{
  "best_metric": 0.8754267260214113,
  "best_model_checkpoint": "./output//roberta-large_ipc1_G_5_32_5e-6_0.01_0.06_07-08-22_06-40/checkpoint-24000",
  "epoch": 0.14484881405033495,
  "global_step": 24000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.0117890840324302e-07,
      "loss": 0.4247,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.03380152270937254,
      "eval_f1": 0.0619012340183338,
      "eval_loss": 0.20814624428749084,
      "eval_roc_auc": 0.5159319239399485,
      "eval_runtime": 8197.4985,
      "eval_samples_per_second": 33.455,
      "eval_steps_per_second": 2.091,
      "step": 2000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.0235781680648604e-07,
      "loss": 0.1716,
      "step": 4000
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.6045477086432718,
      "eval_f1": 0.7149013381719211,
      "eval_loss": 0.12680654227733612,
      "eval_roc_auc": 0.7994218657046591,
      "eval_runtime": 8196.5733,
      "eval_samples_per_second": 33.459,
      "eval_steps_per_second": 2.091,
      "step": 4000
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.03536725209729e-07,
      "loss": 0.114,
      "step": 6000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.7269478719990665,
      "eval_f1": 0.8064969810911458,
      "eval_loss": 0.09042555838823318,
      "eval_roc_auc": 0.863152127136236,
      "eval_runtime": 8195.1585,
      "eval_samples_per_second": 33.465,
      "eval_steps_per_second": 2.092,
      "step": 6000
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.047156336129721e-07,
      "loss": 0.0865,
      "step": 8000
    },
    {
      "epoch": 0.05,
      "eval_accuracy": 0.774762258977276,
      "eval_f1": 0.8402673463726624,
      "eval_loss": 0.07436466217041016,
      "eval_roc_auc": 0.8920166546037435,
      "eval_runtime": 8191.8248,
      "eval_samples_per_second": 33.478,
      "eval_steps_per_second": 2.092,
      "step": 8000
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.005894542016215e-06,
      "loss": 0.0743,
      "step": 10000
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.7829883900703013,
      "eval_f1": 0.8487029462020401,
      "eval_loss": 0.06654931604862213,
      "eval_roc_auc": 0.9001618402078589,
      "eval_runtime": 8196.3415,
      "eval_samples_per_second": 33.46,
      "eval_steps_per_second": 2.091,
      "step": 10000
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.207073450419458e-06,
      "loss": 0.0664,
      "step": 12000
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.794452466380794,
      "eval_f1": 0.859163976123391,
      "eval_loss": 0.061000920832157135,
      "eval_roc_auc": 0.9083440937813021,
      "eval_runtime": 8197.7585,
      "eval_samples_per_second": 33.454,
      "eval_steps_per_second": 2.091,
      "step": 12000
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.4082523588227012e-06,
      "loss": 0.062,
      "step": 14000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.7962172923777019,
      "eval_f1": 0.8624403660379281,
      "eval_loss": 0.05871045961976051,
      "eval_roc_auc": 0.9133217347648154,
      "eval_runtime": 8199.4678,
      "eval_samples_per_second": 33.447,
      "eval_steps_per_second": 2.091,
      "step": 14000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.6094312672259442e-06,
      "loss": 0.0599,
      "step": 16000
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.7979055453458184,
      "eval_f1": 0.8656510165555269,
      "eval_loss": 0.05596928298473358,
      "eval_roc_auc": 0.9150237468241987,
      "eval_runtime": 8200.3089,
      "eval_samples_per_second": 33.444,
      "eval_steps_per_second": 2.09,
      "step": 16000
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.8106101756291871e-06,
      "loss": 0.0569,
      "step": 18000
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8009939908404072,
      "eval_f1": 0.8665697356924421,
      "eval_loss": 0.05469416454434395,
      "eval_roc_auc": 0.9135503362863645,
      "eval_runtime": 8201.2258,
      "eval_samples_per_second": 33.44,
      "eval_steps_per_second": 2.09,
      "step": 18000
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.01178908403243e-06,
      "loss": 0.0554,
      "step": 20000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.8071891135031066,
      "eval_f1": 0.8723540166082954,
      "eval_loss": 0.052826616913080215,
      "eval_roc_auc": 0.9192588608785235,
      "eval_runtime": 8204.8057,
      "eval_samples_per_second": 33.425,
      "eval_steps_per_second": 2.089,
      "step": 20000
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.2129679924356733e-06,
      "loss": 0.0541,
      "step": 22000
    },
    {
      "epoch": 0.13,
      "eval_accuracy": 0.8054935678655816,
      "eval_f1": 0.8706366827585739,
      "eval_loss": 0.05298588052392006,
      "eval_roc_auc": 0.9176729146649489,
      "eval_runtime": 8206.5949,
      "eval_samples_per_second": 33.418,
      "eval_steps_per_second": 2.089,
      "step": 22000
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.414146900838916e-06,
      "loss": 0.0522,
      "step": 24000
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.8137306379627198,
      "eval_f1": 0.8754267260214113,
      "eval_loss": 0.05081520974636078,
      "eval_roc_auc": 0.9180724092422241,
      "eval_runtime": 8275.6912,
      "eval_samples_per_second": 33.139,
      "eval_steps_per_second": 2.071,
      "step": 24000
    }
  ],
  "max_steps": 828450,
  "num_train_epochs": 5,
  "total_flos": 7.15754724655104e+17,
  "trial_name": null,
  "trial_params": null
}