{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9982905982905983,
  "eval_steps": 500,
  "global_step": 146,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.5508419871330261,
      "learning_rate": 2e-05,
      "loss": 49.04,
      "step": 10
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.5306850671768188,
      "learning_rate": 4e-05,
      "loss": 2.103,
      "step": 20
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.5700441002845764,
      "learning_rate": 6e-05,
      "loss": 198.5583,
      "step": 30
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3407396078109741,
      "learning_rate": 8e-05,
      "loss": 86.3314,
      "step": 40
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.24899934232234955,
      "learning_rate": 0.0001,
      "loss": 34.7142,
      "step": 50
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.28806784749031067,
      "learning_rate": 8.958333333333335e-05,
      "loss": 58.7202,
      "step": 60
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.22402526438236237,
      "learning_rate": 7.916666666666666e-05,
      "loss": 62.2985,
      "step": 70
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 1.7743641138076782,
      "learning_rate": 6.875e-05,
      "loss": 4.258542069340605e+28,
      "step": 80
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.290737122297287,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.0231,
      "step": 90
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.28255608677864075,
      "learning_rate": 4.791666666666667e-05,
      "loss": 163.2244,
      "step": 100
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3150412440299988,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 127.8778,
      "step": 110
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.2888839840888977,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 39.3742,
      "step": 120
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.25213536620140076,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 164.5057,
      "step": 130
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.28532907366752625,
      "learning_rate": 6.25e-06,
      "loss": 0.9857,
      "step": 140
    },
    {
      "epoch": 0.9982905982905983,
      "step": 146,
      "total_flos": 220239967997952.0,
      "train_loss": 6.321861250475817e+27,
      "train_runtime": 2187.7139,
      "train_samples_per_second": 0.535,
      "train_steps_per_second": 0.067
    }
  ],
  "logging_steps": 10,
  "max_steps": 146,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 220239967997952.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}