trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 12400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 5e-06,
      "loss": 2.7066,
      "step": 500
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-06,
      "loss": 2.6905,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-06,
      "loss": 2.6876,
      "step": 1500
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-06,
      "loss": 2.6909,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-06,
      "loss": 2.6893,
      "step": 2500
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-06,
      "loss": 2.6863,
      "step": 3000
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-06,
      "loss": 2.6819,
      "step": 3500
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-06,
      "loss": 2.6753,
      "step": 4000
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-06,
      "loss": 2.6755,
      "step": 4500
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-06,
      "loss": 2.6723,
      "step": 5000
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-06,
      "loss": 2.6704,
      "step": 5500
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-06,
      "loss": 2.6583,
      "step": 6000
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-06,
      "loss": 2.6613,
      "step": 6500
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-06,
      "loss": 2.6523,
      "step": 7000
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-06,
      "loss": 2.6655,
      "step": 7500
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-06,
      "loss": 2.6649,
      "step": 8000
    },
    {
      "epoch": 0.69,
      "learning_rate": 5e-06,
      "loss": 2.6646,
      "step": 8500
    },
    {
      "epoch": 0.73,
      "learning_rate": 5e-06,
      "loss": 2.6682,
      "step": 9000
    },
    {
      "epoch": 0.77,
      "learning_rate": 5e-06,
      "loss": 2.6613,
      "step": 9500
    },
    {
      "epoch": 0.81,
      "learning_rate": 5e-06,
      "loss": 2.6573,
      "step": 10000
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-06,
      "loss": 2.6548,
      "step": 10500
    },
    {
      "epoch": 0.89,
      "learning_rate": 5e-06,
      "loss": 2.6486,
      "step": 11000
    },
    {
      "epoch": 0.93,
      "learning_rate": 5e-06,
      "loss": 2.6452,
      "step": 11500
    },
    {
      "epoch": 0.97,
      "learning_rate": 5e-06,
      "loss": 2.656,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "step": 12400,
      "total_flos": 3.23186320404906e+18,
      "train_loss": 2.6698083889868953,
      "train_runtime": 104351.0142,
      "train_samples_per_second": 0.951,
      "train_steps_per_second": 0.119
    }
  ],
  "max_steps": 12400,
  "num_train_epochs": 1,
  "total_flos": 3.23186320404906e+18,
  "trial_name": null,
  "trial_params": null
}