{
  "best_metric": 1.0099247694015503,
  "best_model_checkpoint": "./outputs/checkpoint-800",
  "epoch": 1.0666666666666667,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.0596,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0747358798980713,
      "eval_runtime": 354.4756,
      "eval_samples_per_second": 5.445,
      "eval_steps_per_second": 0.683,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.9173,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.0527141094207764,
      "eval_runtime": 353.1278,
      "eval_samples_per_second": 5.465,
      "eval_steps_per_second": 0.685,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.9029,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0407249927520752,
      "eval_runtime": 353.5098,
      "eval_samples_per_second": 5.46,
      "eval_steps_per_second": 0.685,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.8938,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.033090591430664,
      "eval_runtime": 353.8818,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 0.684,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.881,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.0268442630767822,
      "eval_runtime": 352.5818,
      "eval_samples_per_second": 5.474,
      "eval_steps_per_second": 0.686,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.8815,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.0178813934326172,
      "eval_runtime": 353.5441,
      "eval_samples_per_second": 5.459,
      "eval_steps_per_second": 0.684,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.8785,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.0156869888305664,
      "eval_runtime": 353.6562,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 0.684,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.868,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.0099247694015503,
      "eval_runtime": 354.1025,
      "eval_samples_per_second": 5.45,
      "eval_steps_per_second": 0.683,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.2622081570707046e+17,
  "trial_name": null,
  "trial_params": null
}