{
  "best_metric": 0.9093852639198303,
  "best_model_checkpoint": "GeoBERT/checkpoint-500",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 9.578972816467285,
      "learning_rate": 4.4e-06,
      "loss": 1.3411,
      "step": 11
    },
    {
      "epoch": 0.09,
      "grad_norm": 10.498757362365723,
      "learning_rate": 8.8e-06,
      "loss": 1.2504,
      "step": 22
    },
    {
      "epoch": 0.13,
      "grad_norm": 6.937590599060059,
      "learning_rate": 1.32e-05,
      "loss": 1.234,
      "step": 33
    },
    {
      "epoch": 0.18,
      "grad_norm": 4.935857772827148,
      "learning_rate": 1.76e-05,
      "loss": 1.1156,
      "step": 44
    },
    {
      "epoch": 0.22,
      "grad_norm": 8.856083869934082,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.9942,
      "step": 55
    },
    {
      "epoch": 0.26,
      "grad_norm": 7.843554973602295,
      "learning_rate": 2.64e-05,
      "loss": 0.9665,
      "step": 66
    },
    {
      "epoch": 0.31,
      "grad_norm": 7.1852126121521,
      "learning_rate": 3.08e-05,
      "loss": 1.1064,
      "step": 77
    },
    {
      "epoch": 0.35,
      "grad_norm": 11.667104721069336,
      "learning_rate": 3.52e-05,
      "loss": 1.1114,
      "step": 88
    },
    {
      "epoch": 0.4,
      "grad_norm": 10.513388633728027,
      "learning_rate": 3.960000000000001e-05,
      "loss": 0.9571,
      "step": 99
    },
    {
      "epoch": 0.44,
      "grad_norm": 9.239156723022461,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.93,
      "step": 110
    },
    {
      "epoch": 0.48,
      "grad_norm": 6.3955302238464355,
      "learning_rate": 4.8e-05,
      "loss": 0.9277,
      "step": 121
    },
    {
      "epoch": 0.53,
      "grad_norm": 7.602996826171875,
      "learning_rate": 4.973333333333334e-05,
      "loss": 0.9696,
      "step": 132
    },
    {
      "epoch": 0.57,
      "grad_norm": 6.260980129241943,
      "learning_rate": 4.924444444444445e-05,
      "loss": 0.9792,
      "step": 143
    },
    {
      "epoch": 0.62,
      "grad_norm": 12.462403297424316,
      "learning_rate": 4.875555555555556e-05,
      "loss": 1.1474,
      "step": 154
    },
    {
      "epoch": 0.66,
      "grad_norm": 11.24273681640625,
      "learning_rate": 4.826666666666667e-05,
      "loss": 1.0853,
      "step": 165
    },
    {
      "epoch": 0.7,
      "grad_norm": 5.870580673217773,
      "learning_rate": 4.7777777777777784e-05,
      "loss": 1.0063,
      "step": 176
    },
    {
      "epoch": 0.75,
      "grad_norm": 7.315596580505371,
      "learning_rate": 4.728888888888889e-05,
      "loss": 0.8158,
      "step": 187
    },
    {
      "epoch": 0.79,
      "grad_norm": 9.08304214477539,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 0.8146,
      "step": 198
    },
    {
      "epoch": 0.84,
      "grad_norm": 7.242616176605225,
      "learning_rate": 4.6311111111111113e-05,
      "loss": 0.881,
      "step": 209
    },
    {
      "epoch": 0.88,
      "grad_norm": 6.810551643371582,
      "learning_rate": 4.582222222222222e-05,
      "loss": 1.02,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 9.252344131469727,
      "learning_rate": 4.5333333333333335e-05,
      "loss": 0.8745,
      "step": 231
    },
    {
      "epoch": 0.97,
      "grad_norm": 5.250942707061768,
      "learning_rate": 4.484444444444444e-05,
      "loss": 0.8428,
      "step": 242
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5794979079497908,
      "eval_f1_macro": 0.3207391363205631,
      "eval_f1_micro": 0.5794979079497908,
      "eval_f1_weighted": 0.5288849063689292,
      "eval_loss": 1.0058727264404297,
      "eval_precision_macro": 0.30283025619006726,
      "eval_precision_micro": 0.5794979079497908,
      "eval_precision_weighted": 0.5213967302096602,
      "eval_recall_macro": 0.37342191224507815,
      "eval_recall_micro": 0.5794979079497908,
      "eval_recall_weighted": 0.5794979079497908,
      "eval_runtime": 6.8009,
      "eval_samples_per_second": 70.284,
      "eval_steps_per_second": 4.411,
      "step": 250
    },
    {
      "epoch": 1.01,
      "grad_norm": 8.098525047302246,
      "learning_rate": 4.435555555555556e-05,
      "loss": 0.8954,
      "step": 253
    },
    {
      "epoch": 1.06,
      "grad_norm": 8.491247177124023,
      "learning_rate": 4.3866666666666665e-05,
      "loss": 0.6923,
      "step": 264
    },
    {
      "epoch": 1.1,
      "grad_norm": 8.242985725402832,
      "learning_rate": 4.337777777777778e-05,
      "loss": 0.7433,
      "step": 275
    },
    {
      "epoch": 1.14,
      "grad_norm": 9.606861114501953,
      "learning_rate": 4.2888888888888886e-05,
      "loss": 0.7633,
      "step": 286
    },
    {
      "epoch": 1.19,
      "grad_norm": 4.706633567810059,
      "learning_rate": 4.24e-05,
      "loss": 0.6287,
      "step": 297
    },
    {
      "epoch": 1.23,
      "grad_norm": 16.51137351989746,
      "learning_rate": 4.1911111111111115e-05,
      "loss": 0.6284,
      "step": 308
    },
    {
      "epoch": 1.28,
      "grad_norm": 13.114934921264648,
      "learning_rate": 4.142222222222222e-05,
      "loss": 0.8798,
      "step": 319
    },
    {
      "epoch": 1.32,
      "grad_norm": 10.896364212036133,
      "learning_rate": 4.093333333333334e-05,
      "loss": 0.6527,
      "step": 330
    },
    {
      "epoch": 1.36,
      "grad_norm": 7.2867913246154785,
      "learning_rate": 4.0444444444444444e-05,
      "loss": 0.5512,
      "step": 341
    },
    {
      "epoch": 1.41,
      "grad_norm": 6.902933597564697,
      "learning_rate": 3.995555555555556e-05,
      "loss": 0.7718,
      "step": 352
    },
    {
      "epoch": 1.45,
      "grad_norm": 6.432639122009277,
      "learning_rate": 3.9466666666666666e-05,
      "loss": 0.5573,
      "step": 363
    },
    {
      "epoch": 1.5,
      "grad_norm": 7.4120073318481445,
      "learning_rate": 3.897777777777778e-05,
      "loss": 0.6316,
      "step": 374
    },
    {
      "epoch": 1.54,
      "grad_norm": 4.322595596313477,
      "learning_rate": 3.848888888888889e-05,
      "loss": 0.6219,
      "step": 385
    },
    {
      "epoch": 1.58,
      "grad_norm": 5.752494812011719,
      "learning_rate": 3.8e-05,
      "loss": 0.5568,
      "step": 396
    },
    {
      "epoch": 1.63,
      "grad_norm": 13.906458854675293,
      "learning_rate": 3.7511111111111116e-05,
      "loss": 0.7011,
      "step": 407
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.0408498048782349,
      "learning_rate": 3.7022222222222224e-05,
      "loss": 0.3148,
      "step": 418
    },
    {
      "epoch": 1.72,
      "grad_norm": 9.536336898803711,
      "learning_rate": 3.653333333333334e-05,
      "loss": 0.7209,
      "step": 429
    },
    {
      "epoch": 1.76,
      "grad_norm": 4.775065898895264,
      "learning_rate": 3.6044444444444446e-05,
      "loss": 0.637,
      "step": 440
    },
    {
      "epoch": 1.8,
      "grad_norm": 16.23617172241211,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.6103,
      "step": 451
    },
    {
      "epoch": 1.85,
      "grad_norm": 15.569254875183105,
      "learning_rate": 3.506666666666667e-05,
      "loss": 0.5131,
      "step": 462
    },
    {
      "epoch": 1.89,
      "grad_norm": 11.499606132507324,
      "learning_rate": 3.457777777777778e-05,
      "loss": 0.5525,
      "step": 473
    },
    {
      "epoch": 1.94,
      "grad_norm": 8.275940895080566,
      "learning_rate": 3.408888888888889e-05,
      "loss": 0.5643,
      "step": 484
    },
    {
      "epoch": 1.98,
      "grad_norm": 5.744302272796631,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.4863,
      "step": 495
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6589958158995816,
      "eval_f1_macro": 0.5823605917694434,
      "eval_f1_micro": 0.6589958158995816,
      "eval_f1_weighted": 0.6565370798157575,
      "eval_loss": 0.9093852639198303,
      "eval_precision_macro": 0.6115906152670858,
      "eval_precision_micro": 0.6589958158995816,
      "eval_precision_weighted": 0.6611483212824585,
      "eval_recall_macro": 0.5656902456694988,
      "eval_recall_micro": 0.6589958158995816,
      "eval_recall_weighted": 0.6589958158995816,
      "eval_runtime": 6.8834,
      "eval_samples_per_second": 69.442,
      "eval_steps_per_second": 4.358,
      "step": 500
    }
  ],
  "logging_steps": 11,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1051936888823808.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}