{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018823529411764704,
      "grad_norm": 17.5,
      "learning_rate": 0.0,
      "loss": 1.918,
      "step": 1
    },
    {
      "epoch": 0.03764705882352941,
      "grad_norm": 10.4375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2871,
      "step": 2
    },
    {
      "epoch": 0.05647058823529412,
      "grad_norm": 13.375,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2926,
      "step": 3
    },
    {
      "epoch": 0.07529411764705882,
      "grad_norm": 13.9375,
      "learning_rate": 6e-06,
      "loss": 1.8351,
      "step": 4
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 13.625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.5611,
      "step": 5
    },
    {
      "epoch": 0.11294117647058824,
      "grad_norm": 10.1875,
      "learning_rate": 1e-05,
      "loss": 1.5454,
      "step": 6
    },
    {
      "epoch": 0.13176470588235295,
      "grad_norm": 6.71875,
      "learning_rate": 9.795918367346939e-06,
      "loss": 1.5545,
      "step": 7
    },
    {
      "epoch": 0.15058823529411763,
      "grad_norm": 5.5,
      "learning_rate": 9.591836734693878e-06,
      "loss": 1.3483,
      "step": 8
    },
    {
      "epoch": 0.16941176470588235,
      "grad_norm": 6.6875,
      "learning_rate": 9.387755102040818e-06,
      "loss": 1.3901,
      "step": 9
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 4.9375,
      "learning_rate": 9.183673469387756e-06,
      "loss": 1.5227,
      "step": 10
    },
    {
      "epoch": 0.18823529411764706,
      "eval_loss": 1.383549451828003,
      "eval_model_preparation_time": 0.019,
      "eval_runtime": 7.7252,
      "eval_samples_per_second": 27.572,
      "eval_steps_per_second": 13.851,
      "step": 10
    },
    {
      "epoch": 0.20705882352941177,
      "grad_norm": 4.4375,
      "learning_rate": 8.979591836734695e-06,
      "loss": 1.1463,
      "step": 11
    },
    {
      "epoch": 0.22588235294117648,
      "grad_norm": 4.65625,
      "learning_rate": 8.775510204081633e-06,
      "loss": 1.0785,
      "step": 12
    },
    {
      "epoch": 0.2447058823529412,
      "grad_norm": 3.75,
      "learning_rate": 8.571428571428571e-06,
      "loss": 1.415,
      "step": 13
    },
    {
      "epoch": 0.2635294117647059,
      "grad_norm": 4.5625,
      "learning_rate": 8.36734693877551e-06,
      "loss": 1.5631,
      "step": 14
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 3.203125,
      "learning_rate": 8.16326530612245e-06,
      "loss": 1.2296,
      "step": 15
    },
    {
      "epoch": 0.30117647058823527,
      "grad_norm": 2.765625,
      "learning_rate": 7.959183673469388e-06,
      "loss": 0.9519,
      "step": 16
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.546875,
      "learning_rate": 7.755102040816327e-06,
      "loss": 1.3223,
      "step": 17
    },
    {
      "epoch": 0.3388235294117647,
      "grad_norm": 2.703125,
      "learning_rate": 7.551020408163265e-06,
      "loss": 0.8857,
      "step": 18
    },
    {
      "epoch": 0.35764705882352943,
      "grad_norm": 4.21875,
      "learning_rate": 7.346938775510205e-06,
      "loss": 1.1416,
      "step": 19
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 4.0625,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 1.1297,
      "step": 20
    },
    {
      "epoch": 0.3764705882352941,
      "eval_loss": 1.2308512926101685,
      "eval_model_preparation_time": 0.019,
      "eval_runtime": 7.6768,
      "eval_samples_per_second": 27.746,
      "eval_steps_per_second": 13.938,
      "step": 20
    },
    {
      "epoch": 0.3952941176470588,
      "grad_norm": 4.25,
      "learning_rate": 6.938775510204082e-06,
      "loss": 1.2702,
      "step": 21
    },
    {
      "epoch": 0.41411764705882353,
      "grad_norm": 3.03125,
      "learning_rate": 6.734693877551021e-06,
      "loss": 1.1395,
      "step": 22
    },
    {
      "epoch": 0.4329411764705882,
      "grad_norm": 2.609375,
      "learning_rate": 6.530612244897959e-06,
      "loss": 0.8718,
      "step": 23
    },
    {
      "epoch": 0.45176470588235296,
      "grad_norm": 3.578125,
      "learning_rate": 6.326530612244899e-06,
      "loss": 1.0863,
      "step": 24
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 3.765625,
      "learning_rate": 6.122448979591837e-06,
      "loss": 1.0913,
      "step": 25
    },
    {
      "epoch": 0.4894117647058824,
      "grad_norm": 2.828125,
      "learning_rate": 5.918367346938776e-06,
      "loss": 1.0977,
      "step": 26
    },
    {
      "epoch": 0.508235294117647,
      "grad_norm": 4.15625,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 1.2962,
      "step": 27
    },
    {
      "epoch": 0.5270588235294118,
      "grad_norm": 3.421875,
      "learning_rate": 5.510204081632653e-06,
      "loss": 1.1993,
      "step": 28
    },
    {
      "epoch": 0.5458823529411765,
      "grad_norm": 3.34375,
      "learning_rate": 5.306122448979593e-06,
      "loss": 1.028,
      "step": 29
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 4.46875,
      "learning_rate": 5.1020408163265315e-06,
      "loss": 1.2644,
      "step": 30
    },
    {
      "epoch": 0.5647058823529412,
      "eval_loss": 1.1749615669250488,
      "eval_model_preparation_time": 0.019,
      "eval_runtime": 7.6725,
      "eval_samples_per_second": 27.762,
      "eval_steps_per_second": 13.946,
      "step": 30
    },
    {
      "epoch": 0.5835294117647059,
      "grad_norm": 3.515625,
      "learning_rate": 4.897959183673469e-06,
      "loss": 1.0328,
      "step": 31
    },
    {
      "epoch": 0.6023529411764705,
      "grad_norm": 4.1875,
      "learning_rate": 4.693877551020409e-06,
      "loss": 1.2546,
      "step": 32
    },
    {
      "epoch": 0.6211764705882353,
      "grad_norm": 3.78125,
      "learning_rate": 4.489795918367348e-06,
      "loss": 1.3015,
      "step": 33
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.734375,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.8548,
      "step": 34
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 3.234375,
      "learning_rate": 4.081632653061225e-06,
      "loss": 1.0775,
      "step": 35
    },
    {
      "epoch": 0.6776470588235294,
      "grad_norm": 3.625,
      "learning_rate": 3.877551020408164e-06,
      "loss": 1.1389,
      "step": 36
    },
    {
      "epoch": 0.6964705882352941,
      "grad_norm": 3.078125,
      "learning_rate": 3.6734693877551024e-06,
      "loss": 1.0469,
      "step": 37
    },
    {
      "epoch": 0.7152941176470589,
      "grad_norm": 3.03125,
      "learning_rate": 3.469387755102041e-06,
      "loss": 1.3002,
      "step": 38
    },
    {
      "epoch": 0.7341176470588235,
      "grad_norm": 3.359375,
      "learning_rate": 3.2653061224489794e-06,
      "loss": 1.1927,
      "step": 39
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 2.53125,
      "learning_rate": 3.0612244897959185e-06,
      "loss": 0.9141,
      "step": 40
    },
    {
      "epoch": 0.7529411764705882,
      "eval_loss": 1.1439083814620972,
      "eval_model_preparation_time": 0.019,
      "eval_runtime": 7.7509,
      "eval_samples_per_second": 27.481,
      "eval_steps_per_second": 13.805,
      "step": 40
    },
    {
      "epoch": 0.7717647058823529,
      "grad_norm": 2.59375,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.973,
      "step": 41
    },
    {
      "epoch": 0.7905882352941176,
      "grad_norm": 3.5,
      "learning_rate": 2.6530612244897964e-06,
      "loss": 1.061,
      "step": 42
    },
    {
      "epoch": 0.8094117647058824,
      "grad_norm": 3.140625,
      "learning_rate": 2.4489795918367347e-06,
      "loss": 1.0456,
      "step": 43
    },
    {
      "epoch": 0.8282352941176471,
      "grad_norm": 2.796875,
      "learning_rate": 2.244897959183674e-06,
      "loss": 1.229,
      "step": 44
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 2.78125,
      "learning_rate": 2.0408163265306125e-06,
      "loss": 0.9546,
      "step": 45
    },
    {
      "epoch": 0.8658823529411764,
      "grad_norm": 3.21875,
      "learning_rate": 1.8367346938775512e-06,
      "loss": 0.9939,
      "step": 46
    },
    {
      "epoch": 0.8847058823529412,
      "grad_norm": 3.25,
      "learning_rate": 1.6326530612244897e-06,
      "loss": 1.0063,
      "step": 47
    },
    {
      "epoch": 0.9035294117647059,
      "grad_norm": 2.625,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.9505,
      "step": 48
    },
    {
      "epoch": 0.9223529411764706,
      "grad_norm": 4.09375,
      "learning_rate": 1.2244897959183673e-06,
      "loss": 1.4137,
      "step": 49
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 2.703125,
      "learning_rate": 1.0204081632653063e-06,
      "loss": 0.8221,
      "step": 50
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 1.1319535970687866,
      "eval_model_preparation_time": 0.019,
      "eval_runtime": 7.7224,
      "eval_samples_per_second": 27.582,
      "eval_steps_per_second": 13.856,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 3.671875,
      "learning_rate": 8.163265306122449e-07,
      "loss": 1.1134,
      "step": 51
    },
    {
      "epoch": 0.9788235294117648,
      "grad_norm": 2.953125,
      "learning_rate": 6.122448979591837e-07,
      "loss": 0.8735,
      "step": 52
    },
    {
      "epoch": 0.9976470588235294,
      "grad_norm": 3.71875,
      "learning_rate": 4.0816326530612243e-07,
      "loss": 1.4566,
      "step": 53
    },
    {
      "epoch": 1.0,
      "grad_norm": 16.5,
      "learning_rate": 2.0408163265306121e-07,
      "loss": 0.7701,
      "step": 54
    }
  ],
  "logging_steps": 1,
  "max_steps": 54,
  "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": 1.048439738253312e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}