trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2484,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 19.886152267456055,
      "learning_rate": 2.4608501118568234e-07,
      "loss": 3.3177,
      "step": 2484
    },
    {
      "epoch": 1.0,
      "eval_bleu": 19.1214,
      "eval_gen_len": 9.4576,
      "eval_loss": 1.923163890838623,
      "eval_runtime": 233.2089,
      "eval_samples_per_second": 58.99,
      "eval_steps_per_second": 1.844,
      "step": 2484
    }
  ],
  "logging_steps": 500,
  "max_steps": 2484,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4821854909561856.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}