{
  "best_metric": 0.5278386153994516,
  "best_model_checkpoint": "./CARES/checkpoints/bio-ber/checkpoint-2679",
  "epoch": 19.0,
  "global_step": 2679,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.2276119738817215,
      "eval_macro_f1": 0.09383679038919833,
      "eval_macro_precision": 0.12681117070705897,
      "eval_macro_recall": 0.07667770066244797,
      "eval_micro_f1": 0.36897880539499034,
      "eval_micro_precision": 0.7053406998158379,
      "eval_micro_recall": 0.24983692106979777,
      "eval_runtime": 2.8509,
      "eval_samples_per_second": 338.842,
      "eval_steps_per_second": 21.397,
      "step": 141
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.19956032931804657,
      "eval_macro_f1": 0.13389070512548568,
      "eval_macro_precision": 0.1949068871295339,
      "eval_macro_recall": 0.11313811988335658,
      "eval_micro_f1": 0.4958460865763008,
      "eval_micro_precision": 0.7519893899204244,
      "eval_micro_recall": 0.3698630136986301,
      "eval_runtime": 2.8244,
      "eval_samples_per_second": 342.022,
      "eval_steps_per_second": 21.598,
      "step": 282
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.18670037388801575,
      "eval_macro_f1": 0.22751166658204755,
      "eval_macro_precision": 0.46178526182432433,
      "eval_macro_recall": 0.18375879789138674,
      "eval_micro_f1": 0.5680033071517155,
      "eval_micro_precision": 0.7753950338600452,
      "eval_micro_recall": 0.4481409001956947,
      "eval_runtime": 2.8618,
      "eval_samples_per_second": 337.545,
      "eval_steps_per_second": 21.315,
      "step": 423
    },
    {
      "epoch": 3.55,
      "learning_rate": 4.822695035460993e-05,
      "loss": 0.2081,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.18518751859664917,
      "eval_macro_f1": 0.34478852490640566,
      "eval_macro_precision": 0.5134144581169723,
      "eval_macro_recall": 0.2886504191522892,
      "eval_micro_f1": 0.6130150173276858,
      "eval_micro_precision": 0.7481203007518797,
      "eval_micro_recall": 0.5192433137638617,
      "eval_runtime": 2.8317,
      "eval_samples_per_second": 341.135,
      "eval_steps_per_second": 21.542,
      "step": 564
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.18300610780715942,
      "eval_macro_f1": 0.4238271955718499,
      "eval_macro_precision": 0.6346282008083806,
      "eval_macro_recall": 0.36978265721033565,
      "eval_micro_f1": 0.6232315711094564,
      "eval_micro_precision": 0.7259323503902863,
      "eval_micro_recall": 0.5459882583170255,
      "eval_runtime": 2.8313,
      "eval_samples_per_second": 341.185,
      "eval_steps_per_second": 21.545,
      "step": 705
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.18070942163467407,
      "eval_macro_f1": 0.427572174915214,
      "eval_macro_precision": 0.5867883838688037,
      "eval_macro_recall": 0.3661335629128818,
      "eval_micro_f1": 0.6416332482683194,
      "eval_micro_precision": 0.7272727272727273,
      "eval_micro_recall": 0.5740378343118069,
      "eval_runtime": 2.822,
      "eval_samples_per_second": 342.307,
      "eval_steps_per_second": 21.616,
      "step": 846
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.18207068741321564,
      "eval_macro_f1": 0.47285593173212287,
      "eval_macro_precision": 0.5718512640389848,
      "eval_macro_recall": 0.4270343269721778,
      "eval_micro_f1": 0.6605374823196605,
      "eval_micro_precision": 0.7212355212355213,
      "eval_micro_recall": 0.6092628832354859,
      "eval_runtime": 2.8204,
      "eval_samples_per_second": 342.507,
      "eval_steps_per_second": 21.628,
      "step": 987
    },
    {
      "epoch": 7.09,
      "learning_rate": 4.645390070921986e-05,
      "loss": 0.115,
      "step": 1000
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.18614797294139862,
      "eval_macro_f1": 0.48637001730423257,
      "eval_macro_precision": 0.6057345339339811,
      "eval_macro_recall": 0.4271528815196963,
      "eval_micro_f1": 0.6618128867855844,
      "eval_micro_precision": 0.7487644151565074,
      "eval_micro_recall": 0.5929549902152642,
      "eval_runtime": 2.8241,
      "eval_samples_per_second": 342.057,
      "eval_steps_per_second": 21.6,
      "step": 1128
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.18139992654323578,
      "eval_macro_f1": 0.4968758987364566,
      "eval_macro_precision": 0.6188063911104451,
      "eval_macro_recall": 0.4425857583556203,
      "eval_micro_f1": 0.6716259298618491,
      "eval_micro_precision": 0.7348837209302326,
      "eval_micro_recall": 0.6183953033268101,
      "eval_runtime": 2.8195,
      "eval_samples_per_second": 342.612,
      "eval_steps_per_second": 21.635,
      "step": 1269
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.19238035380840302,
      "eval_macro_f1": 0.4762674411195111,
      "eval_macro_precision": 0.5687316855202853,
      "eval_macro_recall": 0.42920385227971614,
      "eval_micro_f1": 0.6690066690066689,
      "eval_micro_precision": 0.7241641337386018,
      "eval_micro_recall": 0.6216568819308546,
      "eval_runtime": 2.8152,
      "eval_samples_per_second": 343.137,
      "eval_steps_per_second": 21.668,
      "step": 1410
    },
    {
      "epoch": 10.64,
      "learning_rate": 4.468085106382979e-05,
      "loss": 0.0668,
      "step": 1500
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.20003741979599,
      "eval_macro_f1": 0.5041732295700452,
      "eval_macro_precision": 0.5819236883447072,
      "eval_macro_recall": 0.458955350441925,
      "eval_micro_f1": 0.6811645036829183,
      "eval_micro_precision": 0.7367223065250379,
      "eval_micro_recall": 0.6333985649054142,
      "eval_runtime": 2.8186,
      "eval_samples_per_second": 342.72,
      "eval_steps_per_second": 21.642,
      "step": 1551
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.21071653068065643,
      "eval_macro_f1": 0.5060970351192071,
      "eval_macro_precision": 0.6216233664621571,
      "eval_macro_recall": 0.46859394229849854,
      "eval_micro_f1": 0.6627946703108984,
      "eval_micro_precision": 0.6958393113342898,
      "eval_micro_recall": 0.6327462491846053,
      "eval_runtime": 2.817,
      "eval_samples_per_second": 342.914,
      "eval_steps_per_second": 21.654,
      "step": 1692
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.20960789918899536,
      "eval_macro_f1": 0.5055202034151333,
      "eval_macro_precision": 0.6090230781362929,
      "eval_macro_recall": 0.450320346412875,
      "eval_micro_f1": 0.6799041424169804,
      "eval_micro_precision": 0.7154178674351584,
      "eval_micro_recall": 0.6477495107632094,
      "eval_runtime": 4.7452,
      "eval_samples_per_second": 203.576,
      "eval_steps_per_second": 12.855,
      "step": 1833
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.21599768102169037,
      "eval_macro_f1": 0.5190622646217878,
      "eval_macro_precision": 0.6551140465404754,
      "eval_macro_recall": 0.47196058443148803,
      "eval_micro_f1": 0.6803764377831997,
      "eval_micro_precision": 0.7305389221556886,
      "eval_micro_recall": 0.6366601435094585,
      "eval_runtime": 2.819,
      "eval_samples_per_second": 342.677,
      "eval_steps_per_second": 21.639,
      "step": 1974
    },
    {
      "epoch": 14.18,
      "learning_rate": 4.2907801418439716e-05,
      "loss": 0.0365,
      "step": 2000
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.21732226014137268,
      "eval_macro_f1": 0.4982722788861393,
      "eval_macro_precision": 0.5812880908852627,
      "eval_macro_recall": 0.46102462821831114,
      "eval_micro_f1": 0.6856754921928038,
      "eval_micro_precision": 0.7147912243453645,
      "eval_micro_recall": 0.6588388780169602,
      "eval_runtime": 2.837,
      "eval_samples_per_second": 340.498,
      "eval_steps_per_second": 21.501,
      "step": 2115
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.23044872283935547,
      "eval_macro_f1": 0.5067733640623313,
      "eval_macro_precision": 0.6404358198207177,
      "eval_macro_recall": 0.46429191921900426,
      "eval_micro_f1": 0.6748382703438883,
      "eval_micro_precision": 0.7058404558404558,
      "eval_micro_recall": 0.6464448793215917,
      "eval_runtime": 2.8419,
      "eval_samples_per_second": 339.909,
      "eval_steps_per_second": 21.464,
      "step": 2256
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.23040802776813507,
      "eval_macro_f1": 0.5182045437347171,
      "eval_macro_precision": 0.6102649650627312,
      "eval_macro_recall": 0.474946805831835,
      "eval_micro_f1": 0.6864349011588274,
      "eval_micro_precision": 0.7187723054960742,
      "eval_micro_recall": 0.6568819308545336,
      "eval_runtime": 2.8516,
      "eval_samples_per_second": 338.756,
      "eval_steps_per_second": 21.391,
      "step": 2397
    },
    {
      "epoch": 17.73,
      "learning_rate": 4.1134751773049644e-05,
      "loss": 0.021,
      "step": 2500
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.23820702731609344,
      "eval_macro_f1": 0.5109008179961498,
      "eval_macro_precision": 0.6241805280991644,
      "eval_macro_recall": 0.4711108204223084,
      "eval_micro_f1": 0.6758481692979509,
      "eval_micro_precision": 0.6966759002770083,
      "eval_micro_recall": 0.6562296151337247,
      "eval_runtime": 2.8209,
      "eval_samples_per_second": 342.448,
      "eval_steps_per_second": 21.625,
      "step": 2538
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.23519271612167358,
      "eval_macro_f1": 0.5278386153994516,
      "eval_macro_precision": 0.6066088954753265,
      "eval_macro_recall": 0.48873540160049156,
      "eval_micro_f1": 0.6875645883568722,
      "eval_micro_precision": 0.7284671532846715,
      "eval_micro_recall": 0.6510110893672537,
      "eval_runtime": 2.8218,
      "eval_samples_per_second": 342.33,
      "eval_steps_per_second": 21.617,
      "step": 2679
    }
  ],
  "max_steps": 14100,
  "num_train_epochs": 100,
  "total_flos": 1.0688023305003456e+16,
  "trial_name": null,
  "trial_params": null
}