{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 5000,
  "global_step": 1125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 0.392131507396698,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.3156,
      "step": 10
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 0.6833685636520386,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.5258,
      "step": 20
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 0.4975835978984833,
      "learning_rate": 6e-06,
      "loss": 2.5274,
      "step": 30
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 0.47904446721076965,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.2199,
      "step": 40
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.5792201161384583,
      "learning_rate": 1e-05,
      "loss": 2.3423,
      "step": 50
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.48581650853157043,
      "learning_rate": 1.2e-05,
      "loss": 2.3571,
      "step": 60
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 0.4770135283470154,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.4415,
      "step": 70
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.6430277824401855,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.5717,
      "step": 80
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5969924926757812,
      "learning_rate": 1.8e-05,
      "loss": 2.2712,
      "step": 90
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.5458263754844666,
      "learning_rate": 2e-05,
      "loss": 2.1937,
      "step": 100
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 0.49687811732292175,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.3534,
      "step": 110
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.5264276266098022,
      "learning_rate": 2.4e-05,
      "loss": 2.3235,
      "step": 120
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 0.6222357749938965,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.484,
      "step": 130
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 0.5594074130058289,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.3924,
      "step": 140
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.5403823852539062,
      "learning_rate": 3e-05,
      "loss": 2.043,
      "step": 150
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.8265597820281982,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.4271,
      "step": 160
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 0.4910406172275543,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.2711,
      "step": 170
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6300191283226013,
      "learning_rate": 3.6e-05,
      "loss": 2.4088,
      "step": 180
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 0.9516507387161255,
      "learning_rate": 3.8e-05,
      "loss": 2.2007,
      "step": 190
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.6081224679946899,
      "learning_rate": 4e-05,
      "loss": 2.2574,
      "step": 200
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 0.670280396938324,
      "learning_rate": 4.2e-05,
      "loss": 2.1538,
      "step": 210
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 0.5967269539833069,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.3559,
      "step": 220
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 0.6861779093742371,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.2649,
      "step": 230
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.7942169308662415,
      "learning_rate": 4.8e-05,
      "loss": 2.4453,
      "step": 240
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.686896562576294,
      "learning_rate": 5e-05,
      "loss": 2.272,
      "step": 250
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 0.6957288980484009,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.2378,
      "step": 260
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5659416317939758,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.2169,
      "step": 270
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 0.6357027292251587,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.3081,
      "step": 280
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 0.561445951461792,
      "learning_rate": 5.8e-05,
      "loss": 2.3665,
      "step": 290
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.8563527464866638,
      "learning_rate": 6e-05,
      "loss": 2.2106,
      "step": 300
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 0.7866883873939514,
      "learning_rate": 6.2e-05,
      "loss": 2.0944,
      "step": 310
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.9338068962097168,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.2693,
      "step": 320
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 0.7246842384338379,
      "learning_rate": 6.6e-05,
      "loss": 2.2881,
      "step": 330
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 1.0052026510238647,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.3067,
      "step": 340
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.6183302998542786,
      "learning_rate": 7e-05,
      "loss": 2.3916,
      "step": 350
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.7271236777305603,
      "learning_rate": 7.2e-05,
      "loss": 2.4863,
      "step": 360
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 0.8021159768104553,
      "learning_rate": 7.4e-05,
      "loss": 2.5189,
      "step": 370
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 0.670994758605957,
      "learning_rate": 7.6e-05,
      "loss": 2.299,
      "step": 380
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 0.6826931238174438,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.2439,
      "step": 390
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.6512673497200012,
      "learning_rate": 8e-05,
      "loss": 2.2511,
      "step": 400
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 0.6105847358703613,
      "learning_rate": 8.2e-05,
      "loss": 2.2597,
      "step": 410
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.7471911907196045,
      "learning_rate": 8.4e-05,
      "loss": 2.3652,
      "step": 420
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 0.6970444321632385,
      "learning_rate": 8.6e-05,
      "loss": 2.3259,
      "step": 430
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 0.6674960255622864,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.3558,
      "step": 440
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.7472724318504333,
      "learning_rate": 9e-05,
      "loss": 2.2086,
      "step": 450
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 0.7264606356620789,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.084,
      "step": 460
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 0.6516128182411194,
      "learning_rate": 9.4e-05,
      "loss": 2.0929,
      "step": 470
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.8081138134002686,
      "learning_rate": 9.6e-05,
      "loss": 2.1653,
      "step": 480
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 0.8400042653083801,
      "learning_rate": 9.8e-05,
      "loss": 2.3939,
      "step": 490
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.4789764881134033,
      "learning_rate": 0.0001,
      "loss": 2.2763,
      "step": 500
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 0.7314158082008362,
      "learning_rate": 9.84e-05,
      "loss": 2.3742,
      "step": 510
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.5646970272064209,
      "learning_rate": 9.680000000000001e-05,
      "loss": 2.1478,
      "step": 520
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 0.4644782841205597,
      "learning_rate": 9.52e-05,
      "loss": 2.2953,
      "step": 530
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6332143545150757,
      "learning_rate": 9.360000000000001e-05,
      "loss": 2.2399,
      "step": 540
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.706084668636322,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.2324,
      "step": 550
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.6272305250167847,
      "learning_rate": 9.04e-05,
      "loss": 2.2321,
      "step": 560
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 0.5707433223724365,
      "learning_rate": 8.88e-05,
      "loss": 2.2092,
      "step": 570
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 0.660696268081665,
      "learning_rate": 8.72e-05,
      "loss": 1.9807,
      "step": 580
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 0.5993101000785828,
      "learning_rate": 8.560000000000001e-05,
      "loss": 1.9566,
      "step": 590
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5725361704826355,
      "learning_rate": 8.4e-05,
      "loss": 2.1722,
      "step": 600
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 0.651642918586731,
      "learning_rate": 8.24e-05,
      "loss": 2.1262,
      "step": 610
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 0.5352093577384949,
      "learning_rate": 8.080000000000001e-05,
      "loss": 2.1979,
      "step": 620
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5744340419769287,
      "learning_rate": 7.920000000000001e-05,
      "loss": 2.0399,
      "step": 630
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.6103332042694092,
      "learning_rate": 7.76e-05,
      "loss": 2.2209,
      "step": 640
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.6434329152107239,
      "learning_rate": 7.6e-05,
      "loss": 2.379,
      "step": 650
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.5661439299583435,
      "learning_rate": 7.44e-05,
      "loss": 2.1698,
      "step": 660
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 0.5890876054763794,
      "learning_rate": 7.280000000000001e-05,
      "loss": 2.058,
      "step": 670
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 0.4725685715675354,
      "learning_rate": 7.12e-05,
      "loss": 2.0658,
      "step": 680
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 0.6357767581939697,
      "learning_rate": 6.96e-05,
      "loss": 2.1107,
      "step": 690
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.6726393699645996,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.1904,
      "step": 700
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 0.5009137392044067,
      "learning_rate": 6.64e-05,
      "loss": 2.0765,
      "step": 710
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7313541173934937,
      "learning_rate": 6.48e-05,
      "loss": 2.3566,
      "step": 720
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 0.7757258415222168,
      "learning_rate": 6.32e-05,
      "loss": 2.2077,
      "step": 730
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 0.5176954865455627,
      "learning_rate": 6.16e-05,
      "loss": 2.1287,
      "step": 740
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.6251640915870667,
      "learning_rate": 6e-05,
      "loss": 2.1726,
      "step": 750
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 0.5190748572349548,
      "learning_rate": 5.8399999999999997e-05,
      "loss": 2.1528,
      "step": 760
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 0.6299232840538025,
      "learning_rate": 5.68e-05,
      "loss": 1.9734,
      "step": 770
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.6707553863525391,
      "learning_rate": 5.520000000000001e-05,
      "loss": 1.9959,
      "step": 780
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 0.5231025815010071,
      "learning_rate": 5.360000000000001e-05,
      "loss": 2.0261,
      "step": 790
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.489175021648407,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.1987,
      "step": 800
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6425113677978516,
      "learning_rate": 5.0400000000000005e-05,
      "loss": 2.0759,
      "step": 810
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 0.6148718595504761,
      "learning_rate": 4.88e-05,
      "loss": 2.158,
      "step": 820
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 0.7482603192329407,
      "learning_rate": 4.72e-05,
      "loss": 1.9579,
      "step": 830
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.5650503039360046,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 2.1253,
      "step": 840
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.6965321898460388,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.1034,
      "step": 850
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 0.5848603844642639,
      "learning_rate": 4.24e-05,
      "loss": 2.0139,
      "step": 860
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 0.566116988658905,
      "learning_rate": 4.08e-05,
      "loss": 2.0551,
      "step": 870
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.5044224858283997,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 1.9789,
      "step": 880
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 0.566875159740448,
      "learning_rate": 3.76e-05,
      "loss": 2.3283,
      "step": 890
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5149425268173218,
      "learning_rate": 3.6e-05,
      "loss": 1.9651,
      "step": 900
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 0.5834816694259644,
      "learning_rate": 3.4399999999999996e-05,
      "loss": 1.9825,
      "step": 910
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 0.7403817772865295,
      "learning_rate": 3.2800000000000004e-05,
      "loss": 2.0542,
      "step": 920
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 0.6044632792472839,
      "learning_rate": 3.12e-05,
      "loss": 2.2774,
      "step": 930
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 0.6258851885795593,
      "learning_rate": 2.96e-05,
      "loss": 2.1449,
      "step": 940
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.6421411037445068,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.0822,
      "step": 950
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.34951749444007874,
      "learning_rate": 2.64e-05,
      "loss": 1.9521,
      "step": 960
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 0.5875269770622253,
      "learning_rate": 2.48e-05,
      "loss": 2.0813,
      "step": 970
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 0.5003840327262878,
      "learning_rate": 2.32e-05,
      "loss": 1.9155,
      "step": 980
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4974331259727478,
      "learning_rate": 2.16e-05,
      "loss": 2.0593,
      "step": 990
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.505962610244751,
      "learning_rate": 2e-05,
      "loss": 2.0306,
      "step": 1000
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 0.5298508405685425,
      "learning_rate": 1.84e-05,
      "loss": 2.136,
      "step": 1010
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 0.4652698338031769,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.9021,
      "step": 1020
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 0.5339078307151794,
      "learning_rate": 1.52e-05,
      "loss": 2.0262,
      "step": 1030
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.5623987317085266,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.8597,
      "step": 1040
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.689896285533905,
      "learning_rate": 1.2e-05,
      "loss": 2.1377,
      "step": 1050
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 0.460510790348053,
      "learning_rate": 1.04e-05,
      "loss": 1.889,
      "step": 1060
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 0.5239367485046387,
      "learning_rate": 8.8e-06,
      "loss": 2.1753,
      "step": 1070
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5576533079147339,
      "learning_rate": 7.2e-06,
      "loss": 2.1375,
      "step": 1080
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 0.5585991144180298,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.9434,
      "step": 1090
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.5961203575134277,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.0194,
      "step": 1100
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 0.6022922396659851,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.9679,
      "step": 1110
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.4506663382053375,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.1243,
      "step": 1120
    }
  ],
  "logging_steps": 10,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.4276096434176e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}