{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00565171317555634,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": 1.004011631011963,
      "eval_runtime": 367.7456,
      "eval_samples_per_second": 4.052,
      "eval_steps_per_second": 2.026,
      "step": 1
    },
    {
      "epoch": 0.0008477569763334511,
      "grad_norm": 6.393833637237549,
      "learning_rate": 3e-05,
      "loss": 4.1435,
      "step": 3
    },
    {
      "epoch": 0.0016955139526669022,
      "grad_norm": 3.2712793350219727,
      "learning_rate": 6e-05,
      "loss": 3.7446,
      "step": 6
    },
    {
      "epoch": 0.0022606852702225363,
      "eval_loss": 0.8163854479789734,
      "eval_runtime": 370.5173,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.011,
      "step": 8
    },
    {
      "epoch": 0.002543270929000353,
      "grad_norm": 3.5384421348571777,
      "learning_rate": 9e-05,
      "loss": 3.3809,
      "step": 9
    },
    {
      "epoch": 0.0033910279053338045,
      "grad_norm": 4.092407703399658,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8404,
      "step": 12
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": 2.0768399238586426,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5214,
      "step": 15
    },
    {
      "epoch": 0.004521370540445073,
      "eval_loss": 0.639369010925293,
      "eval_runtime": 370.4721,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "step": 16
    },
    {
      "epoch": 0.005086541858000706,
      "grad_norm": 1.9335154294967651,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5936,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.406260607975424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}