{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014272970561998216,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002854594112399643,
      "grad_norm": 0.11384379863739014,
      "learning_rate": 1e-05,
      "loss": 10.3522,
      "step": 1
    },
    {
      "epoch": 0.002854594112399643,
      "eval_loss": 10.365853309631348,
      "eval_runtime": 12.302,
      "eval_samples_per_second": 47.96,
      "eval_steps_per_second": 23.98,
      "step": 1
    },
    {
      "epoch": 0.005709188224799286,
      "grad_norm": 0.12375456839799881,
      "learning_rate": 2e-05,
      "loss": 10.3373,
      "step": 2
    },
    {
      "epoch": 0.005709188224799286,
      "eval_loss": 10.365823745727539,
      "eval_runtime": 1.1516,
      "eval_samples_per_second": 512.317,
      "eval_steps_per_second": 256.158,
      "step": 2
    },
    {
      "epoch": 0.00856378233719893,
      "grad_norm": 0.11590752005577087,
      "learning_rate": 3e-05,
      "loss": 10.3682,
      "step": 3
    },
    {
      "epoch": 0.011418376449598573,
      "grad_norm": 0.1116405725479126,
      "learning_rate": 4e-05,
      "loss": 10.3703,
      "step": 4
    },
    {
      "epoch": 0.011418376449598573,
      "eval_loss": 10.365663528442383,
      "eval_runtime": 1.1943,
      "eval_samples_per_second": 494.022,
      "eval_steps_per_second": 247.011,
      "step": 4
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 0.11406431347131729,
      "learning_rate": 5e-05,
      "loss": 10.3489,
      "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": 507538145280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}