{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 5.815704345703125,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.9944,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.37742123007774353,
      "eval_runtime": 10.6636,
      "eval_samples_per_second": 6.471,
      "eval_steps_per_second": 1.125,
      "step": 12
    },
    {
      "epoch": 2.0,
      "eval_accuracy_fol": 0.9855072463768116,
      "eval_loss": 0.36990299820899963,
      "eval_runtime": 10.0571,
      "eval_samples_per_second": 6.861,
      "eval_steps_per_second": 1.193,
      "step": 24
    },
    {
      "epoch": 3.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.4505714774131775,
      "eval_runtime": 10.0403,
      "eval_samples_per_second": 6.872,
      "eval_steps_per_second": 1.195,
      "step": 36
    },
    {
      "epoch": 4.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.49083924293518066,
      "eval_runtime": 10.1223,
      "eval_samples_per_second": 6.817,
      "eval_steps_per_second": 1.186,
      "step": 48
    },
    {
      "epoch": 5.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.551354706287384,
      "eval_runtime": 9.943,
      "eval_samples_per_second": 6.94,
      "eval_steps_per_second": 1.207,
      "step": 60
    },
    {
      "epoch": 6.0,
      "eval_accuracy_fol": 0.9565217391304348,
      "eval_loss": 0.5758901834487915,
      "eval_runtime": 10.0414,
      "eval_samples_per_second": 6.872,
      "eval_steps_per_second": 1.195,
      "step": 72
    },
    {
      "epoch": 7.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.6346259117126465,
      "eval_runtime": 10.0121,
      "eval_samples_per_second": 6.892,
      "eval_steps_per_second": 1.199,
      "step": 84
    },
    {
      "epoch": 8.0,
      "eval_accuracy_fol": 0.9855072463768116,
      "eval_loss": 0.6786300539970398,
      "eval_runtime": 9.853,
      "eval_samples_per_second": 7.003,
      "eval_steps_per_second": 1.218,
      "step": 96
    },
    {
      "epoch": 9.0,
      "eval_accuracy_fol": 0.9855072463768116,
      "eval_loss": 0.7070556282997131,
      "eval_runtime": 10.0666,
      "eval_samples_per_second": 6.854,
      "eval_steps_per_second": 1.192,
      "step": 108
    },
    {
      "epoch": 10.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.7301931381225586,
      "eval_runtime": 9.8811,
      "eval_samples_per_second": 6.983,
      "eval_steps_per_second": 1.214,
      "step": 120
    },
    {
      "epoch": 11.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.7777052521705627,
      "eval_runtime": 10.0443,
      "eval_samples_per_second": 6.87,
      "eval_steps_per_second": 1.195,
      "step": 132
    },
    {
      "epoch": 12.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.7906161546707153,
      "eval_runtime": 9.9021,
      "eval_samples_per_second": 6.968,
      "eval_steps_per_second": 1.212,
      "step": 144
    },
    {
      "epoch": 13.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.7852453589439392,
      "eval_runtime": 10.0952,
      "eval_samples_per_second": 6.835,
      "eval_steps_per_second": 1.189,
      "step": 156
    },
    {
      "epoch": 14.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8031890392303467,
      "eval_runtime": 9.9012,
      "eval_samples_per_second": 6.969,
      "eval_steps_per_second": 1.212,
      "step": 168
    },
    {
      "epoch": 15.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8141315579414368,
      "eval_runtime": 10.0811,
      "eval_samples_per_second": 6.845,
      "eval_steps_per_second": 1.19,
      "step": 180
    },
    {
      "epoch": 16.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8203307390213013,
      "eval_runtime": 10.0556,
      "eval_samples_per_second": 6.862,
      "eval_steps_per_second": 1.193,
      "step": 192
    },
    {
      "epoch": 17.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8233786225318909,
      "eval_runtime": 10.038,
      "eval_samples_per_second": 6.874,
      "eval_steps_per_second": 1.195,
      "step": 204
    },
    {
      "epoch": 18.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8255409002304077,
      "eval_runtime": 9.8663,
      "eval_samples_per_second": 6.993,
      "eval_steps_per_second": 1.216,
      "step": 216
    },
    {
      "epoch": 19.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8259706497192383,
      "eval_runtime": 9.9818,
      "eval_samples_per_second": 6.913,
      "eval_steps_per_second": 1.202,
      "step": 228
    },
    {
      "epoch": 20.0,
      "eval_accuracy_fol": 1.0,
      "eval_loss": 0.8260682821273804,
      "eval_runtime": 9.8198,
      "eval_samples_per_second": 7.027,
      "eval_steps_per_second": 1.222,
      "step": 240
    },
    {
      "epoch": 20.0,
      "step": 240,
      "total_flos": 4.93214716919808e+16,
      "train_loss": 0.09651691963275273,
      "train_runtime": 472.7445,
      "train_samples_per_second": 11.846,
      "train_steps_per_second": 0.508
    }
  ],
  "logging_steps": 700,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 4.93214716919808e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}