{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992160961588712,
  "global_step": 478,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 1.2141,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 1.1281,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 1.1091,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 1.0959,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 1.0903,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 1.0811,
      "step": 120
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 1.0693,
      "step": 140
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 1.0702,
      "step": 160
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 1.0631,
      "step": 180
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 1.0627,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 1.0575,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 1.0518,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 1.0492,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 1.0476,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 1.0422,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 1.044,
      "step": 320
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 1.0367,
      "step": 340
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 1.0353,
      "step": 360
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 1.0292,
      "step": 380
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 1.0264,
      "step": 400
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 1.0239,
      "step": 420
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 1.0224,
      "step": 440
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 1.018,
      "step": 460
    },
    {
      "epoch": 1.0,
      "step": 478,
      "total_flos": 3741093011128320.0,
      "train_loss": 1.0616770588703235,
      "train_runtime": 173276.7886,
      "train_samples_per_second": 4.24,
      "train_steps_per_second": 0.003
    }
  ],
  "max_steps": 478,
  "num_train_epochs": 1,
  "total_flos": 3741093011128320.0,
  "trial_name": null,
  "trial_params": null
}