{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002498828674059035,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006247071685147587,
      "grad_norm": 10.409964561462402,
      "learning_rate": 1e-05,
      "loss": 4.6825,
      "step": 1
    },
    {
      "epoch": 0.0006247071685147587,
      "eval_loss": 4.6200666427612305,
      "eval_runtime": 568.2362,
      "eval_samples_per_second": 4.746,
      "eval_steps_per_second": 2.374,
      "step": 1
    },
    {
      "epoch": 0.0012494143370295175,
      "grad_norm": 9.638011932373047,
      "learning_rate": 2e-05,
      "loss": 4.4834,
      "step": 2
    },
    {
      "epoch": 0.0012494143370295175,
      "eval_loss": 4.438206195831299,
      "eval_runtime": 144.7582,
      "eval_samples_per_second": 18.631,
      "eval_steps_per_second": 9.319,
      "step": 2
    },
    {
      "epoch": 0.0018741215055442762,
      "grad_norm": 8.082115173339844,
      "learning_rate": 3e-05,
      "loss": 3.6311,
      "step": 3
    },
    {
      "epoch": 0.002498828674059035,
      "grad_norm": 10.77220344543457,
      "learning_rate": 4e-05,
      "loss": 4.1225,
      "step": 4
    },
    {
      "epoch": 0.002498828674059035,
      "eval_loss": 3.387336015701294,
      "eval_runtime": 86.0062,
      "eval_samples_per_second": 31.358,
      "eval_steps_per_second": 15.685,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3283829787721728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}