{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9411764705882355,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 160.71739196777344,
      "learning_rate": 2e-05,
      "loss": 2.163,
      "step": 1
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 167.84927368164062,
      "learning_rate": 2e-05,
      "loss": 4.2743,
      "step": 2
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 134.49913024902344,
      "learning_rate": 2e-05,
      "loss": 3.5496,
      "step": 3
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 327.9437255859375,
      "learning_rate": 2e-05,
      "loss": 4.2971,
      "step": 4
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 286.48297119140625,
      "learning_rate": 2e-05,
      "loss": 4.238,
      "step": 5
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 160.5793914794922,
      "learning_rate": 2e-05,
      "loss": 4.8738,
      "step": 6
    },
    {
      "epoch": 0.20588235294117646,
      "grad_norm": 173.0782012939453,
      "learning_rate": 2e-05,
      "loss": 4.2928,
      "step": 7
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 452.2684020996094,
      "learning_rate": 2e-05,
      "loss": 6.4371,
      "step": 8
    },
    {
      "epoch": 0.2647058823529412,
      "grad_norm": 101.81562042236328,
      "learning_rate": 2e-05,
      "loss": 2.8329,
      "step": 9
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 157.65127563476562,
      "learning_rate": 2e-05,
      "loss": 3.053,
      "step": 10
    },
    {
      "epoch": 0.3235294117647059,
      "grad_norm": 143.43881225585938,
      "learning_rate": 2e-05,
      "loss": 2.6041,
      "step": 11
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 119.99986267089844,
      "learning_rate": 2e-05,
      "loss": 2.7732,
      "step": 12
    },
    {
      "epoch": 0.38235294117647056,
      "grad_norm": 340.0208435058594,
      "learning_rate": 2e-05,
      "loss": 4.7953,
      "step": 13
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 139.62266540527344,
      "learning_rate": 2e-05,
      "loss": 3.9037,
      "step": 14
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 133.6896209716797,
      "learning_rate": 2e-05,
      "loss": 3.2289,
      "step": 15
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 402.2488708496094,
      "learning_rate": 2e-05,
      "loss": 5.3283,
      "step": 16
    },
    {
      "epoch": 0.5,
      "grad_norm": 154.9514617919922,
      "learning_rate": 2e-05,
      "loss": 2.5564,
      "step": 17
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 408.76507568359375,
      "learning_rate": 2e-05,
      "loss": 2.8475,
      "step": 18
    },
    {
      "epoch": 0.5588235294117647,
      "grad_norm": 849.7493286132812,
      "learning_rate": 2e-05,
      "loss": 3.2031,
      "step": 19
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 583.0057373046875,
      "learning_rate": 2e-05,
      "loss": 3.9562,
      "step": 20
    },
    {
      "epoch": 0.6176470588235294,
      "grad_norm": 261.2338562011719,
      "learning_rate": 2e-05,
      "loss": 3.2209,
      "step": 21
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 409.6594543457031,
      "learning_rate": 2e-05,
      "loss": 4.913,
      "step": 22
    },
    {
      "epoch": 0.6764705882352942,
      "grad_norm": 224.56918334960938,
      "learning_rate": 2e-05,
      "loss": 4.1768,
      "step": 23
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 384.32147216796875,
      "learning_rate": 2e-05,
      "loss": 4.7449,
      "step": 24
    },
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 57.91896057128906,
      "learning_rate": 2e-05,
      "loss": 1.3582,
      "step": 25
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 58.27327346801758,
      "learning_rate": 2e-05,
      "loss": 2.1744,
      "step": 26
    },
    {
      "epoch": 0.7941176470588235,
      "grad_norm": 96.63125610351562,
      "learning_rate": 2e-05,
      "loss": 2.6751,
      "step": 27
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 124.51710510253906,
      "learning_rate": 2e-05,
      "loss": 2.8836,
      "step": 28
    },
    {
      "epoch": 0.8529411764705882,
      "grad_norm": 408.7486877441406,
      "learning_rate": 2e-05,
      "loss": 4.733,
      "step": 29
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 167.9065399169922,
      "learning_rate": 2e-05,
      "loss": 3.5512,
      "step": 30
    },
    {
      "epoch": 0.9117647058823529,
      "grad_norm": 203.8374786376953,
      "learning_rate": 2e-05,
      "loss": 3.7913,
      "step": 31
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 313.9844665527344,
      "learning_rate": 2e-05,
      "loss": 4.509,
      "step": 32
    },
    {
      "epoch": 0.9705882352941176,
      "grad_norm": 144.14212036132812,
      "learning_rate": 2e-05,
      "loss": 2.1653,
      "step": 33
    },
    {
      "epoch": 1.0,
      "grad_norm": 95.7232894897461,
      "learning_rate": 2e-05,
      "loss": 3.2242,
      "step": 34
    },
    {
      "epoch": 1.0294117647058822,
      "grad_norm": 43.582393646240234,
      "learning_rate": 2e-05,
      "loss": 1.3664,
      "step": 35
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 388.4141540527344,
      "learning_rate": 2e-05,
      "loss": 1.9917,
      "step": 36
    },
    {
      "epoch": 1.088235294117647,
      "grad_norm": 56.53749465942383,
      "learning_rate": 2e-05,
      "loss": 2.393,
      "step": 37
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 174.79148864746094,
      "learning_rate": 2e-05,
      "loss": 1.9908,
      "step": 38
    },
    {
      "epoch": 1.1470588235294117,
      "grad_norm": 1044.60498046875,
      "learning_rate": 2e-05,
      "loss": 2.7904,
      "step": 39
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1415.9786376953125,
      "learning_rate": 2e-05,
      "loss": 2.5518,
      "step": 40
    },
    {
      "epoch": 1.2058823529411764,
      "grad_norm": 307.51263427734375,
      "learning_rate": 2e-05,
      "loss": 3.9784,
      "step": 41
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 230.46514892578125,
      "learning_rate": 2e-05,
      "loss": 3.7486,
      "step": 42
    },
    {
      "epoch": 1.2647058823529411,
      "grad_norm": 134.46823120117188,
      "learning_rate": 2e-05,
      "loss": 2.2822,
      "step": 43
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 69.17707061767578,
      "learning_rate": 2e-05,
      "loss": 1.7713,
      "step": 44
    },
    {
      "epoch": 1.3235294117647058,
      "grad_norm": 66.95726776123047,
      "learning_rate": 2e-05,
      "loss": 2.6892,
      "step": 45
    },
    {
      "epoch": 1.3529411764705883,
      "grad_norm": 174.15359497070312,
      "learning_rate": 2e-05,
      "loss": 3.2474,
      "step": 46
    },
    {
      "epoch": 1.3823529411764706,
      "grad_norm": 159.84739685058594,
      "learning_rate": 2e-05,
      "loss": 2.2839,
      "step": 47
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 61.734619140625,
      "learning_rate": 2e-05,
      "loss": 2.0586,
      "step": 48
    },
    {
      "epoch": 1.4411764705882353,
      "grad_norm": 258.8429260253906,
      "learning_rate": 2e-05,
      "loss": 3.829,
      "step": 49
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 256.6245422363281,
      "learning_rate": 2e-05,
      "loss": 3.2496,
      "step": 50
    },
    {
      "epoch": 1.5,
      "grad_norm": 38.860015869140625,
      "learning_rate": 2e-05,
      "loss": 0.9418,
      "step": 51
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 169.32525634765625,
      "learning_rate": 2e-05,
      "loss": 1.8798,
      "step": 52
    },
    {
      "epoch": 1.5588235294117647,
      "grad_norm": 547.1870727539062,
      "learning_rate": 2e-05,
      "loss": 2.0999,
      "step": 53
    },
    {
      "epoch": 1.5882352941176472,
      "grad_norm": 69.51364135742188,
      "learning_rate": 2e-05,
      "loss": 1.9031,
      "step": 54
    },
    {
      "epoch": 1.6176470588235294,
      "grad_norm": 47.159114837646484,
      "learning_rate": 2e-05,
      "loss": 2.5062,
      "step": 55
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 215.8884735107422,
      "learning_rate": 2e-05,
      "loss": 2.8866,
      "step": 56
    },
    {
      "epoch": 1.6764705882352942,
      "grad_norm": 612.4532470703125,
      "learning_rate": 2e-05,
      "loss": 2.0209,
      "step": 57
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 375.0256652832031,
      "learning_rate": 2e-05,
      "loss": 3.1054,
      "step": 58
    },
    {
      "epoch": 1.7352941176470589,
      "grad_norm": 63.03890609741211,
      "learning_rate": 2e-05,
      "loss": 1.5422,
      "step": 59
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1484.6824951171875,
      "learning_rate": 2e-05,
      "loss": 2.5796,
      "step": 60
    },
    {
      "epoch": 1.7941176470588234,
      "grad_norm": 209.3314208984375,
      "learning_rate": 2e-05,
      "loss": 2.5442,
      "step": 61
    },
    {
      "epoch": 1.8235294117647058,
      "grad_norm": 187.7886505126953,
      "learning_rate": 2e-05,
      "loss": 3.0212,
      "step": 62
    },
    {
      "epoch": 1.8529411764705883,
      "grad_norm": 510.379150390625,
      "learning_rate": 2e-05,
      "loss": 3.3788,
      "step": 63
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 224.35646057128906,
      "learning_rate": 2e-05,
      "loss": 4.1101,
      "step": 64
    },
    {
      "epoch": 1.9117647058823528,
      "grad_norm": 244.10589599609375,
      "learning_rate": 2e-05,
      "loss": 4.0655,
      "step": 65
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 254.54693603515625,
      "learning_rate": 2e-05,
      "loss": 2.653,
      "step": 66
    },
    {
      "epoch": 1.9705882352941178,
      "grad_norm": 57.74852752685547,
      "learning_rate": 2e-05,
      "loss": 1.993,
      "step": 67
    },
    {
      "epoch": 2.0,
      "grad_norm": 81.31387329101562,
      "learning_rate": 2e-05,
      "loss": 2.6492,
      "step": 68
    },
    {
      "epoch": 2.0294117647058822,
      "grad_norm": 40.57068634033203,
      "learning_rate": 2e-05,
      "loss": 1.0186,
      "step": 69
    },
    {
      "epoch": 2.0588235294117645,
      "grad_norm": 67.01395416259766,
      "learning_rate": 2e-05,
      "loss": 2.239,
      "step": 70
    },
    {
      "epoch": 2.088235294117647,
      "grad_norm": 110.17364501953125,
      "learning_rate": 2e-05,
      "loss": 2.4758,
      "step": 71
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 68.4447021484375,
      "learning_rate": 2e-05,
      "loss": 1.5485,
      "step": 72
    },
    {
      "epoch": 2.1470588235294117,
      "grad_norm": 267.31463623046875,
      "learning_rate": 2e-05,
      "loss": 3.1875,
      "step": 73
    },
    {
      "epoch": 2.176470588235294,
      "grad_norm": 86.10749053955078,
      "learning_rate": 2e-05,
      "loss": 2.3052,
      "step": 74
    },
    {
      "epoch": 2.2058823529411766,
      "grad_norm": 292.28314208984375,
      "learning_rate": 2e-05,
      "loss": 2.8977,
      "step": 75
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 782.0560913085938,
      "learning_rate": 2e-05,
      "loss": 2.7391,
      "step": 76
    },
    {
      "epoch": 2.264705882352941,
      "grad_norm": 132.75177001953125,
      "learning_rate": 2e-05,
      "loss": 1.6825,
      "step": 77
    },
    {
      "epoch": 2.2941176470588234,
      "grad_norm": 231.06690979003906,
      "learning_rate": 2e-05,
      "loss": 1.819,
      "step": 78
    },
    {
      "epoch": 2.323529411764706,
      "grad_norm": 586.24658203125,
      "learning_rate": 2e-05,
      "loss": 1.9857,
      "step": 79
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 77.22154235839844,
      "learning_rate": 2e-05,
      "loss": 1.8883,
      "step": 80
    },
    {
      "epoch": 2.3823529411764706,
      "grad_norm": 214.43612670898438,
      "learning_rate": 2e-05,
      "loss": 3.4815,
      "step": 81
    },
    {
      "epoch": 2.411764705882353,
      "grad_norm": 145.10537719726562,
      "learning_rate": 2e-05,
      "loss": 3.3451,
      "step": 82
    },
    {
      "epoch": 2.4411764705882355,
      "grad_norm": 85.24402618408203,
      "learning_rate": 2e-05,
      "loss": 2.1772,
      "step": 83
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 402.4455261230469,
      "learning_rate": 2e-05,
      "loss": 3.2879,
      "step": 84
    },
    {
      "epoch": 2.5,
      "grad_norm": 77.11824798583984,
      "learning_rate": 2e-05,
      "loss": 1.1511,
      "step": 85
    },
    {
      "epoch": 2.5294117647058822,
      "grad_norm": 106.68152618408203,
      "learning_rate": 2e-05,
      "loss": 1.4542,
      "step": 86
    },
    {
      "epoch": 2.5588235294117645,
      "grad_norm": 84.24452209472656,
      "learning_rate": 2e-05,
      "loss": 1.523,
      "step": 87
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 125.50318145751953,
      "learning_rate": 2e-05,
      "loss": 2.8231,
      "step": 88
    },
    {
      "epoch": 2.6176470588235294,
      "grad_norm": 41.62876510620117,
      "learning_rate": 2e-05,
      "loss": 1.5234,
      "step": 89
    },
    {
      "epoch": 2.6470588235294117,
      "grad_norm": 204.7890167236328,
      "learning_rate": 2e-05,
      "loss": 1.3231,
      "step": 90
    },
    {
      "epoch": 2.6764705882352944,
      "grad_norm": 336.05963134765625,
      "learning_rate": 2e-05,
      "loss": 1.5473,
      "step": 91
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 167.6499786376953,
      "learning_rate": 2e-05,
      "loss": 2.2598,
      "step": 92
    },
    {
      "epoch": 2.735294117647059,
      "grad_norm": 39.165950775146484,
      "learning_rate": 2e-05,
      "loss": 0.5955,
      "step": 93
    },
    {
      "epoch": 2.764705882352941,
      "grad_norm": 103.95963287353516,
      "learning_rate": 2e-05,
      "loss": 1.3233,
      "step": 94
    },
    {
      "epoch": 2.7941176470588234,
      "grad_norm": 141.0578155517578,
      "learning_rate": 2e-05,
      "loss": 2.0557,
      "step": 95
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 79.57919311523438,
      "learning_rate": 2e-05,
      "loss": 2.6418,
      "step": 96
    },
    {
      "epoch": 2.8529411764705883,
      "grad_norm": 167.03134155273438,
      "learning_rate": 2e-05,
      "loss": 2.3345,
      "step": 97
    },
    {
      "epoch": 2.8823529411764706,
      "grad_norm": 1838.4185791015625,
      "learning_rate": 2e-05,
      "loss": 3.5249,
      "step": 98
    },
    {
      "epoch": 2.911764705882353,
      "grad_norm": 724.2003173828125,
      "learning_rate": 2e-05,
      "loss": 1.6495,
      "step": 99
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 703.0057373046875,
      "learning_rate": 2e-05,
      "loss": 2.7896,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 331537700093952.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}