{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 125.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 12.21626091003418,
      "step": 1
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0,
      "learning_rate": 4.91e-05,
      "loss": 12.21626196967231,
      "step": 10
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0,
      "learning_rate": 4.8100000000000004e-05,
      "loss": 12.216262054443359,
      "step": 20
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.0,
      "learning_rate": 4.71e-05,
      "loss": 12.216262054443359,
      "step": 30
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.0,
      "learning_rate": 4.61e-05,
      "loss": 12.216262054443359,
      "step": 40
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.0,
      "learning_rate": 4.5100000000000005e-05,
      "loss": 12.216262054443359,
      "step": 50
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.0,
      "learning_rate": 4.41e-05,
      "loss": 12.216262054443359,
      "step": 60
    },
    {
      "epoch": 17.5,
      "grad_norm": 0.0,
      "learning_rate": 4.3100000000000004e-05,
      "loss": 12.216262054443359,
      "step": 70
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.0,
      "learning_rate": 4.21e-05,
      "loss": 12.216262054443359,
      "step": 80
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.0,
      "learning_rate": 4.11e-05,
      "loss": 12.216262054443359,
      "step": 90
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.0,
      "learning_rate": 4.0100000000000006e-05,
      "loss": 12.216262054443359,
      "step": 100
    },
    {
      "epoch": 27.5,
      "grad_norm": 0.0,
      "learning_rate": 3.91e-05,
      "loss": 12.216262054443359,
      "step": 110
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.0,
      "learning_rate": 3.8100000000000005e-05,
      "loss": 12.216262054443359,
      "step": 120
    },
    {
      "epoch": 32.5,
      "grad_norm": 0.0,
      "learning_rate": 3.71e-05,
      "loss": 12.216262054443359,
      "step": 130
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.0,
      "learning_rate": 3.61e-05,
      "loss": 12.216262054443359,
      "step": 140
    },
    {
      "epoch": 37.5,
      "grad_norm": 0.0,
      "learning_rate": 3.51e-05,
      "loss": 12.216262054443359,
      "step": 150
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.0,
      "learning_rate": 3.41e-05,
      "loss": 12.216262054443359,
      "step": 160
    },
    {
      "epoch": 42.5,
      "grad_norm": 0.0,
      "learning_rate": 3.3100000000000005e-05,
      "loss": 12.216262054443359,
      "step": 170
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.0,
      "learning_rate": 3.21e-05,
      "loss": 12.216262054443359,
      "step": 180
    },
    {
      "epoch": 47.5,
      "grad_norm": 0.0,
      "learning_rate": 3.1100000000000004e-05,
      "loss": 12.216262054443359,
      "step": 190
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.0,
      "learning_rate": 3.01e-05,
      "loss": 12.216262054443359,
      "step": 200
    },
    {
      "epoch": 52.5,
      "grad_norm": 0.0,
      "learning_rate": 2.91e-05,
      "loss": 12.216262054443359,
      "step": 210
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.0,
      "learning_rate": 2.8100000000000005e-05,
      "loss": 12.216262054443359,
      "step": 220
    },
    {
      "epoch": 57.5,
      "grad_norm": 0.0,
      "learning_rate": 2.7100000000000005e-05,
      "loss": 12.216262054443359,
      "step": 230
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.0,
      "learning_rate": 2.61e-05,
      "loss": 12.216262054443359,
      "step": 240
    },
    {
      "epoch": 62.5,
      "grad_norm": 0.0,
      "learning_rate": 2.51e-05,
      "loss": 12.216262054443359,
      "step": 250
    },
    {
      "epoch": 65.0,
      "grad_norm": 0.0,
      "learning_rate": 2.41e-05,
      "loss": 12.216262054443359,
      "step": 260
    },
    {
      "epoch": 67.5,
      "grad_norm": 0.0,
      "learning_rate": 2.3100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 270
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.0,
      "learning_rate": 2.2100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 280
    },
    {
      "epoch": 72.5,
      "grad_norm": 0.0,
      "learning_rate": 2.11e-05,
      "loss": 12.216262054443359,
      "step": 290
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.0,
      "learning_rate": 2.01e-05,
      "loss": 12.216262054443359,
      "step": 300
    },
    {
      "epoch": 77.5,
      "grad_norm": 0.0,
      "learning_rate": 1.91e-05,
      "loss": 12.216262054443359,
      "step": 310
    },
    {
      "epoch": 80.0,
      "grad_norm": 0.0,
      "learning_rate": 1.81e-05,
      "loss": 12.216262054443359,
      "step": 320
    },
    {
      "epoch": 82.5,
      "grad_norm": 0.0,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 330
    },
    {
      "epoch": 85.0,
      "grad_norm": 0.0,
      "learning_rate": 1.6100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 340
    },
    {
      "epoch": 87.5,
      "grad_norm": 0.0,
      "learning_rate": 1.51e-05,
      "loss": 12.216262054443359,
      "step": 350
    },
    {
      "epoch": 90.0,
      "grad_norm": 0.0,
      "learning_rate": 1.4099999999999999e-05,
      "loss": 12.216262054443359,
      "step": 360
    },
    {
      "epoch": 92.5,
      "grad_norm": 0.0,
      "learning_rate": 1.3100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 370
    },
    {
      "epoch": 95.0,
      "grad_norm": 0.0,
      "learning_rate": 1.2100000000000001e-05,
      "loss": 12.216262054443359,
      "step": 380
    },
    {
      "epoch": 97.5,
      "grad_norm": 0.0,
      "learning_rate": 1.11e-05,
      "loss": 12.216262054443359,
      "step": 390
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.0,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 12.216262054443359,
      "step": 400
    },
    {
      "epoch": 102.5,
      "grad_norm": 0.0,
      "learning_rate": 9.100000000000001e-06,
      "loss": 12.216262054443359,
      "step": 410
    },
    {
      "epoch": 105.0,
      "grad_norm": 0.0,
      "learning_rate": 8.1e-06,
      "loss": 12.216262054443359,
      "step": 420
    },
    {
      "epoch": 107.5,
      "grad_norm": 0.0,
      "learning_rate": 7.1e-06,
      "loss": 12.216262054443359,
      "step": 430
    },
    {
      "epoch": 110.0,
      "grad_norm": 0.0,
      "learning_rate": 6.1e-06,
      "loss": 12.216262054443359,
      "step": 440
    },
    {
      "epoch": 112.5,
      "grad_norm": 0.0,
      "learning_rate": 5.1e-06,
      "loss": 12.216262054443359,
      "step": 450
    },
    {
      "epoch": 115.0,
      "grad_norm": 0.0,
      "learning_rate": 4.1000000000000006e-06,
      "loss": 12.216262054443359,
      "step": 460
    },
    {
      "epoch": 117.5,
      "grad_norm": 0.0,
      "learning_rate": 3.1e-06,
      "loss": 12.216262054443359,
      "step": 470
    },
    {
      "epoch": 120.0,
      "grad_norm": 0.0,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 12.216262054443359,
      "step": 480
    },
    {
      "epoch": 122.5,
      "grad_norm": 0.0,
      "learning_rate": 1.1e-06,
      "loss": 12.216262054443359,
      "step": 490
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.0,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 12.216262054443359,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 125,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2013482975232000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}