{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 14.220000481200906,
      "learning_rate": 5e-06,
      "loss": 13.9265,
      "step": 1
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 14.702762596013635,
      "learning_rate": 1e-05,
      "loss": 13.95,
      "step": 2
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 14.297305924795248,
      "learning_rate": 1.5e-05,
      "loss": 13.9116,
      "step": 3
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 14.484767601202535,
      "learning_rate": 2e-05,
      "loss": 13.753,
      "step": 4
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 14.480323510985746,
      "learning_rate": 2.5e-05,
      "loss": 13.222,
      "step": 5
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 14.002264166506258,
      "learning_rate": 3e-05,
      "loss": 12.1647,
      "step": 6
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 7.226601449948956,
      "learning_rate": 3.5e-05,
      "loss": 11.1642,
      "step": 7
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 13.608621977990989,
      "learning_rate": 4e-05,
      "loss": 10.8504,
      "step": 8
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 6.436610267622404,
      "learning_rate": 4.5e-05,
      "loss": 10.4279,
      "step": 9
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 4.922039728837155,
      "learning_rate": 5e-05,
      "loss": 10.1287,
      "step": 10
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 12.033200559896779,
      "learning_rate": 4.9397590361445786e-05,
      "loss": 9.9607,
      "step": 11
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 3.5396711201156807,
      "learning_rate": 4.879518072289157e-05,
      "loss": 9.6616,
      "step": 12
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 3.4751992441084534,
      "learning_rate": 4.8192771084337354e-05,
      "loss": 9.3783,
      "step": 13
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 3.9005409440562735,
      "learning_rate": 4.759036144578313e-05,
      "loss": 9.1355,
      "step": 14
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 2.8756405244423915,
      "learning_rate": 4.698795180722892e-05,
      "loss": 8.8203,
      "step": 15
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 3.9300784221492027,
      "learning_rate": 4.63855421686747e-05,
      "loss": 8.5065,
      "step": 16
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 5.84606546682727,
      "learning_rate": 4.578313253012048e-05,
      "loss": 8.3534,
      "step": 17
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 5.025102319247832,
      "learning_rate": 4.5180722891566266e-05,
      "loss": 8.1611,
      "step": 18
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 3.5261942209741486,
      "learning_rate": 4.457831325301205e-05,
      "loss": 8.0223,
      "step": 19
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 8.46799283954891,
      "learning_rate": 4.3975903614457834e-05,
      "loss": 7.8982,
      "step": 20
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 3.926166227638816,
      "learning_rate": 4.337349397590362e-05,
      "loss": 7.6319,
      "step": 21
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 3.358443458515684,
      "learning_rate": 4.27710843373494e-05,
      "loss": 7.4718,
      "step": 22
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 2.7982062504728487,
      "learning_rate": 4.2168674698795186e-05,
      "loss": 7.3488,
      "step": 23
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 3.1113638072919216,
      "learning_rate": 4.156626506024097e-05,
      "loss": 7.15,
      "step": 24
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 3.1595449829251945,
      "learning_rate": 4.0963855421686746e-05,
      "loss": 7.0563,
      "step": 25
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 2.108212146858006,
      "learning_rate": 4.036144578313254e-05,
      "loss": 6.9565,
      "step": 26
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 2.461122936407565,
      "learning_rate": 3.9759036144578314e-05,
      "loss": 6.8685,
      "step": 27
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 1.6920822731314087,
      "learning_rate": 3.91566265060241e-05,
      "loss": 6.7245,
      "step": 28
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 2.2327133352179276,
      "learning_rate": 3.855421686746988e-05,
      "loss": 6.6712,
      "step": 29
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 2.398221999231477,
      "learning_rate": 3.7951807228915666e-05,
      "loss": 6.5071,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9848914786193277,
      "learning_rate": 3.734939759036144e-05,
      "loss": 6.3974,
      "step": 31
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 1.8070671857380076,
      "learning_rate": 3.674698795180723e-05,
      "loss": 6.3319,
      "step": 32
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 1.6370922118025715,
      "learning_rate": 3.614457831325301e-05,
      "loss": 6.1884,
      "step": 33
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 1.3131279804848621,
      "learning_rate": 3.5542168674698794e-05,
      "loss": 6.1036,
      "step": 34
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 1.340531475202813,
      "learning_rate": 3.4939759036144585e-05,
      "loss": 5.9671,
      "step": 35
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 2.005454028622789,
      "learning_rate": 3.433734939759036e-05,
      "loss": 5.8771,
      "step": 36
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 1.4142674915557123,
      "learning_rate": 3.3734939759036146e-05,
      "loss": 5.8714,
      "step": 37
    },
    {
      "epoch": 1.2258064516129032,
      "grad_norm": 1.2956798900198585,
      "learning_rate": 3.313253012048193e-05,
      "loss": 5.7898,
      "step": 38
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 1.6593235984258043,
      "learning_rate": 3.253012048192771e-05,
      "loss": 5.6873,
      "step": 39
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.380163595182406,
      "learning_rate": 3.192771084337349e-05,
      "loss": 5.7097,
      "step": 40
    },
    {
      "epoch": 1.3225806451612903,
      "grad_norm": 1.0401057745638052,
      "learning_rate": 3.132530120481928e-05,
      "loss": 5.6556,
      "step": 41
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 0.8473367054648464,
      "learning_rate": 3.072289156626506e-05,
      "loss": 5.4949,
      "step": 42
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 1.1572154596782513,
      "learning_rate": 3.012048192771085e-05,
      "loss": 5.4822,
      "step": 43
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 1.1443583002498423,
      "learning_rate": 2.951807228915663e-05,
      "loss": 5.4141,
      "step": 44
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 1.1052929131923555,
      "learning_rate": 2.891566265060241e-05,
      "loss": 5.3635,
      "step": 45
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 0.8970565525154285,
      "learning_rate": 2.8313253012048197e-05,
      "loss": 5.2672,
      "step": 46
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 0.756063967066019,
      "learning_rate": 2.7710843373493977e-05,
      "loss": 5.2908,
      "step": 47
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.7264373375167542,
      "learning_rate": 2.7108433734939758e-05,
      "loss": 5.2698,
      "step": 48
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 0.7011676067381816,
      "learning_rate": 2.6506024096385545e-05,
      "loss": 5.2454,
      "step": 49
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.6927754707271319,
      "learning_rate": 2.5903614457831325e-05,
      "loss": 5.1169,
      "step": 50
    },
    {
      "epoch": 1.6451612903225805,
      "grad_norm": 0.6274016321054947,
      "learning_rate": 2.530120481927711e-05,
      "loss": 5.079,
      "step": 51
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 0.6260513529033087,
      "learning_rate": 2.4698795180722893e-05,
      "loss": 5.0318,
      "step": 52
    },
    {
      "epoch": 1.7096774193548387,
      "grad_norm": 0.6122295776355817,
      "learning_rate": 2.4096385542168677e-05,
      "loss": 5.0809,
      "step": 53
    },
    {
      "epoch": 1.7419354838709677,
      "grad_norm": 0.6219482405443587,
      "learning_rate": 2.349397590361446e-05,
      "loss": 4.9977,
      "step": 54
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.7127219759114208,
      "learning_rate": 2.289156626506024e-05,
      "loss": 4.9713,
      "step": 55
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 0.6728184125308878,
      "learning_rate": 2.2289156626506025e-05,
      "loss": 4.9564,
      "step": 56
    },
    {
      "epoch": 1.838709677419355,
      "grad_norm": 0.6658692158816993,
      "learning_rate": 2.168674698795181e-05,
      "loss": 4.8953,
      "step": 57
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 0.6480363491872242,
      "learning_rate": 2.1084337349397593e-05,
      "loss": 4.8271,
      "step": 58
    },
    {
      "epoch": 1.903225806451613,
      "grad_norm": 0.6798514027495196,
      "learning_rate": 2.0481927710843373e-05,
      "loss": 4.856,
      "step": 59
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.5868913336163518,
      "learning_rate": 1.9879518072289157e-05,
      "loss": 4.7935,
      "step": 60
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.5793335785631702,
      "learning_rate": 1.927710843373494e-05,
      "loss": 4.8151,
      "step": 61
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5816955191304313,
      "learning_rate": 1.867469879518072e-05,
      "loss": 4.7828,
      "step": 62
    },
    {
      "epoch": 2.032258064516129,
      "grad_norm": 0.5845389898807549,
      "learning_rate": 1.8072289156626505e-05,
      "loss": 4.6459,
      "step": 63
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 0.5946763020956095,
      "learning_rate": 1.7469879518072292e-05,
      "loss": 4.7297,
      "step": 64
    },
    {
      "epoch": 2.096774193548387,
      "grad_norm": 0.5627139324820443,
      "learning_rate": 1.6867469879518073e-05,
      "loss": 4.6863,
      "step": 65
    },
    {
      "epoch": 2.129032258064516,
      "grad_norm": 0.5636104401228851,
      "learning_rate": 1.6265060240963857e-05,
      "loss": 4.6437,
      "step": 66
    },
    {
      "epoch": 2.161290322580645,
      "grad_norm": 0.5966948986254044,
      "learning_rate": 1.566265060240964e-05,
      "loss": 4.6102,
      "step": 67
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 0.5635496928050323,
      "learning_rate": 1.5060240963855424e-05,
      "loss": 4.56,
      "step": 68
    },
    {
      "epoch": 2.225806451612903,
      "grad_norm": 0.6201573994580546,
      "learning_rate": 1.4457831325301205e-05,
      "loss": 4.5522,
      "step": 69
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 0.5283310806265233,
      "learning_rate": 1.3855421686746989e-05,
      "loss": 4.5434,
      "step": 70
    },
    {
      "epoch": 2.2903225806451615,
      "grad_norm": 0.5830200387240102,
      "learning_rate": 1.3253012048192772e-05,
      "loss": 4.5213,
      "step": 71
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 0.5366398051729224,
      "learning_rate": 1.2650602409638555e-05,
      "loss": 4.4882,
      "step": 72
    },
    {
      "epoch": 2.3548387096774195,
      "grad_norm": 0.5278747342683787,
      "learning_rate": 1.2048192771084338e-05,
      "loss": 4.4285,
      "step": 73
    },
    {
      "epoch": 2.3870967741935485,
      "grad_norm": 0.5187375955155756,
      "learning_rate": 1.144578313253012e-05,
      "loss": 4.4649,
      "step": 74
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 0.49022439094573594,
      "learning_rate": 1.0843373493975904e-05,
      "loss": 4.4827,
      "step": 75
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 0.4832270774924177,
      "learning_rate": 1.0240963855421687e-05,
      "loss": 4.4521,
      "step": 76
    },
    {
      "epoch": 2.4838709677419355,
      "grad_norm": 0.5104329783830706,
      "learning_rate": 9.63855421686747e-06,
      "loss": 4.4009,
      "step": 77
    },
    {
      "epoch": 2.5161290322580645,
      "grad_norm": 0.46199522908208795,
      "learning_rate": 9.036144578313253e-06,
      "loss": 4.3962,
      "step": 78
    },
    {
      "epoch": 2.5483870967741935,
      "grad_norm": 0.4752588993383047,
      "learning_rate": 8.433734939759036e-06,
      "loss": 4.4422,
      "step": 79
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 0.48368008070516033,
      "learning_rate": 7.83132530120482e-06,
      "loss": 4.2568,
      "step": 80
    },
    {
      "epoch": 2.6129032258064515,
      "grad_norm": 0.47323578510274494,
      "learning_rate": 7.228915662650602e-06,
      "loss": 4.3716,
      "step": 81
    },
    {
      "epoch": 2.6451612903225805,
      "grad_norm": 0.47907919622898615,
      "learning_rate": 6.626506024096386e-06,
      "loss": 4.4467,
      "step": 82
    },
    {
      "epoch": 2.6774193548387095,
      "grad_norm": 0.5132262686017864,
      "learning_rate": 6.024096385542169e-06,
      "loss": 4.353,
      "step": 83
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 0.4512163239687551,
      "learning_rate": 5.421686746987952e-06,
      "loss": 4.3904,
      "step": 84
    },
    {
      "epoch": 2.741935483870968,
      "grad_norm": 0.4613864288737105,
      "learning_rate": 4.819277108433735e-06,
      "loss": 4.3699,
      "step": 85
    },
    {
      "epoch": 2.774193548387097,
      "grad_norm": 0.4834904636291854,
      "learning_rate": 4.216867469879518e-06,
      "loss": 4.3382,
      "step": 86
    },
    {
      "epoch": 2.806451612903226,
      "grad_norm": 0.45137040545065016,
      "learning_rate": 3.614457831325301e-06,
      "loss": 4.3651,
      "step": 87
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 0.44625483484835893,
      "learning_rate": 3.0120481927710846e-06,
      "loss": 4.4046,
      "step": 88
    },
    {
      "epoch": 2.870967741935484,
      "grad_norm": 0.4306895833715559,
      "learning_rate": 2.4096385542168676e-06,
      "loss": 4.3594,
      "step": 89
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 0.46583862244193375,
      "learning_rate": 1.8072289156626506e-06,
      "loss": 4.3189,
      "step": 90
    },
    {
      "epoch": 2.935483870967742,
      "grad_norm": 0.4698345242151301,
      "learning_rate": 1.2048192771084338e-06,
      "loss": 4.3348,
      "step": 91
    },
    {
      "epoch": 2.967741935483871,
      "grad_norm": 0.4355936118573381,
      "learning_rate": 6.024096385542169e-07,
      "loss": 4.3989,
      "step": 92
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4741459705347069,
      "learning_rate": 0.0,
      "loss": 4.3099,
      "step": 93
    },
    {
      "epoch": 3.0,
      "step": 93,
      "total_flos": 42389716598784.0,
      "train_loss": 6.370550432512837,
      "train_runtime": 17767.6162,
      "train_samples_per_second": 0.083,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1,
  "max_steps": 93,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 42389716598784.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}