{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000996189574876099,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019923791497521978,
      "grad_norm": 1.6526813507080078,
      "learning_rate": 1e-05,
      "loss": 2.2634,
      "step": 1
    },
    {
      "epoch": 0.00019923791497521978,
      "eval_loss": 2.703291416168213,
      "eval_runtime": 141.977,
      "eval_samples_per_second": 59.545,
      "eval_steps_per_second": 29.772,
      "step": 1
    },
    {
      "epoch": 0.00039847582995043956,
      "grad_norm": 1.9256006479263306,
      "learning_rate": 2e-05,
      "loss": 2.7682,
      "step": 2
    },
    {
      "epoch": 0.00039847582995043956,
      "eval_loss": 2.6866419315338135,
      "eval_runtime": 91.7448,
      "eval_samples_per_second": 92.147,
      "eval_steps_per_second": 46.073,
      "step": 2
    },
    {
      "epoch": 0.0005977137449256594,
      "grad_norm": 1.9943788051605225,
      "learning_rate": 3e-05,
      "loss": 2.7358,
      "step": 3
    },
    {
      "epoch": 0.0007969516599008791,
      "grad_norm": 1.673327088356018,
      "learning_rate": 4e-05,
      "loss": 2.2359,
      "step": 4
    },
    {
      "epoch": 0.0007969516599008791,
      "eval_loss": 2.6501004695892334,
      "eval_runtime": 92.615,
      "eval_samples_per_second": 91.281,
      "eval_steps_per_second": 45.641,
      "step": 4
    },
    {
      "epoch": 0.000996189574876099,
      "grad_norm": 2.082404851913452,
      "learning_rate": 5e-05,
      "loss": 2.7304,
      "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": 991192531599360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}