{
  "best_metric": 1.0260452032089233,
  "best_model_checkpoint": "./outputs/checkpoint-500",
  "epoch": 0.6666666666666666,
  "eval_steps": 100,
  "global_step": 500,
  "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": 1.001,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0910990238189697,
      "eval_runtime": 728.6528,
      "eval_samples_per_second": 2.649,
      "eval_steps_per_second": 0.332,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.8971,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.0677164793014526,
      "eval_runtime": 727.2702,
      "eval_samples_per_second": 2.654,
      "eval_steps_per_second": 0.333,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.8815,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.052659273147583,
      "eval_runtime": 730.164,
      "eval_samples_per_second": 2.643,
      "eval_steps_per_second": 0.331,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.8695,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.0382879972457886,
      "eval_runtime": 732.8796,
      "eval_samples_per_second": 2.633,
      "eval_steps_per_second": 0.33,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.8548,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.0260452032089233,
      "eval_runtime": 730.1971,
      "eval_samples_per_second": 2.643,
      "eval_steps_per_second": 0.331,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 3750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "total_flos": 1.2948397906255872e+17,
  "trial_name": null,
  "trial_params": null
}