{
  "best_global_step": 6000,
  "best_metric": 0.8898390102551531,
  "best_model_checkpoint": "/home/rupak/Desktop/Topic-Modeling /topic modeling 25k/checkpoint/devbert-25k-2e5-256-16-10/checkpoint-6000",
  "epoch": 4.7964814074370254,
  "eval_steps": 1000,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007996801279488205,
      "grad_norm": 0.4310452938079834,
      "learning_rate": 0.0,
      "loss": 1.6087,
      "step": 1
    },
    {
      "epoch": 0.07996801279488205,
      "grad_norm": 0.26220083236694336,
      "learning_rate": 1.5840000000000002e-06,
      "loss": 1.6093,
      "step": 100
    },
    {
      "epoch": 0.1599360255897641,
      "grad_norm": 0.3472769856452942,
      "learning_rate": 3.1840000000000003e-06,
      "loss": 1.6084,
      "step": 200
    },
    {
      "epoch": 0.23990403838464613,
      "grad_norm": 1.6449540853500366,
      "learning_rate": 4.784e-06,
      "loss": 1.5805,
      "step": 300
    },
    {
      "epoch": 0.3198720511795282,
      "grad_norm": 1.4127591848373413,
      "learning_rate": 6.384e-06,
      "loss": 1.5188,
      "step": 400
    },
    {
      "epoch": 0.39984006397441024,
      "grad_norm": 5.077271461486816,
      "learning_rate": 7.984e-06,
      "loss": 1.4544,
      "step": 500
    },
    {
      "epoch": 0.47980807676929227,
      "grad_norm": 3.5584030151367188,
      "learning_rate": 9.584000000000002e-06,
      "loss": 1.3958,
      "step": 600
    },
    {
      "epoch": 0.5597760895641744,
      "grad_norm": 1.296074628829956,
      "learning_rate": 1.1184000000000002e-05,
      "loss": 1.3197,
      "step": 700
    },
    {
      "epoch": 0.6397441023590564,
      "grad_norm": 4.501991271972656,
      "learning_rate": 1.2784000000000002e-05,
      "loss": 1.2325,
      "step": 800
    },
    {
      "epoch": 0.7197121151539384,
      "grad_norm": 4.654054641723633,
      "learning_rate": 1.4384e-05,
      "loss": 1.1412,
      "step": 900
    },
    {
      "epoch": 0.7996801279488205,
      "grad_norm": 9.384488105773926,
      "learning_rate": 1.5984e-05,
      "loss": 1.0117,
      "step": 1000
    },
    {
      "epoch": 0.7996801279488205,
      "eval_accuracy": 0.8544582167133147,
      "eval_auroc_macro": 0.9618420886180832,
      "eval_auroc_weighted": 0.9615798480537472,
      "eval_f1_macro": 0.856019875266712,
      "eval_f1_weighted": 0.8547019706773432,
      "eval_loss": 0.9337552785873413,
      "eval_precision_macro": 0.8603184903555862,
      "eval_precision_weighted": 0.8583909253103899,
      "eval_recall_macro": 0.8551493399366249,
      "eval_recall_weighted": 0.8544582167133147,
      "eval_runtime": 5.4107,
      "eval_samples_per_second": 462.236,
      "eval_steps_per_second": 57.849,
      "step": 1000
    },
    {
      "epoch": 0.8796481407437026,
      "grad_norm": 18.203306198120117,
      "learning_rate": 1.7584e-05,
      "loss": 0.8998,
      "step": 1100
    },
    {
      "epoch": 0.9596161535385845,
      "grad_norm": 2.7862212657928467,
      "learning_rate": 1.9184e-05,
      "loss": 0.766,
      "step": 1200
    },
    {
      "epoch": 1.0391843262694922,
      "grad_norm": 18.253963470458984,
      "learning_rate": 1.991296625222025e-05,
      "loss": 0.6664,
      "step": 1300
    },
    {
      "epoch": 1.1191523390643743,
      "grad_norm": 7.593320846557617,
      "learning_rate": 1.9735346358792185e-05,
      "loss": 0.5607,
      "step": 1400
    },
    {
      "epoch": 1.1991203518592564,
      "grad_norm": 59.942806243896484,
      "learning_rate": 1.955772646536412e-05,
      "loss": 0.5403,
      "step": 1500
    },
    {
      "epoch": 1.2790883646541382,
      "grad_norm": 0.7725094556808472,
      "learning_rate": 1.938010657193606e-05,
      "loss": 0.4974,
      "step": 1600
    },
    {
      "epoch": 1.3590563774490203,
      "grad_norm": 16.6025447845459,
      "learning_rate": 1.9202486678507993e-05,
      "loss": 0.4151,
      "step": 1700
    },
    {
      "epoch": 1.4390243902439024,
      "grad_norm": 1.1761209964752197,
      "learning_rate": 1.902486678507993e-05,
      "loss": 0.4706,
      "step": 1800
    },
    {
      "epoch": 1.5189924030387845,
      "grad_norm": 54.583980560302734,
      "learning_rate": 1.884724689165187e-05,
      "loss": 0.4467,
      "step": 1900
    },
    {
      "epoch": 1.5989604158336665,
      "grad_norm": 11.942007064819336,
      "learning_rate": 1.86696269982238e-05,
      "loss": 0.4461,
      "step": 2000
    },
    {
      "epoch": 1.5989604158336665,
      "eval_accuracy": 0.8764494202319072,
      "eval_auroc_macro": 0.9746426854506958,
      "eval_auroc_weighted": 0.9743177557711681,
      "eval_f1_macro": 0.8768568573710604,
      "eval_f1_weighted": 0.8756671988428442,
      "eval_loss": 0.44375643134117126,
      "eval_precision_macro": 0.8779572504070272,
      "eval_precision_weighted": 0.8777298556014099,
      "eval_recall_macro": 0.8785597331691118,
      "eval_recall_weighted": 0.8764494202319072,
      "eval_runtime": 5.1574,
      "eval_samples_per_second": 484.93,
      "eval_steps_per_second": 60.689,
      "step": 2000
    },
    {
      "epoch": 1.6789284286285486,
      "grad_norm": 9.612055778503418,
      "learning_rate": 1.849200710479574e-05,
      "loss": 0.3987,
      "step": 2100
    },
    {
      "epoch": 1.7588964414234307,
      "grad_norm": 5.084634780883789,
      "learning_rate": 1.8314387211367673e-05,
      "loss": 0.3739,
      "step": 2200
    },
    {
      "epoch": 1.8388644542183128,
      "grad_norm": 6.8124189376831055,
      "learning_rate": 1.813676731793961e-05,
      "loss": 0.3977,
      "step": 2300
    },
    {
      "epoch": 1.9188324670131949,
      "grad_norm": 10.295258522033691,
      "learning_rate": 1.795914742451155e-05,
      "loss": 0.3448,
      "step": 2400
    },
    {
      "epoch": 1.9988004798080767,
      "grad_norm": 38.840545654296875,
      "learning_rate": 1.778152753108348e-05,
      "loss": 0.3768,
      "step": 2500
    },
    {
      "epoch": 2.0783686525389844,
      "grad_norm": 22.47418975830078,
      "learning_rate": 1.760390763765542e-05,
      "loss": 0.295,
      "step": 2600
    },
    {
      "epoch": 2.1583366653338665,
      "grad_norm": 4.453575611114502,
      "learning_rate": 1.7426287744227356e-05,
      "loss": 0.2606,
      "step": 2700
    },
    {
      "epoch": 2.2383046781287486,
      "grad_norm": 16.484058380126953,
      "learning_rate": 1.724866785079929e-05,
      "loss": 0.2679,
      "step": 2800
    },
    {
      "epoch": 2.3182726909236306,
      "grad_norm": 12.952738761901855,
      "learning_rate": 1.7071047957371228e-05,
      "loss": 0.3045,
      "step": 2900
    },
    {
      "epoch": 2.3982407037185127,
      "grad_norm": 11.249642372131348,
      "learning_rate": 1.6893428063943164e-05,
      "loss": 0.2717,
      "step": 3000
    },
    {
      "epoch": 2.3982407037185127,
      "eval_accuracy": 0.8864454218312675,
      "eval_auroc_macro": 0.9779443713757704,
      "eval_auroc_weighted": 0.9775420371638723,
      "eval_f1_macro": 0.8870663037749968,
      "eval_f1_weighted": 0.8858490764571578,
      "eval_loss": 0.446412593126297,
      "eval_precision_macro": 0.8872521228455227,
      "eval_precision_weighted": 0.8864077664482325,
      "eval_recall_macro": 0.887994043517794,
      "eval_recall_weighted": 0.8864454218312675,
      "eval_runtime": 11.1989,
      "eval_samples_per_second": 223.326,
      "eval_steps_per_second": 27.949,
      "step": 3000
    },
    {
      "epoch": 2.478208716513395,
      "grad_norm": 7.011690616607666,
      "learning_rate": 1.67158081705151e-05,
      "loss": 0.2891,
      "step": 3100
    },
    {
      "epoch": 2.5581767293082764,
      "grad_norm": 31.688766479492188,
      "learning_rate": 1.6538188277087036e-05,
      "loss": 0.272,
      "step": 3200
    },
    {
      "epoch": 2.638144742103159,
      "grad_norm": 41.41433334350586,
      "learning_rate": 1.636056838365897e-05,
      "loss": 0.2974,
      "step": 3300
    },
    {
      "epoch": 2.7181127548980406,
      "grad_norm": 19.226070404052734,
      "learning_rate": 1.6182948490230908e-05,
      "loss": 0.2716,
      "step": 3400
    },
    {
      "epoch": 2.7980807676929227,
      "grad_norm": 10.691811561584473,
      "learning_rate": 1.6005328596802844e-05,
      "loss": 0.3165,
      "step": 3500
    },
    {
      "epoch": 2.8780487804878048,
      "grad_norm": 41.410648345947266,
      "learning_rate": 1.582770870337478e-05,
      "loss": 0.2957,
      "step": 3600
    },
    {
      "epoch": 2.958016793282687,
      "grad_norm": 23.03882598876953,
      "learning_rate": 1.5650088809946716e-05,
      "loss": 0.2706,
      "step": 3700
    },
    {
      "epoch": 3.0375849660135947,
      "grad_norm": 15.799474716186523,
      "learning_rate": 1.5472468916518652e-05,
      "loss": 0.2558,
      "step": 3800
    },
    {
      "epoch": 3.117552978808477,
      "grad_norm": 55.276039123535156,
      "learning_rate": 1.5294849023090588e-05,
      "loss": 0.1939,
      "step": 3900
    },
    {
      "epoch": 3.1975209916033585,
      "grad_norm": 0.27553507685661316,
      "learning_rate": 1.5117229129662522e-05,
      "loss": 0.1901,
      "step": 4000
    },
    {
      "epoch": 3.1975209916033585,
      "eval_accuracy": 0.8780487804878049,
      "eval_auroc_macro": 0.9775238021803437,
      "eval_auroc_weighted": 0.9771502062836797,
      "eval_f1_macro": 0.8782218318403483,
      "eval_f1_weighted": 0.8773058500309727,
      "eval_loss": 0.5235865712165833,
      "eval_precision_macro": 0.879600015200233,
      "eval_precision_weighted": 0.8798996264465522,
      "eval_recall_macro": 0.8801531290003837,
      "eval_recall_weighted": 0.8780487804878049,
      "eval_runtime": 10.9914,
      "eval_samples_per_second": 227.541,
      "eval_steps_per_second": 28.477,
      "step": 4000
    },
    {
      "epoch": 3.2774890043982405,
      "grad_norm": 18.42435073852539,
      "learning_rate": 1.493960923623446e-05,
      "loss": 0.1653,
      "step": 4100
    },
    {
      "epoch": 3.3574570171931226,
      "grad_norm": 17.452335357666016,
      "learning_rate": 1.4761989342806396e-05,
      "loss": 0.1836,
      "step": 4200
    },
    {
      "epoch": 3.4374250299880047,
      "grad_norm": 15.6238431930542,
      "learning_rate": 1.458436944937833e-05,
      "loss": 0.2147,
      "step": 4300
    },
    {
      "epoch": 3.517393042782887,
      "grad_norm": 12.460476875305176,
      "learning_rate": 1.4406749555950268e-05,
      "loss": 0.1915,
      "step": 4400
    },
    {
      "epoch": 3.597361055577769,
      "grad_norm": 0.0901951715350151,
      "learning_rate": 1.4229129662522204e-05,
      "loss": 0.1974,
      "step": 4500
    },
    {
      "epoch": 3.677329068372651,
      "grad_norm": 32.219451904296875,
      "learning_rate": 1.4051509769094141e-05,
      "loss": 0.2216,
      "step": 4600
    },
    {
      "epoch": 3.757297081167533,
      "grad_norm": 36.39286804199219,
      "learning_rate": 1.3873889875666075e-05,
      "loss": 0.2213,
      "step": 4700
    },
    {
      "epoch": 3.837265093962415,
      "grad_norm": 17.522869110107422,
      "learning_rate": 1.3696269982238011e-05,
      "loss": 0.1782,
      "step": 4800
    },
    {
      "epoch": 3.917233106757297,
      "grad_norm": 25.343130111694336,
      "learning_rate": 1.3518650088809947e-05,
      "loss": 0.2049,
      "step": 4900
    },
    {
      "epoch": 3.9972011195521793,
      "grad_norm": 22.79625701904297,
      "learning_rate": 1.3341030195381883e-05,
      "loss": 0.243,
      "step": 5000
    },
    {
      "epoch": 3.9972011195521793,
      "eval_accuracy": 0.8780487804878049,
      "eval_auroc_macro": 0.9782727204836601,
      "eval_auroc_weighted": 0.9777861708465245,
      "eval_f1_macro": 0.8777430745584673,
      "eval_f1_weighted": 0.876559163117517,
      "eval_loss": 0.513638973236084,
      "eval_precision_macro": 0.8786821562656968,
      "eval_precision_weighted": 0.8789539637786691,
      "eval_recall_macro": 0.8805887059904469,
      "eval_recall_weighted": 0.8780487804878049,
      "eval_runtime": 10.6315,
      "eval_samples_per_second": 235.244,
      "eval_steps_per_second": 29.441,
      "step": 5000
    },
    {
      "epoch": 4.076769292283087,
      "grad_norm": 0.23742330074310303,
      "learning_rate": 1.3163410301953821e-05,
      "loss": 0.1388,
      "step": 5100
    },
    {
      "epoch": 4.156737305077969,
      "grad_norm": 28.940744400024414,
      "learning_rate": 1.2985790408525755e-05,
      "loss": 0.1438,
      "step": 5200
    },
    {
      "epoch": 4.23670531787285,
      "grad_norm": 1.0431197881698608,
      "learning_rate": 1.2808170515097691e-05,
      "loss": 0.1472,
      "step": 5300
    },
    {
      "epoch": 4.316673330667733,
      "grad_norm": 0.15917949378490448,
      "learning_rate": 1.2630550621669629e-05,
      "loss": 0.1311,
      "step": 5400
    },
    {
      "epoch": 4.396641343462615,
      "grad_norm": 0.9857933521270752,
      "learning_rate": 1.2452930728241563e-05,
      "loss": 0.1344,
      "step": 5500
    },
    {
      "epoch": 4.476609356257497,
      "grad_norm": 6.277559280395508,
      "learning_rate": 1.22753108348135e-05,
      "loss": 0.1485,
      "step": 5600
    },
    {
      "epoch": 4.556577369052379,
      "grad_norm": 9.504846572875977,
      "learning_rate": 1.2097690941385437e-05,
      "loss": 0.1595,
      "step": 5700
    },
    {
      "epoch": 4.636545381847261,
      "grad_norm": 21.835948944091797,
      "learning_rate": 1.1920071047957371e-05,
      "loss": 0.1244,
      "step": 5800
    },
    {
      "epoch": 4.716513394642143,
      "grad_norm": 29.40694236755371,
      "learning_rate": 1.1742451154529309e-05,
      "loss": 0.1769,
      "step": 5900
    },
    {
      "epoch": 4.7964814074370254,
      "grad_norm": 0.27311843633651733,
      "learning_rate": 1.1564831261101243e-05,
      "loss": 0.1324,
      "step": 6000
    },
    {
      "epoch": 4.7964814074370254,
      "eval_accuracy": 0.8904438224710116,
      "eval_auroc_macro": 0.9776520963746929,
      "eval_auroc_weighted": 0.9772511883623387,
      "eval_f1_macro": 0.8908663046661234,
      "eval_f1_weighted": 0.8898390102551531,
      "eval_loss": 0.5423629283905029,
      "eval_precision_macro": 0.8905857912652019,
      "eval_precision_weighted": 0.8900698959322657,
      "eval_recall_macro": 0.8919702300588481,
      "eval_recall_weighted": 0.8904438224710116,
      "eval_runtime": 10.8006,
      "eval_samples_per_second": 231.562,
      "eval_steps_per_second": 28.98,
      "step": 6000
    }
  ],
  "logging_steps": 100,
  "max_steps": 12510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 15,
        "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": 1615218552661368.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}