{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008132395397064205,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.132395397064206e-05,
      "grad_norm": 0.011654906906187534,
      "learning_rate": 2e-05,
      "loss": 11.9317,
      "step": 1
    },
    {
      "epoch": 8.132395397064206e-05,
      "eval_loss": 11.933029174804688,
      "eval_runtime": 18.7625,
      "eval_samples_per_second": 275.976,
      "eval_steps_per_second": 137.988,
      "step": 1
    },
    {
      "epoch": 0.00016264790794128412,
      "grad_norm": 0.010800319723784924,
      "learning_rate": 4e-05,
      "loss": 11.9352,
      "step": 2
    },
    {
      "epoch": 0.00024397186191192616,
      "grad_norm": 0.00888215471059084,
      "learning_rate": 6e-05,
      "loss": 11.9322,
      "step": 3
    },
    {
      "epoch": 0.00024397186191192616,
      "eval_loss": 11.933025360107422,
      "eval_runtime": 19.13,
      "eval_samples_per_second": 270.675,
      "eval_steps_per_second": 135.337,
      "step": 3
    },
    {
      "epoch": 0.00032529581588256823,
      "grad_norm": 0.01088379044085741,
      "learning_rate": 8e-05,
      "loss": 11.9312,
      "step": 4
    },
    {
      "epoch": 0.00040661976985321025,
      "grad_norm": 0.012420984916388988,
      "learning_rate": 0.0001,
      "loss": 11.9306,
      "step": 5
    },
    {
      "epoch": 0.0004879437238238523,
      "grad_norm": 0.01234439667314291,
      "learning_rate": 0.00012,
      "loss": 11.9318,
      "step": 6
    },
    {
      "epoch": 0.0004879437238238523,
      "eval_loss": 11.933008193969727,
      "eval_runtime": 19.3224,
      "eval_samples_per_second": 267.979,
      "eval_steps_per_second": 133.989,
      "step": 6
    },
    {
      "epoch": 0.0005692676777944944,
      "grad_norm": 0.009680359624326229,
      "learning_rate": 0.00014,
      "loss": 11.9351,
      "step": 7
    },
    {
      "epoch": 0.0006505916317651365,
      "grad_norm": 0.009907381609082222,
      "learning_rate": 0.00016,
      "loss": 11.9327,
      "step": 8
    },
    {
      "epoch": 0.0007319155857357784,
      "grad_norm": 0.009030411951243877,
      "learning_rate": 0.00018,
      "loss": 11.9317,
      "step": 9
    },
    {
      "epoch": 0.0007319155857357784,
      "eval_loss": 11.932974815368652,
      "eval_runtime": 19.3159,
      "eval_samples_per_second": 268.069,
      "eval_steps_per_second": 134.035,
      "step": 9
    },
    {
      "epoch": 0.0008132395397064205,
      "grad_norm": 0.007081515155732632,
      "learning_rate": 0.0002,
      "loss": 11.9329,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}