{
  "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": 0.22639048099517822,
      "learning_rate": 1.668763102725367e-05,
      "loss": 0.3747,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.03193548387096774,
      "eval_loss": 0.3335977792739868,
      "eval_runtime": 7.4881,
      "eval_samples_per_second": 413.99,
      "eval_steps_per_second": 8.68,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 0.30140212178230286,
      "learning_rate": 1.3364779874213839e-05,
      "loss": 0.3296,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.03129032258064516,
      "eval_loss": 0.320537269115448,
      "eval_runtime": 7.4323,
      "eval_samples_per_second": 417.096,
      "eval_steps_per_second": 8.746,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 0.5023254156112671,
      "learning_rate": 1.0041928721174005e-05,
      "loss": 0.3139,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.03,
      "eval_loss": 0.3181561529636383,
      "eval_runtime": 7.4867,
      "eval_samples_per_second": 414.067,
      "eval_steps_per_second": 8.682,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 0.45329922437667847,
      "learning_rate": 6.719077568134172e-06,
      "loss": 0.3037,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.03,
      "eval_loss": 0.3125706911087036,
      "eval_runtime": 7.4639,
      "eval_samples_per_second": 415.334,
      "eval_steps_per_second": 8.709,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 0.4133148193359375,
      "learning_rate": 3.3962264150943395e-06,
      "loss": 0.2964,
      "step": 1585
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.03064516129032258,
      "eval_loss": 0.31172773241996765,
      "eval_runtime": 7.4476,
      "eval_samples_per_second": 416.242,
      "eval_steps_per_second": 8.728,
      "step": 1590
    },
    {
      "epoch": 5.981132075471698,
      "grad_norm": 0.45181864500045776,
      "learning_rate": 7.337526205450734e-08,
      "loss": 0.2925,
      "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": 0.21711211950054954,
    "num_train_epochs": 6,
    "temperature": 20
  }
}