{
  "best_metric": 0.8924948901640382,
  "best_model_checkpoint": "/content/drive/MyDrive/PUBH 8885 CB/nuc_arg_long_readv4/checkpoint-1500",
  "epoch": 3.663003663003663,
  "eval_steps": 100,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2442002442002442,
      "grad_norm": 25.231292724609375,
      "learning_rate": 5e-06,
      "loss": 2.8722,
      "step": 100
    },
    {
      "epoch": 0.2442002442002442,
      "eval_loss": 2.381986141204834,
      "eval_macro_f1": 0.07916135790210403,
      "eval_macro_precision": 0.06590895945398809,
      "eval_macro_recall": 0.10263326510757667,
      "eval_micro_f1": 0.4847560975609756,
      "eval_micro_precision": 0.4847560975609756,
      "eval_micro_recall": 0.4847560975609756,
      "eval_runtime": 27.9503,
      "eval_samples_per_second": 82.146,
      "eval_steps_per_second": 1.288,
      "eval_weighted_f1": 0.3658094645034367,
      "eval_weighted_precision": 0.3000991244760369,
      "eval_weighted_recall": 0.4847560975609756,
      "step": 100
    },
    {
      "epoch": 0.4884004884004884,
      "grad_norm": 74.01921844482422,
      "learning_rate": 9.950000000000001e-06,
      "loss": 1.9467,
      "step": 200
    },
    {
      "epoch": 0.4884004884004884,
      "eval_loss": 1.6188805103302002,
      "eval_macro_f1": 0.12352787740442463,
      "eval_macro_precision": 0.1729632869793354,
      "eval_macro_recall": 0.14519904411264478,
      "eval_micro_f1": 0.6032229965156795,
      "eval_micro_precision": 0.6032229965156795,
      "eval_micro_recall": 0.6032229965156795,
      "eval_runtime": 27.9989,
      "eval_samples_per_second": 82.003,
      "eval_steps_per_second": 1.286,
      "eval_weighted_f1": 0.502828345764972,
      "eval_weighted_precision": 0.5102415198384107,
      "eval_weighted_recall": 0.6032229965156795,
      "step": 200
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 61.67491149902344,
      "learning_rate": 1.4950000000000001e-05,
      "loss": 1.5019,
      "step": 300
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 1.3270624876022339,
      "eval_macro_f1": 0.18095213980700245,
      "eval_macro_precision": 0.1639157420556758,
      "eval_macro_recall": 0.2060668906229992,
      "eval_micro_f1": 0.6872822299651568,
      "eval_micro_precision": 0.6872822299651568,
      "eval_micro_recall": 0.6872822299651568,
      "eval_runtime": 28.1715,
      "eval_samples_per_second": 81.501,
      "eval_steps_per_second": 1.278,
      "eval_weighted_f1": 0.6267031640391093,
      "eval_weighted_precision": 0.5821328002832489,
      "eval_weighted_recall": 0.6872822299651568,
      "step": 300
    },
    {
      "epoch": 0.9768009768009768,
      "grad_norm": 93.83369445800781,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 1.2602,
      "step": 400
    },
    {
      "epoch": 0.9768009768009768,
      "eval_loss": 1.1570900678634644,
      "eval_macro_f1": 0.24796229984985535,
      "eval_macro_precision": 0.250395185204251,
      "eval_macro_recall": 0.2602306770905881,
      "eval_micro_f1": 0.7151567944250871,
      "eval_micro_precision": 0.7151567944250871,
      "eval_micro_recall": 0.7151567944250871,
      "eval_runtime": 28.097,
      "eval_samples_per_second": 81.717,
      "eval_steps_per_second": 1.281,
      "eval_weighted_f1": 0.6742913163869271,
      "eval_weighted_precision": 0.6523515088941247,
      "eval_weighted_recall": 0.7151567944250871,
      "step": 400
    },
    {
      "epoch": 1.221001221001221,
      "grad_norm": 27.968883514404297,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 1.0116,
      "step": 500
    },
    {
      "epoch": 1.221001221001221,
      "eval_loss": 0.8759449124336243,
      "eval_macro_f1": 0.40662329686945736,
      "eval_macro_precision": 0.4270552853235523,
      "eval_macro_recall": 0.40522488609544827,
      "eval_micro_f1": 0.801829268292683,
      "eval_micro_precision": 0.801829268292683,
      "eval_micro_recall": 0.801829268292683,
      "eval_runtime": 28.1259,
      "eval_samples_per_second": 81.633,
      "eval_steps_per_second": 1.28,
      "eval_weighted_f1": 0.7856079074786287,
      "eval_weighted_precision": 0.778677751235951,
      "eval_weighted_recall": 0.801829268292683,
      "step": 500
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 40.660743713378906,
      "learning_rate": 2.4752635521978294e-05,
      "loss": 0.8539,
      "step": 600
    },
    {
      "epoch": 1.4652014652014653,
      "eval_loss": 0.7635390758514404,
      "eval_macro_f1": 0.47249477353778435,
      "eval_macro_precision": 0.49858319443807503,
      "eval_macro_recall": 0.49267372749042937,
      "eval_micro_f1": 0.8340592334494773,
      "eval_micro_precision": 0.8340592334494773,
      "eval_micro_recall": 0.8340592334494773,
      "eval_runtime": 28.2397,
      "eval_samples_per_second": 81.304,
      "eval_steps_per_second": 1.275,
      "eval_weighted_f1": 0.8260353217142836,
      "eval_weighted_precision": 0.8263412894566534,
      "eval_weighted_recall": 0.8340592334494773,
      "step": 600
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 69.74828338623047,
      "learning_rate": 2.40005092726346e-05,
      "loss": 0.7398,
      "step": 700
    },
    {
      "epoch": 1.7094017094017095,
      "eval_loss": 0.6827709674835205,
      "eval_macro_f1": 0.5156494920599783,
      "eval_macro_precision": 0.595919953102261,
      "eval_macro_recall": 0.516030034812032,
      "eval_micro_f1": 0.8466898954703833,
      "eval_micro_precision": 0.8466898954703833,
      "eval_micro_recall": 0.8466898954703833,
      "eval_runtime": 28.0593,
      "eval_samples_per_second": 81.827,
      "eval_steps_per_second": 1.283,
      "eval_weighted_f1": 0.8359309638776365,
      "eval_weighted_precision": 0.8368823626772747,
      "eval_weighted_recall": 0.8466898954703833,
      "step": 700
    },
    {
      "epoch": 1.9536019536019538,
      "grad_norm": 18.172765731811523,
      "learning_rate": 2.2774508957989417e-05,
      "loss": 0.6728,
      "step": 800
    },
    {
      "epoch": 1.9536019536019538,
      "eval_loss": 0.6122449040412903,
      "eval_macro_f1": 0.5609693508323702,
      "eval_macro_precision": 0.6700802281488617,
      "eval_macro_recall": 0.5537448671543558,
      "eval_micro_f1": 0.8527874564459931,
      "eval_micro_precision": 0.8527874564459931,
      "eval_micro_recall": 0.8527874564459931,
      "eval_runtime": 28.5179,
      "eval_samples_per_second": 80.511,
      "eval_steps_per_second": 1.262,
      "eval_weighted_f1": 0.8465989784626531,
      "eval_weighted_precision": 0.8602585363665758,
      "eval_weighted_recall": 0.8527874564459931,
      "step": 800
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 22.065692901611328,
      "learning_rate": 2.112515144989503e-05,
      "loss": 0.5593,
      "step": 900
    },
    {
      "epoch": 2.197802197802198,
      "eval_loss": 0.6033230423927307,
      "eval_macro_f1": 0.6269631440779232,
      "eval_macro_precision": 0.6458086803108424,
      "eval_macro_recall": 0.6223857477581206,
      "eval_micro_f1": 0.8628048780487805,
      "eval_micro_precision": 0.8628048780487805,
      "eval_micro_recall": 0.8628048780487805,
      "eval_runtime": 28.0799,
      "eval_samples_per_second": 81.767,
      "eval_steps_per_second": 1.282,
      "eval_weighted_f1": 0.8604939320250599,
      "eval_weighted_precision": 0.8620706032280505,
      "eval_weighted_recall": 0.8628048780487805,
      "step": 900
    },
    {
      "epoch": 2.442002442002442,
      "grad_norm": 46.23727035522461,
      "learning_rate": 1.912039789067721e-05,
      "loss": 0.5492,
      "step": 1000
    },
    {
      "epoch": 2.442002442002442,
      "eval_loss": 0.5785375833511353,
      "eval_macro_f1": 0.656816564197882,
      "eval_macro_precision": 0.7161193189547552,
      "eval_macro_recall": 0.656158547673032,
      "eval_micro_f1": 0.8610627177700348,
      "eval_micro_precision": 0.8610627177700348,
      "eval_micro_recall": 0.8610627177700348,
      "eval_runtime": 27.9572,
      "eval_samples_per_second": 82.126,
      "eval_steps_per_second": 1.288,
      "eval_weighted_f1": 0.8635374104852748,
      "eval_weighted_precision": 0.8750576393113125,
      "eval_weighted_recall": 0.8610627177700348,
      "step": 1000
    },
    {
      "epoch": 2.6862026862026864,
      "grad_norm": 18.426353454589844,
      "learning_rate": 1.6842853380380934e-05,
      "loss": 0.5028,
      "step": 1100
    },
    {
      "epoch": 2.6862026862026864,
      "eval_loss": 0.5303468108177185,
      "eval_macro_f1": 0.7262289134052592,
      "eval_macro_precision": 0.7495966854257389,
      "eval_macro_recall": 0.7177312989902742,
      "eval_micro_f1": 0.8854529616724739,
      "eval_micro_precision": 0.8854529616724739,
      "eval_micro_recall": 0.8854529616724739,
      "eval_runtime": 28.1073,
      "eval_samples_per_second": 81.687,
      "eval_steps_per_second": 1.281,
      "eval_weighted_f1": 0.8844974105345418,
      "eval_weighted_precision": 0.8869278196582587,
      "eval_weighted_recall": 0.8854529616724739,
      "step": 1100
    },
    {
      "epoch": 2.9304029304029307,
      "grad_norm": 18.274917602539062,
      "learning_rate": 1.4386363265365535e-05,
      "loss": 0.5033,
      "step": 1200
    },
    {
      "epoch": 2.9304029304029307,
      "eval_loss": 0.49514588713645935,
      "eval_macro_f1": 0.7355993207563093,
      "eval_macro_precision": 0.7372036245463958,
      "eval_macro_recall": 0.7414049084020491,
      "eval_micro_f1": 0.8876306620209059,
      "eval_micro_precision": 0.8876306620209059,
      "eval_micro_recall": 0.8876306620209059,
      "eval_runtime": 27.7713,
      "eval_samples_per_second": 82.675,
      "eval_steps_per_second": 1.296,
      "eval_weighted_f1": 0.8867237445831763,
      "eval_weighted_precision": 0.8876630720638423,
      "eval_weighted_recall": 0.8876306620209059,
      "step": 1200
    },
    {
      "epoch": 3.1746031746031744,
      "grad_norm": 16.126319885253906,
      "learning_rate": 1.1852146276869743e-05,
      "loss": 0.4332,
      "step": 1300
    },
    {
      "epoch": 3.1746031746031744,
      "eval_loss": 0.5176035165786743,
      "eval_macro_f1": 0.8066235690769744,
      "eval_macro_precision": 0.8112408819720179,
      "eval_macro_recall": 0.8135936233566461,
      "eval_micro_f1": 0.8867595818815331,
      "eval_micro_precision": 0.8867595818815331,
      "eval_micro_recall": 0.8867595818815331,
      "eval_runtime": 28.2301,
      "eval_samples_per_second": 81.332,
      "eval_steps_per_second": 1.275,
      "eval_weighted_f1": 0.8881457405419927,
      "eval_weighted_precision": 0.892519346409985,
      "eval_weighted_recall": 0.8867595818815331,
      "step": 1300
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 25.683168411254883,
      "learning_rate": 9.344623852086093e-06,
      "loss": 0.4328,
      "step": 1400
    },
    {
      "epoch": 3.4188034188034186,
      "eval_loss": 0.48010551929473877,
      "eval_macro_f1": 0.8188574972016193,
      "eval_macro_precision": 0.8223473803322559,
      "eval_macro_recall": 0.8205261076151831,
      "eval_micro_f1": 0.8906794425087108,
      "eval_micro_precision": 0.8906794425087108,
      "eval_micro_recall": 0.8906794425087108,
      "eval_runtime": 28.1842,
      "eval_samples_per_second": 81.464,
      "eval_steps_per_second": 1.277,
      "eval_weighted_f1": 0.8908187701448725,
      "eval_weighted_precision": 0.8923647873870492,
      "eval_weighted_recall": 0.8906794425087108,
      "step": 1400
    },
    {
      "epoch": 3.663003663003663,
      "grad_norm": 32.259490966796875,
      "learning_rate": 6.967117488967232e-06,
      "loss": 0.3965,
      "step": 1500
    },
    {
      "epoch": 3.663003663003663,
      "eval_loss": 0.48184239864349365,
      "eval_macro_f1": 0.8216617574200699,
      "eval_macro_precision": 0.8214437028036421,
      "eval_macro_recall": 0.8278310307484175,
      "eval_micro_f1": 0.89198606271777,
      "eval_micro_precision": 0.89198606271777,
      "eval_micro_recall": 0.89198606271777,
      "eval_runtime": 27.8631,
      "eval_samples_per_second": 82.403,
      "eval_steps_per_second": 1.292,
      "eval_weighted_f1": 0.8924948901640382,
      "eval_weighted_precision": 0.8949476957454691,
      "eval_weighted_recall": 0.89198606271777,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 2045,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 5.46348379202519e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}