{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 11940,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8375209380234506,
      "grad_norm": 0.8667312860488892,
      "learning_rate": 4.581239530988275e-05,
      "loss": 7.6874,
      "step": 500
    },
    {
      "epoch": 1.675041876046901,
      "grad_norm": 1.0515320301055908,
      "learning_rate": 4.16247906197655e-05,
      "loss": 7.1236,
      "step": 1000
    },
    {
      "epoch": 2.5125628140703515,
      "grad_norm": 0.9544970393180847,
      "learning_rate": 3.7437185929648245e-05,
      "loss": 6.9511,
      "step": 1500
    },
    {
      "epoch": 3.3500837520938025,
      "grad_norm": 1.0608201026916504,
      "learning_rate": 3.324958123953099e-05,
      "loss": 6.8374,
      "step": 2000
    },
    {
      "epoch": 4.187604690117253,
      "grad_norm": 1.3822133541107178,
      "learning_rate": 2.906197654941374e-05,
      "loss": 6.7455,
      "step": 2500
    },
    {
      "epoch": 5.025125628140704,
      "grad_norm": 1.3496253490447998,
      "learning_rate": 2.4874371859296484e-05,
      "loss": 6.6841,
      "step": 3000
    },
    {
      "epoch": 5.8626465661641545,
      "grad_norm": 1.0734386444091797,
      "learning_rate": 2.0686767169179232e-05,
      "loss": 6.6407,
      "step": 3500
    },
    {
      "epoch": 6.700167504187605,
      "grad_norm": 1.4356346130371094,
      "learning_rate": 1.6499162479061976e-05,
      "loss": 6.6059,
      "step": 4000
    },
    {
      "epoch": 7.5376884422110555,
      "grad_norm": 1.3260369300842285,
      "learning_rate": 1.2311557788944725e-05,
      "loss": 6.5782,
      "step": 4500
    },
    {
      "epoch": 8.375209380234505,
      "grad_norm": 1.589943528175354,
      "learning_rate": 8.123953098827471e-06,
      "loss": 6.5581,
      "step": 5000
    },
    {
      "epoch": 9.212730318257956,
      "grad_norm": 1.1932653188705444,
      "learning_rate": 3.936348408710218e-06,
      "loss": 6.5496,
      "step": 5500
    },
    {
      "epoch": 10.0,
      "step": 5970,
      "total_flos": 7568723438714880.0,
      "train_loss": 6.792878454773869,
      "train_runtime": 2074.686,
      "train_samples_per_second": 92.024,
      "train_steps_per_second": 2.878
    },
    {
      "epoch": 10.050251256281408,
      "grad_norm": 1.6812041997909546,
      "learning_rate": 4.9874371859296486e-05,
      "loss": 6.5362,
      "step": 6000
    },
    {
      "epoch": 10.887772194304858,
      "grad_norm": 1.7040314674377441,
      "learning_rate": 4.778056951423786e-05,
      "loss": 6.542,
      "step": 6500
    },
    {
      "epoch": 11.725293132328309,
      "grad_norm": 1.5005360841751099,
      "learning_rate": 4.568676716917923e-05,
      "loss": 6.4812,
      "step": 7000
    },
    {
      "epoch": 12.56281407035176,
      "grad_norm": 2.1963107585906982,
      "learning_rate": 4.35929648241206e-05,
      "loss": 6.4312,
      "step": 7500
    },
    {
      "epoch": 13.40033500837521,
      "grad_norm": 1.4487565755844116,
      "learning_rate": 4.1499162479061974e-05,
      "loss": 6.4049,
      "step": 8000
    },
    {
      "epoch": 14.23785594639866,
      "grad_norm": 1.7677375078201294,
      "learning_rate": 3.940536013400335e-05,
      "loss": 6.3664,
      "step": 8500
    },
    {
      "epoch": 15.075376884422111,
      "grad_norm": 1.8846427202224731,
      "learning_rate": 3.731155778894472e-05,
      "loss": 6.3339,
      "step": 9000
    },
    {
      "epoch": 15.912897822445562,
      "grad_norm": 1.711972713470459,
      "learning_rate": 3.5217755443886095e-05,
      "loss": 6.3093,
      "step": 9500
    },
    {
      "epoch": 16.75041876046901,
      "grad_norm": 1.8777658939361572,
      "learning_rate": 3.312395309882747e-05,
      "loss": 6.2826,
      "step": 10000
    },
    {
      "epoch": 17.587939698492463,
      "grad_norm": 1.5985726118087769,
      "learning_rate": 3.103015075376884e-05,
      "loss": 6.2612,
      "step": 10500
    },
    {
      "epoch": 18.42546063651591,
      "grad_norm": 1.8098769187927246,
      "learning_rate": 2.8936348408710216e-05,
      "loss": 6.2504,
      "step": 11000
    },
    {
      "epoch": 19.262981574539364,
      "grad_norm": 1.4644687175750732,
      "learning_rate": 2.684254606365159e-05,
      "loss": 6.2358,
      "step": 11500
    },
    {
      "epoch": 20.0,
      "step": 11940,
      "total_flos": 1.513744687742976e+16,
      "train_loss": 3.172654545207319,
      "train_runtime": 2061.7586,
      "train_samples_per_second": 185.201,
      "train_steps_per_second": 5.791
    }
  ],
  "logging_steps": 500,
  "max_steps": 11940,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.513744687742976e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}