{
  "best_metric": 0.10954569280147552,
  "best_model_checkpoint": "./models/results_comb_693/checkpoint-400",
  "epoch": 0.887040887040887,
  "global_step": 400,
  "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": 0.6881,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.5e-06,
      "loss": 0.6788,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 0.6504,
      "step": 24
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5841623557500994,
      "eval_f1": 0.7375031399145943,
      "eval_loss": 0.6672813892364502,
      "eval_precision": 0.5841623557500994,
      "eval_recall": 1.0,
      "eval_runtime": 35.6463,
      "eval_samples_per_second": 211.494,
      "eval_steps_per_second": 26.454,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.55e-05,
      "loss": 0.6723,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.598,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.35e-05,
      "loss": 0.4717,
      "step": 48
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8839368616527391,
      "eval_f1": 0.9069841607313702,
      "eval_loss": 0.3077848255634308,
      "eval_precision": 0.8526883869678193,
      "eval_recall": 0.9686648501362398,
      "eval_runtime": 34.1268,
      "eval_samples_per_second": 220.911,
      "eval_steps_per_second": 27.632,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.3128,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.15e-05,
      "loss": 0.332,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.55e-05,
      "loss": 0.2701,
      "step": 72
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.89322191272052,
      "eval_f1": 0.9027425395674761,
      "eval_loss": 0.25026363134384155,
      "eval_precision": 0.9646269042086238,
      "eval_recall": 0.8483197093551317,
      "eval_runtime": 33.4359,
      "eval_samples_per_second": 225.476,
      "eval_steps_per_second": 28.203,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.284,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.35e-05,
      "loss": 0.283,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.75e-05,
      "loss": 0.1908,
      "step": 96
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.9243931555909272,
      "eval_f1": 0.9354327140915271,
      "eval_loss": 0.2004704475402832,
      "eval_precision": 0.9333182640144665,
      "eval_recall": 0.9375567665758402,
      "eval_runtime": 33.8959,
      "eval_samples_per_second": 222.416,
      "eval_steps_per_second": 27.82,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.957142857142857e-05,
      "loss": 0.237,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.842857142857143e-05,
      "loss": 0.2298,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.728571428571429e-05,
      "loss": 0.2824,
      "step": 120
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.8917628332670116,
      "eval_f1": 0.9143397018685703,
      "eval_loss": 0.301138699054718,
      "eval_precision": 0.850253807106599,
      "eval_recall": 0.9888737511353315,
      "eval_runtime": 33.5038,
      "eval_samples_per_second": 225.019,
      "eval_steps_per_second": 28.146,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.6142857142857145e-05,
      "loss": 0.2522,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5e-05,
      "loss": 0.1874,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.385714285714286e-05,
      "loss": 0.1865,
      "step": 144
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.9358005040456294,
      "eval_f1": 0.9457033879291002,
      "eval_loss": 0.16087646782398224,
      "eval_precision": 0.934589800443459,
      "eval_recall": 0.9570844686648501,
      "eval_runtime": 33.8925,
      "eval_samples_per_second": 222.439,
      "eval_steps_per_second": 27.823,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.271428571428572e-05,
      "loss": 0.2079,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.1571428571428575e-05,
      "loss": 0.2041,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.042857142857143e-05,
      "loss": 0.1723,
      "step": 168
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9396471680594243,
      "eval_f1": 0.9485468732330657,
      "eval_loss": 0.16514933109283447,
      "eval_precision": 0.9448073890515882,
      "eval_recall": 0.952316076294278,
      "eval_runtime": 32.9214,
      "eval_samples_per_second": 229.0,
      "eval_steps_per_second": 28.644,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.1804,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.814285714285715e-05,
      "loss": 0.1687,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.7e-05,
      "loss": 0.2033,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.585714285714286e-05,
      "loss": 0.1858,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.9452181987000928,
      "eval_f1": 0.9521492295214923,
      "eval_loss": 0.15048551559448242,
      "eval_precision": 0.9720842204873432,
      "eval_recall": 0.9330154405086285,
      "eval_runtime": 32.8586,
      "eval_samples_per_second": 229.438,
      "eval_steps_per_second": 28.699,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.471428571428571e-05,
      "loss": 0.1741,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.357142857142857e-05,
      "loss": 0.1503,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.242857142857143e-05,
      "loss": 0.1293,
      "step": 224
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9112614405093514,
      "eval_f1": 0.9184643510054844,
      "eval_loss": 0.25113266706466675,
      "eval_precision": 0.9913180741910024,
      "eval_recall": 0.8555858310626703,
      "eval_runtime": 33.3517,
      "eval_samples_per_second": 226.045,
      "eval_steps_per_second": 28.274,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.1285714285714285e-05,
      "loss": 0.2328,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.0142857142857146e-05,
      "loss": 0.1614,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.9e-05,
      "loss": 0.1339,
      "step": 248
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.9495954370606181,
      "eval_f1": 0.9561909153792945,
      "eval_loss": 0.12891609966754913,
      "eval_precision": 0.9711943793911006,
      "eval_recall": 0.9416439600363307,
      "eval_runtime": 32.9115,
      "eval_samples_per_second": 229.069,
      "eval_steps_per_second": 28.653,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.785714285714286e-05,
      "loss": 0.1318,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6714285714285715e-05,
      "loss": 0.1038,
      "step": 264
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.5571428571428572e-05,
      "loss": 0.1714,
      "step": 272
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.9599416368218596,
      "eval_f1": 0.9657052009993187,
      "eval_loss": 0.12271451950073242,
      "eval_precision": 0.9659245797364834,
      "eval_recall": 0.9654859218891917,
      "eval_runtime": 33.9975,
      "eval_samples_per_second": 221.752,
      "eval_steps_per_second": 27.737,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.442857142857143e-05,
      "loss": 0.1444,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.3285714285714287e-05,
      "loss": 0.1771,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.214285714285714e-05,
      "loss": 0.1438,
      "step": 296
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.954105319007826,
      "eval_f1": 0.9600369600369599,
      "eval_loss": 0.12011300027370453,
      "eval_precision": 0.9769628584861307,
      "eval_recall": 0.9436875567665758,
      "eval_runtime": 34.0522,
      "eval_samples_per_second": 221.395,
      "eval_steps_per_second": 27.693,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.1e-05,
      "loss": 0.1213,
      "step": 304
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9857142857142856e-05,
      "loss": 0.1517,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8714285714285714e-05,
      "loss": 0.132,
      "step": 320
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9594110624751293,
      "eval_f1": 0.9649885583524028,
      "eval_loss": 0.11286678165197372,
      "eval_precision": 0.9725553505535055,
      "eval_recall": 0.9575386012715713,
      "eval_runtime": 33.5869,
      "eval_samples_per_second": 224.463,
      "eval_steps_per_second": 28.076,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.757142857142857e-05,
      "loss": 0.1399,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.1393,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5285714285714286e-05,
      "loss": 0.123,
      "step": 344
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9590131317150816,
      "eval_f1": 0.964802369290352,
      "eval_loss": 0.11320723593235016,
      "eval_precision": 0.968,
      "eval_recall": 0.9616257947320618,
      "eval_runtime": 37.7864,
      "eval_samples_per_second": 199.516,
      "eval_steps_per_second": 24.956,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4142857142857143e-05,
      "loss": 0.1067,
      "step": 352
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.1252,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1857142857142858e-05,
      "loss": 0.1513,
      "step": 368
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9595437060618119,
      "eval_f1": 0.9653684569092766,
      "eval_loss": 0.11097515374422073,
      "eval_precision": 0.9654780831251419,
      "eval_recall": 0.965258855585831,
      "eval_runtime": 37.8195,
      "eval_samples_per_second": 199.342,
      "eval_steps_per_second": 24.934,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 0.1322,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.571428571428572e-06,
      "loss": 0.1199,
      "step": 384
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.428571428571429e-06,
      "loss": 0.1171,
      "step": 392
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.285714285714286e-06,
      "loss": 0.1583,
      "step": 400
    },
    {
      "epoch": 0.89,
      "eval_accuracy": 0.9600742804085423,
      "eval_f1": 0.965643191416505,
      "eval_loss": 0.10954569280147552,
      "eval_precision": 0.970851503327978,
      "eval_recall": 0.9604904632152589,
      "eval_runtime": 37.3506,
      "eval_samples_per_second": 201.844,
      "eval_steps_per_second": 25.247,
      "step": 400
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 1,
  "total_flos": 4354487966208000.0,
  "trial_name": null,
  "trial_params": null
}