{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 15.142274856567383,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 4.5661,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.56865119934082,
      "learning_rate": 3.7e-06,
      "loss": 4.056,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08292586621653063,
      "eval_chrf": 12.115072823446873,
      "eval_loss": 3.7036895751953125,
      "eval_runtime": 178.6768,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 0.056,
      "step": 40
    },
    {
      "epoch": 1.5,
      "grad_norm": 4.7472944259643555,
      "learning_rate": 5.7e-06,
      "loss": 3.6426,
      "step": 60
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.151535987854004,
      "learning_rate": 7.7e-06,
      "loss": 3.4175,
      "step": 80
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.11532396839386093,
      "eval_chrf": 11.26745223357386,
      "eval_loss": 3.222604274749756,
      "eval_runtime": 179.1154,
      "eval_samples_per_second": 7.051,
      "eval_steps_per_second": 0.056,
      "step": 80
    },
    {
      "epoch": 2.5,
      "grad_norm": 4.280997276306152,
      "learning_rate": 9.7e-06,
      "loss": 3.271,
      "step": 100
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.886098861694336,
      "learning_rate": 7.166666666666667e-06,
      "loss": 3.1704,
      "step": 120
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.28031201145196877,
      "eval_chrf": 12.970874439653402,
      "eval_loss": 3.114114999771118,
      "eval_runtime": 173.6137,
      "eval_samples_per_second": 7.275,
      "eval_steps_per_second": 0.058,
      "step": 120
    },
    {
      "epoch": 3.5,
      "grad_norm": 4.001130104064941,
      "learning_rate": 3.833333333333334e-06,
      "loss": 3.0489,
      "step": 140
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.64552116394043,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.0286,
      "step": 160
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.403603847823992,
      "eval_chrf": 13.32793093086563,
      "eval_loss": 3.0850913524627686,
      "eval_runtime": 173.0697,
      "eval_samples_per_second": 7.298,
      "eval_steps_per_second": 0.058,
      "step": 160
    },
    {
      "epoch": 4.0,
      "step": 160,
      "total_flos": 2.6372074438656e+18,
      "train_loss": 3.52513427734375,
      "train_runtime": 5653.8341,
      "train_samples_per_second": 7.192,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 20,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 2.6372074438656e+18,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}