{
  "best_metric": 0.03530377894639969,
  "best_model_checkpoint": "my_awesome_ds_model/checkpoint-22473",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 74910,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 9.933253237217995e-05,
      "loss": 0.2746,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.86650647443599e-05,
      "loss": 0.0897,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.799759711653985e-05,
      "loss": 0.0718,
      "step": 1500
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.73301294887198e-05,
      "loss": 0.0616,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.666266186089975e-05,
      "loss": 0.0568,
      "step": 2500
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.59951942330797e-05,
      "loss": 0.0525,
      "step": 3000
    },
    {
      "epoch": 0.47,
      "learning_rate": 9.532772660525965e-05,
      "loss": 0.0495,
      "step": 3500
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.46602589774396e-05,
      "loss": 0.0488,
      "step": 4000
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.399279134961955e-05,
      "loss": 0.0457,
      "step": 4500
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.33253237217995e-05,
      "loss": 0.0422,
      "step": 5000
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.265785609397944e-05,
      "loss": 0.0431,
      "step": 5500
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.199038846615939e-05,
      "loss": 0.0467,
      "step": 6000
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.132292083833934e-05,
      "loss": 0.0473,
      "step": 6500
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.065545321051929e-05,
      "loss": 0.0458,
      "step": 7000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9874301209567,
      "eval_f1": 0.9027943197434722,
      "eval_loss": 0.04262871295213699,
      "eval_precision": 0.9134223210975158,
      "eval_recall": 0.8924107951458069,
      "eval_runtime": 108.0836,
      "eval_samples_per_second": 76.441,
      "eval_steps_per_second": 9.557,
      "step": 7491
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.998798558269924e-05,
      "loss": 0.0423,
      "step": 7500
    },
    {
      "epoch": 1.07,
      "learning_rate": 8.932051795487919e-05,
      "loss": 0.0369,
      "step": 8000
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.865305032705914e-05,
      "loss": 0.0363,
      "step": 8500
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.798558269923909e-05,
      "loss": 0.0333,
      "step": 9000
    },
    {
      "epoch": 1.27,
      "learning_rate": 8.731811507141903e-05,
      "loss": 0.0356,
      "step": 9500
    },
    {
      "epoch": 1.33,
      "learning_rate": 8.665064744359898e-05,
      "loss": 0.036,
      "step": 10000
    },
    {
      "epoch": 1.4,
      "learning_rate": 8.598317981577893e-05,
      "loss": 0.0372,
      "step": 10500
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.531571218795888e-05,
      "loss": 0.0354,
      "step": 11000
    },
    {
      "epoch": 1.54,
      "learning_rate": 8.464824456013883e-05,
      "loss": 0.0356,
      "step": 11500
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.398077693231878e-05,
      "loss": 0.0323,
      "step": 12000
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.331330930449873e-05,
      "loss": 0.037,
      "step": 12500
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.264584167667868e-05,
      "loss": 0.0361,
      "step": 13000
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.197837404885863e-05,
      "loss": 0.0346,
      "step": 13500
    },
    {
      "epoch": 1.87,
      "learning_rate": 8.131090642103857e-05,
      "loss": 0.0351,
      "step": 14000
    },
    {
      "epoch": 1.94,
      "learning_rate": 8.064343879321852e-05,
      "loss": 0.0326,
      "step": 14500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9869225169145689,
      "eval_f1": 0.8974685334464715,
      "eval_loss": 0.03918388485908508,
      "eval_precision": 0.935896175400649,
      "eval_recall": 0.8620720883897844,
      "eval_runtime": 107.1166,
      "eval_samples_per_second": 77.131,
      "eval_steps_per_second": 9.644,
      "step": 14982
    },
    {
      "epoch": 2.0,
      "learning_rate": 7.997597116539847e-05,
      "loss": 0.0342,
      "step": 15000
    },
    {
      "epoch": 2.07,
      "learning_rate": 7.930850353757842e-05,
      "loss": 0.0269,
      "step": 15500
    },
    {
      "epoch": 2.14,
      "learning_rate": 7.864103590975837e-05,
      "loss": 0.0273,
      "step": 16000
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.797356828193832e-05,
      "loss": 0.0247,
      "step": 16500
    },
    {
      "epoch": 2.27,
      "learning_rate": 7.730610065411827e-05,
      "loss": 0.0262,
      "step": 17000
    },
    {
      "epoch": 2.34,
      "learning_rate": 7.663863302629822e-05,
      "loss": 0.0274,
      "step": 17500
    },
    {
      "epoch": 2.4,
      "learning_rate": 7.597116539847817e-05,
      "loss": 0.0262,
      "step": 18000
    },
    {
      "epoch": 2.47,
      "learning_rate": 7.530369777065813e-05,
      "loss": 0.0272,
      "step": 18500
    },
    {
      "epoch": 2.54,
      "learning_rate": 7.463623014283808e-05,
      "loss": 0.0278,
      "step": 19000
    },
    {
      "epoch": 2.6,
      "learning_rate": 7.396876251501803e-05,
      "loss": 0.0291,
      "step": 19500
    },
    {
      "epoch": 2.67,
      "learning_rate": 7.330129488719797e-05,
      "loss": 0.0265,
      "step": 20000
    },
    {
      "epoch": 2.74,
      "learning_rate": 7.263382725937792e-05,
      "loss": 0.0245,
      "step": 20500
    },
    {
      "epoch": 2.8,
      "learning_rate": 7.196635963155787e-05,
      "loss": 0.0271,
      "step": 21000
    },
    {
      "epoch": 2.87,
      "learning_rate": 7.129889200373782e-05,
      "loss": 0.0283,
      "step": 21500
    },
    {
      "epoch": 2.94,
      "learning_rate": 7.063142437591777e-05,
      "loss": 0.0277,
      "step": 22000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9892468091074852,
      "eval_f1": 0.9156408399710355,
      "eval_loss": 0.03530377894639969,
      "eval_precision": 0.9151438393341776,
      "eval_recall": 0.9161383807281289,
      "eval_runtime": 107.1556,
      "eval_samples_per_second": 77.103,
      "eval_steps_per_second": 9.64,
      "step": 22473
    },
    {
      "epoch": 3.0,
      "learning_rate": 6.996395674809772e-05,
      "loss": 0.0232,
      "step": 22500
    },
    {
      "epoch": 3.07,
      "learning_rate": 6.929648912027767e-05,
      "loss": 0.0195,
      "step": 23000
    },
    {
      "epoch": 3.14,
      "learning_rate": 6.862902149245762e-05,
      "loss": 0.0198,
      "step": 23500
    },
    {
      "epoch": 3.2,
      "learning_rate": 6.796155386463757e-05,
      "loss": 0.0202,
      "step": 24000
    },
    {
      "epoch": 3.27,
      "learning_rate": 6.729408623681752e-05,
      "loss": 0.0181,
      "step": 24500
    },
    {
      "epoch": 3.34,
      "learning_rate": 6.662661860899748e-05,
      "loss": 0.0193,
      "step": 25000
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.595915098117743e-05,
      "loss": 0.0198,
      "step": 25500
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.529168335335738e-05,
      "loss": 0.0198,
      "step": 26000
    },
    {
      "epoch": 3.54,
      "learning_rate": 6.462421572553732e-05,
      "loss": 0.0197,
      "step": 26500
    },
    {
      "epoch": 3.6,
      "learning_rate": 6.395674809771727e-05,
      "loss": 0.0194,
      "step": 27000
    },
    {
      "epoch": 3.67,
      "learning_rate": 6.328928046989722e-05,
      "loss": 0.0203,
      "step": 27500
    },
    {
      "epoch": 3.74,
      "learning_rate": 6.262181284207717e-05,
      "loss": 0.0203,
      "step": 28000
    },
    {
      "epoch": 3.8,
      "learning_rate": 6.195434521425712e-05,
      "loss": 0.0211,
      "step": 28500
    },
    {
      "epoch": 3.87,
      "learning_rate": 6.128687758643707e-05,
      "loss": 0.0201,
      "step": 29000
    },
    {
      "epoch": 3.94,
      "learning_rate": 6.061940995861701e-05,
      "loss": 0.0209,
      "step": 29500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9885855880526038,
      "eval_f1": 0.9106117466202469,
      "eval_loss": 0.04323778301477432,
      "eval_precision": 0.909255079006772,
      "eval_recall": 0.9119724687556602,
      "eval_runtime": 107.2535,
      "eval_samples_per_second": 77.032,
      "eval_steps_per_second": 9.631,
      "step": 29964
    },
    {
      "epoch": 4.0,
      "learning_rate": 5.995194233079696e-05,
      "loss": 0.0192,
      "step": 30000
    },
    {
      "epoch": 4.07,
      "learning_rate": 5.928447470297691e-05,
      "loss": 0.0115,
      "step": 30500
    },
    {
      "epoch": 4.14,
      "learning_rate": 5.861700707515686e-05,
      "loss": 0.0131,
      "step": 31000
    },
    {
      "epoch": 4.21,
      "learning_rate": 5.794953944733681e-05,
      "loss": 0.014,
      "step": 31500
    },
    {
      "epoch": 4.27,
      "learning_rate": 5.7282071819516756e-05,
      "loss": 0.0134,
      "step": 32000
    },
    {
      "epoch": 4.34,
      "learning_rate": 5.6614604191696705e-05,
      "loss": 0.0136,
      "step": 32500
    },
    {
      "epoch": 4.41,
      "learning_rate": 5.5947136563876653e-05,
      "loss": 0.0152,
      "step": 33000
    },
    {
      "epoch": 4.47,
      "learning_rate": 5.52796689360566e-05,
      "loss": 0.0135,
      "step": 33500
    },
    {
      "epoch": 4.54,
      "learning_rate": 5.461220130823655e-05,
      "loss": 0.0152,
      "step": 34000
    },
    {
      "epoch": 4.61,
      "learning_rate": 5.394473368041651e-05,
      "loss": 0.0138,
      "step": 34500
    },
    {
      "epoch": 4.67,
      "learning_rate": 5.3277266052596456e-05,
      "loss": 0.0154,
      "step": 35000
    },
    {
      "epoch": 4.74,
      "learning_rate": 5.2609798424776405e-05,
      "loss": 0.0139,
      "step": 35500
    },
    {
      "epoch": 4.81,
      "learning_rate": 5.1942330796956354e-05,
      "loss": 0.015,
      "step": 36000
    },
    {
      "epoch": 4.87,
      "learning_rate": 5.12748631691363e-05,
      "loss": 0.0131,
      "step": 36500
    },
    {
      "epoch": 4.94,
      "learning_rate": 5.060739554131625e-05,
      "loss": 0.0141,
      "step": 37000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9885588720503864,
      "eval_f1": 0.9082037484609421,
      "eval_loss": 0.049268897622823715,
      "eval_precision": 0.9146688711307064,
      "eval_recall": 0.9018293787357363,
      "eval_runtime": 107.4361,
      "eval_samples_per_second": 76.902,
      "eval_steps_per_second": 9.615,
      "step": 37455
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.99399279134962e-05,
      "loss": 0.0126,
      "step": 37500
    },
    {
      "epoch": 5.07,
      "learning_rate": 4.927246028567615e-05,
      "loss": 0.0073,
      "step": 38000
    },
    {
      "epoch": 5.14,
      "learning_rate": 4.86049926578561e-05,
      "loss": 0.0076,
      "step": 38500
    },
    {
      "epoch": 5.21,
      "learning_rate": 4.793752503003605e-05,
      "loss": 0.0076,
      "step": 39000
    },
    {
      "epoch": 5.27,
      "learning_rate": 4.7270057402215996e-05,
      "loss": 0.0086,
      "step": 39500
    },
    {
      "epoch": 5.34,
      "learning_rate": 4.6602589774395945e-05,
      "loss": 0.0092,
      "step": 40000
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.5935122146575894e-05,
      "loss": 0.0087,
      "step": 40500
    },
    {
      "epoch": 5.47,
      "learning_rate": 4.526765451875584e-05,
      "loss": 0.0085,
      "step": 41000
    },
    {
      "epoch": 5.54,
      "learning_rate": 4.460018689093579e-05,
      "loss": 0.0086,
      "step": 41500
    },
    {
      "epoch": 5.61,
      "learning_rate": 4.393271926311574e-05,
      "loss": 0.0084,
      "step": 42000
    },
    {
      "epoch": 5.67,
      "learning_rate": 4.326525163529569e-05,
      "loss": 0.0091,
      "step": 42500
    },
    {
      "epoch": 5.74,
      "learning_rate": 4.259778400747564e-05,
      "loss": 0.0083,
      "step": 43000
    },
    {
      "epoch": 5.81,
      "learning_rate": 4.193031637965559e-05,
      "loss": 0.0088,
      "step": 43500
    },
    {
      "epoch": 5.87,
      "learning_rate": 4.1262848751835536e-05,
      "loss": 0.0088,
      "step": 44000
    },
    {
      "epoch": 5.94,
      "learning_rate": 4.0595381124015485e-05,
      "loss": 0.0081,
      "step": 44500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9886724150598104,
      "eval_f1": 0.9117419940949353,
      "eval_loss": 0.058003462851047516,
      "eval_precision": 0.9146085847079194,
      "eval_recall": 0.9088933164281833,
      "eval_runtime": 107.2097,
      "eval_samples_per_second": 77.064,
      "eval_steps_per_second": 9.635,
      "step": 44946
    },
    {
      "epoch": 6.01,
      "learning_rate": 3.9927913496195434e-05,
      "loss": 0.0091,
      "step": 45000
    },
    {
      "epoch": 6.07,
      "learning_rate": 3.926044586837538e-05,
      "loss": 0.004,
      "step": 45500
    },
    {
      "epoch": 6.14,
      "learning_rate": 3.859297824055533e-05,
      "loss": 0.0044,
      "step": 46000
    },
    {
      "epoch": 6.21,
      "learning_rate": 3.792551061273528e-05,
      "loss": 0.0042,
      "step": 46500
    },
    {
      "epoch": 6.27,
      "learning_rate": 3.725804298491523e-05,
      "loss": 0.0042,
      "step": 47000
    },
    {
      "epoch": 6.34,
      "learning_rate": 3.659057535709518e-05,
      "loss": 0.005,
      "step": 47500
    },
    {
      "epoch": 6.41,
      "learning_rate": 3.592310772927513e-05,
      "loss": 0.0036,
      "step": 48000
    },
    {
      "epoch": 6.47,
      "learning_rate": 3.525564010145508e-05,
      "loss": 0.0052,
      "step": 48500
    },
    {
      "epoch": 6.54,
      "learning_rate": 3.4588172473635026e-05,
      "loss": 0.0046,
      "step": 49000
    },
    {
      "epoch": 6.61,
      "learning_rate": 3.392070484581498e-05,
      "loss": 0.0035,
      "step": 49500
    },
    {
      "epoch": 6.67,
      "learning_rate": 3.325323721799493e-05,
      "loss": 0.0051,
      "step": 50000
    },
    {
      "epoch": 6.74,
      "learning_rate": 3.258576959017488e-05,
      "loss": 0.0051,
      "step": 50500
    },
    {
      "epoch": 6.81,
      "learning_rate": 3.191830196235483e-05,
      "loss": 0.0049,
      "step": 51000
    },
    {
      "epoch": 6.87,
      "learning_rate": 3.125083433453478e-05,
      "loss": 0.0051,
      "step": 51500
    },
    {
      "epoch": 6.94,
      "learning_rate": 3.0583366706714726e-05,
      "loss": 0.0048,
      "step": 52000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9884319710398536,
      "eval_f1": 0.9093145069460259,
      "eval_loss": 0.07726183533668518,
      "eval_precision": 0.9146889031430404,
      "eval_recall": 0.90400289802572,
      "eval_runtime": 107.8277,
      "eval_samples_per_second": 76.622,
      "eval_steps_per_second": 9.58,
      "step": 52437
    },
    {
      "epoch": 7.01,
      "learning_rate": 2.9915899078894678e-05,
      "loss": 0.0045,
      "step": 52500
    },
    {
      "epoch": 7.08,
      "learning_rate": 2.9248431451074627e-05,
      "loss": 0.0021,
      "step": 53000
    },
    {
      "epoch": 7.14,
      "learning_rate": 2.8580963823254576e-05,
      "loss": 0.0022,
      "step": 53500
    },
    {
      "epoch": 7.21,
      "learning_rate": 2.7913496195434525e-05,
      "loss": 0.0024,
      "step": 54000
    },
    {
      "epoch": 7.28,
      "learning_rate": 2.7246028567614474e-05,
      "loss": 0.0025,
      "step": 54500
    },
    {
      "epoch": 7.34,
      "learning_rate": 2.6578560939794423e-05,
      "loss": 0.0018,
      "step": 55000
    },
    {
      "epoch": 7.41,
      "learning_rate": 2.591109331197437e-05,
      "loss": 0.0025,
      "step": 55500
    },
    {
      "epoch": 7.48,
      "learning_rate": 2.524362568415432e-05,
      "loss": 0.0027,
      "step": 56000
    },
    {
      "epoch": 7.54,
      "learning_rate": 2.457615805633427e-05,
      "loss": 0.0024,
      "step": 56500
    },
    {
      "epoch": 7.61,
      "learning_rate": 2.390869042851422e-05,
      "loss": 0.0021,
      "step": 57000
    },
    {
      "epoch": 7.68,
      "learning_rate": 2.3241222800694167e-05,
      "loss": 0.0022,
      "step": 57500
    },
    {
      "epoch": 7.74,
      "learning_rate": 2.2573755172874116e-05,
      "loss": 0.0025,
      "step": 58000
    },
    {
      "epoch": 7.81,
      "learning_rate": 2.1906287545054065e-05,
      "loss": 0.0031,
      "step": 58500
    },
    {
      "epoch": 7.88,
      "learning_rate": 2.1238819917234014e-05,
      "loss": 0.0022,
      "step": 59000
    },
    {
      "epoch": 7.94,
      "learning_rate": 2.0571352289413963e-05,
      "loss": 0.0023,
      "step": 59500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9890330810897457,
      "eval_f1": 0.9139605257215121,
      "eval_loss": 0.0873148962855339,
      "eval_precision": 0.9116136588881881,
      "eval_recall": 0.9163195073356276,
      "eval_runtime": 107.6976,
      "eval_samples_per_second": 76.715,
      "eval_steps_per_second": 9.592,
      "step": 59928
    },
    {
      "epoch": 8.01,
      "learning_rate": 1.9903884661593912e-05,
      "loss": 0.0015,
      "step": 60000
    },
    {
      "epoch": 8.08,
      "learning_rate": 1.9236417033773864e-05,
      "loss": 0.001,
      "step": 60500
    },
    {
      "epoch": 8.14,
      "learning_rate": 1.8568949405953813e-05,
      "loss": 0.0008,
      "step": 61000
    },
    {
      "epoch": 8.21,
      "learning_rate": 1.7901481778133762e-05,
      "loss": 0.0011,
      "step": 61500
    },
    {
      "epoch": 8.28,
      "learning_rate": 1.723401415031371e-05,
      "loss": 0.0014,
      "step": 62000
    },
    {
      "epoch": 8.34,
      "learning_rate": 1.656654652249366e-05,
      "loss": 0.0012,
      "step": 62500
    },
    {
      "epoch": 8.41,
      "learning_rate": 1.589907889467361e-05,
      "loss": 0.0012,
      "step": 63000
    },
    {
      "epoch": 8.48,
      "learning_rate": 1.5231611266853558e-05,
      "loss": 0.0008,
      "step": 63500
    },
    {
      "epoch": 8.54,
      "learning_rate": 1.4564143639033507e-05,
      "loss": 0.0013,
      "step": 64000
    },
    {
      "epoch": 8.61,
      "learning_rate": 1.3896676011213459e-05,
      "loss": 0.0012,
      "step": 64500
    },
    {
      "epoch": 8.68,
      "learning_rate": 1.3229208383393408e-05,
      "loss": 0.0008,
      "step": 65000
    },
    {
      "epoch": 8.74,
      "learning_rate": 1.2561740755573357e-05,
      "loss": 0.0011,
      "step": 65500
    },
    {
      "epoch": 8.81,
      "learning_rate": 1.1894273127753304e-05,
      "loss": 0.0013,
      "step": 66000
    },
    {
      "epoch": 8.88,
      "learning_rate": 1.1226805499933253e-05,
      "loss": 0.0012,
      "step": 66500
    },
    {
      "epoch": 8.94,
      "learning_rate": 1.0559337872113203e-05,
      "loss": 0.0013,
      "step": 67000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9886724150598104,
      "eval_f1": 0.9117727148951621,
      "eval_loss": 0.09737657755613327,
      "eval_precision": 0.9138464337700145,
      "eval_recall": 0.9097083861619272,
      "eval_runtime": 107.7722,
      "eval_samples_per_second": 76.662,
      "eval_steps_per_second": 9.585,
      "step": 67419
    },
    {
      "epoch": 9.01,
      "learning_rate": 9.891870244293152e-06,
      "loss": 0.0011,
      "step": 67500
    },
    {
      "epoch": 9.08,
      "learning_rate": 9.224402616473101e-06,
      "loss": 0.0003,
      "step": 68000
    },
    {
      "epoch": 9.14,
      "learning_rate": 8.55693498865305e-06,
      "loss": 0.0005,
      "step": 68500
    },
    {
      "epoch": 9.21,
      "learning_rate": 7.889467360833e-06,
      "loss": 0.0003,
      "step": 69000
    },
    {
      "epoch": 9.28,
      "learning_rate": 7.221999733012949e-06,
      "loss": 0.0006,
      "step": 69500
    },
    {
      "epoch": 9.34,
      "learning_rate": 6.554532105192898e-06,
      "loss": 0.0007,
      "step": 70000
    },
    {
      "epoch": 9.41,
      "learning_rate": 5.887064477372848e-06,
      "loss": 0.0005,
      "step": 70500
    },
    {
      "epoch": 9.48,
      "learning_rate": 5.219596849552797e-06,
      "loss": 0.0005,
      "step": 71000
    },
    {
      "epoch": 9.54,
      "learning_rate": 4.552129221732746e-06,
      "loss": 0.0007,
      "step": 71500
    },
    {
      "epoch": 9.61,
      "learning_rate": 3.884661593912695e-06,
      "loss": 0.0007,
      "step": 72000
    },
    {
      "epoch": 9.68,
      "learning_rate": 3.2171939660926445e-06,
      "loss": 0.0006,
      "step": 72500
    },
    {
      "epoch": 9.75,
      "learning_rate": 2.549726338272594e-06,
      "loss": 0.0006,
      "step": 73000
    },
    {
      "epoch": 9.81,
      "learning_rate": 1.8822587104525433e-06,
      "loss": 0.0006,
      "step": 73500
    },
    {
      "epoch": 9.88,
      "learning_rate": 1.2147910826324925e-06,
      "loss": 0.0002,
      "step": 74000
    },
    {
      "epoch": 9.95,
      "learning_rate": 5.473234548124416e-07,
      "loss": 0.0005,
      "step": 74500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9888661060758868,
      "eval_f1": 0.9123397290170047,
      "eval_loss": 0.10618099570274353,
      "eval_precision": 0.9160883856829802,
      "eval_recall": 0.9086216265169353,
      "eval_runtime": 107.8685,
      "eval_samples_per_second": 76.593,
      "eval_steps_per_second": 9.576,
      "step": 74910
    }
  ],
  "logging_steps": 500,
  "max_steps": 74910,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.4917264852008653e+18,
  "trial_name": null,
  "trial_params": null
}