{
  "best_metric": 0.1847076267004013,
  "best_model_checkpoint": "./models/results_one_liners_23/checkpoint-325",
  "epoch": 0.9374436632413917,
  "global_step": 325,
  "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": 0.694,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6942,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2e-05,
      "loss": 0.6865,
      "step": 24
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.4908517350157729,
      "eval_f1": 0.6584849767245028,
      "eval_loss": 0.6858492493629456,
      "eval_precision": 0.4908517350157729,
      "eval_recall": 1.0,
      "eval_runtime": 15.5866,
      "eval_samples_per_second": 203.38,
      "eval_steps_per_second": 25.471,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6792,
      "step": 32
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.6488,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.4e-05,
      "loss": 0.4778,
      "step": 48
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.8091482649842271,
      "eval_f1": 0.8317107093184979,
      "eval_loss": 0.4457879066467285,
      "eval_precision": 0.73320255026974,
      "eval_recall": 0.9607969151670951,
      "eval_runtime": 15.5131,
      "eval_samples_per_second": 204.343,
      "eval_steps_per_second": 25.591,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.44,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3451,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.6e-05,
      "loss": 0.3646,
      "step": 72
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.8700315457413249,
      "eval_f1": 0.8557422969187675,
      "eval_loss": 0.30672192573547363,
      "eval_precision": 0.94,
      "eval_recall": 0.7853470437017995,
      "eval_runtime": 15.2999,
      "eval_samples_per_second": 207.191,
      "eval_steps_per_second": 25.948,
      "step": 75
    },
    {
      "epoch": 0.23,
      "learning_rate": 4e-05,
      "loss": 0.3381,
      "step": 80
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2767,
      "step": 88
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.75e-05,
      "loss": 0.3318,
      "step": 96
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.9009463722397476,
      "eval_f1": 0.9018750000000001,
      "eval_loss": 0.2531206011772156,
      "eval_precision": 0.8777372262773723,
      "eval_recall": 0.9273778920308483,
      "eval_runtime": 15.1416,
      "eval_samples_per_second": 209.357,
      "eval_steps_per_second": 26.219,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9390243902439024e-05,
      "loss": 0.2726,
      "step": 104
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.776422764227643e-05,
      "loss": 0.3775,
      "step": 112
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.613821138211382e-05,
      "loss": 0.4153,
      "step": 120
    },
    {
      "epoch": 0.36,
      "eval_accuracy": 0.898422712933754,
      "eval_f1": 0.9005558987029031,
      "eval_loss": 0.258443683385849,
      "eval_precision": 0.8668252080856124,
      "eval_recall": 0.9370179948586118,
      "eval_runtime": 15.1593,
      "eval_samples_per_second": 209.112,
      "eval_steps_per_second": 26.189,
      "step": 125
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.451219512195122e-05,
      "loss": 0.3625,
      "step": 128
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.2886178861788616e-05,
      "loss": 0.3033,
      "step": 136
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.126016260162602e-05,
      "loss": 0.3392,
      "step": 144
    },
    {
      "epoch": 0.43,
      "eval_accuracy": 0.91198738170347,
      "eval_f1": 0.9094449853943525,
      "eval_loss": 0.22280997037887573,
      "eval_precision": 0.9186885245901639,
      "eval_recall": 0.9003856041131105,
      "eval_runtime": 14.7479,
      "eval_samples_per_second": 214.945,
      "eval_steps_per_second": 26.919,
      "step": 150
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.9634146341463416e-05,
      "loss": 0.2677,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.800813008130081e-05,
      "loss": 0.2286,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.6382113821138216e-05,
      "loss": 0.284,
      "step": 168
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.8958990536277602,
      "eval_f1": 0.9009603841536614,
      "eval_loss": 0.2512595057487488,
      "eval_precision": 0.8451576576576577,
      "eval_recall": 0.9646529562982005,
      "eval_runtime": 14.9616,
      "eval_samples_per_second": 211.876,
      "eval_steps_per_second": 26.535,
      "step": 175
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.475609756097561e-05,
      "loss": 0.2726,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.313008130081301e-05,
      "loss": 0.2476,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.150406504065041e-05,
      "loss": 0.2403,
      "step": 192
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.9878048780487805e-05,
      "loss": 0.1909,
      "step": 200
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.9148264984227129,
      "eval_f1": 0.9126778783958602,
      "eval_loss": 0.2199183851480484,
      "eval_precision": 0.9186197916666666,
      "eval_recall": 0.9068123393316195,
      "eval_runtime": 15.3053,
      "eval_samples_per_second": 207.118,
      "eval_steps_per_second": 25.939,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.8252032520325205e-05,
      "loss": 0.214,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.66260162601626e-05,
      "loss": 0.2807,
      "step": 216
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5e-05,
      "loss": 0.2116,
      "step": 224
    },
    {
      "epoch": 0.65,
      "eval_accuracy": 0.917981072555205,
      "eval_f1": 0.9144736842105263,
      "eval_loss": 0.2060399204492569,
      "eval_precision": 0.9366576819407008,
      "eval_recall": 0.8933161953727506,
      "eval_runtime": 15.179,
      "eval_samples_per_second": 208.841,
      "eval_steps_per_second": 26.155,
      "step": 225
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.3373983739837398e-05,
      "loss": 0.2214,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.1747967479674798e-05,
      "loss": 0.2164,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.0121951219512197e-05,
      "loss": 0.2329,
      "step": 248
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9097791798107255,
      "eval_f1": 0.9134382566585957,
      "eval_loss": 0.2206372767686844,
      "eval_precision": 0.8632723112128147,
      "eval_recall": 0.9697943444730077,
      "eval_runtime": 14.8474,
      "eval_samples_per_second": 213.506,
      "eval_steps_per_second": 26.739,
      "step": 250
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.8495934959349594e-05,
      "loss": 0.1998,
      "step": 256
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6869918699186994e-05,
      "loss": 0.2386,
      "step": 264
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.524390243902439e-05,
      "loss": 0.1922,
      "step": 272
    },
    {
      "epoch": 0.79,
      "eval_accuracy": 0.9287066246056782,
      "eval_f1": 0.9282083862770013,
      "eval_loss": 0.19086162745952606,
      "eval_precision": 0.917713567839196,
      "eval_recall": 0.9389460154241646,
      "eval_runtime": 14.7603,
      "eval_samples_per_second": 214.766,
      "eval_steps_per_second": 26.896,
      "step": 275
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.3617886178861788e-05,
      "loss": 0.1785,
      "step": 280
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.1991869918699188e-05,
      "loss": 0.2006,
      "step": 288
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0365853658536585e-05,
      "loss": 0.2012,
      "step": 296
    },
    {
      "epoch": 0.87,
      "eval_accuracy": 0.9160883280757098,
      "eval_f1": 0.9183046683046682,
      "eval_loss": 0.21321891248226166,
      "eval_precision": 0.8794117647058823,
      "eval_recall": 0.9607969151670951,
      "eval_runtime": 14.8364,
      "eval_samples_per_second": 213.663,
      "eval_steps_per_second": 26.758,
      "step": 300
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.739837398373985e-06,
      "loss": 0.205,
      "step": 304
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.113821138211382e-06,
      "loss": 0.1995,
      "step": 312
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.487804878048781e-06,
      "loss": 0.1804,
      "step": 320
    },
    {
      "epoch": 0.94,
      "eval_accuracy": 0.9264984227129337,
      "eval_f1": 0.9260552205649001,
      "eval_loss": 0.1847076267004013,
      "eval_precision": 0.9147335423197492,
      "eval_recall": 0.9376606683804627,
      "eval_runtime": 15.3041,
      "eval_samples_per_second": 207.135,
      "eval_steps_per_second": 25.941,
      "step": 325
    }
  ],
  "max_steps": 346,
  "num_train_epochs": 1,
  "total_flos": 619955424192000.0,
  "trial_name": null,
  "trial_params": null
}