{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3529411764705883,
  "eval_steps": 10,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 123.9454574584961,
      "learning_rate": 7e-06,
      "loss": 4.7042,
      "step": 10
    },
    {
      "epoch": 0.11764705882352941,
      "eval_loss": 4.442946434020996,
      "eval_runtime": 9.6408,
      "eval_samples_per_second": 564.786,
      "eval_steps_per_second": 8.92,
      "step": 10
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 92.6566390991211,
      "learning_rate": 1.7e-05,
      "loss": 4.168,
      "step": 20
    },
    {
      "epoch": 0.23529411764705882,
      "eval_loss": 3.8164174556732178,
      "eval_runtime": 9.6135,
      "eval_samples_per_second": 566.388,
      "eval_steps_per_second": 8.946,
      "step": 20
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 79.20145416259766,
      "learning_rate": 1.9222222222222225e-05,
      "loss": 3.4261,
      "step": 30
    },
    {
      "epoch": 0.35294117647058826,
      "eval_loss": 3.0521063804626465,
      "eval_runtime": 9.6635,
      "eval_samples_per_second": 563.46,
      "eval_steps_per_second": 8.899,
      "step": 30
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 74.91513061523438,
      "learning_rate": 1.8111111111111112e-05,
      "loss": 2.4283,
      "step": 40
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 2.2814009189605713,
      "eval_runtime": 9.6413,
      "eval_samples_per_second": 564.758,
      "eval_steps_per_second": 8.92,
      "step": 40
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 54.24647903442383,
      "learning_rate": 1.7e-05,
      "loss": 1.5579,
      "step": 50
    },
    {
      "epoch": 0.5882352941176471,
      "eval_loss": 1.4840773344039917,
      "eval_runtime": 9.7205,
      "eval_samples_per_second": 560.159,
      "eval_steps_per_second": 8.847,
      "step": 50
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 41.453800201416016,
      "learning_rate": 1.588888888888889e-05,
      "loss": 0.8196,
      "step": 60
    },
    {
      "epoch": 0.7058823529411765,
      "eval_loss": 1.028959035873413,
      "eval_runtime": 9.7872,
      "eval_samples_per_second": 556.341,
      "eval_steps_per_second": 8.787,
      "step": 60
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 31.6336612701416,
      "learning_rate": 1.477777777777778e-05,
      "loss": 0.4275,
      "step": 70
    },
    {
      "epoch": 0.8235294117647058,
      "eval_loss": 0.9401000142097473,
      "eval_runtime": 9.8905,
      "eval_samples_per_second": 550.53,
      "eval_steps_per_second": 8.695,
      "step": 70
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 31.739768981933594,
      "learning_rate": 1.3666666666666667e-05,
      "loss": 0.3215,
      "step": 80
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.876151978969574,
      "eval_runtime": 9.9605,
      "eval_samples_per_second": 546.659,
      "eval_steps_per_second": 8.634,
      "step": 80
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 32.853572845458984,
      "learning_rate": 1.2555555555555557e-05,
      "loss": 0.3068,
      "step": 90
    },
    {
      "epoch": 1.0588235294117647,
      "eval_loss": 0.872206449508667,
      "eval_runtime": 10.0229,
      "eval_samples_per_second": 543.258,
      "eval_steps_per_second": 8.58,
      "step": 90
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 41.155303955078125,
      "learning_rate": 1.1444444444444444e-05,
      "loss": 0.2794,
      "step": 100
    },
    {
      "epoch": 1.1764705882352942,
      "eval_loss": 0.8592934608459473,
      "eval_runtime": 10.1063,
      "eval_samples_per_second": 538.774,
      "eval_steps_per_second": 8.51,
      "step": 100
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 40.7620735168457,
      "learning_rate": 1.0333333333333335e-05,
      "loss": 0.2882,
      "step": 110
    },
    {
      "epoch": 1.2941176470588236,
      "eval_loss": 0.8575130701065063,
      "eval_runtime": 10.1379,
      "eval_samples_per_second": 537.092,
      "eval_steps_per_second": 8.483,
      "step": 110
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 36.15983963012695,
      "learning_rate": 9.222222222222224e-06,
      "loss": 0.2279,
      "step": 120
    },
    {
      "epoch": 1.4117647058823528,
      "eval_loss": 0.834524929523468,
      "eval_runtime": 10.3032,
      "eval_samples_per_second": 528.475,
      "eval_steps_per_second": 8.347,
      "step": 120
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 39.788455963134766,
      "learning_rate": 8.111111111111112e-06,
      "loss": 0.2172,
      "step": 130
    },
    {
      "epoch": 1.5294117647058822,
      "eval_loss": 0.8397492170333862,
      "eval_runtime": 10.2209,
      "eval_samples_per_second": 532.731,
      "eval_steps_per_second": 8.414,
      "step": 130
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 39.91408157348633,
      "learning_rate": 7e-06,
      "loss": 0.3203,
      "step": 140
    },
    {
      "epoch": 1.6470588235294117,
      "eval_loss": 0.8325490355491638,
      "eval_runtime": 10.216,
      "eval_samples_per_second": 532.989,
      "eval_steps_per_second": 8.418,
      "step": 140
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 32.257728576660156,
      "learning_rate": 5.88888888888889e-06,
      "loss": 0.2022,
      "step": 150
    },
    {
      "epoch": 1.7647058823529411,
      "eval_loss": 0.8284817337989807,
      "eval_runtime": 10.1662,
      "eval_samples_per_second": 535.596,
      "eval_steps_per_second": 8.459,
      "step": 150
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 19.03813934326172,
      "learning_rate": 4.777777777777778e-06,
      "loss": 0.2078,
      "step": 160
    },
    {
      "epoch": 1.8823529411764706,
      "eval_loss": 0.8244841694831848,
      "eval_runtime": 10.1785,
      "eval_samples_per_second": 534.951,
      "eval_steps_per_second": 8.449,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.51860237121582,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.1584,
      "step": 170
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8192431926727295,
      "eval_runtime": 10.15,
      "eval_samples_per_second": 536.454,
      "eval_steps_per_second": 8.473,
      "step": 170
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 21.15154266357422,
      "learning_rate": 2.5555555555555557e-06,
      "loss": 0.1569,
      "step": 180
    },
    {
      "epoch": 2.1176470588235294,
      "eval_loss": 0.8104143142700195,
      "eval_runtime": 10.1376,
      "eval_samples_per_second": 537.111,
      "eval_steps_per_second": 8.483,
      "step": 180
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 27.973337173461914,
      "learning_rate": 1.4444444444444445e-06,
      "loss": 0.1517,
      "step": 190
    },
    {
      "epoch": 2.235294117647059,
      "eval_loss": 0.8075307607650757,
      "eval_runtime": 10.2062,
      "eval_samples_per_second": 533.499,
      "eval_steps_per_second": 8.426,
      "step": 190
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 42.8331298828125,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.1646,
      "step": 200
    },
    {
      "epoch": 2.3529411764705883,
      "eval_loss": 0.807045042514801,
      "eval_runtime": 10.3431,
      "eval_samples_per_second": 526.439,
      "eval_steps_per_second": 8.315,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 2500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}