{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00670465973851827,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006704659738518271,
      "grad_norm": 4.041480541229248,
      "learning_rate": 2e-05,
      "loss": 5.117,
      "step": 1
    },
    {
      "epoch": 0.0006704659738518271,
      "eval_loss": 5.064063549041748,
      "eval_runtime": 52.7515,
      "eval_samples_per_second": 11.905,
      "eval_steps_per_second": 5.952,
      "step": 1
    },
    {
      "epoch": 0.0013409319477036541,
      "grad_norm": 3.8326361179351807,
      "learning_rate": 4e-05,
      "loss": 5.0327,
      "step": 2
    },
    {
      "epoch": 0.002011397921555481,
      "grad_norm": 3.754926919937134,
      "learning_rate": 6e-05,
      "loss": 4.8776,
      "step": 3
    },
    {
      "epoch": 0.002011397921555481,
      "eval_loss": 5.00453519821167,
      "eval_runtime": 52.682,
      "eval_samples_per_second": 11.921,
      "eval_steps_per_second": 5.96,
      "step": 3
    },
    {
      "epoch": 0.0026818638954073082,
      "grad_norm": 5.529252529144287,
      "learning_rate": 8e-05,
      "loss": 5.7991,
      "step": 4
    },
    {
      "epoch": 0.003352329869259135,
      "grad_norm": 3.168138027191162,
      "learning_rate": 0.0001,
      "loss": 4.8356,
      "step": 5
    },
    {
      "epoch": 0.004022795843110962,
      "grad_norm": 3.3904759883880615,
      "learning_rate": 0.00012,
      "loss": 4.3142,
      "step": 6
    },
    {
      "epoch": 0.004022795843110962,
      "eval_loss": 4.290420055389404,
      "eval_runtime": 52.7807,
      "eval_samples_per_second": 11.898,
      "eval_steps_per_second": 5.949,
      "step": 6
    },
    {
      "epoch": 0.004693261816962789,
      "grad_norm": 3.2405154705047607,
      "learning_rate": 0.00014,
      "loss": 4.1384,
      "step": 7
    },
    {
      "epoch": 0.0053637277908146165,
      "grad_norm": 3.9647226333618164,
      "learning_rate": 0.00016,
      "loss": 3.543,
      "step": 8
    },
    {
      "epoch": 0.006034193764666443,
      "grad_norm": 4.046013832092285,
      "learning_rate": 0.00018,
      "loss": 3.4731,
      "step": 9
    },
    {
      "epoch": 0.006034193764666443,
      "eval_loss": 3.0233943462371826,
      "eval_runtime": 52.9098,
      "eval_samples_per_second": 11.869,
      "eval_steps_per_second": 5.935,
      "step": 9
    },
    {
      "epoch": 0.00670465973851827,
      "grad_norm": 2.753418207168579,
      "learning_rate": 0.0002,
      "loss": 2.7829,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}