{
  "best_global_step": 1400,
  "best_metric": 0.6459359532496649,
  "best_model_checkpoint": "graphcodebert-swa-from-epoch-1/checkpoint-1400",
  "epoch": 2.8629856850715747,
  "eval_steps": 100,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010224948875255624,
      "grad_norm": 2.4707133769989014,
      "learning_rate": 2.0512820512820512e-08,
      "loss": 0.8431,
      "step": 5
    },
    {
      "epoch": 0.02044989775051125,
      "grad_norm": 3.114851951599121,
      "learning_rate": 4.615384615384615e-08,
      "loss": 0.844,
      "step": 10
    },
    {
      "epoch": 0.03067484662576687,
      "grad_norm": 2.2256007194519043,
      "learning_rate": 7.179487179487178e-08,
      "loss": 0.847,
      "step": 15
    },
    {
      "epoch": 0.0408997955010225,
      "grad_norm": 2.5343081951141357,
      "learning_rate": 9.743589743589743e-08,
      "loss": 0.8492,
      "step": 20
    },
    {
      "epoch": 0.05112474437627812,
      "grad_norm": 3.1964163780212402,
      "learning_rate": 1.2307692307692308e-07,
      "loss": 0.8475,
      "step": 25
    },
    {
      "epoch": 0.06134969325153374,
      "grad_norm": 2.0466485023498535,
      "learning_rate": 1.4871794871794872e-07,
      "loss": 0.8445,
      "step": 30
    },
    {
      "epoch": 0.07157464212678936,
      "grad_norm": 2.164569139480591,
      "learning_rate": 1.7435897435897435e-07,
      "loss": 0.8452,
      "step": 35
    },
    {
      "epoch": 0.081799591002045,
      "grad_norm": 2.56343150138855,
      "learning_rate": 2e-07,
      "loss": 0.8473,
      "step": 40
    },
    {
      "epoch": 0.09202453987730061,
      "grad_norm": 2.5742437839508057,
      "learning_rate": 2.2564102564102563e-07,
      "loss": 0.848,
      "step": 45
    },
    {
      "epoch": 0.10224948875255624,
      "grad_norm": 2.587480306625366,
      "learning_rate": 2.5128205128205126e-07,
      "loss": 0.8409,
      "step": 50
    },
    {
      "epoch": 0.11247443762781185,
      "grad_norm": 2.5737764835357666,
      "learning_rate": 2.7692307692307693e-07,
      "loss": 0.8471,
      "step": 55
    },
    {
      "epoch": 0.12269938650306748,
      "grad_norm": 3.044358730316162,
      "learning_rate": 3.0256410256410254e-07,
      "loss": 0.8448,
      "step": 60
    },
    {
      "epoch": 0.1329243353783231,
      "grad_norm": 2.326373815536499,
      "learning_rate": 3.282051282051282e-07,
      "loss": 0.8517,
      "step": 65
    },
    {
      "epoch": 0.14314928425357873,
      "grad_norm": 2.267547607421875,
      "learning_rate": 3.5384615384615386e-07,
      "loss": 0.8387,
      "step": 70
    },
    {
      "epoch": 0.15337423312883436,
      "grad_norm": 2.609232187271118,
      "learning_rate": 3.7948717948717947e-07,
      "loss": 0.841,
      "step": 75
    },
    {
      "epoch": 0.16359918200409,
      "grad_norm": 2.9532523155212402,
      "learning_rate": 4.0512820512820514e-07,
      "loss": 0.8509,
      "step": 80
    },
    {
      "epoch": 0.1738241308793456,
      "grad_norm": 3.002154588699341,
      "learning_rate": 4.307692307692308e-07,
      "loss": 0.8482,
      "step": 85
    },
    {
      "epoch": 0.18404907975460122,
      "grad_norm": 2.701613187789917,
      "learning_rate": 4.5641025641025636e-07,
      "loss": 0.8422,
      "step": 90
    },
    {
      "epoch": 0.19427402862985685,
      "grad_norm": 2.7430365085601807,
      "learning_rate": 4.82051282051282e-07,
      "loss": 0.846,
      "step": 95
    },
    {
      "epoch": 0.20449897750511248,
      "grad_norm": 2.8101418018341064,
      "learning_rate": 5.076923076923076e-07,
      "loss": 0.8444,
      "step": 100
    },
    {
      "epoch": 0.20449897750511248,
      "eval_accuracy": 0.52033,
      "eval_loss": 0.6922348141670227,
      "eval_macro_f1": 0.4427650399783254,
      "eval_precision": 0.6036606007378691,
      "eval_recall": 0.5386742448919869,
      "eval_runtime": 80.6812,
      "eval_samples_per_second": 1239.446,
      "eval_steps_per_second": 0.607,
      "step": 100
    },
    {
      "epoch": 0.2147239263803681,
      "grad_norm": 2.5835089683532715,
      "learning_rate": 5.333333333333333e-07,
      "loss": 0.8437,
      "step": 105
    },
    {
      "epoch": 0.2249488752556237,
      "grad_norm": 2.7237253189086914,
      "learning_rate": 5.58974358974359e-07,
      "loss": 0.8431,
      "step": 110
    },
    {
      "epoch": 0.23517382413087934,
      "grad_norm": 2.4648072719573975,
      "learning_rate": 5.846153846153847e-07,
      "loss": 0.8399,
      "step": 115
    },
    {
      "epoch": 0.24539877300613497,
      "grad_norm": 2.7011852264404297,
      "learning_rate": 6.102564102564103e-07,
      "loss": 0.8409,
      "step": 120
    },
    {
      "epoch": 0.2556237218813906,
      "grad_norm": 2.3170969486236572,
      "learning_rate": 6.358974358974358e-07,
      "loss": 0.8361,
      "step": 125
    },
    {
      "epoch": 0.2658486707566462,
      "grad_norm": 2.517194986343384,
      "learning_rate": 6.615384615384615e-07,
      "loss": 0.839,
      "step": 130
    },
    {
      "epoch": 0.27607361963190186,
      "grad_norm": 2.5092124938964844,
      "learning_rate": 6.871794871794871e-07,
      "loss": 0.8438,
      "step": 135
    },
    {
      "epoch": 0.28629856850715746,
      "grad_norm": 2.3993237018585205,
      "learning_rate": 7.128205128205128e-07,
      "loss": 0.8349,
      "step": 140
    },
    {
      "epoch": 0.2965235173824131,
      "grad_norm": 2.1388165950775146,
      "learning_rate": 7.384615384615384e-07,
      "loss": 0.8363,
      "step": 145
    },
    {
      "epoch": 0.3067484662576687,
      "grad_norm": 1.8425891399383545,
      "learning_rate": 7.64102564102564e-07,
      "loss": 0.8325,
      "step": 150
    },
    {
      "epoch": 0.3169734151329243,
      "grad_norm": 1.8665552139282227,
      "learning_rate": 7.897435897435897e-07,
      "loss": 0.835,
      "step": 155
    },
    {
      "epoch": 0.32719836400818,
      "grad_norm": 1.8765455484390259,
      "learning_rate": 8.153846153846154e-07,
      "loss": 0.8328,
      "step": 160
    },
    {
      "epoch": 0.3374233128834356,
      "grad_norm": 2.640779495239258,
      "learning_rate": 8.41025641025641e-07,
      "loss": 0.8388,
      "step": 165
    },
    {
      "epoch": 0.3476482617586912,
      "grad_norm": 2.174116373062134,
      "learning_rate": 8.666666666666667e-07,
      "loss": 0.8336,
      "step": 170
    },
    {
      "epoch": 0.35787321063394684,
      "grad_norm": 1.8411178588867188,
      "learning_rate": 8.923076923076923e-07,
      "loss": 0.8384,
      "step": 175
    },
    {
      "epoch": 0.36809815950920244,
      "grad_norm": 2.3652143478393555,
      "learning_rate": 9.179487179487179e-07,
      "loss": 0.8318,
      "step": 180
    },
    {
      "epoch": 0.3783231083844581,
      "grad_norm": 1.9870903491973877,
      "learning_rate": 9.435897435897435e-07,
      "loss": 0.8306,
      "step": 185
    },
    {
      "epoch": 0.3885480572597137,
      "grad_norm": 2.458887815475464,
      "learning_rate": 9.692307692307691e-07,
      "loss": 0.8342,
      "step": 190
    },
    {
      "epoch": 0.3987730061349693,
      "grad_norm": 1.9105890989303589,
      "learning_rate": 9.948717948717949e-07,
      "loss": 0.8301,
      "step": 195
    },
    {
      "epoch": 0.40899795501022496,
      "grad_norm": 2.04896879196167,
      "learning_rate": 9.999490793845076e-07,
      "loss": 0.8291,
      "step": 200
    },
    {
      "epoch": 0.40899795501022496,
      "eval_accuracy": 0.52697,
      "eval_loss": 0.6913915872573853,
      "eval_macro_f1": 0.4511625248903547,
      "eval_precision": 0.6198512746424523,
      "eval_recall": 0.5452618609595298,
      "eval_runtime": 80.6395,
      "eval_samples_per_second": 1240.088,
      "eval_steps_per_second": 0.608,
      "step": 200
    },
    {
      "epoch": 0.41922290388548056,
      "grad_norm": 2.394630193710327,
      "learning_rate": 9.997422321595486e-07,
      "loss": 0.8311,
      "step": 205
    },
    {
      "epoch": 0.4294478527607362,
      "grad_norm": 1.7013665437698364,
      "learning_rate": 9.993763415653074e-07,
      "loss": 0.8264,
      "step": 210
    },
    {
      "epoch": 0.4396728016359918,
      "grad_norm": 2.1158103942871094,
      "learning_rate": 9.988515240467613e-07,
      "loss": 0.8262,
      "step": 215
    },
    {
      "epoch": 0.4498977505112474,
      "grad_norm": 1.5985370874404907,
      "learning_rate": 9.981679466275095e-07,
      "loss": 0.8296,
      "step": 220
    },
    {
      "epoch": 0.4601226993865031,
      "grad_norm": 2.0426042079925537,
      "learning_rate": 9.973258268566182e-07,
      "loss": 0.8233,
      "step": 225
    },
    {
      "epoch": 0.4703476482617587,
      "grad_norm": 1.7411834001541138,
      "learning_rate": 9.963254327393853e-07,
      "loss": 0.8269,
      "step": 230
    },
    {
      "epoch": 0.48057259713701433,
      "grad_norm": 2.1182405948638916,
      "learning_rate": 9.95167082652047e-07,
      "loss": 0.8247,
      "step": 235
    },
    {
      "epoch": 0.49079754601226994,
      "grad_norm": 2.0239953994750977,
      "learning_rate": 9.938511452404547e-07,
      "loss": 0.8308,
      "step": 240
    },
    {
      "epoch": 0.5010224948875256,
      "grad_norm": 2.366060495376587,
      "learning_rate": 9.923780393027534e-07,
      "loss": 0.8205,
      "step": 245
    },
    {
      "epoch": 0.5112474437627812,
      "grad_norm": 1.848169207572937,
      "learning_rate": 9.907482336560982e-07,
      "loss": 0.825,
      "step": 250
    },
    {
      "epoch": 0.5214723926380368,
      "grad_norm": 1.8216668367385864,
      "learning_rate": 9.889622469874535e-07,
      "loss": 0.8271,
      "step": 255
    },
    {
      "epoch": 0.5316973415132924,
      "grad_norm": 1.507730484008789,
      "learning_rate": 9.8702064768852e-07,
      "loss": 0.8147,
      "step": 260
    },
    {
      "epoch": 0.5419222903885481,
      "grad_norm": 1.7608263492584229,
      "learning_rate": 9.849240536748438e-07,
      "loss": 0.8221,
      "step": 265
    },
    {
      "epoch": 0.5521472392638037,
      "grad_norm": 2.203326940536499,
      "learning_rate": 9.826731321891641e-07,
      "loss": 0.8292,
      "step": 270
    },
    {
      "epoch": 0.5623721881390593,
      "grad_norm": 1.9529740810394287,
      "learning_rate": 9.802685995890632e-07,
      "loss": 0.8228,
      "step": 275
    },
    {
      "epoch": 0.5725971370143149,
      "grad_norm": 1.6214399337768555,
      "learning_rate": 9.777112211189841e-07,
      "loss": 0.8149,
      "step": 280
    },
    {
      "epoch": 0.5828220858895705,
      "grad_norm": 2.07482647895813,
      "learning_rate": 9.750018106666924e-07,
      "loss": 0.8143,
      "step": 285
    },
    {
      "epoch": 0.5930470347648262,
      "grad_norm": 1.7083203792572021,
      "learning_rate": 9.721412305042538e-07,
      "loss": 0.8188,
      "step": 290
    },
    {
      "epoch": 0.6032719836400818,
      "grad_norm": 2.0022943019866943,
      "learning_rate": 9.69130391013617e-07,
      "loss": 0.8195,
      "step": 295
    },
    {
      "epoch": 0.6134969325153374,
      "grad_norm": 1.5799461603164673,
      "learning_rate": 9.659702503968834e-07,
      "loss": 0.8146,
      "step": 300
    },
    {
      "epoch": 0.6134969325153374,
      "eval_accuracy": 0.55052,
      "eval_loss": 0.6896406412124634,
      "eval_macro_f1": 0.49869783315905847,
      "eval_precision": 0.6264643684302231,
      "eval_recall": 0.5665461014402418,
      "eval_runtime": 80.6145,
      "eval_samples_per_second": 1240.472,
      "eval_steps_per_second": 0.608,
      "step": 300
    },
    {
      "epoch": 0.623721881390593,
      "grad_norm": 1.9373347759246826,
      "learning_rate": 9.626618143713586e-07,
      "loss": 0.8166,
      "step": 305
    },
    {
      "epoch": 0.6339468302658486,
      "grad_norm": 1.6276922225952148,
      "learning_rate": 9.592061358494813e-07,
      "loss": 0.8176,
      "step": 310
    },
    {
      "epoch": 0.6441717791411042,
      "grad_norm": 1.9373250007629395,
      "learning_rate": 9.556043146037337e-07,
      "loss": 0.8168,
      "step": 315
    },
    {
      "epoch": 0.65439672801636,
      "grad_norm": 1.320465087890625,
      "learning_rate": 9.518574969166391e-07,
      "loss": 0.8101,
      "step": 320
    },
    {
      "epoch": 0.6646216768916156,
      "grad_norm": 1.8596330881118774,
      "learning_rate": 9.47966875215954e-07,
      "loss": 0.8167,
      "step": 325
    },
    {
      "epoch": 0.6748466257668712,
      "grad_norm": 1.304662823677063,
      "learning_rate": 9.439336876951793e-07,
      "loss": 0.815,
      "step": 330
    },
    {
      "epoch": 0.6850715746421268,
      "grad_norm": 1.8063029050827026,
      "learning_rate": 9.397592179195033e-07,
      "loss": 0.8121,
      "step": 335
    },
    {
      "epoch": 0.6952965235173824,
      "grad_norm": 1.7432739734649658,
      "learning_rate": 9.354447944173059e-07,
      "loss": 0.8104,
      "step": 340
    },
    {
      "epoch": 0.7055214723926381,
      "grad_norm": 1.4523797035217285,
      "learning_rate": 9.309917902573533e-07,
      "loss": 0.8098,
      "step": 345
    },
    {
      "epoch": 0.7157464212678937,
      "grad_norm": 1.681409478187561,
      "learning_rate": 9.264016226118188e-07,
      "loss": 0.8107,
      "step": 350
    },
    {
      "epoch": 0.7259713701431493,
      "grad_norm": 1.5168694257736206,
      "learning_rate": 9.216757523052652e-07,
      "loss": 0.8085,
      "step": 355
    },
    {
      "epoch": 0.7361963190184049,
      "grad_norm": 1.2200194597244263,
      "learning_rate": 9.168156833497371e-07,
      "loss": 0.8109,
      "step": 360
    },
    {
      "epoch": 0.7464212678936605,
      "grad_norm": 1.2745580673217773,
      "learning_rate": 9.118229624661078e-07,
      "loss": 0.8096,
      "step": 365
    },
    {
      "epoch": 0.7566462167689162,
      "grad_norm": 1.8339142799377441,
      "learning_rate": 9.066991785918333e-07,
      "loss": 0.808,
      "step": 370
    },
    {
      "epoch": 0.7668711656441718,
      "grad_norm": 1.2315114736557007,
      "learning_rate": 9.01445962375273e-07,
      "loss": 0.805,
      "step": 375
    },
    {
      "epoch": 0.7770961145194274,
      "grad_norm": 1.3081412315368652,
      "learning_rate": 8.960649856567333e-07,
      "loss": 0.8066,
      "step": 380
    },
    {
      "epoch": 0.787321063394683,
      "grad_norm": 1.5145998001098633,
      "learning_rate": 8.90557960936404e-07,
      "loss": 0.8028,
      "step": 385
    },
    {
      "epoch": 0.7975460122699386,
      "grad_norm": 1.5990959405899048,
      "learning_rate": 8.84926640829353e-07,
      "loss": 0.8035,
      "step": 390
    },
    {
      "epoch": 0.8077709611451943,
      "grad_norm": 1.2120558023452759,
      "learning_rate": 8.79172817507756e-07,
      "loss": 0.802,
      "step": 395
    },
    {
      "epoch": 0.8179959100204499,
      "grad_norm": 1.5799622535705566,
      "learning_rate": 8.73298322130535e-07,
      "loss": 0.8037,
      "step": 400
    },
    {
      "epoch": 0.8179959100204499,
      "eval_accuracy": 0.58537,
      "eval_loss": 0.6877263784408569,
      "eval_macro_f1": 0.5630337315451738,
      "eval_precision": 0.628845494567806,
      "eval_recall": 0.5970616303474306,
      "eval_runtime": 81.293,
      "eval_samples_per_second": 1230.118,
      "eval_steps_per_second": 0.603,
      "step": 400
    },
    {
      "epoch": 0.8282208588957055,
      "grad_norm": 1.3475037813186646,
      "learning_rate": 8.673050242605921e-07,
      "loss": 0.8067,
      "step": 405
    },
    {
      "epoch": 0.8384458077709611,
      "grad_norm": 1.2836309671401978,
      "learning_rate": 8.611948312698179e-07,
      "loss": 0.7996,
      "step": 410
    },
    {
      "epoch": 0.8486707566462167,
      "grad_norm": 1.460316777229309,
      "learning_rate": 8.5496968773207e-07,
      "loss": 0.802,
      "step": 415
    },
    {
      "epoch": 0.8588957055214724,
      "grad_norm": 1.33119797706604,
      "learning_rate": 8.486315748043109e-07,
      "loss": 0.798,
      "step": 420
    },
    {
      "epoch": 0.869120654396728,
      "grad_norm": 1.9951454401016235,
      "learning_rate": 8.42182509596102e-07,
      "loss": 0.8013,
      "step": 425
    },
    {
      "epoch": 0.8793456032719836,
      "grad_norm": 1.2590746879577637,
      "learning_rate": 8.356245445276584e-07,
      "loss": 0.7963,
      "step": 430
    },
    {
      "epoch": 0.8895705521472392,
      "grad_norm": 1.1192667484283447,
      "learning_rate": 8.28959766676663e-07,
      "loss": 0.8004,
      "step": 435
    },
    {
      "epoch": 0.8997955010224948,
      "grad_norm": 1.1180275678634644,
      "learning_rate": 8.221902971140535e-07,
      "loss": 0.8041,
      "step": 440
    },
    {
      "epoch": 0.9100204498977505,
      "grad_norm": 1.1210858821868896,
      "learning_rate": 8.153182902289897e-07,
      "loss": 0.7991,
      "step": 445
    },
    {
      "epoch": 0.9202453987730062,
      "grad_norm": 1.1266220808029175,
      "learning_rate": 8.083459330432164e-07,
      "loss": 0.8002,
      "step": 450
    },
    {
      "epoch": 0.9304703476482618,
      "grad_norm": 1.0373694896697998,
      "learning_rate": 8.012754445150434e-07,
      "loss": 0.7974,
      "step": 455
    },
    {
      "epoch": 0.9406952965235174,
      "grad_norm": 1.2223235368728638,
      "learning_rate": 7.941090748331589e-07,
      "loss": 0.8001,
      "step": 460
    },
    {
      "epoch": 0.950920245398773,
      "grad_norm": 1.4549195766448975,
      "learning_rate": 7.868491047005065e-07,
      "loss": 0.7993,
      "step": 465
    },
    {
      "epoch": 0.9611451942740287,
      "grad_norm": 1.3064852952957153,
      "learning_rate": 7.794978446084483e-07,
      "loss": 0.8006,
      "step": 470
    },
    {
      "epoch": 0.9713701431492843,
      "grad_norm": 1.2408719062805176,
      "learning_rate": 7.720576341014498e-07,
      "loss": 0.7983,
      "step": 475
    },
    {
      "epoch": 0.9815950920245399,
      "grad_norm": 1.2148370742797852,
      "learning_rate": 7.645308410325187e-07,
      "loss": 0.7959,
      "step": 480
    },
    {
      "epoch": 0.9918200408997955,
      "grad_norm": 1.0927603244781494,
      "learning_rate": 7.569198608096317e-07,
      "loss": 0.7978,
      "step": 485
    },
    {
      "SWA": "started",
      "epoch": 1.0,
      "step": 489
    },
    {
      "epoch": 1.0020449897750512,
      "grad_norm": 1.245108723640442,
      "learning_rate": 7.492271156333967e-07,
      "loss": 0.7965,
      "step": 490
    },
    {
      "epoch": 1.0122699386503067,
      "grad_norm": 1.3393553495407104,
      "learning_rate": 7.414550537261828e-07,
      "loss": 0.795,
      "step": 495
    },
    {
      "epoch": 1.0224948875255624,
      "grad_norm": 1.2823072671890259,
      "learning_rate": 7.336061485529738e-07,
      "loss": 0.8014,
      "step": 500
    },
    {
      "epoch": 1.0224948875255624,
      "eval_accuracy": 0.60723,
      "eval_loss": 0.6864892244338989,
      "eval_macro_f1": 0.5966241921587988,
      "eval_precision": 0.6341761761282843,
      "eval_recall": 0.6160142746967282,
      "eval_runtime": 81.931,
      "eval_samples_per_second": 1220.539,
      "eval_steps_per_second": 0.598,
      "step": 500
    },
    {
      "epoch": 1.032719836400818,
      "grad_norm": 1.1278107166290283,
      "learning_rate": 7.256828980341846e-07,
      "loss": 0.7977,
      "step": 505
    },
    {
      "epoch": 1.0429447852760736,
      "grad_norm": 1.110093355178833,
      "learning_rate": 7.176878237506965e-07,
      "loss": 0.7954,
      "step": 510
    },
    {
      "epoch": 1.0531697341513293,
      "grad_norm": 1.2248748540878296,
      "learning_rate": 7.096234701413617e-07,
      "loss": 0.7957,
      "step": 515
    },
    {
      "epoch": 1.0633946830265848,
      "grad_norm": 1.2420642375946045,
      "learning_rate": 7.014924036932345e-07,
      "loss": 0.7935,
      "step": 520
    },
    {
      "epoch": 1.0736196319018405,
      "grad_norm": 1.0777639150619507,
      "learning_rate": 6.932972121247831e-07,
      "loss": 0.796,
      "step": 525
    },
    {
      "epoch": 1.0838445807770962,
      "grad_norm": 1.3830324411392212,
      "learning_rate": 6.850405035623481e-07,
      "loss": 0.7929,
      "step": 530
    },
    {
      "epoch": 1.0940695296523517,
      "grad_norm": 0.9407713413238525,
      "learning_rate": 6.767249057101023e-07,
      "loss": 0.7964,
      "step": 535
    },
    {
      "epoch": 1.1042944785276074,
      "grad_norm": 1.1688194274902344,
      "learning_rate": 6.683530650137832e-07,
      "loss": 0.7944,
      "step": 540
    },
    {
      "epoch": 1.114519427402863,
      "grad_norm": 0.9509923458099365,
      "learning_rate": 6.599276458184588e-07,
      "loss": 0.7912,
      "step": 545
    },
    {
      "epoch": 1.1247443762781186,
      "grad_norm": 1.0683159828186035,
      "learning_rate": 6.514513295205969e-07,
      "loss": 0.7931,
      "step": 550
    },
    {
      "epoch": 1.1349693251533743,
      "grad_norm": 0.9022642374038696,
      "learning_rate": 6.429268137147104e-07,
      "loss": 0.7945,
      "step": 555
    },
    {
      "epoch": 1.1451942740286298,
      "grad_norm": 1.1609984636306763,
      "learning_rate": 6.343568113348441e-07,
      "loss": 0.7913,
      "step": 560
    },
    {
      "epoch": 1.1554192229038855,
      "grad_norm": 1.2184994220733643,
      "learning_rate": 6.257440497911815e-07,
      "loss": 0.7919,
      "step": 565
    },
    {
      "epoch": 1.165644171779141,
      "grad_norm": 1.0256582498550415,
      "learning_rate": 6.170912701020454e-07,
      "loss": 0.7912,
      "step": 570
    },
    {
      "epoch": 1.1758691206543967,
      "grad_norm": 0.8725862503051758,
      "learning_rate": 6.084012260215645e-07,
      "loss": 0.7907,
      "step": 575
    },
    {
      "epoch": 1.1860940695296525,
      "grad_norm": 1.5192348957061768,
      "learning_rate": 5.996766831632912e-07,
      "loss": 0.7913,
      "step": 580
    },
    {
      "epoch": 1.196319018404908,
      "grad_norm": 1.109052062034607,
      "learning_rate": 5.909204181200414e-07,
      "loss": 0.795,
      "step": 585
    },
    {
      "epoch": 1.2065439672801637,
      "grad_norm": 1.0413333177566528,
      "learning_rate": 5.821352175802419e-07,
      "loss": 0.7924,
      "step": 590
    },
    {
      "epoch": 1.2167689161554192,
      "grad_norm": 0.8926281929016113,
      "learning_rate": 5.733238774410647e-07,
      "loss": 0.7921,
      "step": 595
    },
    {
      "epoch": 1.2269938650306749,
      "grad_norm": 0.9231971502304077,
      "learning_rate": 5.644892019186307e-07,
      "loss": 0.7894,
      "step": 600
    },
    {
      "epoch": 1.2269938650306749,
      "eval_accuracy": 0.62182,
      "eval_loss": 0.6853985786437988,
      "eval_macro_f1": 0.6195549574374046,
      "eval_precision": 0.6317310781859349,
      "eval_recall": 0.6267089641577176,
      "eval_runtime": 81.4512,
      "eval_samples_per_second": 1227.728,
      "eval_steps_per_second": 0.602,
      "step": 600
    },
    {
      "epoch": 1.2372188139059306,
      "grad_norm": 0.9845394492149353,
      "learning_rate": 5.556340026555653e-07,
      "loss": 0.7918,
      "step": 605
    },
    {
      "epoch": 1.247443762781186,
      "grad_norm": 1.3759487867355347,
      "learning_rate": 5.467610978261906e-07,
      "loss": 0.7904,
      "step": 610
    },
    {
      "epoch": 1.2576687116564418,
      "grad_norm": 1.1568200588226318,
      "learning_rate": 5.378733112396398e-07,
      "loss": 0.7923,
      "step": 615
    },
    {
      "epoch": 1.2678936605316973,
      "grad_norm": 1.4351176023483276,
      "learning_rate": 5.289734714411775e-07,
      "loss": 0.7905,
      "step": 620
    },
    {
      "epoch": 1.278118609406953,
      "grad_norm": 1.178076982498169,
      "learning_rate": 5.200644108120121e-07,
      "loss": 0.7947,
      "step": 625
    },
    {
      "epoch": 1.2883435582822087,
      "grad_norm": 1.2398017644882202,
      "learning_rate": 5.111489646678896e-07,
      "loss": 0.796,
      "step": 630
    },
    {
      "epoch": 1.2985685071574642,
      "grad_norm": 1.1236284971237183,
      "learning_rate": 5.022299703567508e-07,
      "loss": 0.7895,
      "step": 635
    },
    {
      "epoch": 1.30879345603272,
      "grad_norm": 1.0112528800964355,
      "learning_rate": 4.933102663557439e-07,
      "loss": 0.79,
      "step": 640
    },
    {
      "epoch": 1.3190184049079754,
      "grad_norm": 1.3201746940612793,
      "learning_rate": 4.843926913678757e-07,
      "loss": 0.7897,
      "step": 645
    },
    {
      "epoch": 1.329243353783231,
      "grad_norm": 0.969918429851532,
      "learning_rate": 4.7548008341859384e-07,
      "loss": 0.7912,
      "step": 650
    },
    {
      "epoch": 1.3394683026584868,
      "grad_norm": 0.8914945125579834,
      "learning_rate": 4.665752789525812e-07,
      "loss": 0.7964,
      "step": 655
    },
    {
      "epoch": 1.3496932515337423,
      "grad_norm": 0.906989574432373,
      "learning_rate": 4.576811119310563e-07,
      "loss": 0.7924,
      "step": 660
    },
    {
      "epoch": 1.359918200408998,
      "grad_norm": 1.2423877716064453,
      "learning_rate": 4.488004129298618e-07,
      "loss": 0.7904,
      "step": 665
    },
    {
      "epoch": 1.3701431492842535,
      "grad_norm": 1.2455909252166748,
      "learning_rate": 4.3993600823863256e-07,
      "loss": 0.7875,
      "step": 670
    },
    {
      "epoch": 1.3803680981595092,
      "grad_norm": 1.4931528568267822,
      "learning_rate": 4.3109071896132574e-07,
      "loss": 0.7947,
      "step": 675
    },
    {
      "epoch": 1.390593047034765,
      "grad_norm": 1.0538350343704224,
      "learning_rate": 4.222673601184029e-07,
      "loss": 0.7886,
      "step": 680
    },
    {
      "epoch": 1.4008179959100204,
      "grad_norm": 0.9246828556060791,
      "learning_rate": 4.134687397509467e-07,
      "loss": 0.7884,
      "step": 685
    },
    {
      "epoch": 1.4110429447852761,
      "grad_norm": 1.0383715629577637,
      "learning_rate": 4.0469765802700033e-07,
      "loss": 0.7943,
      "step": 690
    },
    {
      "epoch": 1.4212678936605316,
      "grad_norm": 1.0180901288986206,
      "learning_rate": 3.9595690635041145e-07,
      "loss": 0.7895,
      "step": 695
    },
    {
      "epoch": 1.4314928425357873,
      "grad_norm": 0.9119181632995605,
      "learning_rate": 3.8724926647246536e-07,
      "loss": 0.7864,
      "step": 700
    },
    {
      "epoch": 1.4314928425357873,
      "eval_accuracy": 0.62357,
      "eval_loss": 0.6852650046348572,
      "eval_macro_f1": 0.6215147432652665,
      "eval_precision": 0.6330088346022082,
      "eval_recall": 0.628302383508456,
      "eval_runtime": 80.5998,
      "eval_samples_per_second": 1240.698,
      "eval_steps_per_second": 0.608,
      "step": 700
    },
    {
      "epoch": 1.441717791411043,
      "grad_norm": 0.8882152438163757,
      "learning_rate": 3.785775096065909e-07,
      "loss": 0.7858,
      "step": 705
    },
    {
      "epoch": 1.4519427402862985,
      "grad_norm": 1.5290203094482422,
      "learning_rate": 3.699443955464192e-07,
      "loss": 0.7837,
      "step": 710
    },
    {
      "epoch": 1.4621676891615543,
      "grad_norm": 0.881521463394165,
      "learning_rate": 3.613526717874774e-07,
      "loss": 0.7858,
      "step": 715
    },
    {
      "epoch": 1.4723926380368098,
      "grad_norm": 0.9955899119377136,
      "learning_rate": 3.5280507265279555e-07,
      "loss": 0.7907,
      "step": 720
    },
    {
      "epoch": 1.4826175869120655,
      "grad_norm": 1.3247544765472412,
      "learning_rate": 3.443043184227067e-07,
      "loss": 0.79,
      "step": 725
    },
    {
      "epoch": 1.4928425357873212,
      "grad_norm": 1.200223445892334,
      "learning_rate": 3.358531144691148e-07,
      "loss": 0.7874,
      "step": 730
    },
    {
      "epoch": 1.5030674846625767,
      "grad_norm": 0.9952226281166077,
      "learning_rate": 3.2745415039450867e-07,
      "loss": 0.7874,
      "step": 735
    },
    {
      "epoch": 1.5132924335378322,
      "grad_norm": 1.2515606880187988,
      "learning_rate": 3.19110099175993e-07,
      "loss": 0.789,
      "step": 740
    },
    {
      "epoch": 1.5235173824130879,
      "grad_norm": 0.8901408314704895,
      "learning_rate": 3.10823616314612e-07,
      "loss": 0.7853,
      "step": 745
    },
    {
      "epoch": 1.5337423312883436,
      "grad_norm": 1.0439373254776,
      "learning_rate": 3.0259733899023345e-07,
      "loss": 0.7899,
      "step": 750
    },
    {
      "epoch": 1.5439672801635993,
      "grad_norm": 1.0658971071243286,
      "learning_rate": 2.944338852222643e-07,
      "loss": 0.7868,
      "step": 755
    },
    {
      "epoch": 1.5541922290388548,
      "grad_norm": 0.927455484867096,
      "learning_rate": 2.8633585303646413e-07,
      "loss": 0.7904,
      "step": 760
    },
    {
      "epoch": 1.5644171779141103,
      "grad_norm": 0.9637423753738403,
      "learning_rate": 2.783058196381214e-07,
      "loss": 0.7856,
      "step": 765
    },
    {
      "epoch": 1.574642126789366,
      "grad_norm": 1.396472692489624,
      "learning_rate": 2.7034634059185437e-07,
      "loss": 0.7903,
      "step": 770
    },
    {
      "epoch": 1.5848670756646217,
      "grad_norm": 0.7922792434692383,
      "learning_rate": 2.6245994900830257e-07,
      "loss": 0.7843,
      "step": 775
    },
    {
      "epoch": 1.5950920245398774,
      "grad_norm": 0.8896881341934204,
      "learning_rate": 2.546491547379619e-07,
      "loss": 0.787,
      "step": 780
    },
    {
      "epoch": 1.605316973415133,
      "grad_norm": 0.8732028007507324,
      "learning_rate": 2.469164435724212e-07,
      "loss": 0.7856,
      "step": 785
    },
    {
      "epoch": 1.6155419222903884,
      "grad_norm": 1.0021744966506958,
      "learning_rate": 2.3926427645325875e-07,
      "loss": 0.7867,
      "step": 790
    },
    {
      "epoch": 1.6257668711656441,
      "grad_norm": 1.1783545017242432,
      "learning_rate": 2.3169508868884453e-07,
      "loss": 0.7897,
      "step": 795
    },
    {
      "epoch": 1.6359918200408998,
      "grad_norm": 0.9119800329208374,
      "learning_rate": 2.2421128917930243e-07,
      "loss": 0.7845,
      "step": 800
    },
    {
      "epoch": 1.6359918200408998,
      "eval_accuracy": 0.62896,
      "eval_loss": 0.6847647428512573,
      "eval_macro_f1": 0.6281943240633717,
      "eval_precision": 0.6346364525627035,
      "eval_recall": 0.6323959922867678,
      "eval_runtime": 80.6105,
      "eval_samples_per_second": 1240.533,
      "eval_steps_per_second": 0.608,
      "step": 800
    },
    {
      "epoch": 1.6462167689161555,
      "grad_norm": 0.8903971314430237,
      "learning_rate": 2.1681525964987474e-07,
      "loss": 0.7824,
      "step": 805
    },
    {
      "epoch": 1.656441717791411,
      "grad_norm": 1.115395188331604,
      "learning_rate": 2.0950935389293656e-07,
      "loss": 0.7824,
      "step": 810
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.9636144638061523,
      "learning_rate": 2.022958970189001e-07,
      "loss": 0.7917,
      "step": 815
    },
    {
      "epoch": 1.6768916155419222,
      "grad_norm": 0.8787257075309753,
      "learning_rate": 1.9517718471624532e-07,
      "loss": 0.7869,
      "step": 820
    },
    {
      "epoch": 1.687116564417178,
      "grad_norm": 1.0157173871994019,
      "learning_rate": 1.88155482520916e-07,
      "loss": 0.7844,
      "step": 825
    },
    {
      "epoch": 1.6973415132924337,
      "grad_norm": 0.9504719972610474,
      "learning_rate": 1.812330250953107e-07,
      "loss": 0.7872,
      "step": 830
    },
    {
      "epoch": 1.7075664621676891,
      "grad_norm": 0.893625795841217,
      "learning_rate": 1.7441201551710016e-07,
      "loss": 0.7879,
      "step": 835
    },
    {
      "epoch": 1.7177914110429446,
      "grad_norm": 0.8460310101509094,
      "learning_rate": 1.6769462457809536e-07,
      "loss": 0.7853,
      "step": 840
    },
    {
      "epoch": 1.7280163599182004,
      "grad_norm": 0.9349818229675293,
      "learning_rate": 1.610829900933917e-07,
      "loss": 0.7862,
      "step": 845
    },
    {
      "epoch": 1.738241308793456,
      "grad_norm": 0.859866738319397,
      "learning_rate": 1.545792162210074e-07,
      "loss": 0.7836,
      "step": 850
    },
    {
      "epoch": 1.7484662576687118,
      "grad_norm": 1.0148438215255737,
      "learning_rate": 1.481853727922341e-07,
      "loss": 0.7859,
      "step": 855
    },
    {
      "epoch": 1.7586912065439673,
      "grad_norm": 0.8861204385757446,
      "learning_rate": 1.4190349465291035e-07,
      "loss": 0.7909,
      "step": 860
    },
    {
      "epoch": 1.7689161554192228,
      "grad_norm": 0.7679073214530945,
      "learning_rate": 1.3573558101583105e-07,
      "loss": 0.785,
      "step": 865
    },
    {
      "epoch": 1.7791411042944785,
      "grad_norm": 0.7364144325256348,
      "learning_rate": 1.2968359482449636e-07,
      "loss": 0.7824,
      "step": 870
    },
    {
      "epoch": 1.7893660531697342,
      "grad_norm": 0.945924699306488,
      "learning_rate": 1.2374946212840288e-07,
      "loss": 0.7864,
      "step": 875
    },
    {
      "epoch": 1.79959100204499,
      "grad_norm": 1.1060514450073242,
      "learning_rate": 1.1793507147007714e-07,
      "loss": 0.7866,
      "step": 880
    },
    {
      "epoch": 1.8098159509202454,
      "grad_norm": 0.9230445623397827,
      "learning_rate": 1.1224227328404534e-07,
      "loss": 0.7895,
      "step": 885
    },
    {
      "epoch": 1.8200408997955009,
      "grad_norm": 0.9153196811676025,
      "learning_rate": 1.0667287930793151e-07,
      "loss": 0.7835,
      "step": 890
    },
    {
      "epoch": 1.8302658486707566,
      "grad_norm": 0.9513780474662781,
      "learning_rate": 1.0122866200586944e-07,
      "loss": 0.7846,
      "step": 895
    },
    {
      "epoch": 1.8404907975460123,
      "grad_norm": 0.8672247529029846,
      "learning_rate": 9.591135400441552e-08,
      "loss": 0.7839,
      "step": 900
    },
    {
      "epoch": 1.8404907975460123,
      "eval_accuracy": 0.63125,
      "eval_loss": 0.6845182776451111,
      "eval_macro_f1": 0.6309538076224105,
      "eval_precision": 0.6350446377333951,
      "eval_recall": 0.6339031903992685,
      "eval_runtime": 80.5646,
      "eval_samples_per_second": 1241.24,
      "eval_steps_per_second": 0.608,
      "step": 900
    },
    {
      "epoch": 1.850715746421268,
      "grad_norm": 1.2127219438552856,
      "learning_rate": 9.072264754113912e-08,
      "loss": 0.7876,
      "step": 905
    },
    {
      "epoch": 1.8609406952965235,
      "grad_norm": 0.875455379486084,
      "learning_rate": 8.566419392606544e-08,
      "loss": 0.787,
      "step": 910
    },
    {
      "epoch": 1.871165644171779,
      "grad_norm": 0.92503821849823,
      "learning_rate": 8.073760301614596e-08,
      "loss": 0.7834,
      "step": 915
    },
    {
      "epoch": 1.8813905930470347,
      "grad_norm": 1.1361068487167358,
      "learning_rate": 7.594444270291922e-08,
      "loss": 0.7821,
      "step": 920
    },
    {
      "epoch": 1.8916155419222904,
      "grad_norm": 1.1415101289749146,
      "learning_rate": 7.128623841352916e-08,
      "loss": 0.7877,
      "step": 925
    },
    {
      "epoch": 1.9018404907975461,
      "grad_norm": 0.9358757138252258,
      "learning_rate": 6.676447262525547e-08,
      "loss": 0.7867,
      "step": 930
    },
    {
      "epoch": 1.9120654396728016,
      "grad_norm": 0.912706732749939,
      "learning_rate": 6.238058439371479e-08,
      "loss": 0.7884,
      "step": 935
    },
    {
      "epoch": 1.9222903885480571,
      "grad_norm": 0.9449842572212219,
      "learning_rate": 5.813596889488009e-08,
      "loss": 0.7893,
      "step": 940
    },
    {
      "epoch": 1.9325153374233128,
      "grad_norm": 0.8449825048446655,
      "learning_rate": 5.403197698106432e-08,
      "loss": 0.7828,
      "step": 945
    },
    {
      "epoch": 1.9427402862985685,
      "grad_norm": 0.9307764768600464,
      "learning_rate": 5.0069914751010913e-08,
      "loss": 0.785,
      "step": 950
    },
    {
      "epoch": 1.9529652351738243,
      "grad_norm": 1.3704556226730347,
      "learning_rate": 4.625104313422673e-08,
      "loss": 0.7874,
      "step": 955
    },
    {
      "epoch": 1.9631901840490797,
      "grad_norm": 1.0163496732711792,
      "learning_rate": 4.257657748969046e-08,
      "loss": 0.7834,
      "step": 960
    },
    {
      "epoch": 1.9734151329243352,
      "grad_norm": 0.8112438321113586,
      "learning_rate": 3.904768721906304e-08,
      "loss": 0.7852,
      "step": 965
    },
    {
      "epoch": 1.983640081799591,
      "grad_norm": 0.885705828666687,
      "learning_rate": 3.566549539452529e-08,
      "loss": 0.7792,
      "step": 970
    },
    {
      "epoch": 1.9938650306748467,
      "grad_norm": 0.8692009449005127,
      "learning_rate": 3.243107840135878e-08,
      "loss": 0.7822,
      "step": 975
    },
    {
      "epoch": 2.0040899795501024,
      "grad_norm": 0.8909807205200195,
      "learning_rate": 2.9345465595385866e-08,
      "loss": 0.7826,
      "step": 980
    },
    {
      "epoch": 2.014314928425358,
      "grad_norm": 0.9065344333648682,
      "learning_rate": 2.6409638975375737e-08,
      "loss": 0.7849,
      "step": 985
    },
    {
      "epoch": 2.0245398773006134,
      "grad_norm": 0.8145809173583984,
      "learning_rate": 2.3624532870522962e-08,
      "loss": 0.7885,
      "step": 990
    },
    {
      "epoch": 2.034764826175869,
      "grad_norm": 0.9461153149604797,
      "learning_rate": 2.0991033643096457e-08,
      "loss": 0.7853,
      "step": 995
    },
    {
      "epoch": 2.044989775051125,
      "grad_norm": 0.8470706343650818,
      "learning_rate": 1.8509979406353794e-08,
      "loss": 0.7881,
      "step": 1000
    },
    {
      "epoch": 2.044989775051125,
      "eval_accuracy": 0.63202,
      "eval_loss": 0.6844514012336731,
      "eval_macro_f1": 0.6318036560759084,
      "eval_precision": 0.6354113747156731,
      "eval_recall": 0.6344858797364747,
      "eval_runtime": 81.1838,
      "eval_samples_per_second": 1231.772,
      "eval_steps_per_second": 0.604,
      "step": 1000
    },
    {
      "epoch": 2.0552147239263805,
      "grad_norm": 0.8817445635795593,
      "learning_rate": 1.6182159757810897e-08,
      "loss": 0.7879,
      "step": 1005
    },
    {
      "epoch": 2.065439672801636,
      "grad_norm": 0.856109082698822,
      "learning_rate": 1.400831552795234e-08,
      "loss": 0.7868,
      "step": 1010
    },
    {
      "epoch": 2.0756646216768915,
      "grad_norm": 0.956066370010376,
      "learning_rate": 1.1989138544461375e-08,
      "loss": 0.7845,
      "step": 1015
    },
    {
      "epoch": 2.085889570552147,
      "grad_norm": 0.930978000164032,
      "learning_rate": 1.0125271412044666e-08,
      "loss": 0.7876,
      "step": 1020
    },
    {
      "epoch": 2.096114519427403,
      "grad_norm": 0.9799636602401733,
      "learning_rate": 8.417307307923615e-09,
      "loss": 0.7861,
      "step": 1025
    },
    {
      "epoch": 2.1063394683026586,
      "grad_norm": 0.9991019368171692,
      "learning_rate": 6.8657897930547435e-09,
      "loss": 0.7852,
      "step": 1030
    },
    {
      "epoch": 2.116564417177914,
      "grad_norm": 1.076750636100769,
      "learning_rate": 5.471212639141132e-09,
      "loss": 0.7789,
      "step": 1035
    },
    {
      "epoch": 2.1267893660531696,
      "grad_norm": 0.9805507063865662,
      "learning_rate": 4.23401967148912e-09,
      "loss": 0.7829,
      "step": 1040
    },
    {
      "epoch": 2.1370143149284253,
      "grad_norm": 0.7899750471115112,
      "learning_rate": 3.154604627760571e-09,
      "loss": 0.7839,
      "step": 1045
    },
    {
      "epoch": 2.147239263803681,
      "grad_norm": 1.1698967218399048,
      "learning_rate": 2.2333110326655526e-09,
      "loss": 0.7869,
      "step": 1050
    },
    {
      "epoch": 2.1574642126789367,
      "grad_norm": 0.9302964806556702,
      "learning_rate": 1.4704320886352873e-09,
      "loss": 0.7832,
      "step": 1055
    },
    {
      "epoch": 2.1676891615541924,
      "grad_norm": 1.057986855506897,
      "learning_rate": 8.662105825103517e-10,
      "loss": 0.7864,
      "step": 1060
    },
    {
      "epoch": 2.1779141104294477,
      "grad_norm": 1.0347933769226074,
      "learning_rate": 4.208388082733161e-10,
      "loss": 0.7822,
      "step": 1065
    },
    {
      "epoch": 2.1881390593047034,
      "grad_norm": 0.9827083945274353,
      "learning_rate": 1.3445850585130924e-10,
      "loss": 0.784,
      "step": 1070
    },
    {
      "epoch": 2.198364008179959,
      "grad_norm": 0.8463678956031799,
      "learning_rate": 7.160816007045767e-12,
      "loss": 0.7811,
      "step": 1075
    },
    {
      "epoch": 2.208588957055215,
      "grad_norm": 0.9141009449958801,
      "learning_rate": 9.999610137486667e-07,
      "loss": 0.7828,
      "step": 1080
    },
    {
      "epoch": 2.21881390593047,
      "grad_norm": 0.8992940783500671,
      "learning_rate": 9.997700753166407e-07,
      "loss": 0.7843,
      "step": 1085
    },
    {
      "epoch": 2.229038854805726,
      "grad_norm": 0.9198014140129089,
      "learning_rate": 9.99420084654225e-07,
      "loss": 0.7867,
      "step": 1090
    },
    {
      "epoch": 2.2392638036809815,
      "grad_norm": 0.841385006904602,
      "learning_rate": 9.98911153146231e-07,
      "loss": 0.7899,
      "step": 1095
    },
    {
      "epoch": 2.2494887525562373,
      "grad_norm": 0.9428244233131409,
      "learning_rate": 9.982434427605222e-07,
      "loss": 0.783,
      "step": 1100
    },
    {
      "epoch": 2.2494887525562373,
      "eval_accuracy": 0.63535,
      "eval_loss": 0.6841139197349548,
      "eval_macro_f1": 0.6353491904387377,
      "eval_precision": 0.6368108503242846,
      "eval_recall": 0.6367719631437929,
      "eval_runtime": 81.1976,
      "eval_samples_per_second": 1231.563,
      "eval_steps_per_second": 0.603,
      "step": 1100
    },
    {
      "epoch": 2.259713701431493,
      "grad_norm": 0.8474355936050415,
      "learning_rate": 9.974171659964687e-07,
      "loss": 0.7805,
      "step": 1105
    },
    {
      "epoch": 2.2699386503067487,
      "grad_norm": 0.8366284370422363,
      "learning_rate": 9.964325858173184e-07,
      "loss": 0.7821,
      "step": 1110
    },
    {
      "epoch": 2.280163599182004,
      "grad_norm": 1.102426290512085,
      "learning_rate": 9.952900155665089e-07,
      "loss": 0.7854,
      "step": 1115
    },
    {
      "epoch": 2.2903885480572597,
      "grad_norm": 0.8815932273864746,
      "learning_rate": 9.939898188679462e-07,
      "loss": 0.7835,
      "step": 1120
    },
    {
      "epoch": 2.3006134969325154,
      "grad_norm": 0.8016415238380432,
      "learning_rate": 9.925324095102806e-07,
      "loss": 0.7842,
      "step": 1125
    },
    {
      "epoch": 2.310838445807771,
      "grad_norm": 0.8805480599403381,
      "learning_rate": 9.909182513152177e-07,
      "loss": 0.7791,
      "step": 1130
    },
    {
      "epoch": 2.3210633946830264,
      "grad_norm": 0.9736661314964294,
      "learning_rate": 9.891478579899078e-07,
      "loss": 0.7825,
      "step": 1135
    },
    {
      "epoch": 2.331288343558282,
      "grad_norm": 0.8331109285354614,
      "learning_rate": 9.872217929634573e-07,
      "loss": 0.7852,
      "step": 1140
    },
    {
      "epoch": 2.341513292433538,
      "grad_norm": 0.8597177267074585,
      "learning_rate": 9.851406692076183e-07,
      "loss": 0.7817,
      "step": 1145
    },
    {
      "epoch": 2.3517382413087935,
      "grad_norm": 0.7928445339202881,
      "learning_rate": 9.829051490417071e-07,
      "loss": 0.7765,
      "step": 1150
    },
    {
      "epoch": 2.361963190184049,
      "grad_norm": 0.8488237857818604,
      "learning_rate": 9.80515943921824e-07,
      "loss": 0.7836,
      "step": 1155
    },
    {
      "epoch": 2.372188139059305,
      "grad_norm": 0.7608004212379456,
      "learning_rate": 9.77973814214429e-07,
      "loss": 0.7834,
      "step": 1160
    },
    {
      "epoch": 2.38241308793456,
      "grad_norm": 0.8542405962944031,
      "learning_rate": 9.752795689543563e-07,
      "loss": 0.7777,
      "step": 1165
    },
    {
      "epoch": 2.392638036809816,
      "grad_norm": 0.8797897100448608,
      "learning_rate": 9.72434065587337e-07,
      "loss": 0.7823,
      "step": 1170
    },
    {
      "epoch": 2.4028629856850716,
      "grad_norm": 0.9687849283218384,
      "learning_rate": 9.69438209697118e-07,
      "loss": 0.7754,
      "step": 1175
    },
    {
      "epoch": 2.4130879345603273,
      "grad_norm": 0.9111893773078918,
      "learning_rate": 9.662929547172574e-07,
      "loss": 0.7806,
      "step": 1180
    },
    {
      "epoch": 2.4233128834355826,
      "grad_norm": 1.0323760509490967,
      "learning_rate": 9.629993016276944e-07,
      "loss": 0.7801,
      "step": 1185
    },
    {
      "epoch": 2.4335378323108383,
      "grad_norm": 0.79954594373703,
      "learning_rate": 9.595582986361872e-07,
      "loss": 0.7781,
      "step": 1190
    },
    {
      "epoch": 2.443762781186094,
      "grad_norm": 0.7106928825378418,
      "learning_rate": 9.559710408447184e-07,
      "loss": 0.7788,
      "step": 1195
    },
    {
      "epoch": 2.4539877300613497,
      "grad_norm": 0.77292400598526,
      "learning_rate": 9.522386699009795e-07,
      "loss": 0.7827,
      "step": 1200
    },
    {
      "epoch": 2.4539877300613497,
      "eval_accuracy": 0.645,
      "eval_loss": 0.6828427314758301,
      "eval_macro_f1": 0.6440359919423964,
      "eval_precision": 0.6441481409802297,
      "eval_recall": 0.6439695264773649,
      "eval_runtime": 81.1775,
      "eval_samples_per_second": 1231.869,
      "eval_steps_per_second": 0.604,
      "step": 1200
    },
    {
      "epoch": 2.4642126789366054,
      "grad_norm": 0.8576335310935974,
      "learning_rate": 9.483623736350402e-07,
      "loss": 0.7765,
      "step": 1205
    },
    {
      "epoch": 2.474437627811861,
      "grad_norm": 0.7940819263458252,
      "learning_rate": 9.443433856813196e-07,
      "loss": 0.7744,
      "step": 1210
    },
    {
      "epoch": 2.4846625766871164,
      "grad_norm": 0.9138656854629517,
      "learning_rate": 9.401829850859823e-07,
      "loss": 0.779,
      "step": 1215
    },
    {
      "epoch": 2.494887525562372,
      "grad_norm": 0.7292961478233337,
      "learning_rate": 9.358824958998804e-07,
      "loss": 0.7741,
      "step": 1220
    },
    {
      "epoch": 2.505112474437628,
      "grad_norm": 0.8346101641654968,
      "learning_rate": 9.314432867571731e-07,
      "loss": 0.7769,
      "step": 1225
    },
    {
      "epoch": 2.5153374233128836,
      "grad_norm": 0.7433446645736694,
      "learning_rate": 9.268667704397576e-07,
      "loss": 0.7811,
      "step": 1230
    },
    {
      "epoch": 2.525562372188139,
      "grad_norm": 0.7142143845558167,
      "learning_rate": 9.22154403427651e-07,
      "loss": 0.7739,
      "step": 1235
    },
    {
      "epoch": 2.5357873210633946,
      "grad_norm": 0.8269698023796082,
      "learning_rate": 9.173076854354633e-07,
      "loss": 0.7751,
      "step": 1240
    },
    {
      "epoch": 2.5460122699386503,
      "grad_norm": 0.7005385160446167,
      "learning_rate": 9.123281589351127e-07,
      "loss": 0.7747,
      "step": 1245
    },
    {
      "epoch": 2.556237218813906,
      "grad_norm": 0.7422548532485962,
      "learning_rate": 9.072174086649326e-07,
      "loss": 0.7764,
      "step": 1250
    },
    {
      "epoch": 2.5664621676891617,
      "grad_norm": 0.7844764590263367,
      "learning_rate": 9.01977061125327e-07,
      "loss": 0.7751,
      "step": 1255
    },
    {
      "epoch": 2.5766871165644174,
      "grad_norm": 0.8993695378303528,
      "learning_rate": 8.966087840611356e-07,
      "loss": 0.7771,
      "step": 1260
    },
    {
      "epoch": 2.5869120654396727,
      "grad_norm": 0.7648841738700867,
      "learning_rate": 8.911142859308729e-07,
      "loss": 0.7771,
      "step": 1265
    },
    {
      "epoch": 2.5971370143149284,
      "grad_norm": 0.789523720741272,
      "learning_rate": 8.854953153630096e-07,
      "loss": 0.7732,
      "step": 1270
    },
    {
      "epoch": 2.607361963190184,
      "grad_norm": 0.7698408365249634,
      "learning_rate": 8.7975366059947e-07,
      "loss": 0.769,
      "step": 1275
    },
    {
      "epoch": 2.61758691206544,
      "grad_norm": 1.019235610961914,
      "learning_rate": 8.738911489265233e-07,
      "loss": 0.7768,
      "step": 1280
    },
    {
      "epoch": 2.627811860940695,
      "grad_norm": 0.8915722966194153,
      "learning_rate": 8.679096460932475e-07,
      "loss": 0.774,
      "step": 1285
    },
    {
      "epoch": 2.638036809815951,
      "grad_norm": 1.0551347732543945,
      "learning_rate": 8.618110557177536e-07,
      "loss": 0.7711,
      "step": 1290
    },
    {
      "epoch": 2.6482617586912065,
      "grad_norm": 0.7630209922790527,
      "learning_rate": 8.555973186813575e-07,
      "loss": 0.7724,
      "step": 1295
    },
    {
      "epoch": 2.658486707566462,
      "grad_norm": 0.6783341765403748,
      "learning_rate": 8.49270412510893e-07,
      "loss": 0.773,
      "step": 1300
    },
    {
      "epoch": 2.658486707566462,
      "eval_accuracy": 0.64275,
      "eval_loss": 0.6818840503692627,
      "eval_macro_f1": 0.6366805441223703,
      "eval_precision": 0.6443671237738225,
      "eval_recall": 0.6381477730287184,
      "eval_runtime": 81.1862,
      "eval_samples_per_second": 1231.736,
      "eval_steps_per_second": 0.604,
      "step": 1300
    },
    {
      "epoch": 2.668711656441718,
      "grad_norm": 0.6987424492835999,
      "learning_rate": 8.428323507493627e-07,
      "loss": 0.7732,
      "step": 1305
    },
    {
      "epoch": 2.6789366053169736,
      "grad_norm": 1.0909086465835571,
      "learning_rate": 8.362851823151251e-07,
      "loss": 0.7753,
      "step": 1310
    },
    {
      "epoch": 2.689161554192229,
      "grad_norm": 0.8491300344467163,
      "learning_rate": 8.296309908498261e-07,
      "loss": 0.776,
      "step": 1315
    },
    {
      "epoch": 2.6993865030674846,
      "grad_norm": 0.739740788936615,
      "learning_rate": 8.228718940552775e-07,
      "loss": 0.7728,
      "step": 1320
    },
    {
      "epoch": 2.7096114519427403,
      "grad_norm": 0.8270577192306519,
      "learning_rate": 8.160100430194969e-07,
      "loss": 0.7703,
      "step": 1325
    },
    {
      "epoch": 2.719836400817996,
      "grad_norm": 0.836187481880188,
      "learning_rate": 8.090476215321226e-07,
      "loss": 0.7742,
      "step": 1330
    },
    {
      "epoch": 2.7300613496932513,
      "grad_norm": 0.7952380180358887,
      "learning_rate": 8.019868453894195e-07,
      "loss": 0.7736,
      "step": 1335
    },
    {
      "epoch": 2.740286298568507,
      "grad_norm": 0.8082153797149658,
      "learning_rate": 7.948299616891019e-07,
      "loss": 0.7742,
      "step": 1340
    },
    {
      "epoch": 2.7505112474437627,
      "grad_norm": 0.7107052206993103,
      "learning_rate": 7.875792481151917e-07,
      "loss": 0.7703,
      "step": 1345
    },
    {
      "epoch": 2.7607361963190185,
      "grad_norm": 0.7359179258346558,
      "learning_rate": 7.802370122131438e-07,
      "loss": 0.7738,
      "step": 1350
    },
    {
      "epoch": 2.770961145194274,
      "grad_norm": 0.7772730588912964,
      "learning_rate": 7.728055906554683e-07,
      "loss": 0.7715,
      "step": 1355
    },
    {
      "epoch": 2.78118609406953,
      "grad_norm": 1.2671797275543213,
      "learning_rate": 7.65287348498082e-07,
      "loss": 0.7735,
      "step": 1360
    },
    {
      "epoch": 2.791411042944785,
      "grad_norm": 0.8609771132469177,
      "learning_rate": 7.576846784276276e-07,
      "loss": 0.77,
      "step": 1365
    },
    {
      "epoch": 2.801635991820041,
      "grad_norm": 0.6689844131469727,
      "learning_rate": 7.500000000000002e-07,
      "loss": 0.7702,
      "step": 1370
    },
    {
      "epoch": 2.8118609406952966,
      "grad_norm": 0.80215984582901,
      "learning_rate": 7.422357588703195e-07,
      "loss": 0.7782,
      "step": 1375
    },
    {
      "epoch": 2.8220858895705523,
      "grad_norm": 0.7997626066207886,
      "learning_rate": 7.343944260146006e-07,
      "loss": 0.7705,
      "step": 1380
    },
    {
      "epoch": 2.8323108384458076,
      "grad_norm": 0.7380858659744263,
      "learning_rate": 7.264784969433624e-07,
      "loss": 0.7718,
      "step": 1385
    },
    {
      "epoch": 2.8425357873210633,
      "grad_norm": 0.7241907119750977,
      "learning_rate": 7.184904909074292e-07,
      "loss": 0.7668,
      "step": 1390
    },
    {
      "epoch": 2.852760736196319,
      "grad_norm": 0.7640359401702881,
      "learning_rate": 7.104329500961783e-07,
      "loss": 0.7726,
      "step": 1395
    },
    {
      "epoch": 2.8629856850715747,
      "grad_norm": 0.8806844353675842,
      "learning_rate": 7.023084388284846e-07,
      "loss": 0.7712,
      "step": 1400
    },
    {
      "epoch": 2.8629856850715747,
      "eval_accuracy": 0.65106,
      "eval_loss": 0.6813496947288513,
      "eval_macro_f1": 0.6459359532496649,
      "eval_precision": 0.6523398288087938,
      "eval_recall": 0.6468889448544942,
      "eval_runtime": 81.1842,
      "eval_samples_per_second": 1231.767,
      "eval_steps_per_second": 0.604,
      "step": 1400
    }
  ],
  "logging_steps": 5,
  "max_steps": 1956,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 3.768087094906061e+17,
  "train_batch_size": 1024,
  "trial_name": null,
  "trial_params": null
}