{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001453646836501072,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014536468365010721,
      "grad_norm": 11.601491928100586,
      "learning_rate": 2e-05,
      "loss": 5.4024,
      "step": 1
    },
    {
      "epoch": 0.00014536468365010721,
      "eval_loss": 4.953571796417236,
      "eval_runtime": 584.8818,
      "eval_samples_per_second": 4.953,
      "eval_steps_per_second": 2.477,
      "step": 1
    },
    {
      "epoch": 0.00029072936730021443,
      "grad_norm": 10.93081283569336,
      "learning_rate": 4e-05,
      "loss": 4.8248,
      "step": 2
    },
    {
      "epoch": 0.00043609405095032164,
      "grad_norm": 11.980188369750977,
      "learning_rate": 6e-05,
      "loss": 3.6753,
      "step": 3
    },
    {
      "epoch": 0.00043609405095032164,
      "eval_loss": 4.856893539428711,
      "eval_runtime": 1207.0774,
      "eval_samples_per_second": 2.4,
      "eval_steps_per_second": 1.2,
      "step": 3
    },
    {
      "epoch": 0.0005814587346004289,
      "grad_norm": 9.486178398132324,
      "learning_rate": 8e-05,
      "loss": 3.6912,
      "step": 4
    },
    {
      "epoch": 0.000726823418250536,
      "grad_norm": 13.129131317138672,
      "learning_rate": 0.0001,
      "loss": 5.223,
      "step": 5
    },
    {
      "epoch": 0.0008721881019006433,
      "grad_norm": 6.86362361907959,
      "learning_rate": 0.00012,
      "loss": 2.7892,
      "step": 6
    },
    {
      "epoch": 0.0008721881019006433,
      "eval_loss": 3.9613561630249023,
      "eval_runtime": 1207.1042,
      "eval_samples_per_second": 2.4,
      "eval_steps_per_second": 1.2,
      "step": 6
    },
    {
      "epoch": 0.0010175527855507504,
      "grad_norm": 6.20792293548584,
      "learning_rate": 0.00014,
      "loss": 2.2971,
      "step": 7
    },
    {
      "epoch": 0.0011629174692008577,
      "grad_norm": 17.221925735473633,
      "learning_rate": 0.00016,
      "loss": 4.6929,
      "step": 8
    },
    {
      "epoch": 0.0013082821528509648,
      "grad_norm": 9.793855667114258,
      "learning_rate": 0.00018,
      "loss": 3.1609,
      "step": 9
    },
    {
      "epoch": 0.0013082821528509648,
      "eval_loss": 2.8166067600250244,
      "eval_runtime": 1204.9844,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 1.203,
      "step": 9
    },
    {
      "epoch": 0.001453646836501072,
      "grad_norm": 6.832985877990723,
      "learning_rate": 0.0002,
      "loss": 2.4614,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 621231451668480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}