trainer_state.json

{
  "best_metric": 3.5809426307678223,
  "best_model_checkpoint": "output/machine-gun-kelly/checkpoint-89",
  "epoch": 1.0,
  "global_step": 89,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 0.00013613432149130463,
      "loss": 4.0171,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013297039589769353,
      "loss": 3.8291,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00012780652431270098,
      "loss": 3.7356,
      "step": 15
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012080314484040238,
      "loss": 3.6492,
      "step": 20
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011217784788872395,
      "loss": 3.8074,
      "step": 25
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010219861577814726,
      "loss": 3.9627,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.117549670673429e-05,
      "loss": 3.6545,
      "step": 35
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.945097175591926e-05,
      "loss": 3.8401,
      "step": 40
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.738931422788137e-05,
      "loss": 3.5858,
      "step": 45
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.536527191290851e-05,
      "loss": 3.3994,
      "step": 50
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.3752423921283795e-05,
      "loss": 3.7921,
      "step": 55
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.2911573825293485e-05,
      "loss": 3.5054,
      "step": 60
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3179539728823493e-05,
      "loss": 3.5062,
      "step": 65
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4858689549730916e-05,
      "loss": 3.5327,
      "step": 70
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.20754664690595e-06,
      "loss": 3.6406,
      "step": 75
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.432757669030831e-06,
      "loss": 3.5643,
      "step": 80
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.826721787084347e-07,
      "loss": 3.6327,
      "step": 85
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.5809426307678223,
      "eval_runtime": 6.0557,
      "eval_samples_per_second": 20.972,
      "eval_steps_per_second": 2.642,
      "step": 89
    }
  ],
  "max_steps": 89,
  "num_train_epochs": 1,
  "total_flos": 92758671360000.0,
  "trial_name": null,
  "trial_params": null
}