{
  "best_global_step": 682,
  "best_metric": 0.65,
  "best_model_checkpoint": "./roberta-base-normclsf-wtrainer_v05/checkpoint-682",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 682,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02932551319648094,
      "grad_norm": 4.605538845062256,
      "learning_rate": 1.989442815249267e-05,
      "loss": 0.8748870849609375,
      "step": 10
    },
    {
      "epoch": 0.05865102639296188,
      "grad_norm": 8.252500534057617,
      "learning_rate": 1.9777126099706747e-05,
      "loss": 0.7471119880676269,
      "step": 20
    },
    {
      "epoch": 0.08797653958944282,
      "grad_norm": 2.074993371963501,
      "learning_rate": 1.9659824046920824e-05,
      "loss": 0.4594985008239746,
      "step": 30
    },
    {
      "epoch": 0.11730205278592376,
      "grad_norm": 3.0788521766662598,
      "learning_rate": 1.95425219941349e-05,
      "loss": 0.5202928066253663,
      "step": 40
    },
    {
      "epoch": 0.1466275659824047,
      "grad_norm": 4.378216743469238,
      "learning_rate": 1.9425219941348975e-05,
      "loss": 0.5494800567626953,
      "step": 50
    },
    {
      "epoch": 0.17595307917888564,
      "grad_norm": 14.331672668457031,
      "learning_rate": 1.9307917888563052e-05,
      "loss": 0.4242433547973633,
      "step": 60
    },
    {
      "epoch": 0.20527859237536658,
      "grad_norm": 4.309084415435791,
      "learning_rate": 1.9190615835777126e-05,
      "loss": 0.4079638957977295,
      "step": 70
    },
    {
      "epoch": 0.23460410557184752,
      "grad_norm": 6.517351150512695,
      "learning_rate": 1.9073313782991203e-05,
      "loss": 0.43054375648498533,
      "step": 80
    },
    {
      "epoch": 0.26392961876832843,
      "grad_norm": 7.656932830810547,
      "learning_rate": 1.895601173020528e-05,
      "loss": 0.41449365615844724,
      "step": 90
    },
    {
      "epoch": 0.2932551319648094,
      "grad_norm": 8.48462963104248,
      "learning_rate": 1.8838709677419354e-05,
      "loss": 0.4581272125244141,
      "step": 100
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 5.62518835067749,
      "learning_rate": 1.872140762463343e-05,
      "loss": 0.45809006690979004,
      "step": 110
    },
    {
      "epoch": 0.3519061583577713,
      "grad_norm": 6.546260833740234,
      "learning_rate": 1.860410557184751e-05,
      "loss": 0.5094863891601562,
      "step": 120
    },
    {
      "epoch": 0.3812316715542522,
      "grad_norm": 4.513675689697266,
      "learning_rate": 1.8486803519061586e-05,
      "loss": 0.33855314254760743,
      "step": 130
    },
    {
      "epoch": 0.41055718475073316,
      "grad_norm": 12.067423820495605,
      "learning_rate": 1.836950146627566e-05,
      "loss": 0.350540018081665,
      "step": 140
    },
    {
      "epoch": 0.4398826979472141,
      "grad_norm": 0.5563814043998718,
      "learning_rate": 1.8252199413489736e-05,
      "loss": 0.2575559139251709,
      "step": 150
    },
    {
      "epoch": 0.46920821114369504,
      "grad_norm": 3.461552143096924,
      "learning_rate": 1.8134897360703814e-05,
      "loss": 0.19520399570465088,
      "step": 160
    },
    {
      "epoch": 0.49853372434017595,
      "grad_norm": 8.978960037231445,
      "learning_rate": 1.801759530791789e-05,
      "loss": 0.40044546127319336,
      "step": 170
    },
    {
      "epoch": 0.5278592375366569,
      "grad_norm": 11.35211181640625,
      "learning_rate": 1.7900293255131968e-05,
      "loss": 0.41159982681274415,
      "step": 180
    },
    {
      "epoch": 0.5571847507331378,
      "grad_norm": 9.079242706298828,
      "learning_rate": 1.778299120234604e-05,
      "loss": 0.25739483833312987,
      "step": 190
    },
    {
      "epoch": 0.5865102639296188,
      "grad_norm": 6.320888042449951,
      "learning_rate": 1.766568914956012e-05,
      "loss": 0.427862548828125,
      "step": 200
    },
    {
      "epoch": 0.6158357771260997,
      "grad_norm": 4.825621604919434,
      "learning_rate": 1.7548387096774196e-05,
      "loss": 0.363921594619751,
      "step": 210
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 4.21811580657959,
      "learning_rate": 1.7431085043988273e-05,
      "loss": 0.2609383583068848,
      "step": 220
    },
    {
      "epoch": 0.6744868035190615,
      "grad_norm": 10.078695297241211,
      "learning_rate": 1.7313782991202347e-05,
      "loss": 0.3769556522369385,
      "step": 230
    },
    {
      "epoch": 0.7038123167155426,
      "grad_norm": 13.502087593078613,
      "learning_rate": 1.7196480938416424e-05,
      "loss": 0.4350841999053955,
      "step": 240
    },
    {
      "epoch": 0.7331378299120235,
      "grad_norm": 11.125184059143066,
      "learning_rate": 1.70791788856305e-05,
      "loss": 0.2560503721237183,
      "step": 250
    },
    {
      "epoch": 0.7624633431085044,
      "grad_norm": 8.523448944091797,
      "learning_rate": 1.6961876832844578e-05,
      "loss": 0.33950209617614746,
      "step": 260
    },
    {
      "epoch": 0.7917888563049853,
      "grad_norm": 9.814420700073242,
      "learning_rate": 1.6844574780058652e-05,
      "loss": 0.31357336044311523,
      "step": 270
    },
    {
      "epoch": 0.8211143695014663,
      "grad_norm": 7.434709072113037,
      "learning_rate": 1.672727272727273e-05,
      "loss": 0.4336878776550293,
      "step": 280
    },
    {
      "epoch": 0.8504398826979472,
      "grad_norm": 5.025743007659912,
      "learning_rate": 1.6609970674486803e-05,
      "loss": 0.27936711311340334,
      "step": 290
    },
    {
      "epoch": 0.8797653958944281,
      "grad_norm": 7.470189094543457,
      "learning_rate": 1.649266862170088e-05,
      "loss": 0.3076458930969238,
      "step": 300
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 7.557694911956787,
      "learning_rate": 1.6375366568914957e-05,
      "loss": 0.39769227504730226,
      "step": 310
    },
    {
      "epoch": 0.9384164222873901,
      "grad_norm": 9.136332511901855,
      "learning_rate": 1.6258064516129034e-05,
      "loss": 0.3063544988632202,
      "step": 320
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 5.551280975341797,
      "learning_rate": 1.6140762463343108e-05,
      "loss": 0.21903605461120607,
      "step": 330
    },
    {
      "epoch": 0.9970674486803519,
      "grad_norm": 6.700067043304443,
      "learning_rate": 1.6023460410557185e-05,
      "loss": 0.30389995574951173,
      "step": 340
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9427627958172813,
      "eval_f1": 0.6,
      "eval_loss": 0.38300660252571106,
      "eval_macro_f1": 0.784588026081802,
      "eval_precision": 0.7684729064039408,
      "eval_recall": 0.4921135646687697,
      "eval_runtime": 28.0518,
      "eval_samples_per_second": 129.546,
      "eval_steps_per_second": 4.064,
      "step": 341
    },
    {
      "epoch": 1.0263929618768328,
      "grad_norm": 0.2962384521961212,
      "learning_rate": 1.5906158357771262e-05,
      "loss": 0.19621171951293945,
      "step": 350
    },
    {
      "epoch": 1.0557184750733137,
      "grad_norm": 10.040809631347656,
      "learning_rate": 1.578885630498534e-05,
      "loss": 0.3155526161193848,
      "step": 360
    },
    {
      "epoch": 1.0850439882697946,
      "grad_norm": 6.042061805725098,
      "learning_rate": 1.5671554252199413e-05,
      "loss": 0.18413875102996827,
      "step": 370
    },
    {
      "epoch": 1.1143695014662756,
      "grad_norm": 15.292718887329102,
      "learning_rate": 1.555425219941349e-05,
      "loss": 0.2554365396499634,
      "step": 380
    },
    {
      "epoch": 1.1436950146627567,
      "grad_norm": 10.669240951538086,
      "learning_rate": 1.5436950146627568e-05,
      "loss": 0.28005428314208985,
      "step": 390
    },
    {
      "epoch": 1.1730205278592376,
      "grad_norm": 10.792296409606934,
      "learning_rate": 1.5319648093841645e-05,
      "loss": 0.2731830596923828,
      "step": 400
    },
    {
      "epoch": 1.2023460410557185,
      "grad_norm": 8.150186538696289,
      "learning_rate": 1.520234604105572e-05,
      "loss": 0.209375,
      "step": 410
    },
    {
      "epoch": 1.2316715542521994,
      "grad_norm": 2.4280498027801514,
      "learning_rate": 1.5085043988269796e-05,
      "loss": 0.24350173473358155,
      "step": 420
    },
    {
      "epoch": 1.2609970674486803,
      "grad_norm": 8.654495239257812,
      "learning_rate": 1.4967741935483873e-05,
      "loss": 0.20527310371398927,
      "step": 430
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 13.059834480285645,
      "learning_rate": 1.485043988269795e-05,
      "loss": 0.2325817346572876,
      "step": 440
    },
    {
      "epoch": 1.3196480938416422,
      "grad_norm": 15.611944198608398,
      "learning_rate": 1.4733137829912025e-05,
      "loss": 0.28686368465423584,
      "step": 450
    },
    {
      "epoch": 1.3489736070381233,
      "grad_norm": 8.841765403747559,
      "learning_rate": 1.4615835777126102e-05,
      "loss": 0.2671750783920288,
      "step": 460
    },
    {
      "epoch": 1.3782991202346042,
      "grad_norm": 2.2132349014282227,
      "learning_rate": 1.4498533724340178e-05,
      "loss": 0.4045552253723145,
      "step": 470
    },
    {
      "epoch": 1.4076246334310851,
      "grad_norm": 4.185707092285156,
      "learning_rate": 1.4381231671554255e-05,
      "loss": 0.28984100818634034,
      "step": 480
    },
    {
      "epoch": 1.436950146627566,
      "grad_norm": 3.6457879543304443,
      "learning_rate": 1.426392961876833e-05,
      "loss": 0.1747618794441223,
      "step": 490
    },
    {
      "epoch": 1.466275659824047,
      "grad_norm": 16.844175338745117,
      "learning_rate": 1.4146627565982404e-05,
      "loss": 0.2803473949432373,
      "step": 500
    },
    {
      "epoch": 1.4956011730205279,
      "grad_norm": 10.1566743850708,
      "learning_rate": 1.4029325513196481e-05,
      "loss": 0.3340228796005249,
      "step": 510
    },
    {
      "epoch": 1.5249266862170088,
      "grad_norm": 11.69490909576416,
      "learning_rate": 1.3912023460410557e-05,
      "loss": 0.2391693115234375,
      "step": 520
    },
    {
      "epoch": 1.5542521994134897,
      "grad_norm": 13.803505897521973,
      "learning_rate": 1.3794721407624634e-05,
      "loss": 0.25829625129699707,
      "step": 530
    },
    {
      "epoch": 1.5835777126099706,
      "grad_norm": 10.649820327758789,
      "learning_rate": 1.367741935483871e-05,
      "loss": 0.3253736734390259,
      "step": 540
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 7.087320327758789,
      "learning_rate": 1.3560117302052787e-05,
      "loss": 0.26409015655517576,
      "step": 550
    },
    {
      "epoch": 1.6422287390029324,
      "grad_norm": 1.1870570182800293,
      "learning_rate": 1.3442815249266864e-05,
      "loss": 0.2954803705215454,
      "step": 560
    },
    {
      "epoch": 1.6715542521994133,
      "grad_norm": 2.9404983520507812,
      "learning_rate": 1.3325513196480939e-05,
      "loss": 0.2627613306045532,
      "step": 570
    },
    {
      "epoch": 1.7008797653958945,
      "grad_norm": 15.945968627929688,
      "learning_rate": 1.3208211143695016e-05,
      "loss": 0.30292611122131347,
      "step": 580
    },
    {
      "epoch": 1.7302052785923754,
      "grad_norm": 2.5892066955566406,
      "learning_rate": 1.3090909090909092e-05,
      "loss": 0.24233815670013428,
      "step": 590
    },
    {
      "epoch": 1.7595307917888563,
      "grad_norm": 6.323796272277832,
      "learning_rate": 1.2973607038123169e-05,
      "loss": 0.28550622463226316,
      "step": 600
    },
    {
      "epoch": 1.7888563049853372,
      "grad_norm": 15.06285285949707,
      "learning_rate": 1.2856304985337244e-05,
      "loss": 0.31177420616149903,
      "step": 610
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 26.516773223876953,
      "learning_rate": 1.2739002932551321e-05,
      "loss": 0.32825593948364257,
      "step": 620
    },
    {
      "epoch": 1.8475073313782993,
      "grad_norm": 4.588010787963867,
      "learning_rate": 1.2621700879765397e-05,
      "loss": 0.2520775079727173,
      "step": 630
    },
    {
      "epoch": 1.8768328445747802,
      "grad_norm": 11.690654754638672,
      "learning_rate": 1.2504398826979474e-05,
      "loss": 0.37928569316864014,
      "step": 640
    },
    {
      "epoch": 1.906158357771261,
      "grad_norm": 7.3419976234436035,
      "learning_rate": 1.238709677419355e-05,
      "loss": 0.30172431468963623,
      "step": 650
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 8.187894821166992,
      "learning_rate": 1.2269794721407627e-05,
      "loss": 0.29463934898376465,
      "step": 660
    },
    {
      "epoch": 1.964809384164223,
      "grad_norm": 15.681519508361816,
      "learning_rate": 1.2152492668621702e-05,
      "loss": 0.3064812898635864,
      "step": 670
    },
    {
      "epoch": 1.9941348973607038,
      "grad_norm": 7.368335723876953,
      "learning_rate": 1.203519061583578e-05,
      "loss": 0.3303363561630249,
      "step": 680
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9383599339570721,
      "eval_f1": 0.65,
      "eval_loss": 0.32171452045440674,
      "eval_macro_f1": 0.8081019915509957,
      "eval_precision": 0.6439628482972136,
      "eval_recall": 0.6561514195583596,
      "eval_runtime": 28.7369,
      "eval_samples_per_second": 126.458,
      "eval_steps_per_second": 3.967,
      "step": 682
    }
  ],
  "logging_steps": 10,
  "max_steps": 1705,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "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": 2868173614479360.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}