{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09913258983890955,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004956629491945477,
      "grad_norm": 57.75039291381836,
      "learning_rate": 1e-05,
      "loss": 17.0424,
      "step": 1
    },
    {
      "epoch": 0.004956629491945477,
      "eval_loss": 1.0527280569076538,
      "eval_runtime": 74.2544,
      "eval_samples_per_second": 4.579,
      "eval_steps_per_second": 2.289,
      "step": 1
    },
    {
      "epoch": 0.009913258983890954,
      "grad_norm": 68.40726470947266,
      "learning_rate": 2e-05,
      "loss": 15.6664,
      "step": 2
    },
    {
      "epoch": 0.01486988847583643,
      "grad_norm": 69.10187530517578,
      "learning_rate": 3e-05,
      "loss": 15.8254,
      "step": 3
    },
    {
      "epoch": 0.01982651796778191,
      "grad_norm": 54.53337097167969,
      "learning_rate": 4e-05,
      "loss": 15.9839,
      "step": 4
    },
    {
      "epoch": 0.024783147459727387,
      "grad_norm": 51.78641891479492,
      "learning_rate": 5e-05,
      "loss": 15.6566,
      "step": 5
    },
    {
      "epoch": 0.024783147459727387,
      "eval_loss": 0.9015545845031738,
      "eval_runtime": 23.2714,
      "eval_samples_per_second": 14.61,
      "eval_steps_per_second": 7.305,
      "step": 5
    },
    {
      "epoch": 0.02973977695167286,
      "grad_norm": 44.10242462158203,
      "learning_rate": 6e-05,
      "loss": 14.3549,
      "step": 6
    },
    {
      "epoch": 0.03469640644361834,
      "grad_norm": 43.91465759277344,
      "learning_rate": 7e-05,
      "loss": 14.9588,
      "step": 7
    },
    {
      "epoch": 0.03965303593556382,
      "grad_norm": 40.00635528564453,
      "learning_rate": 8e-05,
      "loss": 14.169,
      "step": 8
    },
    {
      "epoch": 0.04460966542750929,
      "grad_norm": 28.840185165405273,
      "learning_rate": 9e-05,
      "loss": 12.7394,
      "step": 9
    },
    {
      "epoch": 0.04956629491945477,
      "grad_norm": 26.274221420288086,
      "learning_rate": 0.0001,
      "loss": 12.2512,
      "step": 10
    },
    {
      "epoch": 0.04956629491945477,
      "eval_loss": 0.8085873126983643,
      "eval_runtime": 23.137,
      "eval_samples_per_second": 14.695,
      "eval_steps_per_second": 7.348,
      "step": 10
    },
    {
      "epoch": 0.05452292441140025,
      "grad_norm": 27.2174072265625,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.8522,
      "step": 11
    },
    {
      "epoch": 0.05947955390334572,
      "grad_norm": 24.871192932128906,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.846,
      "step": 12
    },
    {
      "epoch": 0.0644361833952912,
      "grad_norm": 24.186389923095703,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4232,
      "step": 13
    },
    {
      "epoch": 0.06939281288723669,
      "grad_norm": 24.49249839782715,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.1087,
      "step": 14
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 23.352947235107422,
      "learning_rate": 5e-05,
      "loss": 11.0825,
      "step": 15
    },
    {
      "epoch": 0.07434944237918216,
      "eval_loss": 0.7625203132629395,
      "eval_runtime": 23.206,
      "eval_samples_per_second": 14.651,
      "eval_steps_per_second": 7.326,
      "step": 15
    },
    {
      "epoch": 0.07930607187112763,
      "grad_norm": 22.63839340209961,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.5134,
      "step": 16
    },
    {
      "epoch": 0.08426270136307311,
      "grad_norm": 22.474016189575195,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.1247,
      "step": 17
    },
    {
      "epoch": 0.08921933085501858,
      "grad_norm": 22.08704376220703,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.216,
      "step": 18
    },
    {
      "epoch": 0.09417596034696406,
      "grad_norm": 21.62132453918457,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 12.0317,
      "step": 19
    },
    {
      "epoch": 0.09913258983890955,
      "grad_norm": 22.85521125793457,
      "learning_rate": 0.0,
      "loss": 12.7622,
      "step": 20
    },
    {
      "epoch": 0.09913258983890955,
      "eval_loss": 0.7505396008491516,
      "eval_runtime": 23.3853,
      "eval_samples_per_second": 14.539,
      "eval_steps_per_second": 7.27,
      "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": 1.402137439371264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}