{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 30,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.2802587151527405,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3045,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.021381886675953865,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0054,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.017750784754753113,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0039,
      "step": 30
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.0036237684544175863,
      "eval_runtime": 53.377,
      "eval_samples_per_second": 18.735,
      "eval_steps_per_second": 0.468,
      "step": 30
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.009207488968968391,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0036,
      "step": 40
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.03058847412467003,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0037,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.023914409801363945,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0038,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.0036710596177726984,
      "eval_runtime": 53.396,
      "eval_samples_per_second": 18.728,
      "eval_steps_per_second": 0.468,
      "step": 60
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.0324842669069767,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0036,
      "step": 70
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.002750804414972663,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0036,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0023576547391712666,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0036,
      "step": 90
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.003560666460543871,
      "eval_runtime": 53.4786,
      "eval_samples_per_second": 18.699,
      "eval_steps_per_second": 0.467,
      "step": 90
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.016149163246154785,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0036,
      "step": 100
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.0039548748172819614,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0035,
      "step": 110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.0059623029083013535,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0036,
      "step": 120
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.00353414099663496,
      "eval_runtime": 53.3696,
      "eval_samples_per_second": 18.737,
      "eval_steps_per_second": 0.468,
      "step": 120
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.01755256950855255,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0035,
      "step": 130
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.005563901271671057,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0035,
      "step": 140
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.004853326827287674,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0036,
      "step": 150
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.0035362462513148785,
      "eval_runtime": 53.3856,
      "eval_samples_per_second": 18.732,
      "eval_steps_per_second": 0.468,
      "step": 150
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0062214070931077,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0036,
      "step": 160
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.0025808655191212893,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0035,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.00887165404856205,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0035,
      "step": 180
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0035414749290794134,
      "eval_runtime": 53.35,
      "eval_samples_per_second": 18.744,
      "eval_steps_per_second": 0.469,
      "step": 180
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.005598729941993952,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0035,
      "step": 190
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.010787834413349628,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0035,
      "step": 200
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.00533076049759984,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0035,
      "step": 210
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.003532670671120286,
      "eval_runtime": 53.3444,
      "eval_samples_per_second": 18.746,
      "eval_steps_per_second": 0.469,
      "step": 210
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.006618449930101633,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0035,
      "step": 220
    }
  ],
  "logging_steps": 10,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.559164517091901e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}