trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.142857142857143,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.3697612285614014,
      "eval_runtime": 53.7583,
      "eval_samples_per_second": 4.874,
      "eval_steps_per_second": 0.614,
      "step": 140
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.350198745727539,
      "eval_runtime": 52.6608,
      "eval_samples_per_second": 4.975,
      "eval_steps_per_second": 0.627,
      "step": 280
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.6000664234161377,
      "eval_runtime": 51.3966,
      "eval_samples_per_second": 5.098,
      "eval_steps_per_second": 0.642,
      "step": 420
    },
    {
      "epoch": 3.57,
      "learning_rate": 1.2857142857142859e-05,
      "loss": 1.8394,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.011274576187134,
      "eval_runtime": 51.1881,
      "eval_samples_per_second": 5.118,
      "eval_steps_per_second": 0.645,
      "step": 560
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.5172500610351562,
      "eval_runtime": 53.2278,
      "eval_samples_per_second": 4.922,
      "eval_steps_per_second": 0.62,
      "step": 700
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.840390682220459,
      "eval_runtime": 53.3892,
      "eval_samples_per_second": 4.907,
      "eval_steps_per_second": 0.618,
      "step": 840
    },
    {
      "epoch": 7.0,
      "eval_loss": 4.020865440368652,
      "eval_runtime": 52.1972,
      "eval_samples_per_second": 5.019,
      "eval_steps_per_second": 0.632,
      "step": 980
    },
    {
      "epoch": 7.14,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.4408,
      "step": 1000
    }
  ],
  "max_steps": 1400,
  "num_train_epochs": 10,
  "total_flos": 1857413971968000.0,
  "trial_name": null,
  "trial_params": null
}