{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9722222222222223,
  "eval_steps": 27,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 3.136354684829712,
      "learning_rate": 3.0000000000000004e-08,
      "loss": 7.126,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "eval_loss": 5.272334098815918,
      "eval_runtime": 10.9491,
      "eval_samples_per_second": 9.59,
      "eval_steps_per_second": 9.59,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.6424509286880493,
      "learning_rate": 6.000000000000001e-08,
      "loss": 6.2434,
      "step": 2
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 1.3273869752883911,
      "learning_rate": 9e-08,
      "loss": 5.851,
      "step": 3
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.9482982158660889,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 7.0582,
      "step": 4
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 2.214090347290039,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 6.2122,
      "step": 5
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.6521217823028564,
      "learning_rate": 1.8e-07,
      "loss": 6.0318,
      "step": 6
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 1.2911734580993652,
      "learning_rate": 2.1000000000000003e-07,
      "loss": 6.1264,
      "step": 7
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.2651853561401367,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 5.6821,
      "step": 8
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.2058266401290894,
      "learning_rate": 2.7e-07,
      "loss": 5.7295,
      "step": 9
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 2.896589994430542,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 7.4781,
      "step": 10
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 1.313854694366455,
      "learning_rate": 3.3e-07,
      "loss": 6.1254,
      "step": 11
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.281994104385376,
      "learning_rate": 3.6e-07,
      "loss": 6.683,
      "step": 12
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 1.2343209981918335,
      "learning_rate": 3.9e-07,
      "loss": 6.2304,
      "step": 13
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.3297009468078613,
      "learning_rate": 4.2000000000000006e-07,
      "loss": 6.2013,
      "step": 14
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.9952207803726196,
      "learning_rate": 4.5e-07,
      "loss": 6.9842,
      "step": 15
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.3968197107315063,
      "learning_rate": 4.800000000000001e-07,
      "loss": 6.2524,
      "step": 16
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 4.7724127769470215,
      "learning_rate": 5.100000000000001e-07,
      "loss": 8.551,
      "step": 17
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.9988604187965393,
      "learning_rate": 5.4e-07,
      "loss": 5.5391,
      "step": 18
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 1.2599544525146484,
      "learning_rate": 5.7e-07,
      "loss": 6.4559,
      "step": 19
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.984928846359253,
      "learning_rate": 6.000000000000001e-07,
      "loss": 6.954,
      "step": 20
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 1.2283947467803955,
      "learning_rate": 6.3e-07,
      "loss": 6.1821,
      "step": 21
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 2.2317938804626465,
      "learning_rate": 6.6e-07,
      "loss": 6.9164,
      "step": 22
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 1.5473928451538086,
      "learning_rate": 6.900000000000001e-07,
      "loss": 6.5494,
      "step": 23
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.508975625038147,
      "learning_rate": 7.2e-07,
      "loss": 6.4025,
      "step": 24
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 2.4396748542785645,
      "learning_rate": 7.5e-07,
      "loss": 7.2659,
      "step": 25
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 1.1266586780548096,
      "learning_rate": 7.8e-07,
      "loss": 6.0911,
      "step": 26
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.515765905380249,
      "learning_rate": 8.100000000000001e-07,
      "loss": 6.503,
      "step": 27
    },
    {
      "epoch": 0.25,
      "eval_loss": 5.270267963409424,
      "eval_runtime": 10.4888,
      "eval_samples_per_second": 10.011,
      "eval_steps_per_second": 10.011,
      "step": 27
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 1.2845295667648315,
      "learning_rate": 8.400000000000001e-07,
      "loss": 6.3435,
      "step": 28
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 1.528168797492981,
      "learning_rate": 8.699999999999999e-07,
      "loss": 6.8436,
      "step": 29
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.555953860282898,
      "learning_rate": 9e-07,
      "loss": 6.404,
      "step": 30
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 1.293718934059143,
      "learning_rate": 9.3e-07,
      "loss": 6.0386,
      "step": 31
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.0446598529815674,
      "learning_rate": 9.600000000000001e-07,
      "loss": 5.677,
      "step": 32
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 1.3030468225479126,
      "learning_rate": 9.9e-07,
      "loss": 5.8789,
      "step": 33
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 1.108596682548523,
      "learning_rate": 1.0200000000000002e-06,
      "loss": 5.8663,
      "step": 34
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 1.833085536956787,
      "learning_rate": 1.05e-06,
      "loss": 5.7367,
      "step": 35
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.561715006828308,
      "learning_rate": 1.08e-06,
      "loss": 6.2266,
      "step": 36
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 1.6098933219909668,
      "learning_rate": 1.11e-06,
      "loss": 6.3335,
      "step": 37
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 1.6193208694458008,
      "learning_rate": 1.14e-06,
      "loss": 6.3869,
      "step": 38
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 1.5229904651641846,
      "learning_rate": 1.17e-06,
      "loss": 6.0453,
      "step": 39
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.511690616607666,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 6.7203,
      "step": 40
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 0.9691258668899536,
      "learning_rate": 1.2299999999999999e-06,
      "loss": 5.8176,
      "step": 41
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 1.1707255840301514,
      "learning_rate": 1.26e-06,
      "loss": 6.2779,
      "step": 42
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 1.1281574964523315,
      "learning_rate": 1.29e-06,
      "loss": 5.8402,
      "step": 43
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 3.945136308670044,
      "learning_rate": 1.32e-06,
      "loss": 7.5325,
      "step": 44
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 1.8681273460388184,
      "learning_rate": 1.35e-06,
      "loss": 6.3374,
      "step": 45
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 1.300478458404541,
      "learning_rate": 1.3800000000000001e-06,
      "loss": 5.9715,
      "step": 46
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 1.2660181522369385,
      "learning_rate": 1.41e-06,
      "loss": 6.0421,
      "step": 47
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.817872405052185,
      "learning_rate": 1.44e-06,
      "loss": 7.0875,
      "step": 48
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 1.6538351774215698,
      "learning_rate": 1.4700000000000001e-06,
      "loss": 6.1825,
      "step": 49
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.5821293592453003,
      "learning_rate": 1.5e-06,
      "loss": 6.0065,
      "step": 50
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 1.5061155557632446,
      "learning_rate": 1.53e-06,
      "loss": 5.8156,
      "step": 51
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 1.495235562324524,
      "learning_rate": 1.56e-06,
      "loss": 5.792,
      "step": 52
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 1.2974352836608887,
      "learning_rate": 1.59e-06,
      "loss": 6.3621,
      "step": 53
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.2943974733352661,
      "learning_rate": 1.6200000000000002e-06,
      "loss": 5.9853,
      "step": 54
    },
    {
      "epoch": 0.5,
      "eval_loss": 5.2575860023498535,
      "eval_runtime": 10.6855,
      "eval_samples_per_second": 9.826,
      "eval_steps_per_second": 9.826,
      "step": 54
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 1.0820438861846924,
      "learning_rate": 1.65e-06,
      "loss": 5.7026,
      "step": 55
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.9304187297821045,
      "learning_rate": 1.6800000000000002e-06,
      "loss": 6.5805,
      "step": 56
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 1.238295555114746,
      "learning_rate": 1.71e-06,
      "loss": 5.9397,
      "step": 57
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 1.7372101545333862,
      "learning_rate": 1.7399999999999999e-06,
      "loss": 5.8761,
      "step": 58
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 1.6708195209503174,
      "learning_rate": 1.77e-06,
      "loss": 6.0646,
      "step": 59
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.5075998306274414,
      "learning_rate": 1.8e-06,
      "loss": 6.276,
      "step": 60
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 1.4556330442428589,
      "learning_rate": 1.83e-06,
      "loss": 6.4906,
      "step": 61
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 1.2507421970367432,
      "learning_rate": 1.86e-06,
      "loss": 6.2285,
      "step": 62
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 1.1143450736999512,
      "learning_rate": 1.8900000000000001e-06,
      "loss": 5.7344,
      "step": 63
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 2.05438232421875,
      "learning_rate": 1.9200000000000003e-06,
      "loss": 6.85,
      "step": 64
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 1.104891300201416,
      "learning_rate": 1.95e-06,
      "loss": 6.1067,
      "step": 65
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 1.34933602809906,
      "learning_rate": 1.98e-06,
      "loss": 6.1659,
      "step": 66
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 1.5707837343215942,
      "learning_rate": 2.0100000000000002e-06,
      "loss": 6.1741,
      "step": 67
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.9905802607536316,
      "learning_rate": 2.0400000000000004e-06,
      "loss": 5.9072,
      "step": 68
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 1.134399652481079,
      "learning_rate": 2.07e-06,
      "loss": 5.8005,
      "step": 69
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 1.7359548807144165,
      "learning_rate": 2.1e-06,
      "loss": 6.7931,
      "step": 70
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 1.9637112617492676,
      "learning_rate": 2.13e-06,
      "loss": 6.0,
      "step": 71
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.908047080039978,
      "learning_rate": 2.16e-06,
      "loss": 6.9322,
      "step": 72
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 1.6848489046096802,
      "learning_rate": 2.19e-06,
      "loss": 6.3743,
      "step": 73
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 1.158486247062683,
      "learning_rate": 2.22e-06,
      "loss": 5.7395,
      "step": 74
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 2.9409470558166504,
      "learning_rate": 2.25e-06,
      "loss": 7.1889,
      "step": 75
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 1.5408318042755127,
      "learning_rate": 2.28e-06,
      "loss": 6.5631,
      "step": 76
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 1.3003695011138916,
      "learning_rate": 2.31e-06,
      "loss": 5.8228,
      "step": 77
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 1.6015976667404175,
      "learning_rate": 2.34e-06,
      "loss": 6.0852,
      "step": 78
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 1.282989501953125,
      "learning_rate": 2.37e-06,
      "loss": 6.0135,
      "step": 79
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.3845688104629517,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 5.9315,
      "step": 80
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.431152105331421,
      "learning_rate": 2.43e-06,
      "loss": 5.7324,
      "step": 81
    },
    {
      "epoch": 0.75,
      "eval_loss": 5.23203182220459,
      "eval_runtime": 10.3071,
      "eval_samples_per_second": 10.187,
      "eval_steps_per_second": 10.187,
      "step": 81
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 1.7849000692367554,
      "learning_rate": 2.4599999999999997e-06,
      "loss": 6.3697,
      "step": 82
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 1.2546958923339844,
      "learning_rate": 2.49e-06,
      "loss": 6.4323,
      "step": 83
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.3903110027313232,
      "learning_rate": 2.52e-06,
      "loss": 6.1479,
      "step": 84
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 1.8783302307128906,
      "learning_rate": 2.55e-06,
      "loss": 5.7606,
      "step": 85
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 1.2064532041549683,
      "learning_rate": 2.58e-06,
      "loss": 6.0706,
      "step": 86
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 1.9301965236663818,
      "learning_rate": 2.61e-06,
      "loss": 6.2393,
      "step": 87
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.259318232536316,
      "learning_rate": 2.64e-06,
      "loss": 5.8821,
      "step": 88
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 1.88141667842865,
      "learning_rate": 2.6700000000000003e-06,
      "loss": 6.8863,
      "step": 89
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.1480059623718262,
      "learning_rate": 2.7e-06,
      "loss": 5.7941,
      "step": 90
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 1.1357027292251587,
      "learning_rate": 2.73e-06,
      "loss": 5.7938,
      "step": 91
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 1.2564626932144165,
      "learning_rate": 2.7600000000000003e-06,
      "loss": 5.8955,
      "step": 92
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 1.5674831867218018,
      "learning_rate": 2.7900000000000004e-06,
      "loss": 6.0711,
      "step": 93
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 2.784726142883301,
      "learning_rate": 2.82e-06,
      "loss": 6.9214,
      "step": 94
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 1.2815853357315063,
      "learning_rate": 2.85e-06,
      "loss": 5.9669,
      "step": 95
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 3.059992551803589,
      "learning_rate": 2.88e-06,
      "loss": 7.6911,
      "step": 96
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 1.2001030445098877,
      "learning_rate": 2.91e-06,
      "loss": 6.1174,
      "step": 97
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 1.685596227645874,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 6.4517,
      "step": 98
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 1.5668795108795166,
      "learning_rate": 2.97e-06,
      "loss": 6.3579,
      "step": 99
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.2336190938949585,
      "learning_rate": 3e-06,
      "loss": 6.2871,
      "step": 100
    },
    {
      "epoch": 0.9351851851851852,
      "grad_norm": 1.331573247909546,
      "learning_rate": 2.9998524776393626e-06,
      "loss": 5.9677,
      "step": 101
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 1.5391007661819458,
      "learning_rate": 2.9994099395745795e-06,
      "loss": 6.6068,
      "step": 102
    },
    {
      "epoch": 0.9537037037037037,
      "grad_norm": 4.519767761230469,
      "learning_rate": 2.9986724728513302e-06,
      "loss": 8.1238,
      "step": 103
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.5254385471343994,
      "learning_rate": 2.997640222526725e-06,
      "loss": 6.4137,
      "step": 104
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 1.28110671043396,
      "learning_rate": 2.996313391640769e-06,
      "loss": 5.887,
      "step": 105
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 3.4707837104797363,
      "learning_rate": 2.994692241176429e-06,
      "loss": 7.9841,
      "step": 106
    },
    {
      "epoch": 0.9907407407407407,
      "grad_norm": 1.5300663709640503,
      "learning_rate": 2.9927770900082955e-06,
      "loss": 6.2007,
      "step": 107
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.747676134109497,
      "learning_rate": 2.9905683148398643e-06,
      "loss": 6.5292,
      "step": 108
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.185390949249268,
      "eval_runtime": 10.6897,
      "eval_samples_per_second": 9.823,
      "eval_steps_per_second": 9.823,
      "step": 108
    },
    {
      "epoch": 1.0092592592592593,
      "grad_norm": 1.57361900806427,
      "learning_rate": 2.988066350129437e-06,
      "loss": 6.1537,
      "step": 109
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 5.155310153961182,
      "learning_rate": 2.9852716880046687e-06,
      "loss": 7.9648,
      "step": 110
    },
    {
      "epoch": 1.0277777777777777,
      "grad_norm": 1.0643362998962402,
      "learning_rate": 2.982184878165763e-06,
      "loss": 5.1748,
      "step": 111
    },
    {
      "epoch": 1.0092592592592593,
      "grad_norm": 1.0376684665679932,
      "learning_rate": 2.9788065277773537e-06,
      "loss": 5.6556,
      "step": 112
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 1.228864073753357,
      "learning_rate": 2.9751373013490727e-06,
      "loss": 5.7668,
      "step": 113
    },
    {
      "epoch": 1.0277777777777777,
      "grad_norm": 1.7278510332107544,
      "learning_rate": 2.971177920604846e-06,
      "loss": 6.3775,
      "step": 114
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 1.1904284954071045,
      "learning_rate": 2.9669291643409314e-06,
      "loss": 5.7487,
      "step": 115
    },
    {
      "epoch": 1.0462962962962963,
      "grad_norm": 2.941854238510132,
      "learning_rate": 2.9623918682727352e-06,
      "loss": 7.2423,
      "step": 116
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 1.5035470724105835,
      "learning_rate": 2.9575669248704265e-06,
      "loss": 6.1212,
      "step": 117
    },
    {
      "epoch": 1.0648148148148149,
      "grad_norm": 1.4733242988586426,
      "learning_rate": 2.9524552831833926e-06,
      "loss": 6.3059,
      "step": 118
    },
    {
      "epoch": 1.074074074074074,
      "grad_norm": 1.3305742740631104,
      "learning_rate": 2.947057948653564e-06,
      "loss": 6.1691,
      "step": 119
    },
    {
      "epoch": 1.0833333333333333,
      "grad_norm": 1.2160289287567139,
      "learning_rate": 2.9413759829176495e-06,
      "loss": 5.9701,
      "step": 120
    },
    {
      "epoch": 1.0925925925925926,
      "grad_norm": 1.9012755155563354,
      "learning_rate": 2.935410503598313e-06,
      "loss": 6.6399,
      "step": 121
    },
    {
      "epoch": 1.1018518518518519,
      "grad_norm": 1.3863564729690552,
      "learning_rate": 2.9291626840843446e-06,
      "loss": 6.0122,
      "step": 122
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 1.1440134048461914,
      "learning_rate": 2.9226337532998544e-06,
      "loss": 5.9895,
      "step": 123
    },
    {
      "epoch": 1.1203703703703705,
      "grad_norm": 1.4871304035186768,
      "learning_rate": 2.9158249954625514e-06,
      "loss": 6.3919,
      "step": 124
    },
    {
      "epoch": 1.1296296296296295,
      "grad_norm": 1.574532389640808,
      "learning_rate": 2.908737749831142e-06,
      "loss": 6.489,
      "step": 125
    },
    {
      "epoch": 1.1388888888888888,
      "grad_norm": 2.674992322921753,
      "learning_rate": 2.9013734104419e-06,
      "loss": 6.965,
      "step": 126
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 1.4959555864334106,
      "learning_rate": 2.8937334258344676e-06,
      "loss": 5.8652,
      "step": 127
    },
    {
      "epoch": 1.1574074074074074,
      "grad_norm": 3.064631223678589,
      "learning_rate": 2.88581929876693e-06,
      "loss": 7.1246,
      "step": 128
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 1.7988754510879517,
      "learning_rate": 2.8776325859202315e-06,
      "loss": 6.1511,
      "step": 129
    },
    {
      "epoch": 1.175925925925926,
      "grad_norm": 1.4231789112091064,
      "learning_rate": 2.869174897591978e-06,
      "loss": 6.0368,
      "step": 130
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 2.6319122314453125,
      "learning_rate": 2.8604478973797005e-06,
      "loss": 7.1228,
      "step": 131
    },
    {
      "epoch": 1.1944444444444444,
      "grad_norm": 1.4405936002731323,
      "learning_rate": 2.851453301853629e-06,
      "loss": 5.9765,
      "step": 132
    },
    {
      "epoch": 1.2037037037037037,
      "grad_norm": 1.669622540473938,
      "learning_rate": 2.842192880219049e-06,
      "loss": 6.4033,
      "step": 133
    },
    {
      "epoch": 1.212962962962963,
      "grad_norm": 1.1244466304779053,
      "learning_rate": 2.832668453968309e-06,
      "loss": 5.5845,
      "step": 134
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 1.0342087745666504,
      "learning_rate": 2.8228818965225326e-06,
      "loss": 5.6106,
      "step": 135
    },
    {
      "epoch": 1.2222222222222223,
      "eval_loss": 5.1238203048706055,
      "eval_runtime": 10.8032,
      "eval_samples_per_second": 9.719,
      "eval_steps_per_second": 9.719,
      "step": 135
    },
    {
      "epoch": 1.2314814814814814,
      "grad_norm": 2.5150041580200195,
      "learning_rate": 2.8128351328631308e-06,
      "loss": 6.5318,
      "step": 136
    },
    {
      "epoch": 1.2407407407407407,
      "grad_norm": 1.7575809955596924,
      "learning_rate": 2.8025301391531584e-06,
      "loss": 6.225,
      "step": 137
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.5736333131790161,
      "learning_rate": 2.7919689423486137e-06,
      "loss": 5.6247,
      "step": 138
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 0.9995443820953369,
      "learning_rate": 2.781153619799741e-06,
      "loss": 5.4866,
      "step": 139
    },
    {
      "epoch": 1.2685185185185186,
      "grad_norm": 1.7936508655548096,
      "learning_rate": 2.7700862988424264e-06,
      "loss": 6.4679,
      "step": 140
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 1.4072571992874146,
      "learning_rate": 2.7587691563797533e-06,
      "loss": 6.0924,
      "step": 141
    },
    {
      "epoch": 1.287037037037037,
      "grad_norm": 1.9437594413757324,
      "learning_rate": 2.747204418453818e-06,
      "loss": 6.3988,
      "step": 142
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 1.1792351007461548,
      "learning_rate": 2.735394359807872e-06,
      "loss": 6.0245,
      "step": 143
    },
    {
      "epoch": 1.3055555555555556,
      "grad_norm": 1.2097288370132446,
      "learning_rate": 2.7233413034388904e-06,
      "loss": 6.0232,
      "step": 144
    },
    {
      "epoch": 1.3148148148148149,
      "grad_norm": 1.5997315645217896,
      "learning_rate": 2.711047620140644e-06,
      "loss": 5.9724,
      "step": 145
    },
    {
      "epoch": 1.324074074074074,
      "grad_norm": 1.9537619352340698,
      "learning_rate": 2.6985157280373736e-06,
      "loss": 6.336,
      "step": 146
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.4596198797225952,
      "learning_rate": 2.685748092108155e-06,
      "loss": 6.2286,
      "step": 147
    },
    {
      "epoch": 1.3425925925925926,
      "grad_norm": 1.2177029848098755,
      "learning_rate": 2.6727472237020448e-06,
      "loss": 5.8753,
      "step": 148
    },
    {
      "epoch": 1.3518518518518519,
      "grad_norm": 1.5970029830932617,
      "learning_rate": 2.6595156800441053e-06,
      "loss": 6.2522,
      "step": 149
    },
    {
      "epoch": 1.3611111111111112,
      "grad_norm": 1.1032902002334595,
      "learning_rate": 2.646056063732411e-06,
      "loss": 5.795,
      "step": 150
    },
    {
      "epoch": 1.3703703703703702,
      "grad_norm": 1.10838782787323,
      "learning_rate": 2.632371022226124e-06,
      "loss": 5.4648,
      "step": 151
    },
    {
      "epoch": 1.3796296296296298,
      "grad_norm": 1.3732211589813232,
      "learning_rate": 2.6184632473247484e-06,
      "loss": 5.568,
      "step": 152
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 1.188904881477356,
      "learning_rate": 2.6043354746386645e-06,
      "loss": 5.8007,
      "step": 153
    },
    {
      "epoch": 1.3981481481481481,
      "grad_norm": 1.3125028610229492,
      "learning_rate": 2.5899904830510406e-06,
      "loss": 5.7965,
      "step": 154
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": 1.2234677076339722,
      "learning_rate": 2.575431094171241e-06,
      "loss": 5.9759,
      "step": 155
    },
    {
      "epoch": 1.4166666666666667,
      "grad_norm": 2.0235507488250732,
      "learning_rate": 2.5606601717798212e-06,
      "loss": 6.5055,
      "step": 156
    },
    {
      "epoch": 1.425925925925926,
      "grad_norm": 1.3678350448608398,
      "learning_rate": 2.5456806212652348e-06,
      "loss": 5.8768,
      "step": 157
    },
    {
      "epoch": 1.4351851851851851,
      "grad_norm": 1.309804081916809,
      "learning_rate": 2.5304953890523524e-06,
      "loss": 6.0516,
      "step": 158
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 1.4316556453704834,
      "learning_rate": 2.5151074620229114e-06,
      "loss": 6.2186,
      "step": 159
    },
    {
      "epoch": 1.4537037037037037,
      "grad_norm": 1.308398723602295,
      "learning_rate": 2.499519866928006e-06,
      "loss": 5.9185,
      "step": 160
    },
    {
      "epoch": 1.462962962962963,
      "grad_norm": 1.7772057056427002,
      "learning_rate": 2.4837356697927366e-06,
      "loss": 6.4643,
      "step": 161
    },
    {
      "epoch": 1.4722222222222223,
      "grad_norm": 1.4515641927719116,
      "learning_rate": 2.4677579753131316e-06,
      "loss": 6.3981,
      "step": 162
    },
    {
      "epoch": 1.4722222222222223,
      "eval_loss": 5.054426193237305,
      "eval_runtime": 10.7718,
      "eval_samples_per_second": 9.748,
      "eval_steps_per_second": 9.748,
      "step": 162
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 2.9240331649780273,
      "learning_rate": 2.4515899262454685e-06,
      "loss": 6.8221,
      "step": 163
    },
    {
      "epoch": 1.4907407407407407,
      "grad_norm": 3.2064929008483887,
      "learning_rate": 2.4352347027881005e-06,
      "loss": 7.6826,
      "step": 164
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.6117157936096191,
      "learning_rate": 2.4186955219559254e-06,
      "loss": 5.5413,
      "step": 165
    },
    {
      "epoch": 1.5092592592592593,
      "grad_norm": 1.5916537046432495,
      "learning_rate": 2.401975636947609e-06,
      "loss": 6.1638,
      "step": 166
    },
    {
      "epoch": 1.5185185185185186,
      "grad_norm": 1.6315852403640747,
      "learning_rate": 2.3850783365056922e-06,
      "loss": 6.3381,
      "step": 167
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 1.1859897375106812,
      "learning_rate": 2.368006944269709e-06,
      "loss": 5.7726,
      "step": 168
    },
    {
      "epoch": 1.5370370370370372,
      "grad_norm": 1.2986359596252441,
      "learning_rate": 2.3507648181224336e-06,
      "loss": 5.5423,
      "step": 169
    },
    {
      "epoch": 1.5462962962962963,
      "grad_norm": 1.3099842071533203,
      "learning_rate": 2.3333553495294033e-06,
      "loss": 6.2081,
      "step": 170
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 1.8448351621627808,
      "learning_rate": 2.315781962871823e-06,
      "loss": 6.4411,
      "step": 171
    },
    {
      "epoch": 1.5648148148148149,
      "grad_norm": 1.263071894645691,
      "learning_rate": 2.298048114773005e-06,
      "loss": 5.769,
      "step": 172
    },
    {
      "epoch": 1.574074074074074,
      "grad_norm": 1.4397268295288086,
      "learning_rate": 2.280157293418462e-06,
      "loss": 6.1988,
      "step": 173
    },
    {
      "epoch": 1.5833333333333335,
      "grad_norm": 1.3311412334442139,
      "learning_rate": 2.262113017869794e-06,
      "loss": 5.9678,
      "step": 174
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 1.5137203931808472,
      "learning_rate": 2.243918837372502e-06,
      "loss": 6.4093,
      "step": 175
    },
    {
      "epoch": 1.6018518518518519,
      "grad_norm": 2.532318115234375,
      "learning_rate": 2.22557833065786e-06,
      "loss": 6.573,
      "step": 176
    },
    {
      "epoch": 1.6111111111111112,
      "grad_norm": 1.7535362243652344,
      "learning_rate": 2.207095105238997e-06,
      "loss": 6.1462,
      "step": 177
    },
    {
      "epoch": 1.6203703703703702,
      "grad_norm": 1.3252042531967163,
      "learning_rate": 2.1884727967013063e-06,
      "loss": 5.7489,
      "step": 178
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 2.172076463699341,
      "learning_rate": 2.1697150679873442e-06,
      "loss": 6.3797,
      "step": 179
    },
    {
      "epoch": 1.6388888888888888,
      "grad_norm": 0.8812606334686279,
      "learning_rate": 2.150825608676337e-06,
      "loss": 5.4227,
      "step": 180
    },
    {
      "epoch": 1.6481481481481481,
      "grad_norm": 1.4979366064071655,
      "learning_rate": 2.1318081342584566e-06,
      "loss": 5.811,
      "step": 181
    },
    {
      "epoch": 1.6574074074074074,
      "grad_norm": 1.277028203010559,
      "learning_rate": 2.1126663854039945e-06,
      "loss": 5.9072,
      "step": 182
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.668641448020935,
      "learning_rate": 2.0934041272275884e-06,
      "loss": 6.1502,
      "step": 183
    },
    {
      "epoch": 1.675925925925926,
      "grad_norm": 0.8518059849739075,
      "learning_rate": 2.074025148547635e-06,
      "loss": 5.2586,
      "step": 184
    },
    {
      "epoch": 1.6851851851851851,
      "grad_norm": 1.7262235879898071,
      "learning_rate": 2.0545332611410427e-06,
      "loss": 5.9965,
      "step": 185
    },
    {
      "epoch": 1.6944444444444444,
      "grad_norm": 4.665543079376221,
      "learning_rate": 2.0349322989934695e-06,
      "loss": 7.4106,
      "step": 186
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": 1.1285862922668457,
      "learning_rate": 2.0152261175451915e-06,
      "loss": 5.6628,
      "step": 187
    },
    {
      "epoch": 1.7129629629629628,
      "grad_norm": 1.108992338180542,
      "learning_rate": 1.9954185929327507e-06,
      "loss": 5.4876,
      "step": 188
    },
    {
      "epoch": 1.7222222222222223,
      "grad_norm": 1.1134352684020996,
      "learning_rate": 1.9755136212265323e-06,
      "loss": 5.602,
      "step": 189
    },
    {
      "epoch": 1.7222222222222223,
      "eval_loss": 4.992879867553711,
      "eval_runtime": 10.5803,
      "eval_samples_per_second": 9.924,
      "eval_steps_per_second": 9.924,
      "step": 189
    },
    {
      "epoch": 1.7314814814814814,
      "grad_norm": 1.215661883354187,
      "learning_rate": 1.9555151176644222e-06,
      "loss": 5.7391,
      "step": 190
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 1.2140839099884033,
      "learning_rate": 1.9354270158816935e-06,
      "loss": 5.4932,
      "step": 191
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.3728704452514648,
      "learning_rate": 1.915253267137274e-06,
      "loss": 5.7001,
      "step": 192
    },
    {
      "epoch": 1.7592592592592593,
      "grad_norm": 5.121810436248779,
      "learning_rate": 1.894997839536547e-06,
      "loss": 7.9136,
      "step": 193
    },
    {
      "epoch": 1.7685185185185186,
      "grad_norm": 1.3116612434387207,
      "learning_rate": 1.8746647172508404e-06,
      "loss": 5.7987,
      "step": 194
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.1180241107940674,
      "learning_rate": 1.8542578997337519e-06,
      "loss": 5.9064,
      "step": 195
    },
    {
      "epoch": 1.7870370370370372,
      "grad_norm": 5.294866561889648,
      "learning_rate": 1.8337814009344715e-06,
      "loss": 8.2684,
      "step": 196
    },
    {
      "epoch": 1.7962962962962963,
      "grad_norm": 1.0381337404251099,
      "learning_rate": 1.813239248508255e-06,
      "loss": 5.487,
      "step": 197
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 1.2923859357833862,
      "learning_rate": 1.7926354830241926e-06,
      "loss": 6.0108,
      "step": 198
    },
    {
      "epoch": 1.8148148148148149,
      "grad_norm": 1.3527953624725342,
      "learning_rate": 1.7719741571704477e-06,
      "loss": 6.3468,
      "step": 199
    },
    {
      "epoch": 1.824074074074074,
      "grad_norm": 1.4213413000106812,
      "learning_rate": 1.7512593349571046e-06,
      "loss": 6.0251,
      "step": 200
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 1.3854726552963257,
      "learning_rate": 1.730495090916795e-06,
      "loss": 5.8197,
      "step": 201
    },
    {
      "epoch": 1.8425925925925926,
      "grad_norm": 0.9397538304328918,
      "learning_rate": 1.7096855093032494e-06,
      "loss": 5.4813,
      "step": 202
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.7849190831184387,
      "learning_rate": 1.6888346832879382e-06,
      "loss": 5.3213,
      "step": 203
    },
    {
      "epoch": 1.8611111111111112,
      "grad_norm": 1.316622018814087,
      "learning_rate": 1.6679467141549617e-06,
      "loss": 5.358,
      "step": 204
    },
    {
      "epoch": 1.8703703703703702,
      "grad_norm": 1.1983349323272705,
      "learning_rate": 1.6470257104943413e-06,
      "loss": 5.8328,
      "step": 205
    },
    {
      "epoch": 1.8796296296296298,
      "grad_norm": 1.1115864515304565,
      "learning_rate": 1.6260757873938715e-06,
      "loss": 5.6616,
      "step": 206
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 1.6418949365615845,
      "learning_rate": 1.6051010656297009e-06,
      "loss": 5.8618,
      "step": 207
    },
    {
      "epoch": 1.8981481481481481,
      "grad_norm": 1.2098896503448486,
      "learning_rate": 1.5841056708557877e-06,
      "loss": 5.7551,
      "step": 208
    },
    {
      "epoch": 1.9074074074074074,
      "grad_norm": 2.523620843887329,
      "learning_rate": 1.5630937327923979e-06,
      "loss": 6.0457,
      "step": 209
    },
    {
      "epoch": 1.9166666666666665,
      "grad_norm": 1.2053682804107666,
      "learning_rate": 1.5420693844138035e-06,
      "loss": 5.7501,
      "step": 210
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 1.0068210363388062,
      "learning_rate": 1.5210367611353436e-06,
      "loss": 5.2868,
      "step": 211
    },
    {
      "epoch": 1.9351851851851851,
      "grad_norm": 1.0384793281555176,
      "learning_rate": 1.5e-06,
      "loss": 5.5413,
      "step": 212
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 0.9215264916419983,
      "learning_rate": 1.4789632388646567e-06,
      "loss": 5.3834,
      "step": 213
    },
    {
      "epoch": 1.9537037037037037,
      "grad_norm": 1.250044584274292,
      "learning_rate": 1.4579306155861968e-06,
      "loss": 5.9769,
      "step": 214
    },
    {
      "epoch": 1.9629629629629628,
      "grad_norm": 0.9464189410209656,
      "learning_rate": 1.4369062672076026e-06,
      "loss": 5.3573,
      "step": 215
    },
    {
      "epoch": 1.9722222222222223,
      "grad_norm": 0.9586074352264404,
      "learning_rate": 1.4158943291442122e-06,
      "loss": 5.3998,
      "step": 216
    },
    {
      "epoch": 1.9722222222222223,
      "eval_loss": 4.946777820587158,
      "eval_runtime": 10.6655,
      "eval_samples_per_second": 9.845,
      "eval_steps_per_second": 9.845,
      "step": 216
    }
  ],
  "logging_steps": 1,
  "max_steps": 324,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 108,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.029536027869184e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}