{
  "best_metric": 0.7634932999314054,
  "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/Ner_Pipeline/src/ner_pipeline/model_outputs/NER/CeLLaTe_3class_3.0/BiomedNLP_BiomedBERT_base_uncased_abstract_fulltext/BaseStrategy/StandardNerHead/BaseTrainer/no_data_aug/checkpoint-2367",
  "epoch": 14.0,
  "eval_steps": 100,
  "global_step": 3682,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.499980092048645,
      "learning_rate": 1.9204916458613406e-05,
      "loss": 0.3705,
      "step": 263
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9767839315024451,
      "eval_loss": 0.07922293245792389,
      "eval_macro_f1": 0.5607172307233707,
      "eval_micro_f1": 0.5859499733901011,
      "eval_precision": 0.5993467610234078,
      "eval_recall": 0.573138990109318,
      "eval_weighted_f1": 0.5782964332062143,
      "step": 263
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1381945610046387,
      "learning_rate": 1.819473785289034e-05,
      "loss": 0.0578,
      "step": 526
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9811327140125556,
      "eval_loss": 0.06325448304414749,
      "eval_macro_f1": 0.7222045163630888,
      "eval_micro_f1": 0.7245604688332445,
      "eval_precision": 0.7419530823786143,
      "eval_recall": 0.7079646017699115,
      "eval_weighted_f1": 0.7252630809280266,
      "step": 526
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9407679438591003,
      "learning_rate": 1.7184559247167276e-05,
      "loss": 0.0353,
      "step": 789
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9814203766688664,
      "eval_loss": 0.06546597182750702,
      "eval_macro_f1": 0.741575956013186,
      "eval_micro_f1": 0.7426545086119554,
      "eval_precision": 0.7232363098174642,
      "eval_recall": 0.7631441957313899,
      "eval_weighted_f1": 0.7432513213762597,
      "step": 789
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.13222087919712067,
      "learning_rate": 1.617438064144421e-05,
      "loss": 0.0254,
      "step": 1052
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9825879486268339,
      "eval_loss": 0.08073774725198746,
      "eval_macro_f1": 0.745150936861365,
      "eval_micro_f1": 0.7519738633269806,
      "eval_precision": 0.78824200913242,
      "eval_recall": 0.7188964081207704,
      "eval_weighted_f1": 0.750615720684395,
      "step": 1052
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.31658506393432617,
      "learning_rate": 1.5164202035721145e-05,
      "loss": 0.0185,
      "step": 1315
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9817418819906256,
      "eval_loss": 0.07392168790102005,
      "eval_macro_f1": 0.7358482740999972,
      "eval_micro_f1": 0.7386687386687387,
      "eval_precision": 0.7350515463917526,
      "eval_recall": 0.7423217074440396,
      "eval_weighted_f1": 0.7391264972928957,
      "step": 1315
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.009997176006436348,
      "learning_rate": 1.415402342999808e-05,
      "loss": 0.0142,
      "step": 1578
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9806081526981065,
      "eval_loss": 0.08536450564861298,
      "eval_macro_f1": 0.7261304660224934,
      "eval_micro_f1": 0.7289386612369558,
      "eval_precision": 0.7131474103585658,
      "eval_recall": 0.7454450806871421,
      "eval_weighted_f1": 0.7296431528943578,
      "step": 1578
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.22506612539291382,
      "learning_rate": 1.3143844824275017e-05,
      "loss": 0.0104,
      "step": 1841
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9821141513105572,
      "eval_loss": 0.08728903532028198,
      "eval_macro_f1": 0.7474475075874389,
      "eval_micro_f1": 0.7513988808952838,
      "eval_precision": 0.769650655021834,
      "eval_recall": 0.7339927121290994,
      "eval_weighted_f1": 0.7506013649890978,
      "step": 1841
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.015740081667900085,
      "learning_rate": 1.213366621855195e-05,
      "loss": 0.0087,
      "step": 2104
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9818772526524189,
      "eval_loss": 0.09343691915273666,
      "eval_macro_f1": 0.7403039355405312,
      "eval_micro_f1": 0.7418275418275417,
      "eval_precision": 0.7337067209775967,
      "eval_recall": 0.7501301405517959,
      "eval_weighted_f1": 0.7420549217599774,
      "step": 2104
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.6508826613426208,
      "learning_rate": 1.1123487612828885e-05,
      "loss": 0.007,
      "step": 2367
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9828756112831447,
      "eval_loss": 0.09423227608203888,
      "eval_macro_f1": 0.7634932999314054,
      "eval_micro_f1": 0.7683468268477408,
      "eval_precision": 0.7709643605870021,
      "eval_recall": 0.7657470067673087,
      "eval_weighted_f1": 0.7676201589775575,
      "step": 2367
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.005056560505181551,
      "learning_rate": 1.011330900710582e-05,
      "loss": 0.0059,
      "step": 2630
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9820295446469364,
      "eval_loss": 0.10169301927089691,
      "eval_macro_f1": 0.7401422549415057,
      "eval_micro_f1": 0.7419871794871794,
      "eval_precision": 0.761930883159627,
      "eval_recall": 0.7230609057782404,
      "eval_weighted_f1": 0.7416103645962767,
      "step": 2630
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.00294481567107141,
      "learning_rate": 9.103130401382755e-06,
      "loss": 0.005,
      "step": 2893
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9826217912922822,
      "eval_loss": 0.09840236604213715,
      "eval_macro_f1": 0.751826679987133,
      "eval_micro_f1": 0.7548761201897732,
      "eval_precision": 0.7645488521089162,
      "eval_recall": 0.7454450806871421,
      "eval_weighted_f1": 0.7538770398780168,
      "step": 2893
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.4150006175041199,
      "learning_rate": 8.092951795659689e-06,
      "loss": 0.0041,
      "step": 3156
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9817418819906256,
      "eval_loss": 0.11176982522010803,
      "eval_macro_f1": 0.7321679577133663,
      "eval_micro_f1": 0.7333156075511832,
      "eval_precision": 0.7494565217391305,
      "eval_recall": 0.717855283706403,
      "eval_weighted_f1": 0.7336935207710876,
      "step": 3156
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.03623787313699722,
      "learning_rate": 7.082773189936625e-06,
      "loss": 0.0033,
      "step": 3419
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9824525779650405,
      "eval_loss": 0.11363589018583298,
      "eval_macro_f1": 0.7533031808473881,
      "eval_micro_f1": 0.753934942287513,
      "eval_precision": 0.7599153886832364,
      "eval_recall": 0.7480478917230609,
      "eval_weighted_f1": 0.7535596423761834,
      "step": 3419
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.0032901219092309475,
      "learning_rate": 6.072594584213559e-06,
      "loss": 0.0033,
      "step": 3682
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9814372980015906,
      "eval_loss": 0.11802394688129425,
      "eval_macro_f1": 0.7351056070717171,
      "eval_micro_f1": 0.7350697184951328,
      "eval_precision": 0.7430851063829788,
      "eval_recall": 0.7272254034357105,
      "eval_weighted_f1": 0.7352935114270702,
      "step": 3682
    },
    {
      "epoch": 14.0,
      "step": 3682,
      "total_flos": 2981574659125788.0,
      "train_loss": 0.040679274645918806,
      "train_runtime": 972.0928,
      "train_samples_per_second": 173.008,
      "train_steps_per_second": 5.411
    }
  ],
  "logging_steps": 10,
  "max_steps": 5260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2981574659125788.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}