{
  "best_metric": 0.9883040935672515,
  "best_model_checkpoint": "./outputs/convnextv2-nano-22k-384-boulderspot-vN/checkpoint-1015",
  "epoch": 4.993849938499385,
  "eval_steps": 500,
  "global_step": 1015,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 26.665199279785156,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.6334,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 7.943151473999023,
      "learning_rate": 7.84313725490196e-06,
      "loss": 0.365,
      "step": 20
    },
    {
      "epoch": 0.15,
      "grad_norm": 16.875411987304688,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.2382,
      "step": 30
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.587479114532471,
      "learning_rate": 1.568627450980392e-05,
      "loss": 0.1425,
      "step": 40
    },
    {
      "epoch": 0.25,
      "grad_norm": 7.946935176849365,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 0.1257,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 4.481125831604004,
      "learning_rate": 1.9995698998770955e-05,
      "loss": 0.0967,
      "step": 60
    },
    {
      "epoch": 0.34,
      "grad_norm": 9.453625679016113,
      "learning_rate": 1.998083609002402e-05,
      "loss": 0.0829,
      "step": 70
    },
    {
      "epoch": 0.39,
      "grad_norm": 13.032307624816895,
      "learning_rate": 1.995537395500004e-05,
      "loss": 0.1073,
      "step": 80
    },
    {
      "epoch": 0.44,
      "grad_norm": 5.036722183227539,
      "learning_rate": 1.9919339633410737e-05,
      "loss": 0.0788,
      "step": 90
    },
    {
      "epoch": 0.49,
      "grad_norm": 10.13275146484375,
      "learning_rate": 1.9872771392183334e-05,
      "loss": 0.1421,
      "step": 100
    },
    {
      "epoch": 0.54,
      "grad_norm": 10.442366600036621,
      "learning_rate": 1.981571868482269e-05,
      "loss": 0.1035,
      "step": 110
    },
    {
      "epoch": 0.59,
      "grad_norm": 7.753129959106445,
      "learning_rate": 1.974824209889377e-05,
      "loss": 0.1001,
      "step": 120
    },
    {
      "epoch": 0.64,
      "grad_norm": 10.481592178344727,
      "learning_rate": 1.9670413291680223e-05,
      "loss": 0.1007,
      "step": 130
    },
    {
      "epoch": 0.69,
      "grad_norm": 7.881091594696045,
      "learning_rate": 1.9582314914087344e-05,
      "loss": 0.0669,
      "step": 140
    },
    {
      "epoch": 0.74,
      "grad_norm": 12.763803482055664,
      "learning_rate": 1.9484040522870333e-05,
      "loss": 0.0723,
      "step": 150
    },
    {
      "epoch": 0.79,
      "grad_norm": 6.890717029571533,
      "learning_rate": 1.9375694481280965e-05,
      "loss": 0.0804,
      "step": 160
    },
    {
      "epoch": 0.84,
      "grad_norm": 6.086670398712158,
      "learning_rate": 1.9257391848238212e-05,
      "loss": 0.1073,
      "step": 170
    },
    {
      "epoch": 0.89,
      "grad_norm": 4.475172996520996,
      "learning_rate": 1.9129258256140556e-05,
      "loss": 0.0779,
      "step": 180
    },
    {
      "epoch": 0.93,
      "grad_norm": 4.19266414642334,
      "learning_rate": 1.8991429777449674e-05,
      "loss": 0.0934,
      "step": 190
    },
    {
      "epoch": 0.98,
      "grad_norm": 14.975569725036621,
      "learning_rate": 1.884405278018722e-05,
      "loss": 0.1102,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9839181286549707,
      "eval_f1": 0.9840087498605248,
      "eval_loss": 0.0431428886950016,
      "eval_matthews_correlation": 0.8589815510372486,
      "eval_precision": 0.9841155979252388,
      "eval_recall": 0.9839181286549707,
      "eval_runtime": 4.9799,
      "eval_samples_per_second": 137.351,
      "eval_steps_per_second": 8.635,
      "step": 203
    },
    {
      "epoch": 1.03,
      "grad_norm": 14.823522567749023,
      "learning_rate": 1.8687283772498205e-05,
      "loss": 0.0567,
      "step": 210
    },
    {
      "epoch": 1.08,
      "grad_norm": 2.4599366188049316,
      "learning_rate": 1.852128923644593e-05,
      "loss": 0.08,
      "step": 220
    },
    {
      "epoch": 1.13,
      "grad_norm": 1.6709442138671875,
      "learning_rate": 1.8346245451215068e-05,
      "loss": 0.056,
      "step": 230
    },
    {
      "epoch": 1.18,
      "grad_norm": 6.953076362609863,
      "learning_rate": 1.8162338305910636e-05,
      "loss": 0.0683,
      "step": 240
    },
    {
      "epoch": 1.23,
      "grad_norm": 3.510495901107788,
      "learning_rate": 1.79697631021516e-05,
      "loss": 0.0825,
      "step": 250
    },
    {
      "epoch": 1.28,
      "grad_norm": 8.399980545043945,
      "learning_rate": 1.776872434666882e-05,
      "loss": 0.0584,
      "step": 260
    },
    {
      "epoch": 1.33,
      "grad_norm": 14.62066650390625,
      "learning_rate": 1.7559435534127534e-05,
      "loss": 0.0998,
      "step": 270
    },
    {
      "epoch": 1.38,
      "grad_norm": 6.287339210510254,
      "learning_rate": 1.7342118920405035e-05,
      "loss": 0.0813,
      "step": 280
    },
    {
      "epoch": 1.43,
      "grad_norm": 7.23698091506958,
      "learning_rate": 1.7117005286564344e-05,
      "loss": 0.0973,
      "step": 290
    },
    {
      "epoch": 1.48,
      "grad_norm": 12.766968727111816,
      "learning_rate": 1.688433369377444e-05,
      "loss": 0.0928,
      "step": 300
    },
    {
      "epoch": 1.53,
      "grad_norm": 16.611492156982422,
      "learning_rate": 1.6644351229437416e-05,
      "loss": 0.08,
      "step": 310
    },
    {
      "epoch": 1.57,
      "grad_norm": 1.000801920890808,
      "learning_rate": 1.63973127447921e-05,
      "loss": 0.0582,
      "step": 320
    },
    {
      "epoch": 1.62,
      "grad_norm": 10.745514869689941,
      "learning_rate": 1.6143480584272794e-05,
      "loss": 0.0915,
      "step": 330
    },
    {
      "epoch": 1.67,
      "grad_norm": 10.188589096069336,
      "learning_rate": 1.5883124306910563e-05,
      "loss": 0.0869,
      "step": 340
    },
    {
      "epoch": 1.72,
      "grad_norm": 7.215929985046387,
      "learning_rate": 1.5616520400072963e-05,
      "loss": 0.1329,
      "step": 350
    },
    {
      "epoch": 1.77,
      "grad_norm": 4.967738151550293,
      "learning_rate": 1.5343951985846096e-05,
      "loss": 0.0781,
      "step": 360
    },
    {
      "epoch": 1.82,
      "grad_norm": 2.9467406272888184,
      "learning_rate": 1.5065708520370943e-05,
      "loss": 0.0582,
      "step": 370
    },
    {
      "epoch": 1.87,
      "grad_norm": 6.54543399810791,
      "learning_rate": 1.4782085486453155e-05,
      "loss": 0.0626,
      "step": 380
    },
    {
      "epoch": 1.92,
      "grad_norm": 7.8247833251953125,
      "learning_rate": 1.4493384079772815e-05,
      "loss": 0.081,
      "step": 390
    },
    {
      "epoch": 1.97,
      "grad_norm": 8.889460563659668,
      "learning_rate": 1.4199910889027335e-05,
      "loss": 0.0559,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9839181286549707,
      "eval_f1": 0.9845065535493497,
      "eval_loss": 0.04758350923657417,
      "eval_matthews_correlation": 0.8709455436036694,
      "eval_precision": 0.9858048061716136,
      "eval_recall": 0.9839181286549707,
      "eval_runtime": 5.1397,
      "eval_samples_per_second": 133.081,
      "eval_steps_per_second": 8.366,
      "step": 406
    },
    {
      "epoch": 2.02,
      "grad_norm": 11.741949081420898,
      "learning_rate": 1.390197757034721e-05,
      "loss": 0.0806,
      "step": 410
    },
    {
      "epoch": 2.07,
      "grad_norm": 8.677542686462402,
      "learning_rate": 1.3599900516330382e-05,
      "loss": 0.1033,
      "step": 420
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.3803766965866089,
      "learning_rate": 1.3294000520046666e-05,
      "loss": 0.0433,
      "step": 430
    },
    {
      "epoch": 2.16,
      "grad_norm": 8.467944145202637,
      "learning_rate": 1.2984602434369058e-05,
      "loss": 0.0691,
      "step": 440
    },
    {
      "epoch": 2.21,
      "grad_norm": 6.276478290557861,
      "learning_rate": 1.2672034826993716e-05,
      "loss": 0.0678,
      "step": 450
    },
    {
      "epoch": 2.26,
      "grad_norm": 11.57728385925293,
      "learning_rate": 1.235662963151493e-05,
      "loss": 0.0804,
      "step": 460
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.9122611880302429,
      "learning_rate": 1.2038721794925689e-05,
      "loss": 0.0476,
      "step": 470
    },
    {
      "epoch": 2.36,
      "grad_norm": 1.983340859413147,
      "learning_rate": 1.1718648921918112e-05,
      "loss": 0.0545,
      "step": 480
    },
    {
      "epoch": 2.41,
      "grad_norm": 17.866886138916016,
      "learning_rate": 1.1396750916361526e-05,
      "loss": 0.0512,
      "step": 490
    },
    {
      "epoch": 2.46,
      "grad_norm": 9.374113082885742,
      "learning_rate": 1.1073369620338928e-05,
      "loss": 0.0604,
      "step": 500
    },
    {
      "epoch": 2.51,
      "grad_norm": 4.585148811340332,
      "learning_rate": 1.074884845112512e-05,
      "loss": 0.0629,
      "step": 510
    },
    {
      "epoch": 2.56,
      "grad_norm": 9.917503356933594,
      "learning_rate": 1.0423532036492077e-05,
      "loss": 0.054,
      "step": 520
    },
    {
      "epoch": 2.61,
      "grad_norm": 1.8329569101333618,
      "learning_rate": 1.0097765848728825e-05,
      "loss": 0.071,
      "step": 530
    },
    {
      "epoch": 2.66,
      "grad_norm": 10.834183692932129,
      "learning_rate": 9.771895837764438e-06,
      "loss": 0.0642,
      "step": 540
    },
    {
      "epoch": 2.71,
      "grad_norm": 5.503483295440674,
      "learning_rate": 9.446268063783853e-06,
      "loss": 0.0654,
      "step": 550
    },
    {
      "epoch": 2.76,
      "grad_norm": 6.054934024810791,
      "learning_rate": 9.121228329726563e-06,
      "loss": 0.061,
      "step": 560
    },
    {
      "epoch": 2.8,
      "grad_norm": 8.71143627166748,
      "learning_rate": 8.797121814058502e-06,
      "loss": 0.0759,
      "step": 570
    },
    {
      "epoch": 2.85,
      "grad_norm": 4.225427150726318,
      "learning_rate": 8.474292704207095e-06,
      "loss": 0.0662,
      "step": 580
    },
    {
      "epoch": 2.9,
      "grad_norm": 6.926836967468262,
      "learning_rate": 8.153083831048772e-06,
      "loss": 0.07,
      "step": 590
    },
    {
      "epoch": 2.95,
      "grad_norm": 1.132318377494812,
      "learning_rate": 7.833836304837022e-06,
      "loss": 0.0402,
      "step": 600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9809941520467836,
      "eval_f1": 0.9816895632855951,
      "eval_loss": 0.04637432098388672,
      "eval_matthews_correlation": 0.8468348607550005,
      "eval_precision": 0.9830779451248668,
      "eval_recall": 0.9809941520467836,
      "eval_runtime": 5.1222,
      "eval_samples_per_second": 133.536,
      "eval_steps_per_second": 8.395,
      "step": 609
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.548271656036377,
      "learning_rate": 7.516889152957744e-06,
      "loss": 0.0706,
      "step": 610
    },
    {
      "epoch": 3.05,
      "grad_norm": 17.59124755859375,
      "learning_rate": 7.202578959896491e-06,
      "loss": 0.0777,
      "step": 620
    },
    {
      "epoch": 3.1,
      "grad_norm": 10.620137214660645,
      "learning_rate": 6.891239509799932e-06,
      "loss": 0.0443,
      "step": 630
    },
    {
      "epoch": 3.15,
      "grad_norm": 20.15471839904785,
      "learning_rate": 6.583201432011217e-06,
      "loss": 0.0746,
      "step": 640
    },
    {
      "epoch": 3.2,
      "grad_norm": 7.445899486541748,
      "learning_rate": 6.278791849955583e-06,
      "loss": 0.0468,
      "step": 650
    },
    {
      "epoch": 3.25,
      "grad_norm": 10.309353828430176,
      "learning_rate": 5.978334033749076e-06,
      "loss": 0.0698,
      "step": 660
    },
    {
      "epoch": 3.3,
      "grad_norm": 4.898565769195557,
      "learning_rate": 5.682147056899361e-06,
      "loss": 0.058,
      "step": 670
    },
    {
      "epoch": 3.35,
      "grad_norm": 8.0520658493042,
      "learning_rate": 5.390545457463134e-06,
      "loss": 0.0468,
      "step": 680
    },
    {
      "epoch": 3.39,
      "grad_norm": 3.444305419921875,
      "learning_rate": 5.103838904019993e-06,
      "loss": 0.0381,
      "step": 690
    },
    {
      "epoch": 3.44,
      "grad_norm": 11.149181365966797,
      "learning_rate": 4.822331866817478e-06,
      "loss": 0.0693,
      "step": 700
    },
    {
      "epoch": 3.49,
      "grad_norm": 12.743651390075684,
      "learning_rate": 4.546323294436556e-06,
      "loss": 0.0739,
      "step": 710
    },
    {
      "epoch": 3.54,
      "grad_norm": 9.802193641662598,
      "learning_rate": 4.276106296320828e-06,
      "loss": 0.0655,
      "step": 720
    },
    {
      "epoch": 3.59,
      "grad_norm": 6.496978759765625,
      "learning_rate": 4.0119678315067025e-06,
      "loss": 0.066,
      "step": 730
    },
    {
      "epoch": 3.64,
      "grad_norm": 12.13724422454834,
      "learning_rate": 3.754188403885013e-06,
      "loss": 0.0483,
      "step": 740
    },
    {
      "epoch": 3.69,
      "grad_norm": 11.302549362182617,
      "learning_rate": 3.5030417643177416e-06,
      "loss": 0.0727,
      "step": 750
    },
    {
      "epoch": 3.74,
      "grad_norm": 3.291935443878174,
      "learning_rate": 3.258794619926159e-06,
      "loss": 0.0685,
      "step": 760
    },
    {
      "epoch": 3.79,
      "grad_norm": 7.776196479797363,
      "learning_rate": 3.021706350859147e-06,
      "loss": 0.0482,
      "step": 770
    },
    {
      "epoch": 3.84,
      "grad_norm": 7.8189568519592285,
      "learning_rate": 2.792028734842418e-06,
      "loss": 0.0504,
      "step": 780
    },
    {
      "epoch": 3.89,
      "grad_norm": 1.9077569246292114,
      "learning_rate": 2.5700056798012164e-06,
      "loss": 0.0578,
      "step": 790
    },
    {
      "epoch": 3.94,
      "grad_norm": 5.7739667892456055,
      "learning_rate": 2.3558729648404065e-06,
      "loss": 0.0712,
      "step": 800
    },
    {
      "epoch": 3.99,
      "grad_norm": 6.1386027336120605,
      "learning_rate": 2.1498579898570228e-06,
      "loss": 0.0334,
      "step": 810
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9868421052631579,
      "eval_f1": 0.986916249885884,
      "eval_loss": 0.03484980762004852,
      "eval_matthews_correlation": 0.884636226651146,
      "eval_precision": 0.9870070425284395,
      "eval_recall": 0.9868421052631579,
      "eval_runtime": 5.1774,
      "eval_samples_per_second": 132.112,
      "eval_steps_per_second": 8.305,
      "step": 813
    },
    {
      "epoch": 4.03,
      "grad_norm": 2.534424304962158,
      "learning_rate": 1.952179534051183e-06,
      "loss": 0.0613,
      "step": 820
    },
    {
      "epoch": 4.08,
      "grad_norm": 3.645782947540283,
      "learning_rate": 1.763047523591831e-06,
      "loss": 0.0817,
      "step": 830
    },
    {
      "epoch": 4.13,
      "grad_norm": 10.930766105651855,
      "learning_rate": 1.5826628086839968e-06,
      "loss": 0.081,
      "step": 840
    },
    {
      "epoch": 4.18,
      "grad_norm": 6.021533489227295,
      "learning_rate": 1.41121695027438e-06,
      "loss": 0.0522,
      "step": 850
    },
    {
      "epoch": 4.23,
      "grad_norm": 6.584732532501221,
      "learning_rate": 1.2488920166217034e-06,
      "loss": 0.054,
      "step": 860
    },
    {
      "epoch": 4.28,
      "grad_norm": 5.629753112792969,
      "learning_rate": 1.095860389947928e-06,
      "loss": 0.0475,
      "step": 870
    },
    {
      "epoch": 4.33,
      "grad_norm": 4.272614479064941,
      "learning_rate": 9.522845833756001e-07,
      "loss": 0.0458,
      "step": 880
    },
    {
      "epoch": 4.38,
      "grad_norm": 9.34067153930664,
      "learning_rate": 8.183170683457986e-07,
      "loss": 0.0746,
      "step": 890
    },
    {
      "epoch": 4.43,
      "grad_norm": 2.2390189170837402,
      "learning_rate": 6.941001126998892e-07,
      "loss": 0.0509,
      "step": 900
    },
    {
      "epoch": 4.48,
      "grad_norm": 1.508949637413025,
      "learning_rate": 5.797656295970955e-07,
      "loss": 0.0329,
      "step": 910
    },
    {
      "epoch": 4.53,
      "grad_norm": 7.0009355545043945,
      "learning_rate": 4.754350374283001e-07,
      "loss": 0.0709,
      "step": 920
    },
    {
      "epoch": 4.58,
      "grad_norm": 6.07660436630249,
      "learning_rate": 3.8121913087483033e-07,
      "loss": 0.0393,
      "step": 930
    },
    {
      "epoch": 4.62,
      "grad_norm": 6.966567039489746,
      "learning_rate": 2.972179632491989e-07,
      "loss": 0.0464,
      "step": 940
    },
    {
      "epoch": 4.67,
      "grad_norm": 3.8328962326049805,
      "learning_rate": 2.23520740242712e-07,
      "loss": 0.0457,
      "step": 950
    },
    {
      "epoch": 4.72,
      "grad_norm": 3.535372018814087,
      "learning_rate": 1.602057251927891e-07,
      "loss": 0.0599,
      "step": 960
    },
    {
      "epoch": 4.77,
      "grad_norm": 11.542516708374023,
      "learning_rate": 1.0734015597060222e-07,
      "loss": 0.0557,
      "step": 970
    },
    {
      "epoch": 4.82,
      "grad_norm": 7.840158939361572,
      "learning_rate": 6.498017357731035e-08,
      "loss": 0.0564,
      "step": 980
    },
    {
      "epoch": 4.87,
      "grad_norm": 3.7357852458953857,
      "learning_rate": 3.317076252467133e-08,
      "loss": 0.033,
      "step": 990
    },
    {
      "epoch": 4.92,
      "grad_norm": 4.429032802581787,
      "learning_rate": 1.1945703063402925e-08,
      "loss": 0.0496,
      "step": 1000
    },
    {
      "epoch": 4.97,
      "grad_norm": 4.065526485443115,
      "learning_rate": 1.327535309979533e-09,
      "loss": 0.0445,
      "step": 1010
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.9883040935672515,
      "eval_f1": 0.9883040935672515,
      "eval_loss": 0.03396734222769737,
      "eval_matthews_correlation": 0.8962181845768691,
      "eval_precision": 0.9883040935672515,
      "eval_recall": 0.9883040935672515,
      "eval_runtime": 5.2898,
      "eval_samples_per_second": 129.305,
      "eval_steps_per_second": 8.129,
      "step": 1015
    },
    {
      "epoch": 4.99,
      "step": 1015,
      "total_flos": 2.581447650539471e+18,
      "train_loss": 0.08031210996247277,
      "train_runtime": 701.9998,
      "train_samples_per_second": 92.557,
      "train_steps_per_second": 1.446
    }
  ],
  "logging_steps": 10,
  "max_steps": 1015,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2.581447650539471e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}