{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 5913,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2536783358701167,
      "grad_norm": 6.285004615783691,
      "learning_rate": 1.9157787924911212e-05,
      "loss": 1.589,
      "step": 500
    },
    {
      "epoch": 0.5073566717402334,
      "grad_norm": 6.245589256286621,
      "learning_rate": 1.8312193472010826e-05,
      "loss": 0.8971,
      "step": 1000
    },
    {
      "epoch": 0.76103500761035,
      "grad_norm": 7.839916706085205,
      "learning_rate": 1.7466599019110436e-05,
      "loss": 0.7412,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 77.9302498710783,
      "eval_loss": 0.5189284682273865,
      "eval_rouge": {
        "rouge1": 0.8422585807632581,
        "rouge2": 0.7462100224193878,
        "rougeL": 0.8347423871515361,
        "rougeLsum": 0.8348341110331449
      },
      "eval_runtime": 589.3644,
      "eval_samples_per_second": 14.402,
      "eval_steps_per_second": 0.901,
      "step": 1971
    },
    {
      "epoch": 1.0147133434804667,
      "grad_norm": 4.194991111755371,
      "learning_rate": 1.6621004566210046e-05,
      "loss": 0.6173,
      "step": 2000
    },
    {
      "epoch": 1.2683916793505834,
      "grad_norm": 4.830150127410889,
      "learning_rate": 1.5775410113309656e-05,
      "loss": 0.4964,
      "step": 2500
    },
    {
      "epoch": 1.5220700152207,
      "grad_norm": 6.662743091583252,
      "learning_rate": 1.4929815660409268e-05,
      "loss": 0.4655,
      "step": 3000
    },
    {
      "epoch": 1.775748351090817,
      "grad_norm": 5.814598560333252,
      "learning_rate": 1.408422120750888e-05,
      "loss": 0.4562,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_bleu": 82.4671860062862,
      "eval_loss": 0.4167616665363312,
      "eval_rouge": {
        "rouge1": 0.8726285922102037,
        "rouge2": 0.7929049594785995,
        "rougeL": 0.8662329420974849,
        "rougeLsum": 0.8662523269791588
      },
      "eval_runtime": 558.5398,
      "eval_samples_per_second": 15.197,
      "eval_steps_per_second": 0.951,
      "step": 3942
    },
    {
      "epoch": 2.0294266869609334,
      "grad_norm": 4.13426399230957,
      "learning_rate": 1.323862675460849e-05,
      "loss": 0.4122,
      "step": 4000
    },
    {
      "epoch": 2.2831050228310503,
      "grad_norm": 4.324504375457764,
      "learning_rate": 1.2393032301708102e-05,
      "loss": 0.3451,
      "step": 4500
    },
    {
      "epoch": 2.536783358701167,
      "grad_norm": 1.6161426305770874,
      "learning_rate": 1.1549129037713514e-05,
      "loss": 0.3359,
      "step": 5000
    },
    {
      "epoch": 2.7904616945712837,
      "grad_norm": 3.2323482036590576,
      "learning_rate": 1.0703534584813124e-05,
      "loss": 0.3413,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "eval_bleu": 84.42968434246376,
      "eval_loss": 0.3801760971546173,
      "eval_rouge": {
        "rouge1": 0.8853534128903551,
        "rouge2": 0.8130151085172689,
        "rougeL": 0.8794009703754694,
        "rougeLsum": 0.8793662457667164
      },
      "eval_runtime": 553.0346,
      "eval_samples_per_second": 15.348,
      "eval_steps_per_second": 0.96,
      "step": 5913
    }
  ],
  "logging_steps": 500,
  "max_steps": 11826,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 797791397806080.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}