{
  "best_metric": 0.8125,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-p3x3m6lq/checkpoint-400",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 2.7488832473754883,
      "learning_rate": 3.0592064018837074e-05,
      "loss": 0.6298,
      "step": 10
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.7462663650512695,
      "learning_rate": 3.0399661100479608e-05,
      "loss": 0.4571,
      "step": 20
    },
    {
      "epoch": 0.075,
      "grad_norm": 2.3427932262420654,
      "learning_rate": 3.020725818212214e-05,
      "loss": 0.5418,
      "step": 30
    },
    {
      "epoch": 0.1,
      "grad_norm": 8.313847541809082,
      "learning_rate": 3.0014855263764674e-05,
      "loss": 0.7154,
      "step": 40
    },
    {
      "epoch": 0.125,
      "grad_norm": 5.623049736022949,
      "learning_rate": 2.982245234540721e-05,
      "loss": 0.5042,
      "step": 50
    },
    {
      "epoch": 0.15,
      "grad_norm": 8.3486328125,
      "learning_rate": 2.9630049427049746e-05,
      "loss": 0.4505,
      "step": 60
    },
    {
      "epoch": 0.175,
      "grad_norm": 8.559453964233398,
      "learning_rate": 2.943764650869228e-05,
      "loss": 0.6013,
      "step": 70
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.411623477935791,
      "learning_rate": 2.924524359033481e-05,
      "loss": 0.4038,
      "step": 80
    },
    {
      "epoch": 0.225,
      "grad_norm": 13.413679122924805,
      "learning_rate": 2.9052840671977346e-05,
      "loss": 0.5139,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 58.22578048706055,
      "learning_rate": 2.886043775361988e-05,
      "loss": 0.4629,
      "step": 100
    },
    {
      "epoch": 0.275,
      "grad_norm": 23.204715728759766,
      "learning_rate": 2.8668034835262415e-05,
      "loss": 0.4164,
      "step": 110
    },
    {
      "epoch": 0.3,
      "grad_norm": 10.875760078430176,
      "learning_rate": 2.847563191690495e-05,
      "loss": 0.4867,
      "step": 120
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.31249693036079407,
      "learning_rate": 2.828322899854748e-05,
      "loss": 0.354,
      "step": 130
    },
    {
      "epoch": 0.35,
      "grad_norm": 2.2056236267089844,
      "learning_rate": 2.8090826080190015e-05,
      "loss": 0.3876,
      "step": 140
    },
    {
      "epoch": 0.375,
      "grad_norm": 25.380603790283203,
      "learning_rate": 2.789842316183255e-05,
      "loss": 0.5685,
      "step": 150
    },
    {
      "epoch": 0.4,
      "grad_norm": 24.43907356262207,
      "learning_rate": 2.7706020243475087e-05,
      "loss": 0.4975,
      "step": 160
    },
    {
      "epoch": 0.425,
      "grad_norm": 10.648700714111328,
      "learning_rate": 2.7513617325117622e-05,
      "loss": 0.4734,
      "step": 170
    },
    {
      "epoch": 0.45,
      "grad_norm": 18.05457878112793,
      "learning_rate": 2.7321214406760153e-05,
      "loss": 0.445,
      "step": 180
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.766493558883667,
      "learning_rate": 2.7128811488402687e-05,
      "loss": 0.4758,
      "step": 190
    },
    {
      "epoch": 0.5,
      "grad_norm": 14.576363563537598,
      "learning_rate": 2.6936408570045222e-05,
      "loss": 0.8975,
      "step": 200
    },
    {
      "epoch": 0.525,
      "grad_norm": 8.905998229980469,
      "learning_rate": 2.6744005651687756e-05,
      "loss": 0.3158,
      "step": 210
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.797244668006897,
      "learning_rate": 2.655160273333029e-05,
      "loss": 0.1047,
      "step": 220
    },
    {
      "epoch": 0.575,
      "grad_norm": 5.661525726318359,
      "learning_rate": 2.6359199814972822e-05,
      "loss": 0.4476,
      "step": 230
    },
    {
      "epoch": 0.6,
      "grad_norm": 20.741662979125977,
      "learning_rate": 2.6166796896615356e-05,
      "loss": 0.5761,
      "step": 240
    },
    {
      "epoch": 0.625,
      "grad_norm": 25.319080352783203,
      "learning_rate": 2.5974393978257894e-05,
      "loss": 0.497,
      "step": 250
    },
    {
      "epoch": 0.65,
      "grad_norm": 19.864778518676758,
      "learning_rate": 2.578199105990043e-05,
      "loss": 0.3253,
      "step": 260
    },
    {
      "epoch": 0.675,
      "grad_norm": 6.358182907104492,
      "learning_rate": 2.5589588141542963e-05,
      "loss": 0.3098,
      "step": 270
    },
    {
      "epoch": 0.7,
      "grad_norm": 60.80244827270508,
      "learning_rate": 2.5397185223185494e-05,
      "loss": 0.4264,
      "step": 280
    },
    {
      "epoch": 0.725,
      "grad_norm": 30.098163604736328,
      "learning_rate": 2.520478230482803e-05,
      "loss": 0.6623,
      "step": 290
    },
    {
      "epoch": 0.75,
      "grad_norm": 6.609621524810791,
      "learning_rate": 2.5012379386470563e-05,
      "loss": 0.4582,
      "step": 300
    },
    {
      "epoch": 0.775,
      "grad_norm": 2.0694580078125,
      "learning_rate": 2.4819976468113098e-05,
      "loss": 0.8613,
      "step": 310
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5483848452568054,
      "learning_rate": 2.4627573549755632e-05,
      "loss": 0.3662,
      "step": 320
    },
    {
      "epoch": 0.825,
      "grad_norm": 9.217021942138672,
      "learning_rate": 2.4435170631398163e-05,
      "loss": 0.4583,
      "step": 330
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.3683093786239624,
      "learning_rate": 2.4242767713040698e-05,
      "loss": 0.4021,
      "step": 340
    },
    {
      "epoch": 0.875,
      "grad_norm": 6.494662284851074,
      "learning_rate": 2.4050364794683232e-05,
      "loss": 0.3119,
      "step": 350
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.22819127142429352,
      "learning_rate": 2.385796187632577e-05,
      "loss": 0.5917,
      "step": 360
    },
    {
      "epoch": 0.925,
      "grad_norm": 5.446119785308838,
      "learning_rate": 2.3665558957968304e-05,
      "loss": 0.1389,
      "step": 370
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.17951630055904388,
      "learning_rate": 2.3473156039610836e-05,
      "loss": 0.4694,
      "step": 380
    },
    {
      "epoch": 0.975,
      "grad_norm": 4.937567710876465,
      "learning_rate": 2.328075312125337e-05,
      "loss": 0.3972,
      "step": 390
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4045691192150116,
      "learning_rate": 2.3088350202895905e-05,
      "loss": 0.1727,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.895,
      "eval_f1": 0.8125,
      "eval_loss": 0.4174700975418091,
      "eval_precision": 0.900990099009901,
      "eval_recall": 0.7398373983739838,
      "eval_runtime": 1.5257,
      "eval_samples_per_second": 262.167,
      "eval_steps_per_second": 16.385,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 1600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 211815370450944.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 3.078446693719454e-05,
    "metric": "eval/loss",
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 37
  }
}