{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.861003861003861,
  "eval_steps": 100,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 9.922779922779923e-05,
      "loss": 3.4462,
      "step": 100
    },
    {
      "epoch": 0.19,
      "eval_loss": 3.1208043098449707,
      "eval_runtime": 15.8785,
      "eval_samples_per_second": 184.085,
      "eval_steps_per_second": 11.525,
      "step": 100
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.845559845559846e-05,
      "loss": 3.2226,
      "step": 200
    },
    {
      "epoch": 0.39,
      "eval_loss": 3.0490212440490723,
      "eval_runtime": 15.8682,
      "eval_samples_per_second": 184.205,
      "eval_steps_per_second": 11.533,
      "step": 200
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.76833976833977e-05,
      "loss": 3.1286,
      "step": 300
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.997180938720703,
      "eval_runtime": 15.867,
      "eval_samples_per_second": 184.219,
      "eval_steps_per_second": 11.533,
      "step": 300
    },
    {
      "epoch": 0.77,
      "learning_rate": 9.691119691119691e-05,
      "loss": 3.0821,
      "step": 400
    },
    {
      "epoch": 0.77,
      "eval_loss": 2.9679667949676514,
      "eval_runtime": 15.873,
      "eval_samples_per_second": 184.149,
      "eval_steps_per_second": 11.529,
      "step": 400
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.613899613899614e-05,
      "loss": 3.045,
      "step": 500
    },
    {
      "epoch": 0.97,
      "eval_loss": 2.9354896545410156,
      "eval_runtime": 15.8588,
      "eval_samples_per_second": 184.314,
      "eval_steps_per_second": 11.539,
      "step": 500
    },
    {
      "epoch": 1.16,
      "learning_rate": 9.536679536679537e-05,
      "loss": 2.7369,
      "step": 600
    },
    {
      "epoch": 1.16,
      "eval_loss": 2.94718337059021,
      "eval_runtime": 15.8507,
      "eval_samples_per_second": 184.408,
      "eval_steps_per_second": 11.545,
      "step": 600
    },
    {
      "epoch": 1.35,
      "learning_rate": 9.45945945945946e-05,
      "loss": 2.7055,
      "step": 700
    },
    {
      "epoch": 1.35,
      "eval_loss": 2.9227750301361084,
      "eval_runtime": 15.882,
      "eval_samples_per_second": 184.044,
      "eval_steps_per_second": 11.522,
      "step": 700
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.382239382239383e-05,
      "loss": 2.7295,
      "step": 800
    },
    {
      "epoch": 1.54,
      "eval_loss": 2.9112653732299805,
      "eval_runtime": 15.8678,
      "eval_samples_per_second": 184.21,
      "eval_steps_per_second": 11.533,
      "step": 800
    },
    {
      "epoch": 1.74,
      "learning_rate": 9.305019305019306e-05,
      "loss": 2.7564,
      "step": 900
    },
    {
      "epoch": 1.74,
      "eval_loss": 2.9080774784088135,
      "eval_runtime": 15.8632,
      "eval_samples_per_second": 184.263,
      "eval_steps_per_second": 11.536,
      "step": 900
    },
    {
      "epoch": 1.93,
      "learning_rate": 9.227799227799229e-05,
      "loss": 2.7854,
      "step": 1000
    },
    {
      "epoch": 1.93,
      "eval_loss": 2.8891797065734863,
      "eval_runtime": 15.854,
      "eval_samples_per_second": 184.369,
      "eval_steps_per_second": 11.543,
      "step": 1000
    },
    {
      "epoch": 2.12,
      "learning_rate": 9.15057915057915e-05,
      "loss": 2.5298,
      "step": 1100
    },
    {
      "epoch": 2.12,
      "eval_loss": 2.9245471954345703,
      "eval_runtime": 15.8964,
      "eval_samples_per_second": 183.878,
      "eval_steps_per_second": 11.512,
      "step": 1100
    },
    {
      "epoch": 2.32,
      "learning_rate": 9.073359073359073e-05,
      "loss": 2.4042,
      "step": 1200
    },
    {
      "epoch": 2.32,
      "eval_loss": 2.9138386249542236,
      "eval_runtime": 15.8757,
      "eval_samples_per_second": 184.117,
      "eval_steps_per_second": 11.527,
      "step": 1200
    },
    {
      "epoch": 2.51,
      "learning_rate": 8.996138996138996e-05,
      "loss": 2.454,
      "step": 1300
    },
    {
      "epoch": 2.51,
      "eval_loss": 2.910158157348633,
      "eval_runtime": 15.8495,
      "eval_samples_per_second": 184.422,
      "eval_steps_per_second": 11.546,
      "step": 1300
    },
    {
      "epoch": 2.7,
      "learning_rate": 8.918918918918919e-05,
      "loss": 2.4826,
      "step": 1400
    },
    {
      "epoch": 2.7,
      "eval_loss": 2.8909964561462402,
      "eval_runtime": 15.8725,
      "eval_samples_per_second": 184.155,
      "eval_steps_per_second": 11.529,
      "step": 1400
    },
    {
      "epoch": 2.9,
      "learning_rate": 8.841698841698842e-05,
      "loss": 2.4967,
      "step": 1500
    },
    {
      "epoch": 2.9,
      "eval_loss": 2.899423122406006,
      "eval_runtime": 15.8786,
      "eval_samples_per_second": 184.084,
      "eval_steps_per_second": 11.525,
      "step": 1500
    },
    {
      "epoch": 3.09,
      "learning_rate": 8.764478764478765e-05,
      "loss": 2.3621,
      "step": 1600
    },
    {
      "epoch": 3.09,
      "eval_loss": 2.966057538986206,
      "eval_runtime": 15.8621,
      "eval_samples_per_second": 184.276,
      "eval_steps_per_second": 11.537,
      "step": 1600
    },
    {
      "epoch": 3.28,
      "learning_rate": 8.687258687258688e-05,
      "loss": 2.1633,
      "step": 1700
    },
    {
      "epoch": 3.28,
      "eval_loss": 2.950388193130493,
      "eval_runtime": 15.8876,
      "eval_samples_per_second": 183.98,
      "eval_steps_per_second": 11.518,
      "step": 1700
    },
    {
      "epoch": 3.47,
      "learning_rate": 8.61003861003861e-05,
      "loss": 2.2039,
      "step": 1800
    },
    {
      "epoch": 3.47,
      "eval_loss": 2.9389660358428955,
      "eval_runtime": 15.8602,
      "eval_samples_per_second": 184.298,
      "eval_steps_per_second": 11.538,
      "step": 1800
    },
    {
      "epoch": 3.67,
      "learning_rate": 8.532818532818533e-05,
      "loss": 2.2382,
      "step": 1900
    },
    {
      "epoch": 3.67,
      "eval_loss": 2.94706392288208,
      "eval_runtime": 15.8638,
      "eval_samples_per_second": 184.256,
      "eval_steps_per_second": 11.536,
      "step": 1900
    },
    {
      "epoch": 3.86,
      "learning_rate": 8.455598455598456e-05,
      "loss": 2.2235,
      "step": 2000
    },
    {
      "epoch": 3.86,
      "eval_loss": 2.9332854747772217,
      "eval_runtime": 15.8506,
      "eval_samples_per_second": 184.409,
      "eval_steps_per_second": 11.545,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 12950,
  "num_train_epochs": 25,
  "save_steps": 1000,
  "total_flos": 1.0018169220096e+16,
  "trial_name": null,
  "trial_params": null
}