{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.995245641838352,
  "eval_steps": 500,
  "global_step": 630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "global_step": 20,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.5195,
      "step": 20
    },
    {
      "epoch": 0.19,
      "global_step": 40,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.5055,
      "step": 40
    },
    {
      "epoch": 0.29,
      "global_step": 60,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.5483,
      "step": 60
    },
    {
      "epoch": 0.38,
      "global_step": 80,
      "learning_rate": 0.0001,
      "loss": 0.4659,
      "step": 80
    },
    {
      "epoch": 0.48,
      "global_step": 100,
      "learning_rate": 0.0001,
      "loss": 0.5625,
      "step": 100
    },
    {
      "epoch": 0.57,
      "global_step": 120,
      "learning_rate": 0.0001,
      "loss": 0.545,
      "step": 120
    },
    {
      "epoch": 0.67,
      "global_step": 140,
      "learning_rate": 0.0001,
      "loss": 0.4962,
      "step": 140
    },
    {
      "epoch": 0.76,
      "global_step": 160,
      "learning_rate": 0.0001,
      "loss": 0.5508,
      "step": 160
    },
    {
      "epoch": 0.86,
      "global_step": 180,
      "learning_rate": 0.0001,
      "loss": 0.5314,
      "step": 180
    },
    {
      "epoch": 0.95,
      "global_step": 200,
      "learning_rate": 0.0001,
      "loss": 0.5251,
      "step": 200
    },
    {
      "epoch": 1.05,
      "global_step": 220,
      "learning_rate": 0.0001,
      "loss": 0.347,
      "step": 220
    },
    {
      "epoch": 1.14,
      "global_step": 240,
      "learning_rate": 0.0001,
      "loss": 0.2006,
      "step": 240
    },
    {
      "epoch": 1.24,
      "global_step": 260,
      "learning_rate": 0.0001,
      "loss": 0.165,
      "step": 260
    },
    {
      "epoch": 1.33,
      "global_step": 280,
      "learning_rate": 0.0001,
      "loss": 0.2124,
      "step": 280
    },
    {
      "epoch": 1.43,
      "global_step": 300,
      "learning_rate": 0.0001,
      "loss": 0.2007,
      "step": 300
    },
    {
      "epoch": 1.52,
      "global_step": 320,
      "learning_rate": 0.0001,
      "loss": 0.1981,
      "step": 320
    },
    {
      "epoch": 1.62,
      "global_step": 340,
      "learning_rate": 0.0001,
      "loss": 0.2031,
      "step": 340
    },
    {
      "epoch": 1.71,
      "global_step": 360,
      "learning_rate": 0.0001,
      "loss": 0.1392,
      "step": 360
    },
    {
      "epoch": 1.81,
      "global_step": 380,
      "learning_rate": 0.0001,
      "loss": 0.204,
      "step": 380
    },
    {
      "epoch": 1.9,
      "global_step": 400,
      "learning_rate": 0.0001,
      "loss": 0.1626,
      "step": 400
    },
    {
      "epoch": 2.0,
      "global_step": 420,
      "learning_rate": 0.0001,
      "loss": 0.146,
      "step": 420
    },
    {
      "epoch": 2.09,
      "global_step": 440,
      "learning_rate": 0.0001,
      "loss": 0.0404,
      "step": 440
    },
    {
      "epoch": 2.19,
      "global_step": 460,
      "learning_rate": 0.0001,
      "loss": 0.0304,
      "step": 460
    },
    {
      "epoch": 2.28,
      "global_step": 480,
      "learning_rate": 0.0001,
      "loss": 0.0166,
      "step": 480
    },
    {
      "epoch": 2.38,
      "global_step": 500,
      "learning_rate": 0.0001,
      "loss": 0.0366,
      "step": 500
    },
    {
      "epoch": 2.47,
      "global_step": 520,
      "learning_rate": 0.0001,
      "loss": 0.018,
      "step": 520
    },
    {
      "epoch": 2.57,
      "global_step": 540,
      "learning_rate": 0.0001,
      "loss": 0.0186,
      "step": 540
    },
    {
      "epoch": 2.66,
      "global_step": 560,
      "learning_rate": 0.0001,
      "loss": 0.0308,
      "step": 560
    },
    {
      "epoch": 2.76,
      "global_step": 580,
      "learning_rate": 0.0001,
      "loss": 0.0536,
      "step": 580
    },
    {
      "epoch": 2.85,
      "global_step": 600,
      "learning_rate": 0.0001,
      "loss": 0.0563,
      "step": 600
    },
    {
      "epoch": 2.95,
      "global_step": 620,
      "learning_rate": 0.0001,
      "loss": 0.0242,
      "step": 620
    },
    {
      "epoch": 3.0,
      "step": 630,
      "total_flos": 3.402731466386309e+17,
      "train_loss": 0.24650317042592973,
      "train_runtime": 47469.8541,
      "train_samples_per_second": 0.159,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 20,
  "max_steps": 630,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 3.402731466386309e+17,
  "trial_name": null,
  "trial_params": null
}