{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 42.99601593625498,
  "eval_steps": 500,
  "global_step": 2698,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9880478087649402,
      "grad_norm": 0.2889673113822937,
      "learning_rate": 0.0002974798061389337,
      "loss": 0.7635,
      "step": 62
    },
    {
      "epoch": 1.9920318725099602,
      "grad_norm": 0.34704622626304626,
      "learning_rate": 0.0002944264943457189,
      "loss": 0.5643,
      "step": 125
    },
    {
      "epoch": 2.99601593625498,
      "grad_norm": 0.32337236404418945,
      "learning_rate": 0.00029137318255250403,
      "loss": 0.47,
      "step": 188
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5398977994918823,
      "learning_rate": 0.00028831987075928915,
      "loss": 0.3844,
      "step": 251
    },
    {
      "epoch": 4.98804780876494,
      "grad_norm": 0.4496667981147766,
      "learning_rate": 0.0002853150242326333,
      "loss": 0.3176,
      "step": 313
    },
    {
      "epoch": 5.99203187250996,
      "grad_norm": 0.4373694062232971,
      "learning_rate": 0.0002822617124394184,
      "loss": 0.2479,
      "step": 376
    },
    {
      "epoch": 6.99601593625498,
      "grad_norm": 0.5146955251693726,
      "learning_rate": 0.0002792084006462035,
      "loss": 0.1915,
      "step": 439
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.5761932134628296,
      "learning_rate": 0.00027615508885298865,
      "loss": 0.1465,
      "step": 502
    },
    {
      "epoch": 8.98804780876494,
      "grad_norm": 0.46838995814323425,
      "learning_rate": 0.00027315024232633277,
      "loss": 0.1184,
      "step": 564
    },
    {
      "epoch": 9.99203187250996,
      "grad_norm": 0.39898747205734253,
      "learning_rate": 0.0002700969305331179,
      "loss": 0.0931,
      "step": 627
    },
    {
      "epoch": 10.996015936254981,
      "grad_norm": 0.4515402615070343,
      "learning_rate": 0.000267043618739903,
      "loss": 0.0776,
      "step": 690
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.2392401546239853,
      "learning_rate": 0.0002639903069466882,
      "loss": 0.0685,
      "step": 753
    },
    {
      "epoch": 12.98804780876494,
      "grad_norm": 0.3774527609348297,
      "learning_rate": 0.00026098546042003227,
      "loss": 0.0622,
      "step": 815
    },
    {
      "epoch": 13.99203187250996,
      "grad_norm": 0.22206874191761017,
      "learning_rate": 0.0002579321486268174,
      "loss": 0.0534,
      "step": 878
    },
    {
      "epoch": 14.996015936254981,
      "grad_norm": 0.25606569647789,
      "learning_rate": 0.00025487883683360257,
      "loss": 0.0504,
      "step": 941
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.3752060830593109,
      "learning_rate": 0.0002518255250403877,
      "loss": 0.0469,
      "step": 1004
    },
    {
      "epoch": 16.98804780876494,
      "grad_norm": 0.3305172920227051,
      "learning_rate": 0.0002488206785137318,
      "loss": 0.0445,
      "step": 1066
    },
    {
      "epoch": 17.992031872509962,
      "grad_norm": 0.2901972234249115,
      "learning_rate": 0.00024576736672051694,
      "loss": 0.0418,
      "step": 1129
    },
    {
      "epoch": 18.99601593625498,
      "grad_norm": 0.3044564127922058,
      "learning_rate": 0.0002427140549273021,
      "loss": 0.0425,
      "step": 1192
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.2603231966495514,
      "learning_rate": 0.00023966074313408722,
      "loss": 0.0392,
      "step": 1255
    },
    {
      "epoch": 20.98804780876494,
      "grad_norm": 0.2220539152622223,
      "learning_rate": 0.00023665589660743132,
      "loss": 0.0371,
      "step": 1317
    },
    {
      "epoch": 21.992031872509962,
      "grad_norm": 0.20209918916225433,
      "learning_rate": 0.00023360258481421647,
      "loss": 0.0335,
      "step": 1380
    },
    {
      "epoch": 22.99601593625498,
      "grad_norm": 0.271361380815506,
      "learning_rate": 0.0002305492730210016,
      "loss": 0.034,
      "step": 1443
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.29796579480171204,
      "learning_rate": 0.00022749596122778674,
      "loss": 0.0334,
      "step": 1506
    },
    {
      "epoch": 24.98804780876494,
      "grad_norm": 0.2501268684864044,
      "learning_rate": 0.00022449111470113084,
      "loss": 0.0341,
      "step": 1568
    },
    {
      "epoch": 25.992031872509962,
      "grad_norm": 0.24419628083705902,
      "learning_rate": 0.00022143780290791596,
      "loss": 0.0339,
      "step": 1631
    },
    {
      "epoch": 26.99601593625498,
      "grad_norm": 0.2808271050453186,
      "learning_rate": 0.00021838449111470111,
      "loss": 0.0342,
      "step": 1694
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.2101186364889145,
      "learning_rate": 0.00021533117932148624,
      "loss": 0.0349,
      "step": 1757
    },
    {
      "epoch": 28.98804780876494,
      "grad_norm": 0.3779149353504181,
      "learning_rate": 0.00021232633279483034,
      "loss": 0.0338,
      "step": 1819
    },
    {
      "epoch": 29.992031872509962,
      "grad_norm": 0.21218642592430115,
      "learning_rate": 0.00020927302100161549,
      "loss": 0.0324,
      "step": 1882
    },
    {
      "epoch": 30.99601593625498,
      "grad_norm": 0.19775445759296417,
      "learning_rate": 0.0002062197092084006,
      "loss": 0.0301,
      "step": 1945
    },
    {
      "epoch": 32.0,
      "grad_norm": 0.3647628724575043,
      "learning_rate": 0.00020316639741518576,
      "loss": 0.0292,
      "step": 2008
    },
    {
      "epoch": 32.98804780876494,
      "grad_norm": 0.146266907453537,
      "learning_rate": 0.00020016155088852986,
      "loss": 0.0296,
      "step": 2070
    },
    {
      "epoch": 33.99203187250996,
      "grad_norm": 0.17022199928760529,
      "learning_rate": 0.00019710823909531498,
      "loss": 0.0269,
      "step": 2133
    },
    {
      "epoch": 34.99601593625498,
      "grad_norm": 0.12986156344413757,
      "learning_rate": 0.00019405492730210016,
      "loss": 0.0257,
      "step": 2196
    },
    {
      "epoch": 36.0,
      "grad_norm": 0.10818672925233841,
      "learning_rate": 0.00019100161550888528,
      "loss": 0.0262,
      "step": 2259
    },
    {
      "epoch": 36.98804780876494,
      "grad_norm": 0.33398228883743286,
      "learning_rate": 0.0001879967689822294,
      "loss": 0.0263,
      "step": 2321
    },
    {
      "epoch": 37.99203187250996,
      "grad_norm": 0.1804308295249939,
      "learning_rate": 0.00018494345718901453,
      "loss": 0.0259,
      "step": 2384
    },
    {
      "epoch": 38.99601593625498,
      "grad_norm": 0.17181633412837982,
      "learning_rate": 0.00018189014539579966,
      "loss": 0.0246,
      "step": 2447
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.18690842390060425,
      "learning_rate": 0.0001788368336025848,
      "loss": 0.0237,
      "step": 2510
    },
    {
      "epoch": 40.98804780876494,
      "grad_norm": 0.11291439831256866,
      "learning_rate": 0.0001758319870759289,
      "loss": 0.0241,
      "step": 2572
    },
    {
      "epoch": 41.99203187250996,
      "grad_norm": 0.14739790558815002,
      "learning_rate": 0.00017277867528271403,
      "loss": 0.0237,
      "step": 2635
    },
    {
      "epoch": 42.99601593625498,
      "grad_norm": 0.14795717597007751,
      "learning_rate": 0.00016972536348949918,
      "loss": 0.0222,
      "step": 2698
    }
  ],
  "logging_steps": 1,
  "max_steps": 6200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4005000741639619e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}