{
  "best_global_step": 2250,
  "best_metric": 0.9931719428926132,
  "best_model_checkpoint": "./res_Context_Aware_banglabert/checkpoint-2250",
  "epoch": 2.4807056229327453,
  "eval_steps": 250,
  "global_step": 2250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11025358324145534,
      "grad_norm": 9.02037239074707,
      "learning_rate": 4.9315259921744e-05,
      "loss": 0.8721378326416016,
      "step": 100
    },
    {
      "epoch": 0.2205071664829107,
      "grad_norm": 2.885241985321045,
      "learning_rate": 4.791783119060928e-05,
      "loss": 0.35012786865234374,
      "step": 200
    },
    {
      "epoch": 0.2756339581036384,
      "eval_accuracy": 0.9776536312849162,
      "eval_f1": 0.9776510975266813,
      "eval_loss": 0.15934747457504272,
      "eval_runtime": 14.0961,
      "eval_samples_per_second": 114.287,
      "eval_steps_per_second": 0.922,
      "step": 250
    },
    {
      "epoch": 0.33076074972436603,
      "grad_norm": 6.377964496612549,
      "learning_rate": 4.652040245947457e-05,
      "loss": 0.2049967384338379,
      "step": 300
    },
    {
      "epoch": 0.4410143329658214,
      "grad_norm": 0.08052965253591537,
      "learning_rate": 4.5122973728339854e-05,
      "loss": 0.1924136734008789,
      "step": 400
    },
    {
      "epoch": 0.5512679162072768,
      "grad_norm": 6.491593837738037,
      "learning_rate": 4.372554499720514e-05,
      "loss": 0.20583047866821289,
      "step": 500
    },
    {
      "epoch": 0.5512679162072768,
      "eval_accuracy": 0.9745499689633768,
      "eval_f1": 0.9745495371719669,
      "eval_loss": 0.18327105045318604,
      "eval_runtime": 14.1562,
      "eval_samples_per_second": 113.802,
      "eval_steps_per_second": 0.918,
      "step": 500
    },
    {
      "epoch": 0.6615214994487321,
      "grad_norm": 3.80802059173584,
      "learning_rate": 4.232811626607043e-05,
      "loss": 0.15363896369934082,
      "step": 600
    },
    {
      "epoch": 0.7717750826901875,
      "grad_norm": 3.48689603805542,
      "learning_rate": 4.093068753493572e-05,
      "loss": 0.1443716526031494,
      "step": 700
    },
    {
      "epoch": 0.8269018743109151,
      "eval_accuracy": 0.978274363749224,
      "eval_f1": 0.978278215038984,
      "eval_loss": 0.20134644210338593,
      "eval_runtime": 14.1783,
      "eval_samples_per_second": 113.624,
      "eval_steps_per_second": 0.917,
      "step": 750
    },
    {
      "epoch": 0.8820286659316428,
      "grad_norm": 32.31780242919922,
      "learning_rate": 3.953325880380101e-05,
      "loss": 0.1432034492492676,
      "step": 800
    },
    {
      "epoch": 0.9922822491730982,
      "grad_norm": 26.723928451538086,
      "learning_rate": 3.8135830072666296e-05,
      "loss": 0.12749279975891115,
      "step": 900
    },
    {
      "epoch": 1.1025358324145536,
      "grad_norm": 6.3086957931518555,
      "learning_rate": 3.673840134153159e-05,
      "loss": 0.07981213569641113,
      "step": 1000
    },
    {
      "epoch": 1.1025358324145536,
      "eval_accuracy": 0.9869646182495344,
      "eval_f1": 0.9869655730837585,
      "eval_loss": 0.13266624510288239,
      "eval_runtime": 14.2074,
      "eval_samples_per_second": 113.391,
      "eval_steps_per_second": 0.915,
      "step": 1000
    },
    {
      "epoch": 1.2127894156560088,
      "grad_norm": 46.10914611816406,
      "learning_rate": 3.5340972610396874e-05,
      "loss": 0.08848725318908691,
      "step": 1100
    },
    {
      "epoch": 1.3230429988974641,
      "grad_norm": 0.05402166396379471,
      "learning_rate": 3.394354387926216e-05,
      "loss": 0.07142821311950684,
      "step": 1200
    },
    {
      "epoch": 1.3781697905181918,
      "eval_accuracy": 0.9807572936064556,
      "eval_f1": 0.9807591629646968,
      "eval_loss": 0.1913502961397171,
      "eval_runtime": 14.1881,
      "eval_samples_per_second": 113.546,
      "eval_steps_per_second": 0.916,
      "step": 1250
    },
    {
      "epoch": 1.4332965821389196,
      "grad_norm": 0.089525505900383,
      "learning_rate": 3.2546115148127446e-05,
      "loss": 0.0875068473815918,
      "step": 1300
    },
    {
      "epoch": 1.543550165380375,
      "grad_norm": 0.06809459626674652,
      "learning_rate": 3.114868641699273e-05,
      "loss": 0.07411887168884278,
      "step": 1400
    },
    {
      "epoch": 1.6538037486218302,
      "grad_norm": 0.7647103071212769,
      "learning_rate": 2.9751257685858024e-05,
      "loss": 0.0676584243774414,
      "step": 1500
    },
    {
      "epoch": 1.6538037486218302,
      "eval_accuracy": 0.9882060831781502,
      "eval_f1": 0.9882039542277219,
      "eval_loss": 0.10057985037565231,
      "eval_runtime": 14.2098,
      "eval_samples_per_second": 113.372,
      "eval_steps_per_second": 0.915,
      "step": 1500
    },
    {
      "epoch": 1.7640573318632855,
      "grad_norm": 0.023145318031311035,
      "learning_rate": 2.835382895472331e-05,
      "loss": 0.053038196563720705,
      "step": 1600
    },
    {
      "epoch": 1.8743109151047408,
      "grad_norm": 3.5554888248443604,
      "learning_rate": 2.6956400223588595e-05,
      "loss": 0.08461674690246582,
      "step": 1700
    },
    {
      "epoch": 1.9294377067254684,
      "eval_accuracy": 0.9900682805710739,
      "eval_f1": 0.9900675605237899,
      "eval_loss": 0.07765113562345505,
      "eval_runtime": 14.2432,
      "eval_samples_per_second": 113.106,
      "eval_steps_per_second": 0.913,
      "step": 1750
    },
    {
      "epoch": 1.9845644983461963,
      "grad_norm": 0.14184314012527466,
      "learning_rate": 2.5558971492453888e-05,
      "loss": 0.06337377548217774,
      "step": 1800
    },
    {
      "epoch": 2.0948180815876514,
      "grad_norm": 0.011256121098995209,
      "learning_rate": 2.4161542761319173e-05,
      "loss": 0.023933162689208986,
      "step": 1900
    },
    {
      "epoch": 2.205071664829107,
      "grad_norm": 0.014097367413341999,
      "learning_rate": 2.2764114030184462e-05,
      "loss": 0.030810904502868653,
      "step": 2000
    },
    {
      "epoch": 2.205071664829107,
      "eval_accuracy": 0.9919304779639975,
      "eval_f1": 0.9919293886744892,
      "eval_loss": 0.11332618445158005,
      "eval_runtime": 14.1841,
      "eval_samples_per_second": 113.578,
      "eval_steps_per_second": 0.917,
      "step": 2000
    },
    {
      "epoch": 2.3153252480705624,
      "grad_norm": 0.010986179113388062,
      "learning_rate": 2.1366685299049748e-05,
      "loss": 0.029725773334503172,
      "step": 2100
    },
    {
      "epoch": 2.4255788313120177,
      "grad_norm": 10.8602876663208,
      "learning_rate": 1.9969256567915037e-05,
      "loss": 0.041701827049255374,
      "step": 2200
    },
    {
      "epoch": 2.4807056229327453,
      "eval_accuracy": 0.9931719428926132,
      "eval_f1": 0.9931703783739821,
      "eval_loss": 0.08890443295240402,
      "eval_runtime": 14.1525,
      "eval_samples_per_second": 113.831,
      "eval_steps_per_second": 0.919,
      "step": 2250
    }
  ],
  "logging_steps": 100,
  "max_steps": 3628,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 250,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9464367772354560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}