{
  "best_metric": 0.5050071530758227,
  "best_model_checkpoint": "/RuleBert-v0.0-k0/checkpoint-400",
  "epoch": 0.8849557522123894,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 1.999951808959328e-05,
      "loss": 0.6589,
      "step": 25
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9998072404820648e-05,
      "loss": 0.554,
      "step": 50
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.0,
      "eval_f1": 0.4280639431616341,
      "eval_loss": 0.49144598841667175,
      "eval_roc_auc": 0.6450392140327205,
      "eval_runtime": 2.6644,
      "eval_samples_per_second": 90.076,
      "eval_steps_per_second": 3.003,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9995663085020215e-05,
      "loss": 0.471,
      "step": 75
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9992290362407232e-05,
      "loss": 0.4187,
      "step": 100
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.0,
      "eval_f1": 0.4875621890547264,
      "eval_loss": 0.40552660822868347,
      "eval_roc_auc": 0.6698800387923765,
      "eval_runtime": 2.7272,
      "eval_samples_per_second": 88.003,
      "eval_steps_per_second": 2.933,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9987954562051724e-05,
      "loss": 0.3947,
      "step": 125
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.998265610184716e-05,
      "loss": 0.3621,
      "step": 150
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.008333333333333333,
      "eval_f1": 0.49451303155006865,
      "eval_loss": 0.3777387738227844,
      "eval_roc_auc": 0.6711924439197166,
      "eval_runtime": 2.8618,
      "eval_samples_per_second": 83.864,
      "eval_steps_per_second": 2.795,
      "step": 150
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.997639549247016e-05,
      "loss": 0.3516,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9969173337331283e-05,
      "loss": 0.3541,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.025,
      "eval_f1": 0.4965277777777778,
      "eval_loss": 0.3699280917644501,
      "eval_roc_auc": 0.6713821892393321,
      "eval_runtime": 2.8771,
      "eval_samples_per_second": 83.417,
      "eval_steps_per_second": 2.781,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9960990332516875e-05,
      "loss": 0.3512,
      "step": 225
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.995184726672197e-05,
      "loss": 0.3322,
      "step": 250
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.0,
      "eval_f1": 0.4925675675675676,
      "eval_loss": 0.36883607506752014,
      "eval_roc_auc": 0.6711713611064261,
      "eval_runtime": 2.8206,
      "eval_samples_per_second": 85.088,
      "eval_steps_per_second": 2.836,
      "step": 250
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.9941745021174284e-05,
      "loss": 0.3399,
      "step": 275
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.9930684569549265e-05,
      "loss": 0.3276,
      "step": 300
    },
    {
      "epoch": 0.66,
      "eval_accuracy": 0.008333333333333333,
      "eval_f1": 0.49861495844875353,
      "eval_loss": 0.36757946014404297,
      "eval_roc_auc": 0.6724995783437342,
      "eval_runtime": 2.7494,
      "eval_samples_per_second": 87.293,
      "eval_steps_per_second": 2.91,
      "step": 300
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.991866697787626e-05,
      "loss": 0.3467,
      "step": 325
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.990569340443577e-05,
      "loss": 0.3078,
      "step": 350
    },
    {
      "epoch": 0.77,
      "eval_accuracy": 0.016666666666666666,
      "eval_f1": 0.5012285012285013,
      "eval_loss": 0.367951363325119,
      "eval_roc_auc": 0.6728632568729971,
      "eval_runtime": 2.7213,
      "eval_samples_per_second": 88.192,
      "eval_steps_per_second": 2.94,
      "step": 350
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.989176509964781e-05,
      "loss": 0.3211,
      "step": 375
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.3293,
      "step": 400
    },
    {
      "epoch": 0.88,
      "eval_accuracy": 0.0375,
      "eval_f1": 0.5050071530758227,
      "eval_loss": 0.36856791377067566,
      "eval_roc_auc": 0.6734061393152301,
      "eval_runtime": 2.704,
      "eval_samples_per_second": 88.757,
      "eval_steps_per_second": 2.959,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 8000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 18,
  "save_steps": 100,
  "total_flos": 842272879411200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}