{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7647058823529411,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 0.9765625,
      "learning_rate": 2e-05,
      "loss": 2.0227,
      "step": 1
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 0.8125,
      "learning_rate": 4e-05,
      "loss": 1.6615,
      "step": 2
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 0.90625,
      "learning_rate": 6e-05,
      "loss": 1.9129,
      "step": 3
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.296875,
      "learning_rate": 8e-05,
      "loss": 2.2892,
      "step": 4
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001,
      "loss": 2.0247,
      "step": 5
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00012,
      "loss": 1.8962,
      "step": 6
    },
    {
      "epoch": 0.20588235294117646,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00014,
      "loss": 1.703,
      "step": 7
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00016,
      "loss": 1.5534,
      "step": 8
    },
    {
      "epoch": 0.2647058823529412,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00018,
      "loss": 1.4303,
      "step": 9
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.83203125,
      "learning_rate": 0.0002,
      "loss": 1.3701,
      "step": 10
    },
    {
      "epoch": 0.3235294117647059,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019985334138511237,
      "loss": 1.3449,
      "step": 11
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00019941379571543596,
      "loss": 1.3191,
      "step": 12
    },
    {
      "epoch": 0.38235294117647056,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00019868265225415265,
      "loss": 1.0243,
      "step": 13
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019766205557100868,
      "loss": 1.0321,
      "step": 14
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 1.21875,
      "learning_rate": 0.0001963549992519223,
      "loss": 1.2083,
      "step": 15
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.140625,
      "learning_rate": 0.00019476531711828027,
      "loss": 1.2976,
      "step": 16
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.125,
      "learning_rate": 0.00019289767198167916,
      "loss": 1.0929,
      "step": 17
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.9081,
      "step": 18
    },
    {
      "epoch": 0.5588235294117647,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001883512044446023,
      "loss": 0.9417,
      "step": 19
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00018568571761675893,
      "loss": 0.9065,
      "step": 20
    },
    {
      "epoch": 0.6176470588235294,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00018276889981568906,
      "loss": 0.9419,
      "step": 21
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 1.109375,
      "learning_rate": 0.00017960930657056438,
      "loss": 0.9199,
      "step": 22
    },
    {
      "epoch": 0.6764705882352942,
      "grad_norm": 1.15625,
      "learning_rate": 0.00017621620551276366,
      "loss": 0.9139,
      "step": 23
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001725995491923131,
      "loss": 0.7512,
      "step": 24
    },
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 1.234375,
      "learning_rate": 0.00016876994588534234,
      "loss": 0.7435,
      "step": 25
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00016473862847818277,
      "loss": 0.7502,
      "step": 26
    },
    {
      "epoch": 0.7941176470588235,
      "grad_norm": 1.390625,
      "learning_rate": 0.00016051742151937655,
      "loss": 0.956,
      "step": 27
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.8827,
      "step": 28
    },
    {
      "epoch": 0.8529411764705882,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00015155538571770218,
      "loss": 0.7322,
      "step": 29
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00014684084406997903,
      "loss": 0.7407,
      "step": 30
    },
    {
      "epoch": 0.9117647058823529,
      "grad_norm": 0.89453125,
      "learning_rate": 0.00014198891015602646,
      "loss": 0.8105,
      "step": 31
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.3125,
      "learning_rate": 0.00013701381553399145,
      "loss": 0.9126,
      "step": 32
    },
    {
      "epoch": 0.9705882352941176,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000131930153013598,
      "loss": 0.9439,
      "step": 33
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00012675283385292212,
      "loss": 0.7298,
      "step": 34
    },
    {
      "epoch": 1.0294117647058822,
      "grad_norm": 0.87890625,
      "learning_rate": 0.00012149704402110243,
      "loss": 0.4975,
      "step": 35
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.84765625,
      "learning_rate": 0.0001161781996552765,
      "loss": 0.8089,
      "step": 36
    },
    {
      "epoch": 1.088235294117647,
      "grad_norm": 0.83203125,
      "learning_rate": 0.00011081190184239419,
      "loss": 0.6845,
      "step": 37
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.8515625,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.5513,
      "step": 38
    },
    {
      "epoch": 1.1470588235294117,
      "grad_norm": 0.76953125,
      "learning_rate": 0.0001,
      "loss": 0.6271,
      "step": 39
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.71484375,
      "learning_rate": 9.458610914145826e-05,
      "loss": 0.5144,
      "step": 40
    },
    {
      "epoch": 1.2058823529411764,
      "grad_norm": 0.87890625,
      "learning_rate": 8.918809815760585e-05,
      "loss": 0.7141,
      "step": 41
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.91796875,
      "learning_rate": 8.382180034472353e-05,
      "loss": 0.6109,
      "step": 42
    },
    {
      "epoch": 1.2647058823529411,
      "grad_norm": 0.921875,
      "learning_rate": 7.85029559788976e-05,
      "loss": 0.6952,
      "step": 43
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.77734375,
      "learning_rate": 7.324716614707793e-05,
      "loss": 0.6302,
      "step": 44
    },
    {
      "epoch": 1.3235294117647058,
      "grad_norm": 0.734375,
      "learning_rate": 6.806984698640202e-05,
      "loss": 0.4617,
      "step": 45
    },
    {
      "epoch": 1.3529411764705883,
      "grad_norm": 0.9921875,
      "learning_rate": 6.298618446600856e-05,
      "loss": 0.4288,
      "step": 46
    },
    {
      "epoch": 1.3823529411764706,
      "grad_norm": 0.859375,
      "learning_rate": 5.801108984397354e-05,
      "loss": 0.5413,
      "step": 47
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.83203125,
      "learning_rate": 5.3159155930021e-05,
      "loss": 0.5586,
      "step": 48
    },
    {
      "epoch": 1.4411764705882353,
      "grad_norm": 0.96875,
      "learning_rate": 4.844461428229782e-05,
      "loss": 0.7129,
      "step": 49
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.73828125,
      "learning_rate": 4.388129346376178e-05,
      "loss": 0.5006,
      "step": 50
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.88671875,
      "learning_rate": 3.948257848062351e-05,
      "loss": 0.6091,
      "step": 51
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.015625,
      "learning_rate": 3.5261371521817244e-05,
      "loss": 0.5783,
      "step": 52
    },
    {
      "epoch": 1.5588235294117647,
      "grad_norm": 1.1875,
      "learning_rate": 3.123005411465766e-05,
      "loss": 0.817,
      "step": 53
    },
    {
      "epoch": 1.5882352941176472,
      "grad_norm": 0.88671875,
      "learning_rate": 2.7400450807686938e-05,
      "loss": 0.632,
      "step": 54
    },
    {
      "epoch": 1.6176470588235294,
      "grad_norm": 0.97265625,
      "learning_rate": 2.3783794487236365e-05,
      "loss": 0.6843,
      "step": 55
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.76953125,
      "learning_rate": 2.0390693429435627e-05,
      "loss": 0.448,
      "step": 56
    },
    {
      "epoch": 1.6764705882352942,
      "grad_norm": 0.7578125,
      "learning_rate": 1.7231100184310956e-05,
      "loss": 0.4553,
      "step": 57
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.89453125,
      "learning_rate": 1.4314282383241096e-05,
      "loss": 0.3936,
      "step": 58
    },
    {
      "epoch": 1.7352941176470589,
      "grad_norm": 1.046875,
      "learning_rate": 1.1648795555397719e-05,
      "loss": 0.6992,
      "step": 59
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.98046875,
      "learning_rate": 9.242458032904311e-06,
      "loss": 0.6984,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 68,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 12,
  "total_flos": 1.776820044127273e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}