{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14585232452142205,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007292616226071103,
      "grad_norm": 14.881909370422363,
      "learning_rate": 1e-05,
      "loss": 23.6797,
      "step": 1
    },
    {
      "epoch": 0.007292616226071103,
      "eval_loss": 1.4612081050872803,
      "eval_runtime": 19.8009,
      "eval_samples_per_second": 11.666,
      "eval_steps_per_second": 5.858,
      "step": 1
    },
    {
      "epoch": 0.014585232452142206,
      "grad_norm": 15.110391616821289,
      "learning_rate": 2e-05,
      "loss": 25.0312,
      "step": 2
    },
    {
      "epoch": 0.02187784867821331,
      "grad_norm": 17.363327026367188,
      "learning_rate": 3e-05,
      "loss": 26.2812,
      "step": 3
    },
    {
      "epoch": 0.02917046490428441,
      "grad_norm": 15.218398094177246,
      "learning_rate": 4e-05,
      "loss": 23.7734,
      "step": 4
    },
    {
      "epoch": 0.03646308113035551,
      "grad_norm": 15.010531425476074,
      "learning_rate": 5e-05,
      "loss": 25.1953,
      "step": 5
    },
    {
      "epoch": 0.03646308113035551,
      "eval_loss": 1.4239041805267334,
      "eval_runtime": 4.0436,
      "eval_samples_per_second": 57.127,
      "eval_steps_per_second": 28.687,
      "step": 5
    },
    {
      "epoch": 0.04375569735642662,
      "grad_norm": 14.230565071105957,
      "learning_rate": 6e-05,
      "loss": 23.9453,
      "step": 6
    },
    {
      "epoch": 0.05104831358249772,
      "grad_norm": 14.029481887817383,
      "learning_rate": 7e-05,
      "loss": 23.5547,
      "step": 7
    },
    {
      "epoch": 0.05834092980856882,
      "grad_norm": 14.474747657775879,
      "learning_rate": 8e-05,
      "loss": 24.1094,
      "step": 8
    },
    {
      "epoch": 0.06563354603463993,
      "grad_norm": 14.518436431884766,
      "learning_rate": 9e-05,
      "loss": 22.7734,
      "step": 9
    },
    {
      "epoch": 0.07292616226071102,
      "grad_norm": 13.597356796264648,
      "learning_rate": 0.0001,
      "loss": 21.0312,
      "step": 10
    },
    {
      "epoch": 0.07292616226071102,
      "eval_loss": 1.2975852489471436,
      "eval_runtime": 4.0565,
      "eval_samples_per_second": 56.945,
      "eval_steps_per_second": 28.596,
      "step": 10
    },
    {
      "epoch": 0.08021877848678213,
      "grad_norm": 14.542048454284668,
      "learning_rate": 9.755282581475769e-05,
      "loss": 22.168,
      "step": 11
    },
    {
      "epoch": 0.08751139471285324,
      "grad_norm": 13.958735466003418,
      "learning_rate": 9.045084971874738e-05,
      "loss": 21.4062,
      "step": 12
    },
    {
      "epoch": 0.09480401093892434,
      "grad_norm": 12.588117599487305,
      "learning_rate": 7.938926261462366e-05,
      "loss": 20.0664,
      "step": 13
    },
    {
      "epoch": 0.10209662716499544,
      "grad_norm": 12.423447608947754,
      "learning_rate": 6.545084971874738e-05,
      "loss": 18.957,
      "step": 14
    },
    {
      "epoch": 0.10938924339106655,
      "grad_norm": 12.899825096130371,
      "learning_rate": 5e-05,
      "loss": 19.8945,
      "step": 15
    },
    {
      "epoch": 0.10938924339106655,
      "eval_loss": 1.1743100881576538,
      "eval_runtime": 4.0624,
      "eval_samples_per_second": 56.863,
      "eval_steps_per_second": 28.555,
      "step": 15
    },
    {
      "epoch": 0.11668185961713765,
      "grad_norm": 13.522796630859375,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 18.9883,
      "step": 16
    },
    {
      "epoch": 0.12397447584320875,
      "grad_norm": 13.67131233215332,
      "learning_rate": 2.061073738537635e-05,
      "loss": 19.9258,
      "step": 17
    },
    {
      "epoch": 0.13126709206927986,
      "grad_norm": 13.722691535949707,
      "learning_rate": 9.549150281252633e-06,
      "loss": 19.3438,
      "step": 18
    },
    {
      "epoch": 0.13855970829535097,
      "grad_norm": 12.327914237976074,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 17.3555,
      "step": 19
    },
    {
      "epoch": 0.14585232452142205,
      "grad_norm": 19.96782684326172,
      "learning_rate": 0.0,
      "loss": 20.4375,
      "step": 20
    },
    {
      "epoch": 0.14585232452142205,
      "eval_loss": 1.1424343585968018,
      "eval_runtime": 4.0404,
      "eval_samples_per_second": 57.172,
      "eval_steps_per_second": 28.71,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 605317893193728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}