{
  "best_metric": 0.374613881111145,
  "best_model_checkpoint": "/leonardo_work/IscrC_AGENT/PROFES2025/results/balanced/oss_large/checkpoint-1234",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1851,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1.9967585089141006e-05,
      "loss": 0.6786,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.993517017828201e-05,
      "loss": 0.6829,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9902755267423015e-05,
      "loss": 0.6582,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9870340356564023e-05,
      "loss": 0.6107,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9837925445705027e-05,
      "loss": 0.6041,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.980551053484603e-05,
      "loss": 0.6188,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9773095623987036e-05,
      "loss": 0.553,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.974068071312804e-05,
      "loss": 0.5662,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9708265802269045e-05,
      "loss": 0.5633,
      "step": 90
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9675850891410053e-05,
      "loss": 0.591,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9643435980551057e-05,
      "loss": 0.5583,
      "step": 110
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.961102106969206e-05,
      "loss": 0.5978,
      "step": 120
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9578606158833066e-05,
      "loss": 0.5829,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.954619124797407e-05,
      "loss": 0.5787,
      "step": 140
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9513776337115075e-05,
      "loss": 0.6376,
      "step": 150
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.948136142625608e-05,
      "loss": 0.5732,
      "step": 160
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9448946515397084e-05,
      "loss": 0.5465,
      "step": 170
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9416531604538088e-05,
      "loss": 0.5513,
      "step": 180
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9384116693679093e-05,
      "loss": 0.6165,
      "step": 190
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9351701782820097e-05,
      "loss": 0.6196,
      "step": 200
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.93192868719611e-05,
      "loss": 0.5344,
      "step": 210
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.928687196110211e-05,
      "loss": 0.6042,
      "step": 220
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9254457050243114e-05,
      "loss": 0.5838,
      "step": 230
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.9222042139384118e-05,
      "loss": 0.4611,
      "step": 240
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9189627228525122e-05,
      "loss": 0.5259,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.9157212317666127e-05,
      "loss": 0.5705,
      "step": 260
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.912479740680713e-05,
      "loss": 0.5051,
      "step": 270
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.909238249594814e-05,
      "loss": 0.5085,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.9059967585089144e-05,
      "loss": 0.5847,
      "step": 290
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.9027552674230148e-05,
      "loss": 0.5183,
      "step": 300
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.8995137763371152e-05,
      "loss": 0.4574,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.8962722852512157e-05,
      "loss": 0.5197,
      "step": 320
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.893030794165316e-05,
      "loss": 0.5033,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.889789303079417e-05,
      "loss": 0.5166,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.8865478119935173e-05,
      "loss": 0.5017,
      "step": 350
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.8833063209076178e-05,
      "loss": 0.501,
      "step": 360
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.8800648298217182e-05,
      "loss": 0.491,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.8768233387358187e-05,
      "loss": 0.463,
      "step": 380
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.873581847649919e-05,
      "loss": 0.6343,
      "step": 390
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.8703403565640196e-05,
      "loss": 0.4775,
      "step": 400
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.86709886547812e-05,
      "loss": 0.5991,
      "step": 410
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.8638573743922204e-05,
      "loss": 0.5008,
      "step": 420
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.860615883306321e-05,
      "loss": 0.4652,
      "step": 430
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8573743922204213e-05,
      "loss": 0.434,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.8541329011345218e-05,
      "loss": 0.5431,
      "step": 450
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8508914100486226e-05,
      "loss": 0.5627,
      "step": 460
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.847649918962723e-05,
      "loss": 0.5589,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.8444084278768234e-05,
      "loss": 0.4425,
      "step": 480
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.841166936790924e-05,
      "loss": 0.5187,
      "step": 490
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8379254457050243e-05,
      "loss": 0.4464,
      "step": 500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.8346839546191248e-05,
      "loss": 0.4694,
      "step": 510
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.8314424635332255e-05,
      "loss": 0.4667,
      "step": 520
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.828200972447326e-05,
      "loss": 0.4848,
      "step": 530
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.8249594813614264e-05,
      "loss": 0.3969,
      "step": 540
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.821717990275527e-05,
      "loss": 0.4058,
      "step": 550
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.8184764991896273e-05,
      "loss": 0.4945,
      "step": 560
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.8152350081037278e-05,
      "loss": 0.4746,
      "step": 570
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8119935170178285e-05,
      "loss": 0.5074,
      "step": 580
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.808752025931929e-05,
      "loss": 0.5437,
      "step": 590
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.8055105348460294e-05,
      "loss": 0.4835,
      "step": 600
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.80226904376013e-05,
      "loss": 0.5425,
      "step": 610
    },
    {
      "epoch": 1.0,
      "eval_FN": 1004,
      "eval_FP": 3324,
      "eval_TN": 12435,
      "eval_TP": 3902,
      "eval_accuracy": 0.7905637551415436,
      "eval_f1": 0.6432575008242664,
      "eval_loss": 0.4139794707298279,
      "eval_precision": 0.5399944644339884,
      "eval_recall": 0.795352629433347,
      "eval_runtime": 142.1799,
      "eval_samples_per_second": 145.344,
      "eval_steps_per_second": 9.087,
      "step": 617
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.7990275526742303e-05,
      "loss": 0.3872,
      "step": 620
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.7957860615883308e-05,
      "loss": 0.3541,
      "step": 630
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.7925445705024312e-05,
      "loss": 0.3185,
      "step": 640
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.7893030794165316e-05,
      "loss": 0.4364,
      "step": 650
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.7860615883306324e-05,
      "loss": 0.4102,
      "step": 660
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.782820097244733e-05,
      "loss": 0.3797,
      "step": 670
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.7795786061588333e-05,
      "loss": 0.3964,
      "step": 680
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.7763371150729338e-05,
      "loss": 0.4649,
      "step": 690
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.7730956239870342e-05,
      "loss": 0.4855,
      "step": 700
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.7698541329011346e-05,
      "loss": 0.4026,
      "step": 710
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.766612641815235e-05,
      "loss": 0.3695,
      "step": 720
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.7633711507293355e-05,
      "loss": 0.4194,
      "step": 730
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.760129659643436e-05,
      "loss": 0.409,
      "step": 740
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.7568881685575364e-05,
      "loss": 0.3952,
      "step": 750
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7536466774716372e-05,
      "loss": 0.4426,
      "step": 760
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.7504051863857376e-05,
      "loss": 0.333,
      "step": 770
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.747163695299838e-05,
      "loss": 0.4531,
      "step": 780
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.7439222042139385e-05,
      "loss": 0.4094,
      "step": 790
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.740680713128039e-05,
      "loss": 0.4931,
      "step": 800
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.7374392220421394e-05,
      "loss": 0.4147,
      "step": 810
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.7341977309562402e-05,
      "loss": 0.3243,
      "step": 820
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.7309562398703406e-05,
      "loss": 0.3881,
      "step": 830
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.727714748784441e-05,
      "loss": 0.4175,
      "step": 840
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.7244732576985415e-05,
      "loss": 0.4215,
      "step": 850
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.721231766612642e-05,
      "loss": 0.4549,
      "step": 860
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.7179902755267424e-05,
      "loss": 0.4592,
      "step": 870
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.7147487844408432e-05,
      "loss": 0.4325,
      "step": 880
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.7115072933549436e-05,
      "loss": 0.3814,
      "step": 890
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.708265802269044e-05,
      "loss": 0.4048,
      "step": 900
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.7050243111831445e-05,
      "loss": 0.375,
      "step": 910
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.701782820097245e-05,
      "loss": 0.3827,
      "step": 920
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.6985413290113454e-05,
      "loss": 0.3957,
      "step": 930
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.695299837925446e-05,
      "loss": 0.4487,
      "step": 940
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.6920583468395463e-05,
      "loss": 0.4007,
      "step": 950
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.6888168557536467e-05,
      "loss": 0.4355,
      "step": 960
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.685575364667747e-05,
      "loss": 0.4302,
      "step": 970
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.6823338735818476e-05,
      "loss": 0.4294,
      "step": 980
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.679092382495948e-05,
      "loss": 0.4039,
      "step": 990
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.6758508914100488e-05,
      "loss": 0.4001,
      "step": 1000
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.6726094003241493e-05,
      "loss": 0.4316,
      "step": 1010
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.6693679092382497e-05,
      "loss": 0.4332,
      "step": 1020
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.66612641815235e-05,
      "loss": 0.4815,
      "step": 1030
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.6628849270664506e-05,
      "loss": 0.3744,
      "step": 1040
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.659643435980551e-05,
      "loss": 0.4437,
      "step": 1050
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.6564019448946518e-05,
      "loss": 0.4247,
      "step": 1060
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.6531604538087523e-05,
      "loss": 0.4649,
      "step": 1070
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.6499189627228527e-05,
      "loss": 0.4461,
      "step": 1080
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.646677471636953e-05,
      "loss": 0.5386,
      "step": 1090
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.6434359805510536e-05,
      "loss": 0.3934,
      "step": 1100
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.640194489465154e-05,
      "loss": 0.4158,
      "step": 1110
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.6369529983792548e-05,
      "loss": 0.2754,
      "step": 1120
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6337115072933553e-05,
      "loss": 0.4166,
      "step": 1130
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.6304700162074557e-05,
      "loss": 0.3605,
      "step": 1140
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.627228525121556e-05,
      "loss": 0.4361,
      "step": 1150
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.6239870340356566e-05,
      "loss": 0.4436,
      "step": 1160
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.620745542949757e-05,
      "loss": 0.4006,
      "step": 1170
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.6175040518638575e-05,
      "loss": 0.2996,
      "step": 1180
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.614262560777958e-05,
      "loss": 0.4593,
      "step": 1190
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.6110210696920584e-05,
      "loss": 0.4633,
      "step": 1200
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.6077795786061588e-05,
      "loss": 0.3404,
      "step": 1210
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.6045380875202596e-05,
      "loss": 0.3477,
      "step": 1220
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.60129659643436e-05,
      "loss": 0.4074,
      "step": 1230
    },
    {
      "epoch": 2.0,
      "eval_FN": 1412,
      "eval_FP": 1850,
      "eval_TN": 13909,
      "eval_TP": 3494,
      "eval_accuracy": 0.8421485603677716,
      "eval_f1": 0.6817560975609757,
      "eval_loss": 0.374613881111145,
      "eval_precision": 0.6538173652694611,
      "eval_recall": 0.7121891561353445,
      "eval_runtime": 142.3346,
      "eval_samples_per_second": 145.186,
      "eval_steps_per_second": 9.077,
      "step": 1234
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.5980551053484605e-05,
      "loss": 0.3298,
      "step": 1240
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.594813614262561e-05,
      "loss": 0.2898,
      "step": 1250
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.5915721231766613e-05,
      "loss": 0.2781,
      "step": 1260
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.5883306320907618e-05,
      "loss": 0.4103,
      "step": 1270
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.5850891410048622e-05,
      "loss": 0.2744,
      "step": 1280
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.5818476499189627e-05,
      "loss": 0.2781,
      "step": 1290
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.578606158833063e-05,
      "loss": 0.2509,
      "step": 1300
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.575364667747164e-05,
      "loss": 0.2638,
      "step": 1310
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.5721231766612643e-05,
      "loss": 0.4286,
      "step": 1320
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.5688816855753648e-05,
      "loss": 0.3699,
      "step": 1330
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.5656401944894652e-05,
      "loss": 0.3562,
      "step": 1340
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.5623987034035657e-05,
      "loss": 0.4909,
      "step": 1350
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.559157212317666e-05,
      "loss": 0.303,
      "step": 1360
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.555915721231767e-05,
      "loss": 0.2468,
      "step": 1370
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.5526742301458673e-05,
      "loss": 0.3632,
      "step": 1380
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.5494327390599678e-05,
      "loss": 0.2486,
      "step": 1390
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.5461912479740682e-05,
      "loss": 0.2667,
      "step": 1400
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.5429497568881687e-05,
      "loss": 0.205,
      "step": 1410
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.539708265802269e-05,
      "loss": 0.2899,
      "step": 1420
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.53646677471637e-05,
      "loss": 0.3234,
      "step": 1430
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.5332252836304703e-05,
      "loss": 0.2796,
      "step": 1440
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.5299837925445708e-05,
      "loss": 0.3992,
      "step": 1450
    },
    {
      "epoch": 2.37,
      "learning_rate": 1.5267423014586712e-05,
      "loss": 0.3905,
      "step": 1460
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.5235008103727715e-05,
      "loss": 0.3359,
      "step": 1470
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.520259319286872e-05,
      "loss": 0.3915,
      "step": 1480
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.5170178282009727e-05,
      "loss": 0.316,
      "step": 1490
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.5137763371150732e-05,
      "loss": 0.4686,
      "step": 1500
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.5105348460291736e-05,
      "loss": 0.4413,
      "step": 1510
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.507293354943274e-05,
      "loss": 0.2946,
      "step": 1520
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.5040518638573745e-05,
      "loss": 0.3483,
      "step": 1530
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.500810372771475e-05,
      "loss": 0.3222,
      "step": 1540
    },
    {
      "epoch": 2.51,
      "learning_rate": 1.4975688816855755e-05,
      "loss": 0.3557,
      "step": 1550
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.494327390599676e-05,
      "loss": 0.2867,
      "step": 1560
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.4910858995137764e-05,
      "loss": 0.2718,
      "step": 1570
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.4878444084278769e-05,
      "loss": 0.265,
      "step": 1580
    },
    {
      "epoch": 2.58,
      "learning_rate": 1.4846029173419773e-05,
      "loss": 0.3511,
      "step": 1590
    },
    {
      "epoch": 2.59,
      "learning_rate": 1.4813614262560778e-05,
      "loss": 0.3416,
      "step": 1600
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.4781199351701785e-05,
      "loss": 0.3477,
      "step": 1610
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.474878444084279e-05,
      "loss": 0.2636,
      "step": 1620
    },
    {
      "epoch": 2.64,
      "learning_rate": 1.4716369529983794e-05,
      "loss": 0.3245,
      "step": 1630
    },
    {
      "epoch": 2.66,
      "learning_rate": 1.4683954619124799e-05,
      "loss": 0.3413,
      "step": 1640
    },
    {
      "epoch": 2.67,
      "learning_rate": 1.4651539708265803e-05,
      "loss": 0.3294,
      "step": 1650
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.4619124797406807e-05,
      "loss": 0.3222,
      "step": 1660
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.4586709886547814e-05,
      "loss": 0.2559,
      "step": 1670
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.4554294975688818e-05,
      "loss": 0.3845,
      "step": 1680
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.4521880064829822e-05,
      "loss": 0.2523,
      "step": 1690
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.4489465153970827e-05,
      "loss": 0.2542,
      "step": 1700
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.4457050243111831e-05,
      "loss": 0.2859,
      "step": 1710
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.4424635332252836e-05,
      "loss": 0.4221,
      "step": 1720
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.4392220421393844e-05,
      "loss": 0.3414,
      "step": 1730
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.4359805510534848e-05,
      "loss": 0.2738,
      "step": 1740
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.4327390599675852e-05,
      "loss": 0.2955,
      "step": 1750
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.4294975688816857e-05,
      "loss": 0.315,
      "step": 1760
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.4262560777957861e-05,
      "loss": 0.2628,
      "step": 1770
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.4230145867098866e-05,
      "loss": 0.2731,
      "step": 1780
    },
    {
      "epoch": 2.9,
      "learning_rate": 1.4197730956239872e-05,
      "loss": 0.3792,
      "step": 1790
    },
    {
      "epoch": 2.92,
      "learning_rate": 1.4165316045380876e-05,
      "loss": 0.3875,
      "step": 1800
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.413290113452188e-05,
      "loss": 0.2959,
      "step": 1810
    },
    {
      "epoch": 2.95,
      "learning_rate": 1.4100486223662885e-05,
      "loss": 0.2504,
      "step": 1820
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.4068071312803891e-05,
      "loss": 0.3684,
      "step": 1830
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.4035656401944896e-05,
      "loss": 0.3581,
      "step": 1840
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.4003241491085902e-05,
      "loss": 0.3028,
      "step": 1850
    },
    {
      "epoch": 3.0,
      "eval_FN": 932,
      "eval_FP": 2492,
      "eval_TN": 13267,
      "eval_TP": 3974,
      "eval_accuracy": 0.8343092184853618,
      "eval_f1": 0.6989096025325361,
      "eval_loss": 0.39430731534957886,
      "eval_precision": 0.6145994432415713,
      "eval_recall": 0.8100285364859355,
      "eval_runtime": 142.2921,
      "eval_samples_per_second": 145.229,
      "eval_steps_per_second": 9.08,
      "step": 1851
    }
  ],
  "logging_steps": 10,
  "max_steps": 6170,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7789139682877440.0,
  "trial_name": null,
  "trial_params": null
}