{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 9954,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10046212577858148,
      "grad_norm": 3.10841703414917,
      "learning_rate": 1.883778579223417e-05,
      "loss": 0.3172,
      "step": 500
    },
    {
      "epoch": 0.20092425155716295,
      "grad_norm": 4.298633575439453,
      "learning_rate": 1.78414992578448e-05,
      "loss": 0.1925,
      "step": 1000
    },
    {
      "epoch": 0.3013863773357444,
      "grad_norm": 3.002183198928833,
      "learning_rate": 1.6845212723455437e-05,
      "loss": 0.1792,
      "step": 1500
    },
    {
      "epoch": 0.4018485031143259,
      "grad_norm": 5.602917671203613,
      "learning_rate": 1.5848926189066066e-05,
      "loss": 0.174,
      "step": 2000
    },
    {
      "epoch": 0.5023106288929073,
      "grad_norm": 4.334236145019531,
      "learning_rate": 1.4852639654676699e-05,
      "loss": 0.157,
      "step": 2500
    },
    {
      "epoch": 0.6027727546714888,
      "grad_norm": 6.822575092315674,
      "learning_rate": 1.385635312028733e-05,
      "loss": 0.1529,
      "step": 3000
    },
    {
      "epoch": 0.7032348804500703,
      "grad_norm": 3.9460644721984863,
      "learning_rate": 1.2860066585897963e-05,
      "loss": 0.1408,
      "step": 3500
    },
    {
      "epoch": 0.8036970062286518,
      "grad_norm": 15.131864547729492,
      "learning_rate": 1.1863780051508595e-05,
      "loss": 0.1321,
      "step": 4000
    },
    {
      "epoch": 0.9041591320072333,
      "grad_norm": 11.002291679382324,
      "learning_rate": 1.0867493517119226e-05,
      "loss": 0.1378,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9573226552157906,
      "eval_f1": 0.8167489442693154,
      "eval_loss": 0.12773554027080536,
      "eval_precision": 0.7712873511570434,
      "eval_recall": 0.8679054481102263,
      "eval_runtime": 22.6145,
      "eval_samples_per_second": 188.64,
      "eval_steps_per_second": 23.613,
      "step": 4977
    },
    {
      "epoch": 1.0046212577858147,
      "grad_norm": 2.505333662033081,
      "learning_rate": 9.871206982729858e-06,
      "loss": 0.1253,
      "step": 5000
    },
    {
      "epoch": 1.1050833835643963,
      "grad_norm": 8.985626220703125,
      "learning_rate": 8.87492044834049e-06,
      "loss": 0.0926,
      "step": 5500
    },
    {
      "epoch": 1.2055455093429777,
      "grad_norm": 7.380733966827393,
      "learning_rate": 7.878633913951123e-06,
      "loss": 0.0821,
      "step": 6000
    },
    {
      "epoch": 1.306007635121559,
      "grad_norm": 10.697794914245605,
      "learning_rate": 6.882347379561754e-06,
      "loss": 0.0862,
      "step": 6500
    },
    {
      "epoch": 1.4064697609001406,
      "grad_norm": 0.9345781803131104,
      "learning_rate": 5.886060845172386e-06,
      "loss": 0.0861,
      "step": 7000
    },
    {
      "epoch": 1.5069318866787222,
      "grad_norm": 1.141638994216919,
      "learning_rate": 4.889774310783018e-06,
      "loss": 0.0798,
      "step": 7500
    },
    {
      "epoch": 1.6073940124573036,
      "grad_norm": 0.19463206827640533,
      "learning_rate": 3.89348777639365e-06,
      "loss": 0.0794,
      "step": 8000
    },
    {
      "epoch": 1.707856138235885,
      "grad_norm": 1.8121638298034668,
      "learning_rate": 2.897201242004282e-06,
      "loss": 0.0834,
      "step": 8500
    },
    {
      "epoch": 1.8083182640144666,
      "grad_norm": 3.025911808013916,
      "learning_rate": 1.9009147076149141e-06,
      "loss": 0.0777,
      "step": 9000
    },
    {
      "epoch": 1.908780389793048,
      "grad_norm": 3.390535831451416,
      "learning_rate": 9.046281732255461e-07,
      "loss": 0.0696,
      "step": 9500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9658251941226447,
      "eval_f1": 0.8542688910696762,
      "eval_loss": 0.11847011744976044,
      "eval_precision": 0.8297390682711784,
      "eval_recall": 0.8802932625458223,
      "eval_runtime": 26.3397,
      "eval_samples_per_second": 161.961,
      "eval_steps_per_second": 20.274,
      "step": 9954
    }
  ],
  "logging_steps": 500,
  "max_steps": 9954,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1126377730003020.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.983407232662354e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 4,
    "seed": 40
  }
}