trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 28,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.1482367217540741,
      "learning_rate": 0.00012857142857142858,
      "loss": 0.4295,
      "step": 10
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.13569863140583038,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.3544,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 28,
      "total_flos": 3.431561927399424e+16,
      "train_loss": 0.37262931891850065,
      "train_runtime": 25.36,
      "train_samples_per_second": 17.429,
      "train_steps_per_second": 1.104
    }
  ],
  "logging_steps": 10,
  "max_steps": 28,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.431561927399424e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}