{
  "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": 0.562045156955719,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.4506,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.04739459231495857,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0059,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.043884556740522385,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.004,
      "step": 30
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.0038693679962307215,
      "eval_runtime": 107.8736,
      "eval_samples_per_second": 9.27,
      "eval_steps_per_second": 0.232,
      "step": 30
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.08048111200332642,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0038,
      "step": 40
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.0661352202296257,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0039,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.04182339832186699,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0037,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.0035931167658418417,
      "eval_runtime": 107.8341,
      "eval_samples_per_second": 9.274,
      "eval_steps_per_second": 0.232,
      "step": 60
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.03875701501965523,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0037,
      "step": 70
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.09161914885044098,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0036,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.012599254958331585,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0036,
      "step": 90
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.0034141503274440765,
      "eval_runtime": 107.7832,
      "eval_samples_per_second": 9.278,
      "eval_steps_per_second": 0.232,
      "step": 90
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.019785044714808464,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0034,
      "step": 100
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.023052237927913666,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0026,
      "step": 110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.06588639318943024,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0017,
      "step": 120
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.0018878360278904438,
      "eval_runtime": 107.8387,
      "eval_samples_per_second": 9.273,
      "eval_steps_per_second": 0.232,
      "step": 120
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.17472058534622192,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0017,
      "step": 130
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.039111748337745667,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0013,
      "step": 140
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.025146929547190666,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0014,
      "step": 150
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.0015465717297047377,
      "eval_runtime": 107.8431,
      "eval_samples_per_second": 9.273,
      "eval_steps_per_second": 0.232,
      "step": 150
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.03978816792368889,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0016,
      "step": 160
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.047893453389406204,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.001,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.033007632941007614,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0013,
      "step": 180
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0011240115854889154,
      "eval_runtime": 107.821,
      "eval_samples_per_second": 9.275,
      "eval_steps_per_second": 0.232,
      "step": 180
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.038735806941986084,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0011,
      "step": 190
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.062001701444387436,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0011,
      "step": 200
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.034057263284921646,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0011,
      "step": 210
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.001115471706725657,
      "eval_runtime": 107.8087,
      "eval_samples_per_second": 9.276,
      "eval_steps_per_second": 0.232,
      "step": 210
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.04986511170864105,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0013,
      "step": 220
    },
    {
      "epoch": 1.0,
      "step": 225,
      "total_flos": 8.322322373856461e+17,
      "train_loss": 0.022414023884468608,
      "train_runtime": 3919.2651,
      "train_samples_per_second": 2.296,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 10,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8.322322373856461e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}