{
  "best_metric": 0.10937219858169556,
  "best_model_checkpoint": "./models/results_comb_977/checkpoint-375",
  "epoch": 0.8316008316008316,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6852,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6763,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.2e-05,
      "loss": 0.6574,
      "step": 24
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5841623557500994,
      "eval_f1": 0.7375031399145943,
      "eval_loss": 0.6670724749565125,
      "eval_precision": 0.5841623557500994,
      "eval_recall": 1.0,
      "eval_runtime": 49.517,
      "eval_samples_per_second": 152.251,
      "eval_steps_per_second": 19.044,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6057,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.6139,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.4e-05,
      "loss": 0.5282,
      "step": 48
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.7591192465844276,
      "eval_f1": 0.8288084464555052,
      "eval_loss": 0.43177902698516846,
      "eval_precision": 0.708575112830432,
      "eval_recall": 0.9981834695731153,
      "eval_runtime": 49.8289,
      "eval_samples_per_second": 151.298,
      "eval_steps_per_second": 18.925,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.421,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3004,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.6e-05,
      "loss": 0.3156,
      "step": 72
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.9250563735243401,
      "eval_f1": 0.9366094468753505,
      "eval_loss": 0.19340644776821136,
      "eval_precision": 0.9257041472610334,
      "eval_recall": 0.9477747502270663,
      "eval_runtime": 48.8142,
      "eval_samples_per_second": 154.443,
      "eval_steps_per_second": 19.318,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 4e-05,
      "loss": 0.275,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2258,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.75e-05,
      "loss": 0.2682,
      "step": 96
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.931157978511739,
      "eval_f1": 0.9422370617696161,
      "eval_loss": 0.19519653916358948,
      "eval_precision": 0.9240340537000655,
      "eval_recall": 0.9611716621253406,
      "eval_runtime": 48.2615,
      "eval_samples_per_second": 156.212,
      "eval_steps_per_second": 19.539,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.957142857142857e-05,
      "loss": 0.2448,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.842857142857143e-05,
      "loss": 0.2179,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.728571428571429e-05,
      "loss": 0.2161,
      "step": 120
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.9363310783923597,
      "eval_f1": 0.9444444444444444,
      "eval_loss": 0.1711500585079193,
      "eval_precision": 0.9631728045325779,
      "eval_recall": 0.9264305177111717,
      "eval_runtime": 49.0831,
      "eval_samples_per_second": 153.597,
      "eval_steps_per_second": 19.212,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.6142857142857145e-05,
      "loss": 0.185,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5e-05,
      "loss": 0.213,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.385714285714286e-05,
      "loss": 0.2209,
      "step": 144
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.9320864836185171,
      "eval_f1": 0.9418842224744609,
      "eval_loss": 0.18172995746135712,
      "eval_precision": 0.9416704493871992,
      "eval_recall": 0.9420980926430518,
      "eval_runtime": 48.8331,
      "eval_samples_per_second": 154.383,
      "eval_steps_per_second": 19.311,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.271428571428572e-05,
      "loss": 0.1561,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.1571428571428575e-05,
      "loss": 0.2087,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.042857142857143e-05,
      "loss": 0.2013,
      "step": 168
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9460140602201883,
      "eval_f1": 0.9541511771995044,
      "eval_loss": 0.14321394264698029,
      "eval_precision": 0.94679186228482,
      "eval_recall": 0.9616257947320618,
      "eval_runtime": 48.5882,
      "eval_samples_per_second": 155.161,
      "eval_steps_per_second": 19.408,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.1913,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.814285714285715e-05,
      "loss": 0.1259,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.7e-05,
      "loss": 0.1834,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.585714285714286e-05,
      "loss": 0.2194,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.9450855551134103,
      "eval_f1": 0.9540816326530612,
      "eval_loss": 0.1561821550130844,
      "eval_precision": 0.9325672159583694,
      "eval_recall": 0.9766121707538601,
      "eval_runtime": 48.3284,
      "eval_samples_per_second": 155.995,
      "eval_steps_per_second": 19.512,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.471428571428571e-05,
      "loss": 0.1455,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.357142857142857e-05,
      "loss": 0.1617,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.242857142857143e-05,
      "loss": 0.1336,
      "step": 224
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9474731396736967,
      "eval_f1": 0.9546495648190564,
      "eval_loss": 0.13737089931964874,
      "eval_precision": 0.9630314232902033,
      "eval_recall": 0.9464123524069028,
      "eval_runtime": 48.3619,
      "eval_samples_per_second": 155.887,
      "eval_steps_per_second": 19.499,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.1285714285714285e-05,
      "loss": 0.1541,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.0142857142857146e-05,
      "loss": 0.1724,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.9e-05,
      "loss": 0.1387,
      "step": 248
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.9465446345669187,
      "eval_f1": 0.9532102635550912,
      "eval_loss": 0.14909207820892334,
      "eval_precision": 0.9752910430030887,
      "eval_recall": 0.9321071752951862,
      "eval_runtime": 48.4793,
      "eval_samples_per_second": 155.51,
      "eval_steps_per_second": 19.452,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.785714285714286e-05,
      "loss": 0.1559,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6714285714285715e-05,
      "loss": 0.1444,
      "step": 264
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.5571428571428572e-05,
      "loss": 0.1196,
      "step": 272
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.955697042048017,
      "eval_f1": 0.9622342831298055,
      "eval_loss": 0.12214687466621399,
      "eval_precision": 0.9583333333333334,
      "eval_recall": 0.9661671207992734,
      "eval_runtime": 48.8578,
      "eval_samples_per_second": 154.305,
      "eval_steps_per_second": 19.301,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.442857142857143e-05,
      "loss": 0.1397,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.3285714285714287e-05,
      "loss": 0.1284,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.214285714285714e-05,
      "loss": 0.1779,
      "step": 296
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.9549011805279215,
      "eval_f1": 0.9617289509230076,
      "eval_loss": 0.12309886515140533,
      "eval_precision": 0.9535714285714286,
      "eval_recall": 0.9700272479564033,
      "eval_runtime": 48.6426,
      "eval_samples_per_second": 154.987,
      "eval_steps_per_second": 19.386,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.1e-05,
      "loss": 0.1118,
      "step": 304
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9857142857142856e-05,
      "loss": 0.1375,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8714285714285714e-05,
      "loss": 0.097,
      "step": 320
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9547685369412389,
      "eval_f1": 0.9607549775578317,
      "eval_loss": 0.13004465401172638,
      "eval_precision": 0.974095682613769,
      "eval_recall": 0.9477747502270663,
      "eval_runtime": 48.3897,
      "eval_samples_per_second": 155.797,
      "eval_steps_per_second": 19.488,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.757142857142857e-05,
      "loss": 0.1579,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.1502,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5285714285714286e-05,
      "loss": 0.101,
      "step": 344
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9599416368218596,
      "eval_f1": 0.9658834161771351,
      "eval_loss": 0.11177459359169006,
      "eval_precision": 0.9611061151079137,
      "eval_recall": 0.970708446866485,
      "eval_runtime": 48.7108,
      "eval_samples_per_second": 154.771,
      "eval_steps_per_second": 19.359,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4142857142857143e-05,
      "loss": 0.1073,
      "step": 352
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.1431,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1857142857142858e-05,
      "loss": 0.1708,
      "step": 368
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9583499137816687,
      "eval_f1": 0.9646714671467146,
      "eval_loss": 0.10937219858169556,
      "eval_precision": 0.9560660124888493,
      "eval_recall": 0.973433242506812,
      "eval_runtime": 49.3579,
      "eval_samples_per_second": 152.742,
      "eval_steps_per_second": 19.105,
      "step": 375
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 1,
  "total_flos": 4082332468320000.0,
  "trial_name": null,
  "trial_params": null
}