{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.36156149370092083,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009039037342523022,
      "grad_norm": 7.855499744415283,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.4181,
      "step": 10
    },
    {
      "epoch": 0.018078074685046044,
      "grad_norm": 3.3778610229492188,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 1.2494,
      "step": 20
    },
    {
      "epoch": 0.027117112027569064,
      "grad_norm": 2.6225311756134033,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 1.0602,
      "step": 30
    },
    {
      "epoch": 0.03615614937009209,
      "grad_norm": 1.594939112663269,
      "learning_rate": 2.6e-06,
      "loss": 0.9123,
      "step": 40
    },
    {
      "epoch": 0.045195186712615104,
      "grad_norm": 0.9766483902931213,
      "learning_rate": 3.266666666666667e-06,
      "loss": 0.7841,
      "step": 50
    },
    {
      "epoch": 0.05423422405513813,
      "grad_norm": 0.43368658423423767,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 0.6803,
      "step": 60
    },
    {
      "epoch": 0.06327326139766115,
      "grad_norm": 0.49014410376548767,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.5921,
      "step": 70
    },
    {
      "epoch": 0.07231229874018417,
      "grad_norm": 0.46368488669395447,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 0.6214,
      "step": 80
    },
    {
      "epoch": 0.0813513360827072,
      "grad_norm": 0.46477940678596497,
      "learning_rate": 5.933333333333335e-06,
      "loss": 0.6157,
      "step": 90
    },
    {
      "epoch": 0.09039037342523021,
      "grad_norm": 0.4853752553462982,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.6628,
      "step": 100
    },
    {
      "epoch": 0.09942941076775323,
      "grad_norm": 0.36940082907676697,
      "learning_rate": 7.266666666666668e-06,
      "loss": 0.5775,
      "step": 110
    },
    {
      "epoch": 0.10846844811027626,
      "grad_norm": 0.34785982966423035,
      "learning_rate": 7.933333333333334e-06,
      "loss": 0.6343,
      "step": 120
    },
    {
      "epoch": 0.11750748545279928,
      "grad_norm": 0.4787227511405945,
      "learning_rate": 8.6e-06,
      "loss": 0.6016,
      "step": 130
    },
    {
      "epoch": 0.1265465227953223,
      "grad_norm": 0.4643513262271881,
      "learning_rate": 9.266666666666667e-06,
      "loss": 0.6388,
      "step": 140
    },
    {
      "epoch": 0.1355855601378453,
      "grad_norm": 0.384676456451416,
      "learning_rate": 9.933333333333334e-06,
      "loss": 0.5895,
      "step": 150
    },
    {
      "epoch": 0.14462459748036835,
      "grad_norm": 0.4324859380722046,
      "learning_rate": 9.99991503499922e-06,
      "loss": 0.5942,
      "step": 160
    },
    {
      "epoch": 0.15366363482289136,
      "grad_norm": 0.41830965876579285,
      "learning_rate": 9.99962133253095e-06,
      "loss": 0.6121,
      "step": 170
    },
    {
      "epoch": 0.1627026721654144,
      "grad_norm": 0.3795354962348938,
      "learning_rate": 9.999117855964797e-06,
      "loss": 0.6041,
      "step": 180
    },
    {
      "epoch": 0.1717417095079374,
      "grad_norm": 0.28756389021873474,
      "learning_rate": 9.998404626425627e-06,
      "loss": 0.5529,
      "step": 190
    },
    {
      "epoch": 0.18078074685046042,
      "grad_norm": 0.40732458233833313,
      "learning_rate": 9.997481673839125e-06,
      "loss": 0.6321,
      "step": 200
    },
    {
      "epoch": 0.18981978419298345,
      "grad_norm": 0.3699369430541992,
      "learning_rate": 9.996349036930533e-06,
      "loss": 0.5886,
      "step": 210
    },
    {
      "epoch": 0.19885882153550646,
      "grad_norm": 0.4334062337875366,
      "learning_rate": 9.995006763223028e-06,
      "loss": 0.646,
      "step": 220
    },
    {
      "epoch": 0.2078978588780295,
      "grad_norm": 0.3638211786746979,
      "learning_rate": 9.993454909035724e-06,
      "loss": 0.5996,
      "step": 230
    },
    {
      "epoch": 0.2169368962205525,
      "grad_norm": 0.377408891916275,
      "learning_rate": 9.991693539481317e-06,
      "loss": 0.5999,
      "step": 240
    },
    {
      "epoch": 0.22597593356307552,
      "grad_norm": 0.4337885081768036,
      "learning_rate": 9.989722728463345e-06,
      "loss": 0.6233,
      "step": 250
    },
    {
      "epoch": 0.23501497090559856,
      "grad_norm": 0.35624244809150696,
      "learning_rate": 9.98754255867309e-06,
      "loss": 0.6279,
      "step": 260
    },
    {
      "epoch": 0.24405400824812157,
      "grad_norm": 0.385580837726593,
      "learning_rate": 9.985153121586111e-06,
      "loss": 0.5896,
      "step": 270
    },
    {
      "epoch": 0.2530930455906446,
      "grad_norm": 0.36690962314605713,
      "learning_rate": 9.982554517458403e-06,
      "loss": 0.6212,
      "step": 280
    },
    {
      "epoch": 0.26213208293316764,
      "grad_norm": 0.3190907835960388,
      "learning_rate": 9.979746855322192e-06,
      "loss": 0.6019,
      "step": 290
    },
    {
      "epoch": 0.2711711202756906,
      "grad_norm": 0.33014318346977234,
      "learning_rate": 9.976730252981354e-06,
      "loss": 0.5906,
      "step": 300
    },
    {
      "epoch": 0.28021015761821366,
      "grad_norm": 0.4516271650791168,
      "learning_rate": 9.973504837006487e-06,
      "loss": 0.612,
      "step": 310
    },
    {
      "epoch": 0.2892491949607367,
      "grad_norm": 0.3498607873916626,
      "learning_rate": 9.97007074272958e-06,
      "loss": 0.5591,
      "step": 320
    },
    {
      "epoch": 0.2982882323032597,
      "grad_norm": 0.4618026316165924,
      "learning_rate": 9.966428114238353e-06,
      "loss": 0.5808,
      "step": 330
    },
    {
      "epoch": 0.3073272696457827,
      "grad_norm": 0.35378628969192505,
      "learning_rate": 9.962577104370206e-06,
      "loss": 0.5983,
      "step": 340
    },
    {
      "epoch": 0.31636630698830576,
      "grad_norm": 0.3605310916900635,
      "learning_rate": 9.958517874705793e-06,
      "loss": 0.5898,
      "step": 350
    },
    {
      "epoch": 0.3254053443308288,
      "grad_norm": 0.41437646746635437,
      "learning_rate": 9.954250595562267e-06,
      "loss": 0.5746,
      "step": 360
    },
    {
      "epoch": 0.3344443816733518,
      "grad_norm": 0.3715222477912903,
      "learning_rate": 9.949775445986112e-06,
      "loss": 0.5994,
      "step": 370
    },
    {
      "epoch": 0.3434834190158748,
      "grad_norm": 0.41986992955207825,
      "learning_rate": 9.945092613745642e-06,
      "loss": 0.5492,
      "step": 380
    },
    {
      "epoch": 0.35252245635839785,
      "grad_norm": 0.3996647000312805,
      "learning_rate": 9.940202295323116e-06,
      "loss": 0.6066,
      "step": 390
    },
    {
      "epoch": 0.36156149370092083,
      "grad_norm": 0.3808385729789734,
      "learning_rate": 9.935104695906506e-06,
      "loss": 0.5628,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2673534264901837e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}