308e-07,
"loss": 133.8151,
"step": 7560
},
{
"epoch": 0.7950441025641025,
"grad_norm": 76.8125,
"learning_rate": 9.984471794871795e-07,
"loss": 134.1982,
"step": 7570
},
{
"epoch": 0.796094358974359,
"grad_norm": 80.0,
"learning_rate": 9.984451282051281e-07,
"loss": 133.2489,
"step": 7580
},
{
"epoch": 0.7971446153846153,
"grad_norm": 75.0,
"learning_rate": 9.984430769230768e-07,
"loss": 134.1791,
"step": 7590
},
{
"epoch": 0.7981948717948718,
"grad_norm": 77.375,
"learning_rate": 9.984410256410255e-07,
"loss": 134.0118,
"step": 7600
},
{
"epoch": 0.7992451282051282,
"grad_norm": 82.3125,
"learning_rate": 9.984389743589742e-07,
"loss": 132.9163,
"step": 7610
},
{
"epoch": 0.8002953846153846,
"grad_norm": 78.25,
"learning_rate": 9.984369230769231e-07,
"loss": 133.4907,
"step": 7620
},
{
"epoch": 0.801345641025641,
"grad_norm": 72.375,
"learning_rate": 9.984348717948718e-07,
"loss": 134.2763,
"step": 7630
},
{
"epoch": 0.8023958974358975,
"grad_norm": 77.0625,
"learning_rate": 9.984328205128205e-07,
"loss": 133.4557,
"step": 7640
},
{
"epoch": 0.8034461538461538,
"grad_norm": 75.4375,
"learning_rate": 9.984307692307692e-07,
"loss": 133.6842,
"step": 7650
},
{
"epoch": 0.8044964102564103,
"grad_norm": 74.75,
"learning_rate": 9.98428717948718e-07,
"loss": 133.6221,
"step": 7660
},
{
"epoch": 0.8055466666666666,
"grad_norm": 74.1875,
"learning_rate": 9.984266666666666e-07,
"loss": 133.9818,
"step": 7670
},
{
"epoch": 0.8065969230769231,
"grad_norm": 80.9375,
"learning_rate": 9.984246153846153e-07,
"loss": 134.001,
"step": 7680
},
{
"epoch": 0.8076471794871795,
"grad_norm": 73.4375,
"learning_rate": 9.98422564102564e-07,
"loss": 134.0589,
"step": 7690
},
{
"epoch": 0.8086974358974359,
"grad_norm": 74.3125,
"learning_rate": 9.984205128205127e-07,
"loss": 133.7496,
"step": 7700
},
{
"epoch": 0.8097476923076923,
"grad_norm": 74.3125,
"learning_rate": 9.984184615384616e-07,
"loss": 133.3738,
"step": 7710
},
{
"epoch": 0.8107979487179487,
"grad_norm": 72.0,
"learning_rate": 9.984164102564103e-07,
"loss": 133.1667,
"step": 7720
},
{
"epoch": 0.8118482051282051,
"grad_norm": 75.875,
"learning_rate": 9.98414358974359e-07,
"loss": 132.9567,
"step": 7730
},
{
"epoch": 0.8128984615384616,
"grad_norm": 73.3125,
"learning_rate": 9.984123076923077e-07,
"loss": 134.7816,
"step": 7740
},
{
"epoch": 0.8139487179487179,
"grad_norm": 75.875,
"learning_rate": 9.984102564102564e-07,
"loss": 133.8593,
"step": 7750
},
{
"epoch": 0.8149989743589744,
"grad_norm": 78.5625,
"learning_rate": 9.98408205128205e-07,
"loss": 133.8173,
"step": 7760
},
{
"epoch": 0.8160492307692307,
"grad_norm": 72.25,
"learning_rate": 9.984061538461538e-07,
"loss": 133.5827,
"step": 7770
},
{
"epoch": 0.8170994871794872,
"grad_norm": 77.6875,
"learning_rate": 9.984041025641027e-07,
"loss": 132.9576,
"step": 7780
},
{
"epoch": 0.8181497435897436,
"grad_norm": 71.6875,
"learning_rate": 9.984020512820511e-07,
"loss": 133.3698,
"step": 7790
},
{
"epoch": 0.8192,
"grad_norm": 72.8125,
"learning_rate": 9.983999999999998e-07,
"loss": 133.9683,
"step": 7800
},
{
"epoch": 0.8202502564102564,
"grad_norm": 73.25,
"learning_rate": 9.983979487179487e-07,
"loss": 133.8763,
"step": 7810
},
{
"epoch": 0.8213005128205129,
"grad_norm": 71.875,
"learning_rate": 9.983958974358974e-07,
"loss": 132.3762,
"step": 7820
},
{
"epoch": 0.8223507692307692,
"grad_norm": 77.3125,
"learning_rate": 9.983938461538461e-07,
"loss": 133.6236,
"step": 7830
},
{
"epoch": 0.8234010256410257,
"grad_norm": 83.8125,
"learning_rate": 9.983917948717948e-07,
"loss": 132.3988,
"step": 7840
},
{
"epoch": 0.824451282051282,
"grad_norm": 73.375,
"learning_rate": 9.983897435897435e-07,
"loss": 133.4139,
"step": 7850
},
{
"epoch": 0.8255015384615385,
"grad_norm": 79.3125,
"learning_rate": 9.983876923076922e-07,
"loss": 134.3546,
"step": 7860
},
{
"epoch": 0.8265517948717949,
"grad_norm": 78.4375,
"learning_rate": 9.98385641025641e-07,
"loss": 134.4989,
"step": 7870
},
{
"epoch": 0.8276020512820513,
"grad_norm": 78.0,
"learning_rate": 9.983835897435898e-07,
"loss": 133.5446,
"step": 7880
},
{
"epoch": 0.8286523076923077,
"grad_norm": 77.5,
"learning_rate": 9.983815384615383e-07,
"loss": 133.1525,
"step": 7890
},
{
"epoch": 0.8297025641025642,
"grad_norm": 84.1875,
"learning_rate": 9.983794871794872e-07,
"loss": 133.6593,
"step": 7900
},
{
"epoch": 0.8307528205128205,
"grad_norm": 74.1875,
"learning_rate": 9.983774358974359e-07,
"loss": 133.9224,
"step": 7910
},
{
"epoch": 0.831803076923077,
"grad_norm": 76.0,
"learning_rate": 9.983753846153846e-07,
"loss": 134.1779,
"step": 7920
},
{
"epoch": 0.8328533333333333,
"grad_norm": 73.8125,
"learning_rate": 9.983733333333333e-07,
"loss": 135.2825,
"step": 7930
},
{
"epoch": 0.8339035897435897,
"grad_norm": 72.875,
"learning_rate": 9.98371282051282e-07,
"loss": 133.2882,
"step": 7940
},
{
"epoch": 0.8349538461538462,
"grad_norm": 72.4375,
"learning_rate": 9.983692307692307e-07,
"loss": 134.7268,
"step": 7950
},
{
"epoch": 0.8360041025641025,
"grad_norm": 78.8125,
"learning_rate": 9.983671794871794e-07,
"loss": 133.8474,
"step": 7960
},
{
"epoch": 0.837054358974359,
"grad_norm": 74.5,
"learning_rate": 9.983651282051283e-07,
"loss": 131.9032,
"step": 7970
},
{
"epoch": 0.8381046153846153,
"grad_norm": 77.5625,
"learning_rate": 9.98363076923077e-07,
"loss": 134.0065,
"step": 7980
},
{
"epoch": 0.8391548717948718,
"grad_norm": 78.25,
"learning_rate": 9.983610256410257e-07,
"loss": 133.8622,
"step": 7990
},
{
"epoch": 0.8402051282051282,
"grad_norm": 76.3125,
"learning_rate": 9.983589743589743e-07,
"loss": 133.5396,
"step": 8000
},
{
"epoch": 0.8412553846153846,
"grad_norm": 83.25,
"learning_rate": 9.98356923076923e-07,
"loss": 134.0301,
"step": 8010
},
{
"epoch": 0.842305641025641,
"grad_norm": 77.5625,
"learning_rate": 9.983548717948717e-07,
"loss": 133.8874,
"step": 8020
},
{
"epoch": 0.8433558974358975,
"grad_norm": 76.25,
"learning_rate": 9.983528205128204e-07,
"loss": 133.7713,
"step": 8030
},
{
"epoch": 0.8444061538461538,
"grad_norm": 85.25,
"learning_rate": 9.983507692307691e-07,
"loss": 132.7225,
"step": 8040
},
{
"epoch": 0.8454564102564103,
"grad_norm": 77.9375,
"learning_rate": 9.983487179487178e-07,
"loss": 132.4973,
"step": 8050
},
{
"epoch": 0.8465066666666666,
"grad_norm": 77.5,
"learning_rate": 9.983466666666667e-07,
"loss": 134.7827,
"step": 8060
},
{
"epoch": 0.8475569230769231,
"grad_norm": 78.9375,
"learning_rate": 9.983446153846154e-07,
"loss": 134.2993,
"step": 8070
},
{
"epoch": 0.8486071794871795,
"grad_norm": 75.875,
"learning_rate": 9.983425641025641e-07,
"loss": 132.517,
"step": 8080
},
{
"epoch": 0.8496574358974359,
"grad_norm": 72.8125,
"learning_rate": 9.983405128205128e-07,
"loss": 132.6084,
"step": 8090
},
{
"epoch": 0.8507076923076923,
"grad_norm": 75.1875,
"learning_rate": 9.983384615384615e-07,
"loss": 133.5499,
"step": 8100
},
{
"epoch": 0.8517579487179487,
"grad_norm": 76.0,
"learning_rate": 9.983364102564102e-07,
"loss": 131.2289,
"step": 8110
},
{
"epoch": 0.8528082051282051,
"grad_norm": 74.625,
"learning_rate": 9.983343589743589e-07,
"loss": 133.3548,
"step": 8120
},
{
"epoch": 0.8538584615384616,
"grad_norm": 80.9375,
"learning_rate": 9.983323076923078e-07,
"loss": 132.2297,
"step": 8130
},
{
"epoch": 0.8549087179487179,
"grad_norm": 73.125,
"learning_rate": 9.983302564102563e-07,
"loss": 133.2755,
"step": 8140
},
{
"epoch": 0.8559589743589744,
"grad_norm": 75.3125,
"learning_rate": 9.98328205128205e-07,
"loss": 134.9403,
"step": 8150
},
{
"epoch": 0.8570092307692307,
"grad_norm": 73.75,
"learning_rate": 9.983261538461539e-07,
"loss": 133.4854,
"step": 8160
},
{
"epoch": 0.8580594871794872,
"grad_norm": 75.4375,
"learning_rate": 9.983241025641026e-07,
"loss": 133.9221,
"step": 8170
},
{
"epoch": 0.8591097435897436,
"grad_norm": 73.0625,
"learning_rate": 9.983220512820513e-07,
"loss": 133.0202,
"step": 8180
},
{
"epoch": 0.86016,
"grad_norm": 77.8125,
"learning_rate": 9.9832e-07,
"loss": 133.9612,
"step": 8190
},
{
"epoch": 0.8612102564102564,
"grad_norm": 74.75,
"learning_rate": 9.983179487179486e-07,
"loss": 132.866,
"step": 8200
},
{
"epoch": 0.8622605128205129,
"grad_norm": 78.6875,
"learning_rate": 9.983158974358973e-07,
"loss": 131.9501,
"step": 8210
},
{
"epoch": 0.8633107692307692,
"grad_norm": 72.5,
"learning_rate": 9.98313846153846e-07,
"loss": 133.986,
"step": 8220
},
{
"epoch": 0.8643610256410257,
"grad_norm": 77.5625,
"learning_rate": 9.98311794871795e-07,
"loss": 134.4183,
"step": 8230
},
{
"epoch": 0.865411282051282,
"grad_norm": 79.1875,
"learning_rate": 9.983097435897434e-07,
"loss": 133.7371,
"step": 8240
},
{
"epoch": 0.8664615384615385,
"grad_norm": 83.9375,
"learning_rate": 9.983076923076923e-07,
"loss": 131.5742,
"step": 8250
},
{
"epoch": 0.8675117948717949,
"grad_norm": 78.125,
"learning_rate": 9.98305641025641e-07,
"loss": 133.3313,
"step": 8260
},
{
"epoch": 0.8685620512820513,
"grad_norm": 81.25,
"learning_rate": 9.983035897435897e-07,
"loss": 133.0588,
"step": 8270
},
{
"epoch": 0.8696123076923077,
"grad_norm": 74.875,
"learning_rate": 9.983015384615384e-07,
"loss": 132.9553,
"step": 8280
},
{
"epoch": 0.8706625641025642,
"grad_norm": 76.25,
"learning_rate": 9.982994871794871e-07,
"loss": 132.9017,
"step": 8290
},
{
"epoch": 0.8717128205128205,
"grad_norm": 80.25,
"learning_rate": 9.982974358974358e-07,
"loss": 132.7887,
"step": 8300
},
{
"epoch": 0.872763076923077,
"grad_norm": 82.5,
"learning_rate": 9.982953846153845e-07,
"loss": 131.9362,
"step": 8310
},
{
"epoch": 0.8738133333333333,
"grad_norm": 74.6875,
"learning_rate": 9.982933333333334e-07,
"loss": 133.4346,
"step": 8320
},
{
"epoch": 0.8748635897435898,
"grad_norm": 74.4375,
"learning_rate": 9.98291282051282e-07,
"loss": 133.0578,
"step": 8330
},
{
"epoch": 0.8759138461538462,
"grad_norm": 74.75,
"learning_rate": 9.982892307692308e-07,
"loss": 133.309,
"step": 8340
},
{
"epoch": 0.8769641025641025,
"grad_norm": 78.125,
"learning_rate": 9.982871794871795e-07,
"loss": 134.0469,
"step": 8350
},
{
"epoch": 0.878014358974359,
"grad_norm": 82.125,
"learning_rate": 9.982851282051282e-07,
"loss": 131.7594,
"step": 8360
},
{
"epoch": 0.8790646153846153,
"grad_norm": 80.9375,
"learning_rate": 9.982830769230769e-07,
"loss": 134.0729,
"step": 8370
},
{
"epoch": 0.8801148717948718,
"grad_norm": 80.75,
"learning_rate": 9.982810256410256e-07,
"loss": 133.4013,
"step": 8380
},
{
"epoch": 0.8811651282051282,
"grad_norm": 74.6875,
"learning_rate": 9.982789743589743e-07,
"loss": 132.9633,
"step": 8390
},
{
"epoch": 0.8822153846153846,
"grad_norm": 74.3125,
"learning_rate": 9.98276923076923e-07,
"loss": 133.8356,
"step": 8400
},
{
"epoch": 0.883265641025641,
"grad_norm": 75.0,
"learning_rate": 9.982748717948719e-07,
"loss": 133.2425,
"step": 8410
},
{
"epoch": 0.8843158974358974,
"grad_norm": 73.25,
"learning_rate": 9.982728205128206e-07,
"loss": 132.7144,
"step": 8420
},
{
"epoch": 0.8853661538461538,
"grad_norm": 78.625,
"learning_rate": 9.98270769230769e-07,
"loss": 134.2052,
"step": 8430
},
{
"epoch": 0.8864164102564103,
"grad_norm": 71.0,
"learning_rate": 9.98268717948718e-07,
"loss": 133.7353,
"step": 8440
},
{
"epoch": 0.8874666666666666,
"grad_norm": 77.3125,
"learning_rate": 9.982666666666666e-07,
"loss": 134.3944,
"step": 8450
},
{
"epoch": 0.8885169230769231,
"grad_norm": 79.5,
"learning_rate": 9.982646153846153e-07,
"loss": 134.6475,
"step": 8460
},
{
"epoch": 0.8895671794871794,
"grad_norm": 78.375,
"learning_rate": 9.98262564102564e-07,
"loss": 133.3185,
"step": 8470
},
{
"epoch": 0.8906174358974359,
"grad_norm": 83.3125,
"learning_rate": 9.98260512820513e-07,
"loss": 133.362,
"step": 8480
},
{
"epoch": 0.8916676923076923,
"grad_norm": 75.875,
"learning_rate": 9.982584615384614e-07,
"loss": 132.8726,
"step": 8490
},
{
"epoch": 0.8927179487179487,
"grad_norm": 73.5625,
"learning_rate": 9.9825641025641e-07,
"loss": 132.8631,
"step": 8500
},
{
"epoch": 0.8937682051282051,
"grad_norm": 73.4375,
"learning_rate": 9.98254358974359e-07,
"loss": 132.5936,
"step": 8510
},
{
"epoch": 0.8948184615384616,
"grad_norm": 80.75,
"learning_rate": 9.982523076923077e-07,
"loss": 133.115,
"step": 8520
},
{
"epoch": 0.8958687179487179,
"grad_norm": 78.25,
"learning_rate": 9.982502564102564e-07,
"loss": 132.0712,
"step": 8530
},
{
"epoch": 0.8969189743589744,
"grad_norm": 71.3125,
"learning_rate": 9.98248205128205e-07,
"loss": 134.2035,
"step": 8540
},
{
"epoch": 0.8979692307692307,
"grad_norm": 75.8125,
"learning_rate": 9.982461538461538e-07,
"loss": 134.253,
"step": 8550
},
{
"epoch": 0.8990194871794872,
"grad_norm": 76.125,
"learning_rate": 9.982441025641025e-07,
"loss": 132.0401,
"step": 8560
},
{
"epoch": 0.9000697435897436,
"grad_norm": 77.625,
"learning_rate": 9.982420512820512e-07,
"loss": 133.6438,
"step": 8570
},
{
"epoch": 0.90112,
"grad_norm": 74.8125,
"learning_rate": 9.9824e-07,
"loss": 134.649,
"step": 8580
},
{
"epoch": 0.9021702564102564,
"grad_norm": 78.8125,
"learning_rate": 9.982379487179486e-07,
"loss": 133.015,
"step": 8590
},
{
"epoch": 0.9032205128205129,
"grad_norm": 79.5,
"learning_rate": 9.982358974358975e-07,
"loss": 133.7255,
"step": 8600
},
{
"epoch": 0.9042707692307692,
"grad_norm": 76.375,
"learning_rate": 9.982338461538462e-07,
"loss": 133.1744,
"step": 8610
},
{
"epoch": 0.9053210256410257,
"grad_norm": 76.8125,
"learning_rate": 9.982317948717949e-07,
"loss": 133.6467,
"step": 8620
},
{
"epoch": 0.906371282051282,
"grad_norm": 75.5,
"learning_rate": 9.982297435897435e-07,
"loss": 133.2113,
"step": 8630
},
{
"epoch": 0.9074215384615385,
"grad_norm": 90.875,
"learning_rate": 9.982276923076922e-07,
"loss": 134.016,
"step": 8640
},
{
"epoch": 0.9084717948717949,
"grad_norm": 75.625,
"learning_rate": 9.98225641025641e-07,
"loss": 132.7446,
"step": 8650
},
{
"epoch": 0.9095220512820513,
"grad_norm": 83.25,
"learning_rate": 9.982235897435896e-07,
"loss": 134.9909,
"step": 8660
},
{
"epoch": 0.9105723076923077,
"grad_norm": 84.3125,
"learning_rate": 9.982215384615385e-07,
"loss": 133.9167,
"step": 8670
},
{
"epoch": 0.9116225641025641,
"grad_norm": 77.375,
"learning_rate": 9.98219487179487e-07,
"loss": 133.2151,
"step": 8680
},
{
"epoch": 0.9126728205128205,
"grad_norm": 74.375,
"learning_rate": 9.98217435897436e-07,
"loss": 132.7321,
"step": 8690
},
{
"epoch": 0.913723076923077,
"grad_norm": 76.25,
"learning_rate": 9.982153846153846e-07,
"loss": 133.1595,
"step": 8700
},
{
"epoch": 0.9147733333333333,
"grad_norm": 74.125,
"learning_rate": 9.982133333333333e-07,
"loss": 133.1293,
"step": 8710
},
{
"epoch": 0.9158235897435898,
"grad_norm": 75.5625,
"learning_rate": 9.98211282051282e-07,
"loss": 133.3949,
"step": 8720
},
{
"epoch": 0.9168738461538462,
"grad_norm": 77.0,
"learning_rate": 9.982092307692307e-07,
"loss": 133.7157,
"step": 8730
},
{
"epoch": 0.9179241025641026,
"grad_norm": 69.6875,
"learning_rate": 9.982071794871794e-07,
"loss": 131.9628,
"step": 8740
},
{
"epoch": 0.918974358974359,
"grad_norm": 76.75,
"learning_rate": 9.98205128205128e-07,
"loss": 133.9219,
"step": 8750
},
{
"epoch": 0.9200246153846153,
"grad_norm": 77.0,
"learning_rate": 9.98203076923077e-07,
"loss": 133.5647,
"step": 8760
},
{
"epoch": 0.9210748717948718,
"grad_norm": 73.3125,
"learning_rate": 9.982010256410257e-07,
"loss": 133.8773,
"step": 8770
},
{
"epoch": 0.9221251282051282,
"grad_norm": 81.875,
"learning_rate": 9.981989743589742e-07,
"loss": 133.6441,
"step": 8780
},
{
"epoch": 0.9231753846153846,
"grad_norm": 77.375,
"learning_rate": 9.98196923076923e-07,
"loss": 134.1967,
"step": 8790
},
{
"epoch": 0.924225641025641,
"grad_norm": 75.75,
"learning_rate": 9.981948717948718e-07,
"loss": 133.6943,
"step": 8800
},
{
"epoch": 0.9252758974358974,
"grad_norm": 74.5,
"learning_rate": 9.981928205128205e-07,
"loss": 131.9684,
"step": 8810
},
{
"epoch": 0.9263261538461538,
"grad_norm": 77.9375,
"learning_rate": 9.981907692307692e-07,
"loss": 132.8939,
"step": 8820
},
{
"epoch": 0.9273764102564103,
"grad_norm": 82.5625,
"learning_rate": 9.981887179487178e-07,
"loss": 132.9447,
"step": 8830
},
{
"epoch": 0.9284266666666666,
"grad_norm": 78.5625,
"learning_rate": 9.981866666666665e-07,
"loss": 133.4321,
"step": 8840
},
{
"epoch": 0.9294769230769231,
"grad_norm": 78.875,
"learning_rate": 9.981846153846152e-07,
"loss": 133.6094,
"step": 8850
},
{
"epoch": 0.9305271794871794,
"grad_norm": 71.25,
"learning_rate": 9.981825641025641e-07,
"loss": 132.4788,
"step": 8860
},
{
"epoch": 0.9315774358974359,
"grad_norm": 73.9375,
"learning_rate": 9.981805128205128e-07,
"loss": 132.1331,
"step": 8870
},
{
"epoch": 0.9326276923076923,
"grad_norm": 74.6875,
"learning_rate": 9.981784615384615e-07,
"loss": 132.9293,
"step": 8880
},
{
"epoch": 0.9336779487179487,
"grad_norm": 78.0625,
"learning_rate": 9.981764102564102e-07,
"loss": 134.1451,
"step": 8890
},
{
"epoch": 0.9347282051282051,
"grad_norm": 77.75,
"learning_rate": 9.98174358974359e-07,
"loss": 132.7121,
"step": 8900
},
{
"epoch": 0.9357784615384616,
"grad_norm": 72.75,
"learning_rate": 9.981723076923076e-07,
"loss": 132.0682,
"step": 8910
},
{
"epoch": 0.9368287179487179,
"grad_norm": 78.75,
"learning_rate": 9.981702564102563e-07,
"loss": 132.9574,
"step": 8920
},
{
"epoch": 0.9378789743589744,
"grad_norm": 81.625,
"learning_rate": 9.98168205128205e-07,
"loss": 133.9366,
"step": 8930
},
{
"epoch": 0.9389292307692307,
"grad_norm": 74.125,
"learning_rate": 9.981661538461537e-07,
"loss": 134.1782,
"step": 8940
},
{
"epoch": 0.9399794871794872,
"grad_norm": 80.4375,
"learning_rate": 9.981641025641026e-07,
"loss": 134.4583,
"step": 8950
},
{
"epoch": 0.9410297435897436,
"grad_norm": 79.8125,
"learning_rate": 9.981620512820513e-07,
"loss": 134.201,
"step": 8960
},
{
"epoch": 0.94208,
"grad_norm": 77.0,
"learning_rate": 9.9816e-07,
"loss": 133.9063,
"step": 8970
},
{
"epoch": 0.9431302564102564,
"grad_norm": 74.8125,
"learning_rate": 9.981579487179487e-07,
"loss": 133.6804,
"step": 8980
},
{
"epoch": 0.9441805128205129,
"grad_norm": 73.375,
"learning_rate": 9.981558974358974e-07,
"loss": 133.0501,
"step": 8990
},
{
"epoch": 0.9452307692307692,
"grad_norm": 71.5,
"learning_rate": 9.98153846153846e-07,
"loss": 133.0835,
"step": 9000
},
{
"epoch": 0.9462810256410257,
"grad_norm": 76.5625,
"learning_rate": 9.981517948717948e-07,
"loss": 133.7177,
"step": 9010
},
{
"epoch": 0.947331282051282,
"grad_norm": 70.625,
"learning_rate": 9.981497435897437e-07,
"loss": 132.7033,
"step": 9020
},
{
"epoch": 0.9483815384615385,
"grad_norm": 81.25,
"learning_rate": 9.981476923076921e-07,
"loss": 132.286,
"step": 9030
},
{
"epoch": 0.9494317948717949,
"grad_norm": 82.125,
"learning_rate": 9.98145641025641e-07,
"loss": 132.4269,
"step": 9040
},
{
"epoch": 0.9504820512820513,
"grad_norm": 76.875,
"learning_rate": 9.981435897435897e-07,
"loss": 132.6721,
"step": 9050
},
{
"epoch": 0.9515323076923077,
"grad_norm": 72.5,
"learning_rate": 9.981415384615384e-07,
"loss": 132.3392,
"step": 9060
},
{
"epoch": 0.9525825641025641,
"grad_norm": 82.25,
"learning_rate": 9.981394871794871e-07,
"loss": 133.6953,
"step": 9070
},
{
"epoch": 0.9536328205128205,
"grad_norm": 81.0625,
"learning_rate": 9.981374358974358e-07,
"loss": 133.0798,
"step": 9080
},
{
"epoch": 0.954683076923077,
"grad_norm": 75.0625,
"learning_rate": 9.981353846153845e-07,
"loss": 134.3506,
"step": 9090
},
{
"epoch": 0.9557333333333333,
"grad_norm": 82.4375,
"learning_rate": 9.981333333333332e-07,
"loss": 135.1331,
"step": 9100
},
{
"epoch": 0.9567835897435898,
"grad_norm": 76.375,
"learning_rate": 9.981312820512821e-07,
"loss": 131.6688,
"step": 9110
},
{
"epoch": 0.9578338461538461,
"grad_norm": 72.25,
"learning_rate": 9.981292307692308e-07,
"loss": 134.2536,
"step": 9120
},
{
"epoch": 0.9588841025641026,
"grad_norm": 75.375,
"learning_rate": 9.981271794871793e-07,
"loss": 132.993,
"step": 9130
},
{
"epoch": 0.959934358974359,
"grad_norm": 79.625,
"learning_rate": 9.981251282051282e-07,
"loss": 132.7532,
"step": 9140
},
{
"epoch": 0.9609846153846154,
"grad_norm": 72.8125,
"learning_rate": 9.98123076923077e-07,
"loss": 134.5466,
"step": 9150
},
{
"epoch": 0.9620348717948718,
"grad_norm": 73.625,
"learning_rate": 9.981210256410256e-07,
"loss": 133.4606,
"step": 9160
},
{
"epoch": 0.9630851282051283,
"grad_norm": 69.25,
"learning_rate": 9.981189743589743e-07,
"loss": 132.9202,
"step": 9170
},
{
"epoch": 0.9641353846153846,
"grad_norm": 77.625,
"learning_rate": 9.98116923076923e-07,
"loss": 133.554,
"step": 9180
},
{
"epoch": 0.965185641025641,
"grad_norm": 72.0,
"learning_rate": 9.981148717948717e-07,
"loss": 133.4544,
"step": 9190
},
{
"epoch": 0.9662358974358974,
"grad_norm": 72.75,
"learning_rate": 9.981128205128204e-07,
"loss": 132.8837,
"step": 9200
},
{
"epoch": 0.9672861538461538,
"grad_norm": 75.1875,
"learning_rate": 9.981107692307693e-07,
"loss": 133.7232,
"step": 9210
},
{
"epoch": 0.9683364102564103,
"grad_norm": 69.6875,
"learning_rate": 9.98108717948718e-07,
"loss": 132.7222,
"step": 9220
},
{
"epoch": 0.9693866666666666,
"grad_norm": 76.3125,
"learning_rate": 9.981066666666667e-07,
"loss": 134.062,
"step": 9230
},
{
"epoch": 0.9704369230769231,
"grad_norm": 73.8125,
"learning_rate": 9.981046153846154e-07,
"loss": 133.7961,
"step": 9240
},
{
"epoch": 0.9714871794871794,
"grad_norm": 76.25,
"learning_rate": 9.98102564102564e-07,
"loss": 133.53,
"step": 9250
},
{
"epoch": 0.9725374358974359,
"grad_norm": 76.8125,
"learning_rate": 9.981005128205127e-07,
"loss": 134.952,
"step": 9260
},
{
"epoch": 0.9735876923076923,
"grad_norm": 74.1875,
"learning_rate": 9.980984615384614e-07,
"loss": 132.9375,
"step": 9270
},
{
"epoch": 0.9746379487179487,
"grad_norm": 87.25,
"learning_rate": 9.980964102564101e-07,
"loss": 132.9781,
"step": 9280
},
{
"epoch": 0.9756882051282051,
"grad_norm": 74.4375,
"learning_rate": 9.980943589743588e-07,
"loss": 132.2021,
"step": 9290
},
{
"epoch": 0.9767384615384616,
"grad_norm": 73.0,
"learning_rate": 9.980923076923077e-07,
"loss": 132.5939,
"step": 9300
},
{
"epoch": 0.9777887179487179,
"grad_norm": 77.5,
"learning_rate": 9.980902564102564e-07,
"loss": 133.525,
"step": 9310
},
{
"epoch": 0.9788389743589744,
"grad_norm": 79.1875,
"learning_rate": 9.980882051282051e-07,
"loss": 132.8209,
"step": 9320
},
{
"epoch": 0.9798892307692307,
"grad_norm": 76.9375,
"learning_rate": 9.980861538461538e-07,
"loss": 133.3684,
"step": 9330
},
{
"epoch": 0.9809394871794872,
"grad_norm": 71.9375,
"learning_rate": 9.980841025641025e-07,
"loss": 130.963,
"step": 9340
},
{
"epoch": 0.9819897435897436,
"grad_norm": 79.9375,
"learning_rate": 9.980820512820512e-07,
"loss": 133.7593,
"step": 9350
},
{
"epoch": 0.98304,
"grad_norm": 77.125,
"learning_rate": 9.9808e-07,
"loss": 132.379,
"step": 9360
},
{
"epoch": 0.9840902564102564,
"grad_norm": 76.75,
"learning_rate": 9.980779487179488e-07,
"loss": 131.4839,
"step": 9370
},
{
"epoch": 0.9851405128205128,
"grad_norm": 73.8125,
"learning_rate": 9.980758974358973e-07,
"loss": 133.2282,
"step": 9380
},
{
"epoch": 0.9861907692307692,
"grad_norm": 73.9375,
"learning_rate": 9.980738461538462e-07,
"loss": 132.6678,
"step": 9390
},
{
"epoch": 0.9872410256410257,
"grad_norm": 76.625,
"learning_rate": 9.980717948717949e-07,
"loss": 132.3676,
"step": 9400
},
{
"epoch": 0.988291282051282,
"grad_norm": 73.125,
"learning_rate": 9.980697435897436e-07,
"loss": 132.7415,
"step": 9410
},
{
"epoch": 0.9893415384615385,
"grad_norm": 74.75,
"learning_rate": 9.980676923076923e-07,
"loss": 134.5323,
"step": 9420
},
{
"epoch": 0.9903917948717949,
"grad_norm": 75.75,
"learning_rate": 9.98065641025641e-07,
"loss": 132.3584,
"step": 9430
},
{
"epoch": 0.9914420512820513,
"grad_norm": 77.5625,
"learning_rate": 9.980635897435897e-07,
"loss": 132.1099,
"step": 9440
},
{
"epoch": 0.9924923076923077,
"grad_norm": 75.5625,
"learning_rate": 9.980615384615384e-07,
"loss": 132.6088,
"step": 9450
},
{
"epoch": 0.9935425641025641,
"grad_norm": 77.75,
"learning_rate": 9.980594871794873e-07,
"loss": 132.0042,
"step": 9460
},
{
"epoch": 0.9945928205128205,
"grad_norm": 76.6875,
"learning_rate": 9.98057435897436e-07,
"loss": 132.9037,
"step": 9470
},
{
"epoch": 0.995643076923077,
"grad_norm": 75.5,
"learning_rate": 9.980553846153844e-07,
"loss": 133.0483,
"step": 9480
},
{
"epoch": 0.9966933333333333,
"grad_norm": 74.8125,
"learning_rate": 9.980533333333333e-07,
"loss": 134.3751,
"step": 9490
},
{
"epoch": 0.9977435897435898,
"grad_norm": 74.625,
"learning_rate": 9.98051282051282e-07,
"loss": 132.6699,
"step": 9500
},
{
"epoch": 0.9987938461538461,
"grad_norm": 79.875,
"learning_rate": 9.980492307692307e-07,
"loss": 132.3946,
"step": 9510
},
{
"epoch": 0.9998441025641026,
"grad_norm": 73.5625,
"learning_rate": 9.980471794871794e-07,
"loss": 133.7389,
"step": 9520
}
],
"logging_steps": 10,
"max_steps": 9521,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.6288590936506106e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}