{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1908,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968553459119497,
      "grad_norm": 5.187047004699707,
      "learning_rate": 1.6677148846960168e-05,
      "loss": 6.1132,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7012903225806452,
      "eval_loss": 4.3197245597839355,
      "eval_runtime": 1.6635,
      "eval_samples_per_second": 1863.573,
      "eval_steps_per_second": 39.075,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 5.349358081817627,
      "learning_rate": 1.3354297693920338e-05,
      "loss": 3.3768,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8435483870967742,
      "eval_loss": 2.160186767578125,
      "eval_runtime": 1.6762,
      "eval_samples_per_second": 1849.466,
      "eval_steps_per_second": 38.779,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 5.328630447387695,
      "learning_rate": 1.0031446540880504e-05,
      "loss": 1.7892,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8935483870967742,
      "eval_loss": 1.2737469673156738,
      "eval_runtime": 1.7036,
      "eval_samples_per_second": 1819.697,
      "eval_steps_per_second": 38.155,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 4.597011089324951,
      "learning_rate": 6.708595387840672e-06,
      "loss": 1.1236,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.9856231808662415,
      "eval_runtime": 1.7312,
      "eval_samples_per_second": 1790.696,
      "eval_steps_per_second": 37.547,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 3.8782036304473877,
      "learning_rate": 3.385744234800839e-06,
      "loss": 0.8713,
      "step": 1585
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9274193548387096,
      "eval_loss": 0.886253297328949,
      "eval_runtime": 1.7341,
      "eval_samples_per_second": 1787.663,
      "eval_steps_per_second": 37.483,
      "step": 1590
    },
    {
      "epoch": 5.981132075471698,
      "grad_norm": 5.870248794555664,
      "learning_rate": 6.289308176100629e-08,
      "loss": 0.7789,
      "step": 1902
    }
  ],
  "logging_steps": 317,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 1000000000.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 495439677408900.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.5566758316651013,
    "num_train_epochs": 6,
    "temperature": 13
  }
}