{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0042739608932578265,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021369804466289135,
      "eval_loss": 2.4877243041992188,
      "eval_runtime": 457.0551,
      "eval_samples_per_second": 4.312,
      "eval_steps_per_second": 2.157,
      "step": 1
    },
    {
      "epoch": 0.000641094133988674,
      "grad_norm": 4.445597171783447,
      "learning_rate": 6e-05,
      "loss": 10.3211,
      "step": 3
    },
    {
      "epoch": 0.001282188267977348,
      "grad_norm": 6.202150821685791,
      "learning_rate": 0.00012,
      "loss": 9.753,
      "step": 6
    },
    {
      "epoch": 0.0017095843573031308,
      "eval_loss": 1.6582492589950562,
      "eval_runtime": 459.9811,
      "eval_samples_per_second": 4.285,
      "eval_steps_per_second": 2.144,
      "step": 8
    },
    {
      "epoch": 0.001923282401966022,
      "grad_norm": 3.8049893379211426,
      "learning_rate": 0.00018,
      "loss": 7.5124,
      "step": 9
    },
    {
      "epoch": 0.002564376535954696,
      "grad_norm": 5.509289264678955,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.9222,
      "step": 12
    },
    {
      "epoch": 0.00320547066994337,
      "grad_norm": 4.7509236335754395,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.0086,
      "step": 15
    },
    {
      "epoch": 0.0034191687146062615,
      "eval_loss": 0.9060437679290771,
      "eval_runtime": 459.6826,
      "eval_samples_per_second": 4.288,
      "eval_steps_per_second": 2.145,
      "step": 16
    },
    {
      "epoch": 0.003846564803932044,
      "grad_norm": 3.560378313064575,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.3933,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.26956599246848e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}