{
  "best_global_step": 610,
  "best_metric": 0.6933962264150944,
  "best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-610",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1830,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.040983606557377046,
      "grad_norm": 3.1041932106018066,
      "learning_rate": 1.573770491803279e-06,
      "loss": 0.526744384765625,
      "step": 25
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 4.816498279571533,
      "learning_rate": 3.213114754098361e-06,
      "loss": 0.46380462646484377,
      "step": 50
    },
    {
      "epoch": 0.12295081967213115,
      "grad_norm": 5.105863571166992,
      "learning_rate": 4.8524590163934435e-06,
      "loss": 0.3628129577636719,
      "step": 75
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 3.479628324508667,
      "learning_rate": 6.491803278688526e-06,
      "loss": 0.3321057891845703,
      "step": 100
    },
    {
      "epoch": 0.20491803278688525,
      "grad_norm": 5.271286487579346,
      "learning_rate": 8.131147540983607e-06,
      "loss": 0.29200584411621094,
      "step": 125
    },
    {
      "epoch": 0.2459016393442623,
      "grad_norm": 2.9103591442108154,
      "learning_rate": 9.770491803278689e-06,
      "loss": 0.20765865325927735,
      "step": 150
    },
    {
      "epoch": 0.28688524590163933,
      "grad_norm": 5.441774845123291,
      "learning_rate": 1.1409836065573771e-05,
      "loss": 0.22107566833496095,
      "step": 175
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 17.181110382080078,
      "learning_rate": 1.3049180327868853e-05,
      "loss": 0.22224016189575196,
      "step": 200
    },
    {
      "epoch": 0.36885245901639346,
      "grad_norm": 5.543371677398682,
      "learning_rate": 1.4688524590163935e-05,
      "loss": 0.20201002120971678,
      "step": 225
    },
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 5.812751770019531,
      "learning_rate": 1.6327868852459016e-05,
      "loss": 0.2299608612060547,
      "step": 250
    },
    {
      "epoch": 0.45081967213114754,
      "grad_norm": 2.845670461654663,
      "learning_rate": 1.79672131147541e-05,
      "loss": 0.21673511505126952,
      "step": 275
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 18.98938751220703,
      "learning_rate": 1.9606557377049183e-05,
      "loss": 0.21523273468017579,
      "step": 300
    },
    {
      "epoch": 0.5327868852459017,
      "grad_norm": 5.82402229309082,
      "learning_rate": 1.9861566484517306e-05,
      "loss": 0.15432929039001464,
      "step": 325
    },
    {
      "epoch": 0.5737704918032787,
      "grad_norm": 0.48278993368148804,
      "learning_rate": 1.9679417122040073e-05,
      "loss": 0.16572830200195313,
      "step": 350
    },
    {
      "epoch": 0.6147540983606558,
      "grad_norm": 5.946134567260742,
      "learning_rate": 1.9497267759562843e-05,
      "loss": 0.17543071746826172,
      "step": 375
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 13.494661331176758,
      "learning_rate": 1.9315118397085614e-05,
      "loss": 0.15327459335327148,
      "step": 400
    },
    {
      "epoch": 0.6967213114754098,
      "grad_norm": 9.058329582214355,
      "learning_rate": 1.913296903460838e-05,
      "loss": 0.19322505950927735,
      "step": 425
    },
    {
      "epoch": 0.7377049180327869,
      "grad_norm": 9.420262336730957,
      "learning_rate": 1.895081967213115e-05,
      "loss": 0.18702877044677735,
      "step": 450
    },
    {
      "epoch": 0.7786885245901639,
      "grad_norm": 0.29203546047210693,
      "learning_rate": 1.8768670309653917e-05,
      "loss": 0.13424430847167967,
      "step": 475
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 5.464226245880127,
      "learning_rate": 1.8586520947176687e-05,
      "loss": 0.1403522300720215,
      "step": 500
    },
    {
      "epoch": 0.860655737704918,
      "grad_norm": 0.3305734395980835,
      "learning_rate": 1.8404371584699454e-05,
      "loss": 0.1768626403808594,
      "step": 525
    },
    {
      "epoch": 0.9016393442622951,
      "grad_norm": 6.791965007781982,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 0.22005313873291016,
      "step": 550
    },
    {
      "epoch": 0.9426229508196722,
      "grad_norm": 3.971740484237671,
      "learning_rate": 1.804007285974499e-05,
      "loss": 0.17844413757324218,
      "step": 575
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 1.6787421703338623,
      "learning_rate": 1.785792349726776e-05,
      "loss": 0.16104537963867188,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9376199616122841,
      "eval_f1": 0.6933962264150944,
      "eval_loss": 0.17767289280891418,
      "eval_precision": 0.6533333333333333,
      "eval_recall": 0.7386934673366834,
      "eval_roc_auc": 0.9544433040534235,
      "eval_runtime": 8.7237,
      "eval_samples_per_second": 238.89,
      "eval_steps_per_second": 7.566,
      "step": 610
    },
    {
      "epoch": 1.0245901639344261,
      "grad_norm": 5.573081016540527,
      "learning_rate": 1.7675774134790528e-05,
      "loss": 0.10441858291625977,
      "step": 625
    },
    {
      "epoch": 1.0655737704918034,
      "grad_norm": 0.11036327481269836,
      "learning_rate": 1.7493624772313298e-05,
      "loss": 0.16641632080078125,
      "step": 650
    },
    {
      "epoch": 1.1065573770491803,
      "grad_norm": 6.172032833099365,
      "learning_rate": 1.731147540983607e-05,
      "loss": 0.14472474098205568,
      "step": 675
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 5.863953113555908,
      "learning_rate": 1.7129326047358835e-05,
      "loss": 0.1113892936706543,
      "step": 700
    },
    {
      "epoch": 1.1885245901639343,
      "grad_norm": 0.25357893109321594,
      "learning_rate": 1.6947176684881602e-05,
      "loss": 0.12171897888183594,
      "step": 725
    },
    {
      "epoch": 1.2295081967213115,
      "grad_norm": 4.559972763061523,
      "learning_rate": 1.6765027322404372e-05,
      "loss": 0.08190732002258301,
      "step": 750
    },
    {
      "epoch": 1.2704918032786885,
      "grad_norm": 5.443191051483154,
      "learning_rate": 1.6582877959927142e-05,
      "loss": 0.06097976684570312,
      "step": 775
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 7.672996997833252,
      "learning_rate": 1.6400728597449912e-05,
      "loss": 0.09989359855651855,
      "step": 800
    },
    {
      "epoch": 1.3524590163934427,
      "grad_norm": 0.30564695596694946,
      "learning_rate": 1.621857923497268e-05,
      "loss": 0.08488804817199708,
      "step": 825
    },
    {
      "epoch": 1.3934426229508197,
      "grad_norm": 0.5056689977645874,
      "learning_rate": 1.6036429872495446e-05,
      "loss": 0.15551289558410644,
      "step": 850
    },
    {
      "epoch": 1.4344262295081966,
      "grad_norm": 0.06402106583118439,
      "learning_rate": 1.5854280510018216e-05,
      "loss": 0.1194021987915039,
      "step": 875
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.8240995407104492,
      "learning_rate": 1.5672131147540986e-05,
      "loss": 0.11723342895507813,
      "step": 900
    },
    {
      "epoch": 1.5163934426229508,
      "grad_norm": 0.07588805258274078,
      "learning_rate": 1.5489981785063753e-05,
      "loss": 0.12805092811584473,
      "step": 925
    },
    {
      "epoch": 1.5573770491803278,
      "grad_norm": 29.323896408081055,
      "learning_rate": 1.5307832422586523e-05,
      "loss": 0.15534672737121583,
      "step": 950
    },
    {
      "epoch": 1.598360655737705,
      "grad_norm": 11.02952766418457,
      "learning_rate": 1.512568306010929e-05,
      "loss": 0.1811429214477539,
      "step": 975
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.9738644957542419,
      "learning_rate": 1.494353369763206e-05,
      "loss": 0.1270007610321045,
      "step": 1000
    },
    {
      "epoch": 1.680327868852459,
      "grad_norm": 2.311349630355835,
      "learning_rate": 1.4761384335154829e-05,
      "loss": 0.1843573570251465,
      "step": 1025
    },
    {
      "epoch": 1.721311475409836,
      "grad_norm": 7.105762004852295,
      "learning_rate": 1.4579234972677595e-05,
      "loss": 0.15470240592956544,
      "step": 1050
    },
    {
      "epoch": 1.762295081967213,
      "grad_norm": 9.120081901550293,
      "learning_rate": 1.4397085610200366e-05,
      "loss": 0.1170622444152832,
      "step": 1075
    },
    {
      "epoch": 1.8032786885245902,
      "grad_norm": 0.09794076532125473,
      "learning_rate": 1.4214936247723134e-05,
      "loss": 0.14307721138000487,
      "step": 1100
    },
    {
      "epoch": 1.8442622950819674,
      "grad_norm": 10.330300331115723,
      "learning_rate": 1.4032786885245904e-05,
      "loss": 0.15037315368652343,
      "step": 1125
    },
    {
      "epoch": 1.8852459016393444,
      "grad_norm": 0.7867186069488525,
      "learning_rate": 1.3850637522768671e-05,
      "loss": 0.10941274642944336,
      "step": 1150
    },
    {
      "epoch": 1.9262295081967213,
      "grad_norm": 7.952847003936768,
      "learning_rate": 1.366848816029144e-05,
      "loss": 0.1380799674987793,
      "step": 1175
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 11.602045059204102,
      "learning_rate": 1.348633879781421e-05,
      "loss": 0.07221244812011719,
      "step": 1200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.935700575815739,
      "eval_f1": 0.6854460093896714,
      "eval_loss": 0.24323046207427979,
      "eval_precision": 0.6431718061674009,
      "eval_recall": 0.7336683417085427,
      "eval_roc_auc": 0.9480599282886581,
      "eval_runtime": 8.6243,
      "eval_samples_per_second": 241.642,
      "eval_steps_per_second": 7.653,
      "step": 1220
    },
    {
      "epoch": 2.0081967213114753,
      "grad_norm": 4.202751636505127,
      "learning_rate": 1.3304189435336978e-05,
      "loss": 0.16997112274169923,
      "step": 1225
    },
    {
      "epoch": 2.0491803278688523,
      "grad_norm": 0.40695664286613464,
      "learning_rate": 1.3122040072859745e-05,
      "loss": 0.0950162410736084,
      "step": 1250
    },
    {
      "epoch": 2.0901639344262297,
      "grad_norm": 2.8617703914642334,
      "learning_rate": 1.2939890710382515e-05,
      "loss": 0.10194917678833008,
      "step": 1275
    },
    {
      "epoch": 2.1311475409836067,
      "grad_norm": 0.08977202326059341,
      "learning_rate": 1.2757741347905283e-05,
      "loss": 0.0662102746963501,
      "step": 1300
    },
    {
      "epoch": 2.1721311475409837,
      "grad_norm": 0.10930905491113663,
      "learning_rate": 1.2575591985428054e-05,
      "loss": 0.07460547924041748,
      "step": 1325
    },
    {
      "epoch": 2.2131147540983607,
      "grad_norm": 11.703680038452148,
      "learning_rate": 1.239344262295082e-05,
      "loss": 0.11810153961181641,
      "step": 1350
    },
    {
      "epoch": 2.2540983606557377,
      "grad_norm": 3.0462427139282227,
      "learning_rate": 1.2211293260473589e-05,
      "loss": 0.11896968841552734,
      "step": 1375
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 11.854302406311035,
      "learning_rate": 1.2029143897996359e-05,
      "loss": 0.10016871452331542,
      "step": 1400
    },
    {
      "epoch": 2.3360655737704916,
      "grad_norm": 5.737449645996094,
      "learning_rate": 1.1846994535519127e-05,
      "loss": 0.12308047294616699,
      "step": 1425
    },
    {
      "epoch": 2.3770491803278686,
      "grad_norm": 3.3703978061676025,
      "learning_rate": 1.1664845173041894e-05,
      "loss": 0.10508214950561523,
      "step": 1450
    },
    {
      "epoch": 2.418032786885246,
      "grad_norm": 15.429414749145508,
      "learning_rate": 1.1482695810564664e-05,
      "loss": 0.05040365219116211,
      "step": 1475
    },
    {
      "epoch": 2.459016393442623,
      "grad_norm": 14.725594520568848,
      "learning_rate": 1.1300546448087433e-05,
      "loss": 0.13564690589904785,
      "step": 1500
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.18430812656879425,
      "learning_rate": 1.1118397085610201e-05,
      "loss": 0.08556642532348632,
      "step": 1525
    },
    {
      "epoch": 2.540983606557377,
      "grad_norm": 0.062474410980939865,
      "learning_rate": 1.0936247723132968e-05,
      "loss": 0.08463016510009766,
      "step": 1550
    },
    {
      "epoch": 2.581967213114754,
      "grad_norm": 0.20876172184944153,
      "learning_rate": 1.0754098360655738e-05,
      "loss": 0.1799280548095703,
      "step": 1575
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 6.137902736663818,
      "learning_rate": 1.0571948998178507e-05,
      "loss": 0.12623875617980956,
      "step": 1600
    },
    {
      "epoch": 2.663934426229508,
      "grad_norm": 17.05773162841797,
      "learning_rate": 1.0389799635701277e-05,
      "loss": 0.09255536079406738,
      "step": 1625
    },
    {
      "epoch": 2.7049180327868854,
      "grad_norm": 1.2578394412994385,
      "learning_rate": 1.0207650273224044e-05,
      "loss": 0.0888406753540039,
      "step": 1650
    },
    {
      "epoch": 2.7459016393442623,
      "grad_norm": 15.845796585083008,
      "learning_rate": 1.0025500910746812e-05,
      "loss": 0.10764387130737305,
      "step": 1675
    },
    {
      "epoch": 2.7868852459016393,
      "grad_norm": 12.588105201721191,
      "learning_rate": 9.843351548269582e-06,
      "loss": 0.12151247024536133,
      "step": 1700
    },
    {
      "epoch": 2.8278688524590163,
      "grad_norm": 7.840113162994385,
      "learning_rate": 9.66120218579235e-06,
      "loss": 0.1787535858154297,
      "step": 1725
    },
    {
      "epoch": 2.8688524590163933,
      "grad_norm": 5.082641124725342,
      "learning_rate": 9.47905282331512e-06,
      "loss": 0.07576138019561768,
      "step": 1750
    },
    {
      "epoch": 2.9098360655737707,
      "grad_norm": 14.185094833374023,
      "learning_rate": 9.296903460837888e-06,
      "loss": 0.1186930274963379,
      "step": 1775
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 31.60809898376465,
      "learning_rate": 9.114754098360656e-06,
      "loss": 0.10553586959838868,
      "step": 1800
    },
    {
      "epoch": 2.9918032786885247,
      "grad_norm": 2.9622690677642822,
      "learning_rate": 8.932604735883426e-06,
      "loss": 0.054716997146606446,
      "step": 1825
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9414587332053743,
      "eval_f1": 0.6903553299492385,
      "eval_loss": 0.24261149764060974,
      "eval_precision": 0.6974358974358974,
      "eval_recall": 0.6834170854271356,
      "eval_roc_auc": 0.9521560054916492,
      "eval_runtime": 8.6527,
      "eval_samples_per_second": 240.849,
      "eval_steps_per_second": 7.628,
      "step": 1830
    }
  ],
  "logging_steps": 25,
  "max_steps": 3050,
  "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3849183184389120.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}