{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011641443538998836,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00038804811796662784,
      "eval_loss": 1.5013787746429443,
      "eval_runtime": 37.3718,
      "eval_samples_per_second": 29.033,
      "eval_steps_per_second": 14.53,
      "step": 1
    },
    {
      "epoch": 0.0011641443538998836,
      "grad_norm": 1.8987535238265991,
      "learning_rate": 6e-05,
      "loss": 1.33,
      "step": 3
    },
    {
      "epoch": 0.002328288707799767,
      "grad_norm": 1.7740483283996582,
      "learning_rate": 0.00012,
      "loss": 1.5014,
      "step": 6
    },
    {
      "epoch": 0.0031043849437330227,
      "eval_loss": 1.2200710773468018,
      "eval_runtime": 36.8484,
      "eval_samples_per_second": 29.445,
      "eval_steps_per_second": 14.736,
      "step": 8
    },
    {
      "epoch": 0.0034924330616996507,
      "grad_norm": 2.091332197189331,
      "learning_rate": 0.00018,
      "loss": 1.2489,
      "step": 9
    },
    {
      "epoch": 0.004656577415599534,
      "grad_norm": 2.9655942916870117,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.0554,
      "step": 12
    },
    {
      "epoch": 0.005820721769499418,
      "grad_norm": 2.6194820404052734,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3735,
      "step": 15
    },
    {
      "epoch": 0.006208769887466045,
      "eval_loss": 1.0012933015823364,
      "eval_runtime": 36.2958,
      "eval_samples_per_second": 29.893,
      "eval_steps_per_second": 14.96,
      "step": 16
    },
    {
      "epoch": 0.006984866123399301,
      "grad_norm": 1.85113525390625,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8351,
      "step": 18
    },
    {
      "epoch": 0.008149010477299184,
      "grad_norm": 2.585838794708252,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.9041,
      "step": 21
    },
    {
      "epoch": 0.009313154831199068,
      "grad_norm": 2.0504302978515625,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.7262,
      "step": 24
    },
    {
      "epoch": 0.009313154831199068,
      "eval_loss": 0.9423869848251343,
      "eval_runtime": 36.8752,
      "eval_samples_per_second": 29.424,
      "eval_steps_per_second": 14.725,
      "step": 24
    },
    {
      "epoch": 0.010477299185098952,
      "grad_norm": 1.880564570426941,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.845,
      "step": 27
    },
    {
      "epoch": 0.011641443538998836,
      "grad_norm": 2.275709867477417,
      "learning_rate": 0.0,
      "loss": 0.7635,
      "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": 1451583854346240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}