{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.048800325335502236,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016266775111834079,
      "eval_loss": 10.376843452453613,
      "eval_runtime": 1.1942,
      "eval_samples_per_second": 216.883,
      "eval_steps_per_second": 108.86,
      "step": 1
    },
    {
      "epoch": 0.004880032533550223,
      "grad_norm": 0.02079518884420395,
      "learning_rate": 3e-05,
      "loss": 10.3774,
      "step": 3
    },
    {
      "epoch": 0.009760065067100447,
      "grad_norm": 0.022636570036411285,
      "learning_rate": 6e-05,
      "loss": 10.3764,
      "step": 6
    },
    {
      "epoch": 0.013013420089467263,
      "eval_loss": 10.376595497131348,
      "eval_runtime": 1.1635,
      "eval_samples_per_second": 222.603,
      "eval_steps_per_second": 111.731,
      "step": 8
    },
    {
      "epoch": 0.014640097600650671,
      "grad_norm": 0.02258269302546978,
      "learning_rate": 9e-05,
      "loss": 10.3775,
      "step": 9
    },
    {
      "epoch": 0.019520130134200894,
      "grad_norm": 0.027647899463772774,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3766,
      "step": 12
    },
    {
      "epoch": 0.024400162667751118,
      "grad_norm": 0.03362681344151497,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3779,
      "step": 15
    },
    {
      "epoch": 0.026026840178934526,
      "eval_loss": 10.375920295715332,
      "eval_runtime": 1.1746,
      "eval_samples_per_second": 220.505,
      "eval_steps_per_second": 110.678,
      "step": 16
    },
    {
      "epoch": 0.029280195201301342,
      "grad_norm": 0.0261590126901865,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3749,
      "step": 18
    },
    {
      "epoch": 0.03416022773485156,
      "grad_norm": 0.026697570458054543,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 10.3763,
      "step": 21
    },
    {
      "epoch": 0.03904026026840179,
      "grad_norm": 0.025341402739286423,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3751,
      "step": 24
    },
    {
      "epoch": 0.03904026026840179,
      "eval_loss": 10.375518798828125,
      "eval_runtime": 1.1708,
      "eval_samples_per_second": 221.22,
      "eval_steps_per_second": 111.037,
      "step": 24
    },
    {
      "epoch": 0.04392029280195201,
      "grad_norm": 0.027155835181474686,
      "learning_rate": 5.449673790581611e-06,
      "loss": 10.3758,
      "step": 27
    },
    {
      "epoch": 0.048800325335502236,
      "grad_norm": 0.03356350585818291,
      "learning_rate": 0.0,
      "loss": 10.3747,
      "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": 1562535591936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}