{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 7500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.0562,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 400
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 600
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 0.0068,
      "step": 800
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 1000
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.0009,
      "step": 1200
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 1400
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.0018,
      "step": 1600
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 1800
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.001,
      "step": 2000
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.0017,
      "step": 2200
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.0018,
      "step": 2400
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 2600
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 0.0023,
      "step": 2800
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 3000
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.0009,
      "step": 3200
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 3400
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 0.0055,
      "step": 3600
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.0083,
      "step": 3800
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.0017,
      "step": 4000
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4200
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4400
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.001,
      "step": 4600
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 0.0006,
      "step": 4800
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.0006,
      "step": 5000
    },
    {
      "epoch": 2.08,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 5200
    },
    {
      "epoch": 2.16,
      "learning_rate": 2e-05,
      "loss": 0.0018,
      "step": 5400
    },
    {
      "epoch": 2.24,
      "learning_rate": 2e-05,
      "loss": 0.0016,
      "step": 5600
    },
    {
      "epoch": 2.32,
      "learning_rate": 2e-05,
      "loss": 0.0008,
      "step": 5800
    },
    {
      "epoch": 2.4,
      "learning_rate": 2e-05,
      "loss": 0.0104,
      "step": 6000
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 0.0016,
      "step": 6200
    },
    {
      "epoch": 2.56,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 6400
    },
    {
      "epoch": 2.64,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 6600
    },
    {
      "epoch": 2.72,
      "learning_rate": 2e-05,
      "loss": 0.0004,
      "step": 6800
    },
    {
      "epoch": 2.8,
      "learning_rate": 2e-05,
      "loss": 0.0016,
      "step": 7000
    },
    {
      "epoch": 2.88,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 7200
    },
    {
      "epoch": 2.96,
      "learning_rate": 2e-05,
      "loss": 0.0021,
      "step": 7400
    },
    {
      "epoch": 3.0,
      "step": 7500,
      "total_flos": 5.614442768026829e+16,
      "train_loss": 0.0007468190386891366,
      "train_runtime": 9266.3598,
      "train_samples_per_second": 51.8,
      "train_steps_per_second": 0.809
    }
  ],
  "logging_steps": 200,
  "max_steps": 7500,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 5.614442768026829e+16,
  "trial_name": null,
  "trial_params": null
}