checkpoint-100/trainer_state.json

{
  "best_metric": 0.39582160115242004,
  "best_model_checkpoint": "output/checkpoint-100",
  "epoch": 1.0,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.7359,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7009,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.5e-05,
      "loss": 0.6794,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6755,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.6509,
      "step": 25
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.6442,
      "step": 30
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 0.5768,
      "step": 35
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.6882,
      "step": 40
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.6102,
      "step": 45
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.5241,
      "step": 50
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.6044,
      "step": 55
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0186,
      "step": 60
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.6259,
      "step": 65
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.5959,
      "step": 70
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.5036,
      "step": 75
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.3528,
      "step": 80
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.5124,
      "step": 85
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.4032,
      "step": 90
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.3113,
      "step": 95
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.4913,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.835,
      "eval_auc": 0.9411999999999999,
      "eval_f1": 0.8533333333333333,
      "eval_loss": 0.39582160115242004,
      "eval_precision": 0.768,
      "eval_recall": 0.96,
      "eval_runtime": 0.9665,
      "eval_samples_per_second": 206.925,
      "eval_steps_per_second": 13.45,
      "step": 100
    }
  ],
  "max_steps": 300,
  "num_train_epochs": 3,
  "total_flos": 105244422144000.0,
  "trial_name": null,
  "trial_params": null
}