{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012132241431604488,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002426448286320898,
      "grad_norm": Infinity,
      "learning_rate": 1e-05,
      "loss": 55.5938,
      "step": 1
    },
    {
      "epoch": 0.002426448286320898,
      "eval_loss": 3.6129047870635986,
      "eval_runtime": 91.9031,
      "eval_samples_per_second": 7.562,
      "eval_steps_per_second": 3.787,
      "step": 1
    },
    {
      "epoch": 0.004852896572641796,
      "grad_norm": 19.853017807006836,
      "learning_rate": 2e-05,
      "loss": 55.6406,
      "step": 2
    },
    {
      "epoch": 0.004852896572641796,
      "eval_loss": 3.60894775390625,
      "eval_runtime": 4.231,
      "eval_samples_per_second": 164.263,
      "eval_steps_per_second": 82.25,
      "step": 2
    },
    {
      "epoch": 0.007279344858962694,
      "grad_norm": 19.75115966796875,
      "learning_rate": 3e-05,
      "loss": 56.7031,
      "step": 3
    },
    {
      "epoch": 0.009705793145283591,
      "grad_norm": 20.263111114501953,
      "learning_rate": 4e-05,
      "loss": 58.7344,
      "step": 4
    },
    {
      "epoch": 0.009705793145283591,
      "eval_loss": 3.588758945465088,
      "eval_runtime": 4.3018,
      "eval_samples_per_second": 161.562,
      "eval_steps_per_second": 80.897,
      "step": 4
    },
    {
      "epoch": 0.012132241431604488,
      "grad_norm": 18.69461441040039,
      "learning_rate": 5e-05,
      "loss": 57.1094,
      "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": 157646271283200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}