{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00897084475454772,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033225350942769335,
      "eval_loss": 2.1395199298858643,
      "eval_runtime": 220.9563,
      "eval_samples_per_second": 22.941,
      "eval_steps_per_second": 2.869,
      "step": 1
    },
    {
      "epoch": 0.00099676052828308,
      "grad_norm": 5.9584269523620605,
      "learning_rate": 1.5e-05,
      "loss": 9.4483,
      "step": 3
    },
    {
      "epoch": 0.00199352105656616,
      "grad_norm": 4.213073253631592,
      "learning_rate": 3e-05,
      "loss": 7.8813,
      "step": 6
    },
    {
      "epoch": 0.00299028158484924,
      "grad_norm": 4.823021411895752,
      "learning_rate": 4.5e-05,
      "loss": 7.9607,
      "step": 9
    },
    {
      "epoch": 0.00299028158484924,
      "eval_loss": 2.070302963256836,
      "eval_runtime": 221.304,
      "eval_samples_per_second": 22.905,
      "eval_steps_per_second": 2.865,
      "step": 9
    },
    {
      "epoch": 0.00398704211313232,
      "grad_norm": 7.021877765655518,
      "learning_rate": 4.993910125649561e-05,
      "loss": 9.0723,
      "step": 12
    },
    {
      "epoch": 0.0049838026414154,
      "grad_norm": 10.367716789245605,
      "learning_rate": 4.962019382530521e-05,
      "loss": 8.6656,
      "step": 15
    },
    {
      "epoch": 0.00598056316969848,
      "grad_norm": 3.396527051925659,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 6.5636,
      "step": 18
    },
    {
      "epoch": 0.00598056316969848,
      "eval_loss": 1.8593316078186035,
      "eval_runtime": 221.3173,
      "eval_samples_per_second": 22.904,
      "eval_steps_per_second": 2.865,
      "step": 18
    },
    {
      "epoch": 0.00697732369798156,
      "grad_norm": 5.275881290435791,
      "learning_rate": 4.817959636416969e-05,
      "loss": 7.3881,
      "step": 21
    },
    {
      "epoch": 0.00797408422626464,
      "grad_norm": 4.454370975494385,
      "learning_rate": 4.707368982147318e-05,
      "loss": 7.0281,
      "step": 24
    },
    {
      "epoch": 0.00897084475454772,
      "grad_norm": 4.078393936157227,
      "learning_rate": 4.572593931387604e-05,
      "loss": 6.9298,
      "step": 27
    },
    {
      "epoch": 0.00897084475454772,
      "eval_loss": 1.7337881326675415,
      "eval_runtime": 221.3769,
      "eval_samples_per_second": 22.898,
      "eval_steps_per_second": 2.864,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2244945314316288.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}