{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009710741293713509,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019421482587427018,
      "grad_norm": 606.1136474609375,
      "learning_rate": 1e-05,
      "loss": 44.9038,
      "step": 1
    },
    {
      "epoch": 0.00019421482587427018,
      "eval_loss": 2.784213066101074,
      "eval_runtime": 331.9237,
      "eval_samples_per_second": 26.126,
      "eval_steps_per_second": 13.063,
      "step": 1
    },
    {
      "epoch": 0.00038842965174854037,
      "grad_norm": 616.8704833984375,
      "learning_rate": 2e-05,
      "loss": 44.8379,
      "step": 2
    },
    {
      "epoch": 0.00038842965174854037,
      "eval_loss": 2.322169065475464,
      "eval_runtime": 345.8513,
      "eval_samples_per_second": 25.074,
      "eval_steps_per_second": 12.537,
      "step": 2
    },
    {
      "epoch": 0.0005826444776228106,
      "grad_norm": 299.1457824707031,
      "learning_rate": 3e-05,
      "loss": 37.8144,
      "step": 3
    },
    {
      "epoch": 0.0007768593034970807,
      "grad_norm": 277.48291015625,
      "learning_rate": 4e-05,
      "loss": 31.9779,
      "step": 4
    },
    {
      "epoch": 0.0007768593034970807,
      "eval_loss": 1.6035250425338745,
      "eval_runtime": 288.7068,
      "eval_samples_per_second": 30.037,
      "eval_steps_per_second": 15.019,
      "step": 4
    },
    {
      "epoch": 0.0009710741293713509,
      "grad_norm": 263.9320373535156,
      "learning_rate": 5e-05,
      "loss": 26.2169,
      "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": 3505343598428160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}