{
  "best_global_step": null,
  "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": 6.568359851837158,
      "learning_rate": 1.668763102725367e-05,
      "loss": 23.9469,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0070967741935483875,
      "eval_loss": 19.398099899291992,
      "eval_runtime": 7.658,
      "eval_samples_per_second": 404.807,
      "eval_steps_per_second": 8.488,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 14.670075416564941,
      "learning_rate": 1.3364779874213839e-05,
      "loss": 17.703,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.004838709677419355,
      "eval_loss": 16.108619689941406,
      "eval_runtime": 7.7352,
      "eval_samples_per_second": 400.766,
      "eval_steps_per_second": 8.403,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 42.273590087890625,
      "learning_rate": 1.0041928721174005e-05,
      "loss": 14.7937,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.005806451612903226,
      "eval_loss": 13.997490882873535,
      "eval_runtime": 7.6549,
      "eval_samples_per_second": 404.968,
      "eval_steps_per_second": 8.491,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 32.075355529785156,
      "learning_rate": 6.719077568134172e-06,
      "loss": 12.6826,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.004838709677419355,
      "eval_loss": 12.563783645629883,
      "eval_runtime": 7.7014,
      "eval_samples_per_second": 402.525,
      "eval_steps_per_second": 8.44,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 50.96983337402344,
      "learning_rate": 3.3962264150943395e-06,
      "loss": 11.4688,
      "step": 1585
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.005483870967741935,
      "eval_loss": 11.872635841369629,
      "eval_runtime": 7.674,
      "eval_samples_per_second": 403.959,
      "eval_steps_per_second": 8.47,
      "step": 1590
    },
    {
      "epoch": 5.981132075471698,
      "grad_norm": 32.64015197753906,
      "learning_rate": 7.337526205450734e-08,
      "loss": 10.8325,
      "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": 0.7211960233580677,
    "num_train_epochs": 6,
    "temperature": 14
  }
}