{
  "best_metric": 0.6816325187683105,
  "best_model_checkpoint": "./vietquill/checkpoint-6250",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 2.7459194660186768,
      "learning_rate": 4.7333333333333336e-05,
      "loss": 1.0259,
      "step": 500
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.7354345321655273,
      "learning_rate": 4.466666666666667e-05,
      "loss": 0.6894,
      "step": 1000
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.6172490119934082,
      "learning_rate": 4.2e-05,
      "loss": 0.6605,
      "step": 1500
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.7326663732528687,
      "learning_rate": 3.933333333333333e-05,
      "loss": 0.6403,
      "step": 2000
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6991186141967773,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.6282,
      "step": 2500
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.655566692352295,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.6161,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.691973090171814,
      "eval_runtime": 3.7801,
      "eval_samples_per_second": 264.545,
      "eval_steps_per_second": 8.465,
      "step": 3125
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.739039659500122,
      "learning_rate": 3.1333333333333334e-05,
      "loss": 0.5487,
      "step": 3500
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.6791564226150513,
      "learning_rate": 2.8666666666666668e-05,
      "loss": 0.5273,
      "step": 4000
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.7030389308929443,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.5231,
      "step": 4500
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.8268135786056519,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.5201,
      "step": 5000
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.5327303409576416,
      "learning_rate": 2.0666666666666666e-05,
      "loss": 0.5208,
      "step": 5500
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.5141078233718872,
      "learning_rate": 1.8e-05,
      "loss": 0.5112,
      "step": 6000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6816325187683105,
      "eval_runtime": 3.7827,
      "eval_samples_per_second": 264.364,
      "eval_steps_per_second": 8.46,
      "step": 6250
    }
  ],
  "logging_steps": 500,
  "max_steps": 9375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.1417960448e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}