{
  "best_metric": 0.9242643511818619,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4510",
  "epoch": 9.988925802879292,
  "eval_steps": 500,
  "global_step": 4510,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9988925802879292,
      "eval_accuracy": 0.9983575694624772,
      "eval_f1": 0.900350525788683,
      "eval_loss": 0.005117920693010092,
      "eval_precision": 0.9325726141078838,
      "eval_recall": 0.8702807357212003,
      "eval_runtime": 17.4335,
      "eval_samples_per_second": 389.938,
      "eval_steps_per_second": 48.757,
      "step": 451
    },
    {
      "epoch": 1.1074197120708749,
      "grad_norm": 0.20482830703258514,
      "learning_rate": 4.445676274944568e-05,
      "loss": 0.0116,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9985328486107504,
      "eval_f1": 0.9135446685878963,
      "eval_loss": 0.004852809943258762,
      "eval_precision": 0.9065776930409915,
      "eval_recall": 0.920619554695063,
      "eval_runtime": 17.467,
      "eval_samples_per_second": 389.192,
      "eval_steps_per_second": 48.663,
      "step": 903
    },
    {
      "epoch": 2.2148394241417497,
      "grad_norm": 0.3147585690021515,
      "learning_rate": 3.8913525498891355e-05,
      "loss": 0.0034,
      "step": 1000
    },
    {
      "epoch": 2.9988925802879294,
      "eval_accuracy": 0.9983900285640094,
      "eval_f1": 0.910133843212237,
      "eval_loss": 0.005565761122852564,
      "eval_precision": 0.898961284230406,
      "eval_recall": 0.9215876089060987,
      "eval_runtime": 17.4422,
      "eval_samples_per_second": 389.744,
      "eval_steps_per_second": 48.732,
      "step": 1354
    },
    {
      "epoch": 3.3222591362126246,
      "grad_norm": 0.10508228093385696,
      "learning_rate": 3.337028824833703e-05,
      "loss": 0.0018,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9984874058686055,
      "eval_f1": 0.9164265129682997,
      "eval_loss": 0.00661922711879015,
      "eval_precision": 0.909437559580553,
      "eval_recall": 0.9235237173281704,
      "eval_runtime": 17.6875,
      "eval_samples_per_second": 384.339,
      "eval_steps_per_second": 48.056,
      "step": 1806
    },
    {
      "epoch": 4.4296788482834994,
      "grad_norm": 0.16867227852344513,
      "learning_rate": 2.7827050997782704e-05,
      "loss": 0.0011,
      "step": 2000
    },
    {
      "epoch": 4.998892580287929,
      "eval_accuracy": 0.9986237340950402,
      "eval_f1": 0.9186602870813397,
      "eval_loss": 0.0055653550662100315,
      "eval_precision": 0.9082308420056765,
      "eval_recall": 0.9293320425943853,
      "eval_runtime": 17.4102,
      "eval_samples_per_second": 390.461,
      "eval_steps_per_second": 48.822,
      "step": 2257
    },
    {
      "epoch": 5.537098560354375,
      "grad_norm": 0.060708414763212204,
      "learning_rate": 2.2283813747228384e-05,
      "loss": 0.0007,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9985328486107504,
      "eval_f1": 0.9127061105722599,
      "eval_loss": 0.006837355904281139,
      "eval_precision": 0.9144800777453839,
      "eval_recall": 0.9109390125847048,
      "eval_runtime": 17.4499,
      "eval_samples_per_second": 389.572,
      "eval_steps_per_second": 48.711,
      "step": 2709
    },
    {
      "epoch": 6.644518272425249,
      "grad_norm": 0.001121490728110075,
      "learning_rate": 1.674057649667406e-05,
      "loss": 0.0005,
      "step": 3000
    },
    {
      "epoch": 6.998892580287929,
      "eval_accuracy": 0.9983705531030901,
      "eval_f1": 0.9077141504969238,
      "eval_loss": 0.0075966897420585155,
      "eval_precision": 0.887962962962963,
      "eval_recall": 0.9283639883833494,
      "eval_runtime": 17.4659,
      "eval_samples_per_second": 389.215,
      "eval_steps_per_second": 48.666,
      "step": 3160
    },
    {
      "epoch": 7.751937984496124,
      "grad_norm": 0.010231947526335716,
      "learning_rate": 1.1197339246119735e-05,
      "loss": 0.0003,
      "step": 3500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9985653077122826,
      "eval_f1": 0.9164265129682997,
      "eval_loss": 0.008048146031796932,
      "eval_precision": 0.909437559580553,
      "eval_recall": 0.9235237173281704,
      "eval_runtime": 17.4601,
      "eval_samples_per_second": 389.346,
      "eval_steps_per_second": 48.683,
      "step": 3612
    },
    {
      "epoch": 8.859357696566999,
      "grad_norm": 0.003443971276283264,
      "learning_rate": 5.65410199556541e-06,
      "loss": 0.0002,
      "step": 4000
    },
    {
      "epoch": 8.99889258028793,
      "eval_accuracy": 0.9985847831732018,
      "eval_f1": 0.9183969097054564,
      "eval_loss": 0.007848693057894707,
      "eval_precision": 0.9161849710982659,
      "eval_recall": 0.920619554695063,
      "eval_runtime": 17.4184,
      "eval_samples_per_second": 390.276,
      "eval_steps_per_second": 48.799,
      "step": 4063
    },
    {
      "epoch": 9.966777408637874,
      "grad_norm": 0.0008140078862197697,
      "learning_rate": 1.1086474501108648e-07,
      "loss": 0.0001,
      "step": 4500
    },
    {
      "epoch": 9.988925802879292,
      "eval_accuracy": 0.9986302259153467,
      "eval_f1": 0.9242643511818619,
      "eval_loss": 0.007998762652277946,
      "eval_precision": 0.9211538461538461,
      "eval_recall": 0.9273959341723137,
      "eval_runtime": 17.8292,
      "eval_samples_per_second": 381.284,
      "eval_steps_per_second": 47.675,
      "step": 4510
    },
    {
      "epoch": 9.988925802879292,
      "step": 4510,
      "total_flos": 1.6091832702504528e+16,
      "train_loss": 0.002201940788383577,
      "train_runtime": 2471.8222,
      "train_samples_per_second": 116.817,
      "train_steps_per_second": 1.825
    }
  ],
  "logging_steps": 500,
  "max_steps": 4510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1.6091832702504528e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}