{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 551,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03634711494775102,
      "grad_norm": 1.1015625,
      "learning_rate": 4.997919498361457e-05,
      "loss": 1.0851,
      "step": 20
    },
    {
      "epoch": 0.07269422989550205,
      "grad_norm": 0.90625,
      "learning_rate": 4.969106773218577e-05,
      "loss": 1.017,
      "step": 40
    },
    {
      "epoch": 0.10904134484325306,
      "grad_norm": 0.9375,
      "learning_rate": 4.906779742499551e-05,
      "loss": 0.9936,
      "step": 60
    },
    {
      "epoch": 0.1453884597910041,
      "grad_norm": 0.80078125,
      "learning_rate": 4.811784399247625e-05,
      "loss": 0.9768,
      "step": 80
    },
    {
      "epoch": 0.18173557473875512,
      "grad_norm": 0.75,
      "learning_rate": 4.685410158321884e-05,
      "loss": 0.9572,
      "step": 100
    },
    {
      "epoch": 0.21808268968650613,
      "grad_norm": 0.83984375,
      "learning_rate": 4.5293723545848285e-05,
      "loss": 0.9608,
      "step": 120
    },
    {
      "epoch": 0.25442980463425713,
      "grad_norm": 0.71875,
      "learning_rate": 4.345788959884658e-05,
      "loss": 0.9339,
      "step": 140
    },
    {
      "epoch": 0.2907769195820082,
      "grad_norm": 0.77734375,
      "learning_rate": 4.137151834863213e-05,
      "loss": 0.9492,
      "step": 160
    },
    {
      "epoch": 0.3271240345297592,
      "grad_norm": 0.7265625,
      "learning_rate": 3.9062929058018275e-05,
      "loss": 0.945,
      "step": 180
    },
    {
      "epoch": 0.36347114947751025,
      "grad_norm": 0.76953125,
      "learning_rate": 3.656345725602089e-05,
      "loss": 0.93,
      "step": 200
    },
    {
      "epoch": 0.39981826442526125,
      "grad_norm": 0.7421875,
      "learning_rate": 3.390702940651737e-05,
      "loss": 0.9214,
      "step": 220
    },
    {
      "epoch": 0.43616537937301225,
      "grad_norm": 0.6953125,
      "learning_rate": 3.1129702408972315e-05,
      "loss": 0.9016,
      "step": 240
    },
    {
      "epoch": 0.4725124943207633,
      "grad_norm": 0.6875,
      "learning_rate": 2.8269174181795e-05,
      "loss": 0.9047,
      "step": 260
    },
    {
      "epoch": 0.5088596092685143,
      "grad_norm": 0.6953125,
      "learning_rate": 2.536427197140289e-05,
      "loss": 0.9123,
      "step": 280
    },
    {
      "epoch": 0.5452067242162654,
      "grad_norm": 0.66796875,
      "learning_rate": 2.2454425332404122e-05,
      "loss": 0.8958,
      "step": 300
    },
    {
      "epoch": 0.5815538391640164,
      "grad_norm": 0.6640625,
      "learning_rate": 1.9579130932377774e-05,
      "loss": 0.9014,
      "step": 320
    },
    {
      "epoch": 0.6179009541117674,
      "grad_norm": 0.63671875,
      "learning_rate": 1.6777416445699508e-05,
      "loss": 0.9097,
      "step": 340
    },
    {
      "epoch": 0.6542480690595184,
      "grad_norm": 0.59765625,
      "learning_rate": 1.4087310813224414e-05,
      "loss": 0.8954,
      "step": 360
    },
    {
      "epoch": 0.6905951840072694,
      "grad_norm": 0.66015625,
      "learning_rate": 1.15453280582328e-05,
      "loss": 0.8896,
      "step": 380
    },
    {
      "epoch": 0.7269422989550205,
      "grad_norm": 0.6328125,
      "learning_rate": 9.185971665038959e-06,
      "loss": 0.8946,
      "step": 400
    },
    {
      "epoch": 0.7632894139027715,
      "grad_norm": 0.609375,
      "learning_rate": 7.041266247556813e-06,
      "loss": 0.8794,
      "step": 420
    },
    {
      "epoch": 0.7996365288505225,
      "grad_norm": 0.65234375,
      "learning_rate": 5.140322864697183e-06,
      "loss": 0.8875,
      "step": 440
    },
    {
      "epoch": 0.8359836437982735,
      "grad_norm": 0.62109375,
      "learning_rate": 3.508943882768065e-06,
      "loss": 0.8903,
      "step": 460
    },
    {
      "epoch": 0.8723307587460245,
      "grad_norm": 0.66796875,
      "learning_rate": 2.169272748259454e-06,
      "loss": 0.9018,
      "step": 480
    },
    {
      "epoch": 0.9086778736937755,
      "grad_norm": 1.453125,
      "learning_rate": 1.1394934248056765e-06,
      "loss": 0.8806,
      "step": 500
    },
    {
      "epoch": 0.9086778736937755,
      "eval_loss": 0.9066952466964722,
      "eval_runtime": 9.9793,
      "eval_samples_per_second": 142.595,
      "eval_steps_per_second": 4.509,
      "step": 500
    },
    {
      "epoch": 0.9450249886415266,
      "grad_norm": 0.6328125,
      "learning_rate": 4.335835740034516e-07,
      "loss": 0.8712,
      "step": 520
    },
    {
      "epoch": 0.9813721035892776,
      "grad_norm": 0.640625,
      "learning_rate": 6.11248302744255e-08,
      "loss": 0.8882,
      "step": 540
    }
  ],
  "logging_steps": 20,
  "max_steps": 551,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.138689887309922e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}