trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 18850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.4446191337159036e-05,
      "loss": 3.7069,
      "step": 2827
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.1980156898498535,
      "eval_runtime": 24.6141,
      "eval_samples_per_second": 200.048,
      "eval_steps_per_second": 1.584,
      "step": 2827
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.333464350286927e-05,
      "loss": 3.0719,
      "step": 5654
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.040849447250366,
      "eval_runtime": 7.1854,
      "eval_samples_per_second": 685.277,
      "eval_steps_per_second": 5.428,
      "step": 5654
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.2223095668579518e-05,
      "loss": 2.8585,
      "step": 8481
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.969093084335327,
      "eval_runtime": 7.1989,
      "eval_samples_per_second": 683.998,
      "eval_steps_per_second": 5.418,
      "step": 8481
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.7462,
      "step": 11310
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.61379075050354,
      "eval_runtime": 25.0394,
      "eval_samples_per_second": 196.57,
      "eval_steps_per_second": 2.077,
      "step": 11310
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.6518,
      "step": 15080
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.5971875190734863,
      "eval_runtime": 14.767,
      "eval_samples_per_second": 333.31,
      "eval_steps_per_second": 3.521,
      "step": 15080
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 2.5587,
      "step": 18850
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.5887153148651123,
      "eval_runtime": 7.6626,
      "eval_samples_per_second": 642.341,
      "eval_steps_per_second": 6.786,
      "step": 18850
    }
  ],
  "max_steps": 18850,
  "num_train_epochs": 5,
  "total_flos": 6.795617845248e+16,
  "trial_name": null,
  "trial_params": null
}