{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9607843137254903,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 39.0,
      "learning_rate": 2.1296160035092786e-06,
      "loss": 3.2954,
      "step": 5
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 32.5,
      "learning_rate": 4.791636007895876e-06,
      "loss": 3.1065,
      "step": 10
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 22.5,
      "learning_rate": 7.453656012282475e-06,
      "loss": 2.7239,
      "step": 15
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 14.125,
      "learning_rate": 1.0115676016669073e-05,
      "loss": 2.3646,
      "step": 20
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 11.6875,
      "learning_rate": 1.2777696021055669e-05,
      "loss": 2.2096,
      "step": 25
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 10.375,
      "learning_rate": 1.3301162443729815e-05,
      "loss": 2.0956,
      "step": 30
    },
    {
      "epoch": 0.6862745098039216,
      "grad_norm": 9.6875,
      "learning_rate": 1.3264899241847857e-05,
      "loss": 2.0555,
      "step": 35
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 10.6875,
      "learning_rate": 1.320092076314487e-05,
      "loss": 2.0435,
      "step": 40
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 9.125,
      "learning_rate": 1.3109525304822242e-05,
      "loss": 1.9732,
      "step": 45
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 12.1875,
      "learning_rate": 1.2991138994696549e-05,
      "loss": 2.0273,
      "step": 50
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 1.8947075605392456,
      "eval_runtime": 2.9897,
      "eval_samples_per_second": 33.113,
      "eval_steps_per_second": 33.113,
      "step": 50
    },
    {
      "epoch": 1.0784313725490196,
      "grad_norm": 9.125,
      "learning_rate": 1.2846313804394955e-05,
      "loss": 1.7671,
      "step": 55
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 9.125,
      "learning_rate": 1.2675724975808696e-05,
      "loss": 1.7969,
      "step": 60
    },
    {
      "epoch": 1.2745098039215685,
      "grad_norm": 9.6875,
      "learning_rate": 1.2480167872803672e-05,
      "loss": 1.7652,
      "step": 65
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 9.5,
      "learning_rate": 1.226055427286695e-05,
      "loss": 1.7045,
      "step": 70
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 9.9375,
      "learning_rate": 1.2017908115979228e-05,
      "loss": 1.7647,
      "step": 75
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 10.25,
      "learning_rate": 1.1753360730533978e-05,
      "loss": 1.693,
      "step": 80
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 10.875,
      "learning_rate": 1.1468145558562219e-05,
      "loss": 1.7666,
      "step": 85
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 11.1875,
      "learning_rate": 1.1163592404856405e-05,
      "loss": 1.7751,
      "step": 90
    },
    {
      "epoch": 1.8627450980392157,
      "grad_norm": 10.125,
      "learning_rate": 1.0841121236806615e-05,
      "loss": 1.7446,
      "step": 95
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 10.8125,
      "learning_rate": 1.0502235563857085e-05,
      "loss": 1.769,
      "step": 100
    },
    {
      "epoch": 1.9607843137254903,
      "eval_loss": 1.8683315515518188,
      "eval_runtime": 2.8557,
      "eval_samples_per_second": 34.667,
      "eval_steps_per_second": 34.667,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 255,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.185757206109225e+17,
  "train_batch_size": 100,
  "trial_name": null,
  "trial_params": null
}