{
  "best_metric": 0.8863966683436749,
  "best_model_checkpoint": "./stool-condition-classification\\checkpoint-300",
  "epoch": 5.882352941176471,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.00019980392156862745,
      "loss": 0.6109,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019960784313725492,
      "loss": 0.5518,
      "step": 20
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019941176470588236,
      "loss": 0.4854,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001992156862745098,
      "loss": 0.5984,
      "step": 40
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019901960784313727,
      "loss": 0.5832,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019882352941176472,
      "loss": 0.5199,
      "step": 60
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019862745098039218,
      "loss": 0.5347,
      "step": 70
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019843137254901963,
      "loss": 0.5159,
      "step": 80
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019823529411764707,
      "loss": 0.5069,
      "step": 90
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019803921568627454,
      "loss": 0.5303,
      "step": 100
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.7941952506596306,
      "eval_auroc": 0.8826094247861815,
      "eval_f1": 0.7664670658682635,
      "eval_loss": 0.43268465995788574,
      "eval_runtime": 19.5335,
      "eval_samples_per_second": 19.403,
      "eval_sensitivity": 0.7191011235955056,
      "eval_specificty": 0.8606965174129353,
      "eval_steps_per_second": 2.457,
      "step": 100
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019784313725490198,
      "loss": 0.514,
      "step": 110
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019764705882352942,
      "loss": 0.3919,
      "step": 120
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001974509803921569,
      "loss": 0.5246,
      "step": 130
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019725490196078433,
      "loss": 0.5262,
      "step": 140
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019705882352941177,
      "loss": 0.4092,
      "step": 150
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019686274509803922,
      "loss": 0.6038,
      "step": 160
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019666666666666666,
      "loss": 0.5079,
      "step": 170
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00019647058823529413,
      "loss": 0.4992,
      "step": 180
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00019627450980392157,
      "loss": 0.4788,
      "step": 190
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.000196078431372549,
      "loss": 0.3909,
      "step": 200
    },
    {
      "epoch": 1.96,
      "eval_accuracy": 0.8047493403693932,
      "eval_auroc": 0.8674604505562076,
      "eval_f1": 0.8042328042328041,
      "eval_loss": 0.5196136832237244,
      "eval_runtime": 19.2864,
      "eval_samples_per_second": 19.651,
      "eval_sensitivity": 0.8539325842696629,
      "eval_specificty": 0.7611940298507462,
      "eval_steps_per_second": 2.489,
      "step": 200
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00019588235294117648,
      "loss": 0.4421,
      "step": 210
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00019568627450980392,
      "loss": 0.4479,
      "step": 220
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00019549019607843136,
      "loss": 0.4655,
      "step": 230
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00019529411764705883,
      "loss": 0.4479,
      "step": 240
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00019509803921568628,
      "loss": 0.3894,
      "step": 250
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00019490196078431372,
      "loss": 0.4315,
      "step": 260
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001947058823529412,
      "loss": 0.4783,
      "step": 270
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00019450980392156863,
      "loss": 0.3792,
      "step": 280
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001943137254901961,
      "loss": 0.5301,
      "step": 290
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00019411764705882354,
      "loss": 0.5328,
      "step": 300
    },
    {
      "epoch": 2.94,
      "eval_accuracy": 0.8073878627968337,
      "eval_auroc": 0.8863966683436749,
      "eval_f1": 0.7859237536656891,
      "eval_loss": 0.4421083927154541,
      "eval_runtime": 19.1397,
      "eval_samples_per_second": 19.802,
      "eval_sensitivity": 0.7528089887640449,
      "eval_specificty": 0.8557213930348259,
      "eval_steps_per_second": 2.508,
      "step": 300
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00019392156862745098,
      "loss": 0.4437,
      "step": 310
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00019372549019607845,
      "loss": 0.3859,
      "step": 320
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001935294117647059,
      "loss": 0.4995,
      "step": 330
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.4282,
      "step": 340
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0001931372549019608,
      "loss": 0.4742,
      "step": 350
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.00019294117647058825,
      "loss": 0.4219,
      "step": 360
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001927450980392157,
      "loss": 0.4531,
      "step": 370
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.00019254901960784316,
      "loss": 0.545,
      "step": 380
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0001923529411764706,
      "loss": 0.4216,
      "step": 390
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.00019215686274509807,
      "loss": 0.4834,
      "step": 400
    },
    {
      "epoch": 3.92,
      "eval_accuracy": 0.7757255936675461,
      "eval_auroc": 0.8596483872770976,
      "eval_f1": 0.7492625368731564,
      "eval_loss": 0.4720683693885803,
      "eval_runtime": 19.0669,
      "eval_samples_per_second": 19.877,
      "eval_sensitivity": 0.7134831460674157,
      "eval_specificty": 0.8308457711442786,
      "eval_steps_per_second": 2.517,
      "step": 400
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001919607843137255,
      "loss": 0.3281,
      "step": 410
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.00019176470588235295,
      "loss": 0.5168,
      "step": 420
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00019156862745098042,
      "loss": 0.5219,
      "step": 430
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00019137254901960786,
      "loss": 0.4131,
      "step": 440
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001911764705882353,
      "loss": 0.4494,
      "step": 450
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.00019098039215686277,
      "loss": 0.4206,
      "step": 460
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.00019078431372549022,
      "loss": 0.3932,
      "step": 470
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00019058823529411766,
      "loss": 0.4607,
      "step": 480
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0001903921568627451,
      "loss": 0.3892,
      "step": 490
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00019019607843137254,
      "loss": 0.4209,
      "step": 500
    },
    {
      "epoch": 4.9,
      "eval_accuracy": 0.7862796833773087,
      "eval_auroc": 0.8624853261780983,
      "eval_f1": 0.7492260061919503,
      "eval_loss": 0.47969380021095276,
      "eval_runtime": 18.951,
      "eval_samples_per_second": 19.999,
      "eval_sensitivity": 0.6797752808988764,
      "eval_specificty": 0.8805970149253731,
      "eval_steps_per_second": 2.533,
      "step": 500
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00019,
      "loss": 0.3681,
      "step": 510
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00018980392156862745,
      "loss": 0.397,
      "step": 520
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.0001896078431372549,
      "loss": 0.3833,
      "step": 530
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00018941176470588236,
      "loss": 0.4202,
      "step": 540
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.0001892156862745098,
      "loss": 0.4304,
      "step": 550
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00018901960784313725,
      "loss": 0.3883,
      "step": 560
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.00018882352941176472,
      "loss": 0.4737,
      "step": 570
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.00018862745098039216,
      "loss": 0.4661,
      "step": 580
    },
    {
      "epoch": 5.78,
      "learning_rate": 0.0001884313725490196,
      "loss": 0.3469,
      "step": 590
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.00018823529411764707,
      "loss": 0.4567,
      "step": 600
    },
    {
      "epoch": 5.88,
      "eval_accuracy": 0.7941952506596306,
      "eval_auroc": 0.8687741069931243,
      "eval_f1": 0.7328767123287672,
      "eval_loss": 0.514951765537262,
      "eval_runtime": 18.7983,
      "eval_samples_per_second": 20.161,
      "eval_sensitivity": 0.601123595505618,
      "eval_specificty": 0.9651741293532339,
      "eval_steps_per_second": 2.553,
      "step": 600
    },
    {
      "epoch": 5.88,
      "step": 600,
      "total_flos": 7.412108806635725e+17,
      "train_loss": 0.4638279656569163,
      "train_runtime": 457.0802,
      "train_samples_per_second": 355.517,
      "train_steps_per_second": 22.316
    }
  ],
  "logging_steps": 10,
  "max_steps": 10200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 100,
  "total_flos": 7.412108806635725e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}