{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00032073641079919497,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.414728215983899e-05,
      "grad_norm": 1.9259012937545776,
      "learning_rate": 1e-05,
      "loss": 5.1804,
      "step": 1
    },
    {
      "epoch": 6.414728215983899e-05,
      "eval_loss": 5.126567363739014,
      "eval_runtime": 766.6906,
      "eval_samples_per_second": 34.246,
      "eval_steps_per_second": 17.123,
      "step": 1
    },
    {
      "epoch": 0.00012829456431967797,
      "grad_norm": 1.4639827013015747,
      "learning_rate": 2e-05,
      "loss": 4.9218,
      "step": 2
    },
    {
      "epoch": 0.00012829456431967797,
      "eval_loss": 5.070332050323486,
      "eval_runtime": 685.0831,
      "eval_samples_per_second": 38.325,
      "eval_steps_per_second": 19.163,
      "step": 2
    },
    {
      "epoch": 0.00019244184647951697,
      "grad_norm": 1.6009812355041504,
      "learning_rate": 3e-05,
      "loss": 4.845,
      "step": 3
    },
    {
      "epoch": 0.00025658912863935594,
      "grad_norm": 1.580448031425476,
      "learning_rate": 4e-05,
      "loss": 5.0451,
      "step": 4
    },
    {
      "epoch": 0.00025658912863935594,
      "eval_loss": 5.014610767364502,
      "eval_runtime": 641.9917,
      "eval_samples_per_second": 40.898,
      "eval_steps_per_second": 20.449,
      "step": 4
    },
    {
      "epoch": 0.00032073641079919497,
      "grad_norm": 1.6791365146636963,
      "learning_rate": 5e-05,
      "loss": 4.8827,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3295645846732800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}