{
  "best_metric": 0.1497994363307953,
  "best_model_checkpoint": "/home/paperspace/distilbert_distilbert-base-uncased_cpt_f80627ff/checkpoint-8592",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 8592,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 9.418063314711358e-07,
      "loss": 0.5529,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.836126629422719e-07,
      "loss": 0.2622,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "learning_rate": 8.254189944134078e-07,
      "loss": 0.1843,
      "step": 1500
    },
    {
      "epoch": 0.93,
      "learning_rate": 7.672253258845437e-07,
      "loss": 0.1707,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9436447582835416,
      "eval_f1": 0.9439168742293816,
      "eval_loss": 0.16297364234924316,
      "eval_precision": 0.944853339492281,
      "eval_recall": 0.9436447582835416,
      "eval_runtime": 3.7301,
      "eval_samples_per_second": 1974.215,
      "eval_steps_per_second": 123.59,
      "step": 2148
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.090316573556797e-07,
      "loss": 0.165,
      "step": 2500
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.508379888268156e-07,
      "loss": 0.1518,
      "step": 3000
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.926443202979516e-07,
      "loss": 0.1561,
      "step": 3500
    },
    {
      "epoch": 1.86,
      "learning_rate": 5.344506517690875e-07,
      "loss": 0.15,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9496197718631179,
      "eval_f1": 0.9497706506636553,
      "eval_loss": 0.15333020687103271,
      "eval_precision": 0.9501640547936412,
      "eval_recall": 0.9496197718631179,
      "eval_runtime": 3.7323,
      "eval_samples_per_second": 1973.021,
      "eval_steps_per_second": 123.515,
      "step": 4296
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.7625698324022343e-07,
      "loss": 0.1467,
      "step": 4500
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.1806331471135937e-07,
      "loss": 0.1454,
      "step": 5000
    },
    {
      "epoch": 2.56,
      "learning_rate": 3.598696461824953e-07,
      "loss": 0.1536,
      "step": 5500
    },
    {
      "epoch": 2.79,
      "learning_rate": 3.016759776536313e-07,
      "loss": 0.1474,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9505703422053232,
      "eval_f1": 0.950777849389015,
      "eval_loss": 0.15110179781913757,
      "eval_precision": 0.9514811036756906,
      "eval_recall": 0.9505703422053232,
      "eval_runtime": 3.7273,
      "eval_samples_per_second": 1975.7,
      "eval_steps_per_second": 123.682,
      "step": 6444
    },
    {
      "epoch": 3.03,
      "learning_rate": 2.4348230912476723e-07,
      "loss": 0.1481,
      "step": 6500
    },
    {
      "epoch": 3.26,
      "learning_rate": 1.8528864059590317e-07,
      "loss": 0.1325,
      "step": 7000
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.270949720670391e-07,
      "loss": 0.1521,
      "step": 7500
    },
    {
      "epoch": 3.72,
      "learning_rate": 6.890130353817504e-08,
      "loss": 0.1482,
      "step": 8000
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.0707635009310987e-08,
      "loss": 0.1417,
      "step": 8500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9507061379684953,
      "eval_f1": 0.950911417495333,
      "eval_loss": 0.1497994363307953,
      "eval_precision": 0.951604073542191,
      "eval_recall": 0.9507061379684953,
      "eval_runtime": 3.7541,
      "eval_samples_per_second": 1961.603,
      "eval_steps_per_second": 122.8,
      "step": 8592
    }
  ],
  "logging_steps": 500,
  "max_steps": 8592,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 1751875913992452.0,
  "trial_name": null,
  "trial_params": null
}