{
  "best_global_step": 1000,
  "best_metric": 0.9968069666182874,
  "best_model_checkpoint": "models/tinybert-enron\\checkpoint-1000",
  "epoch": 2.1119324181626187,
  "eval_steps": 200,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05279831045406547,
      "grad_norm": 0.7054851055145264,
      "learning_rate": 3.878627968337731e-06,
      "loss": 0.6916,
      "step": 50
    },
    {
      "epoch": 0.10559662090813093,
      "grad_norm": 4.758987903594971,
      "learning_rate": 7.836411609498681e-06,
      "loss": 0.6419,
      "step": 100
    },
    {
      "epoch": 0.1583949313621964,
      "grad_norm": 2.878147602081299,
      "learning_rate": 1.179419525065963e-05,
      "loss": 0.4382,
      "step": 150
    },
    {
      "epoch": 0.21119324181626187,
      "grad_norm": 0.9188410639762878,
      "learning_rate": 1.575197889182058e-05,
      "loss": 0.2162,
      "step": 200
    },
    {
      "epoch": 0.21119324181626187,
      "eval_accuracy": 0.997920997920998,
      "eval_f1": 0.997965707643127,
      "eval_loss": 0.11409526318311691,
      "eval_precision": 0.9959396751740139,
      "eval_recall": 1.0,
      "eval_runtime": 77.9734,
      "eval_samples_per_second": 43.181,
      "eval_steps_per_second": 2.706,
      "step": 200
    },
    {
      "epoch": 0.26399155227032733,
      "grad_norm": 0.42353588342666626,
      "learning_rate": 1.970976253298153e-05,
      "loss": 0.0759,
      "step": 250
    },
    {
      "epoch": 0.3167898627243928,
      "grad_norm": 0.22129850089550018,
      "learning_rate": 2.3667546174142482e-05,
      "loss": 0.0466,
      "step": 300
    },
    {
      "epoch": 0.36958817317845827,
      "grad_norm": 0.14293035864830017,
      "learning_rate": 2.762532981530343e-05,
      "loss": 0.0333,
      "step": 350
    },
    {
      "epoch": 0.42238648363252373,
      "grad_norm": 0.09417829662561417,
      "learning_rate": 2.982399530654151e-05,
      "loss": 0.015,
      "step": 400
    },
    {
      "epoch": 0.42238648363252373,
      "eval_accuracy": 0.9988119988119988,
      "eval_f1": 0.9988365328679465,
      "eval_loss": 0.012017497792840004,
      "eval_precision": 0.9976757699012202,
      "eval_recall": 1.0,
      "eval_runtime": 75.9348,
      "eval_samples_per_second": 44.341,
      "eval_steps_per_second": 2.779,
      "step": 400
    },
    {
      "epoch": 0.4751847940865892,
      "grad_norm": 0.06869468092918396,
      "learning_rate": 2.938398357289528e-05,
      "loss": 0.0143,
      "step": 450
    },
    {
      "epoch": 0.5279831045406547,
      "grad_norm": 0.05820750445127487,
      "learning_rate": 2.8943971839249047e-05,
      "loss": 0.0161,
      "step": 500
    },
    {
      "epoch": 0.5807814149947201,
      "grad_norm": 0.053672004491090775,
      "learning_rate": 2.8503960105602817e-05,
      "loss": 0.0107,
      "step": 550
    },
    {
      "epoch": 0.6335797254487856,
      "grad_norm": 121.33438873291016,
      "learning_rate": 2.8063948371956588e-05,
      "loss": 0.0068,
      "step": 600
    },
    {
      "epoch": 0.6335797254487856,
      "eval_accuracy": 0.9991089991089991,
      "eval_f1": 0.999127145766657,
      "eval_loss": 0.006898785941302776,
      "eval_precision": 0.9982558139534884,
      "eval_recall": 1.0,
      "eval_runtime": 87.7806,
      "eval_samples_per_second": 38.357,
      "eval_steps_per_second": 2.404,
      "step": 600
    },
    {
      "epoch": 0.6863780359028511,
      "grad_norm": 0.2175891101360321,
      "learning_rate": 2.7623936638310355e-05,
      "loss": 0.0123,
      "step": 650
    },
    {
      "epoch": 0.7391763463569165,
      "grad_norm": 0.031244030222296715,
      "learning_rate": 2.7183924904664125e-05,
      "loss": 0.0087,
      "step": 700
    },
    {
      "epoch": 0.791974656810982,
      "grad_norm": 0.028063887730240822,
      "learning_rate": 2.6743913171017896e-05,
      "loss": 0.0122,
      "step": 750
    },
    {
      "epoch": 0.8447729672650475,
      "grad_norm": 0.025719981640577316,
      "learning_rate": 2.6303901437371663e-05,
      "loss": 0.0077,
      "step": 800
    },
    {
      "epoch": 0.8447729672650475,
      "eval_accuracy": 0.9994059994059994,
      "eval_f1": 0.9994179278230501,
      "eval_loss": 0.004702265374362469,
      "eval_precision": 0.9988365328679465,
      "eval_recall": 1.0,
      "eval_runtime": 99.4766,
      "eval_samples_per_second": 33.847,
      "eval_steps_per_second": 2.121,
      "step": 800
    },
    {
      "epoch": 0.8975712777191129,
      "grad_norm": 0.02354113757610321,
      "learning_rate": 2.5863889703725433e-05,
      "loss": 0.0058,
      "step": 850
    },
    {
      "epoch": 0.9503695881731784,
      "grad_norm": 0.02310008369386196,
      "learning_rate": 2.5423877970079204e-05,
      "loss": 0.0056,
      "step": 900
    },
    {
      "epoch": 1.0031678986272439,
      "grad_norm": 0.019235238432884216,
      "learning_rate": 2.498386623643297e-05,
      "loss": 0.0106,
      "step": 950
    },
    {
      "epoch": 1.0559662090813093,
      "grad_norm": 208.1472930908203,
      "learning_rate": 2.454385450278674e-05,
      "loss": 0.0124,
      "step": 1000
    },
    {
      "epoch": 1.0559662090813093,
      "eval_accuracy": 0.9967329967329968,
      "eval_f1": 0.9968069666182874,
      "eval_loss": 0.016226448118686676,
      "eval_precision": 0.9936342592592593,
      "eval_recall": 1.0,
      "eval_runtime": 88.1246,
      "eval_samples_per_second": 38.207,
      "eval_steps_per_second": 2.394,
      "step": 1000
    },
    {
      "epoch": 1.1087645195353748,
      "grad_norm": 0.01713796705007553,
      "learning_rate": 2.4103842769140512e-05,
      "loss": 0.0012,
      "step": 1050
    },
    {
      "epoch": 1.1615628299894403,
      "grad_norm": 0.015752457082271576,
      "learning_rate": 2.366383103549428e-05,
      "loss": 0.001,
      "step": 1100
    },
    {
      "epoch": 1.2143611404435057,
      "grad_norm": 0.014375035651028156,
      "learning_rate": 2.322381930184805e-05,
      "loss": 0.0054,
      "step": 1150
    },
    {
      "epoch": 1.2671594508975712,
      "grad_norm": 0.014459795318543911,
      "learning_rate": 2.278380756820182e-05,
      "loss": 0.0009,
      "step": 1200
    },
    {
      "epoch": 1.2671594508975712,
      "eval_accuracy": 0.9997029997029997,
      "eval_f1": 0.9997088791848617,
      "eval_loss": 0.0029172594659030437,
      "eval_precision": 0.9994179278230501,
      "eval_recall": 1.0,
      "eval_runtime": 70.0694,
      "eval_samples_per_second": 48.052,
      "eval_steps_per_second": 3.011,
      "step": 1200
    },
    {
      "epoch": 1.3199577613516367,
      "grad_norm": 0.012884082272648811,
      "learning_rate": 2.2343795834555587e-05,
      "loss": 0.0008,
      "step": 1250
    },
    {
      "epoch": 1.3727560718057021,
      "grad_norm": 0.013439378701150417,
      "learning_rate": 2.1903784100909357e-05,
      "loss": 0.0127,
      "step": 1300
    },
    {
      "epoch": 1.4255543822597676,
      "grad_norm": 0.014692062512040138,
      "learning_rate": 2.1463772367263128e-05,
      "loss": 0.0101,
      "step": 1350
    },
    {
      "epoch": 1.478352692713833,
      "grad_norm": 0.012950174510478973,
      "learning_rate": 2.10237606336169e-05,
      "loss": 0.0054,
      "step": 1400
    },
    {
      "epoch": 1.478352692713833,
      "eval_accuracy": 0.9997029997029997,
      "eval_f1": 0.9997088791848617,
      "eval_loss": 0.002878110622987151,
      "eval_precision": 0.9994179278230501,
      "eval_recall": 1.0,
      "eval_runtime": 82.6217,
      "eval_samples_per_second": 40.752,
      "eval_steps_per_second": 2.554,
      "step": 1400
    },
    {
      "epoch": 1.5311510031678988,
      "grad_norm": 0.01537719089537859,
      "learning_rate": 2.0583748899970665e-05,
      "loss": 0.0053,
      "step": 1450
    },
    {
      "epoch": 1.583949313621964,
      "grad_norm": 0.01542325783520937,
      "learning_rate": 2.0143737166324436e-05,
      "loss": 0.0053,
      "step": 1500
    },
    {
      "epoch": 1.6367476240760297,
      "grad_norm": 0.012001622468233109,
      "learning_rate": 1.9703725432678206e-05,
      "loss": 0.0061,
      "step": 1550
    },
    {
      "epoch": 1.689545934530095,
      "grad_norm": 0.015623683109879494,
      "learning_rate": 1.9263713699031974e-05,
      "loss": 0.0007,
      "step": 1600
    },
    {
      "epoch": 1.689545934530095,
      "eval_accuracy": 0.9994059994059994,
      "eval_f1": 0.9994179278230501,
      "eval_loss": 0.003968308679759502,
      "eval_precision": 0.9988365328679465,
      "eval_recall": 1.0,
      "eval_runtime": 73.337,
      "eval_samples_per_second": 45.911,
      "eval_steps_per_second": 2.877,
      "step": 1600
    },
    {
      "epoch": 1.7423442449841606,
      "grad_norm": 0.009684963151812553,
      "learning_rate": 1.8823701965385744e-05,
      "loss": 0.0024,
      "step": 1650
    },
    {
      "epoch": 1.7951425554382259,
      "grad_norm": 0.010225261561572552,
      "learning_rate": 1.8383690231739514e-05,
      "loss": 0.0055,
      "step": 1700
    },
    {
      "epoch": 1.8479408658922916,
      "grad_norm": 0.00971356499940157,
      "learning_rate": 1.794367849809328e-05,
      "loss": 0.0006,
      "step": 1750
    },
    {
      "epoch": 1.9007391763463568,
      "grad_norm": 0.00992420595139265,
      "learning_rate": 1.7503666764447052e-05,
      "loss": 0.0053,
      "step": 1800
    },
    {
      "epoch": 1.9007391763463568,
      "eval_accuracy": 0.9997029997029997,
      "eval_f1": 0.9997088791848617,
      "eval_loss": 0.0027877786196768284,
      "eval_precision": 0.9994179278230501,
      "eval_recall": 1.0,
      "eval_runtime": 91.0379,
      "eval_samples_per_second": 36.985,
      "eval_steps_per_second": 2.318,
      "step": 1800
    },
    {
      "epoch": 1.9535374868004225,
      "grad_norm": 0.009032746776938438,
      "learning_rate": 1.7063655030800823e-05,
      "loss": 0.0005,
      "step": 1850
    },
    {
      "epoch": 2.0063357972544877,
      "grad_norm": 0.009780782274901867,
      "learning_rate": 1.662364329715459e-05,
      "loss": 0.0053,
      "step": 1900
    },
    {
      "epoch": 2.0591341077085534,
      "grad_norm": 0.00858134776353836,
      "learning_rate": 1.618363156350836e-05,
      "loss": 0.0005,
      "step": 1950
    },
    {
      "epoch": 2.1119324181626187,
      "grad_norm": 0.00789894163608551,
      "learning_rate": 1.574361982986213e-05,
      "loss": 0.0005,
      "step": 2000
    },
    {
      "epoch": 2.1119324181626187,
      "eval_accuracy": 0.9997029997029997,
      "eval_f1": 0.9997088791848617,
      "eval_loss": 0.0027642312925308943,
      "eval_precision": 0.9994179278230501,
      "eval_recall": 1.0,
      "eval_runtime": 74.3591,
      "eval_samples_per_second": 45.28,
      "eval_steps_per_second": 2.838,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 3788,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0005
      },
      "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": 458747506194432.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}