{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.056607111268353084,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028303555634176542,
      "grad_norm": 0.25189030170440674,
      "learning_rate": 1e-05,
      "loss": 10.3994,
      "step": 1
    },
    {
      "epoch": 0.0028303555634176542,
      "eval_loss": 10.435837745666504,
      "eval_runtime": 15.0074,
      "eval_samples_per_second": 39.647,
      "eval_steps_per_second": 19.857,
      "step": 1
    },
    {
      "epoch": 0.0056607111268353084,
      "grad_norm": 0.2289780080318451,
      "learning_rate": 2e-05,
      "loss": 10.4148,
      "step": 2
    },
    {
      "epoch": 0.008491066690252963,
      "grad_norm": 0.2822679281234741,
      "learning_rate": 3e-05,
      "loss": 10.4469,
      "step": 3
    },
    {
      "epoch": 0.011321422253670617,
      "grad_norm": 0.22503499686717987,
      "learning_rate": 4e-05,
      "loss": 10.4274,
      "step": 4
    },
    {
      "epoch": 0.014151777817088271,
      "grad_norm": 0.24327203631401062,
      "learning_rate": 5e-05,
      "loss": 10.4156,
      "step": 5
    },
    {
      "epoch": 0.014151777817088271,
      "eval_loss": 10.435239791870117,
      "eval_runtime": 0.8985,
      "eval_samples_per_second": 662.242,
      "eval_steps_per_second": 331.677,
      "step": 5
    },
    {
      "epoch": 0.016982133380505925,
      "grad_norm": 0.19562780857086182,
      "learning_rate": 6e-05,
      "loss": 10.4608,
      "step": 6
    },
    {
      "epoch": 0.01981248894392358,
      "grad_norm": 0.23854123055934906,
      "learning_rate": 7e-05,
      "loss": 10.4212,
      "step": 7
    },
    {
      "epoch": 0.022642844507341234,
      "grad_norm": 0.19920575618743896,
      "learning_rate": 8e-05,
      "loss": 10.4239,
      "step": 8
    },
    {
      "epoch": 0.02547320007075889,
      "grad_norm": 0.2488528937101364,
      "learning_rate": 9e-05,
      "loss": 10.4237,
      "step": 9
    },
    {
      "epoch": 0.028303555634176542,
      "grad_norm": 0.25861698389053345,
      "learning_rate": 0.0001,
      "loss": 10.4333,
      "step": 10
    },
    {
      "epoch": 0.028303555634176542,
      "eval_loss": 10.433311462402344,
      "eval_runtime": 0.9486,
      "eval_samples_per_second": 627.236,
      "eval_steps_per_second": 314.145,
      "step": 10
    },
    {
      "epoch": 0.031133911197594198,
      "grad_norm": 0.21499280631542206,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.427,
      "step": 11
    },
    {
      "epoch": 0.03396426676101185,
      "grad_norm": 0.23338869214057922,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.4358,
      "step": 12
    },
    {
      "epoch": 0.0367946223244295,
      "grad_norm": 0.2607021927833557,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.4101,
      "step": 13
    },
    {
      "epoch": 0.03962497788784716,
      "grad_norm": 0.2081250101327896,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.4021,
      "step": 14
    },
    {
      "epoch": 0.042455333451264815,
      "grad_norm": 0.23302486538887024,
      "learning_rate": 5e-05,
      "loss": 10.4127,
      "step": 15
    },
    {
      "epoch": 0.042455333451264815,
      "eval_loss": 10.430887222290039,
      "eval_runtime": 0.9221,
      "eval_samples_per_second": 645.281,
      "eval_steps_per_second": 323.183,
      "step": 15
    },
    {
      "epoch": 0.04528568901468247,
      "grad_norm": 0.21131035685539246,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.4549,
      "step": 16
    },
    {
      "epoch": 0.04811604457810013,
      "grad_norm": 0.2003251314163208,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.4232,
      "step": 17
    },
    {
      "epoch": 0.05094640014151778,
      "grad_norm": 0.2581706941127777,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.4216,
      "step": 18
    },
    {
      "epoch": 0.05377675570493543,
      "grad_norm": 0.2147359549999237,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.4219,
      "step": 19
    },
    {
      "epoch": 0.056607111268353084,
      "grad_norm": 0.27223360538482666,
      "learning_rate": 0.0,
      "loss": 10.404,
      "step": 20
    },
    {
      "epoch": 0.056607111268353084,
      "eval_loss": 10.43026065826416,
      "eval_runtime": 0.9038,
      "eval_samples_per_second": 658.328,
      "eval_steps_per_second": 329.717,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1034472652800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}