{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003502453176579096,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1674843921930319e-05,
      "eval_loss": 11.106888771057129,
      "eval_runtime": 134.6193,
      "eval_samples_per_second": 267.904,
      "eval_steps_per_second": 133.955,
      "step": 1
    },
    {
      "epoch": 3.5024531765790956e-05,
      "grad_norm": 1.325600266456604,
      "learning_rate": 3e-05,
      "loss": 44.4101,
      "step": 3
    },
    {
      "epoch": 7.004906353158191e-05,
      "grad_norm": 1.239603042602539,
      "learning_rate": 6e-05,
      "loss": 44.4322,
      "step": 6
    },
    {
      "epoch": 9.339875137544255e-05,
      "eval_loss": 11.099414825439453,
      "eval_runtime": 135.0776,
      "eval_samples_per_second": 266.995,
      "eval_steps_per_second": 133.501,
      "step": 8
    },
    {
      "epoch": 0.00010507359529737287,
      "grad_norm": 1.0928877592086792,
      "learning_rate": 9e-05,
      "loss": 44.3899,
      "step": 9
    },
    {
      "epoch": 0.00014009812706316382,
      "grad_norm": 1.4743366241455078,
      "learning_rate": 9.755282581475769e-05,
      "loss": 44.366,
      "step": 12
    },
    {
      "epoch": 0.0001751226588289548,
      "grad_norm": 1.376222014427185,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.3771,
      "step": 15
    },
    {
      "epoch": 0.0001867975027508851,
      "eval_loss": 11.076936721801758,
      "eval_runtime": 134.3207,
      "eval_samples_per_second": 268.499,
      "eval_steps_per_second": 134.253,
      "step": 16
    },
    {
      "epoch": 0.00021014719059474573,
      "grad_norm": 1.1501511335372925,
      "learning_rate": 6.545084971874738e-05,
      "loss": 44.3103,
      "step": 18
    },
    {
      "epoch": 0.0002451717223605367,
      "grad_norm": 1.211173415184021,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 44.2847,
      "step": 21
    },
    {
      "epoch": 0.00028019625412632765,
      "grad_norm": 1.3824774026870728,
      "learning_rate": 2.061073738537635e-05,
      "loss": 44.2822,
      "step": 24
    },
    {
      "epoch": 0.00028019625412632765,
      "eval_loss": 11.062167167663574,
      "eval_runtime": 135.0742,
      "eval_samples_per_second": 267.001,
      "eval_steps_per_second": 133.504,
      "step": 24
    },
    {
      "epoch": 0.0003152207858921186,
      "grad_norm": 1.1789239645004272,
      "learning_rate": 5.449673790581611e-06,
      "loss": 44.2502,
      "step": 27
    },
    {
      "epoch": 0.0003502453176579096,
      "grad_norm": 1.5418906211853027,
      "learning_rate": 0.0,
      "loss": 44.2545,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 811182587904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}