{
  "best_global_step": 716,
  "best_metric": 0.9046100241222194,
  "best_model_checkpoint": "../results\\checkpoint-716",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1074,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 3.396728038787842,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.7053,
      "step": 10
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 4.982423782348633,
      "learning_rate": 2.5333333333333338e-06,
      "loss": 0.6988,
      "step": 20
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 2.757077217102051,
      "learning_rate": 3.866666666666667e-06,
      "loss": 0.6758,
      "step": 30
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 2.6699273586273193,
      "learning_rate": 5.2e-06,
      "loss": 0.6315,
      "step": 40
    },
    {
      "epoch": 0.27932960893854747,
      "grad_norm": 4.097516059875488,
      "learning_rate": 6.533333333333334e-06,
      "loss": 0.6425,
      "step": 50
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 4.445736408233643,
      "learning_rate": 7.866666666666667e-06,
      "loss": 0.6255,
      "step": 60
    },
    {
      "epoch": 0.39106145251396646,
      "grad_norm": 4.867759704589844,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.5891,
      "step": 70
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 6.38022518157959,
      "learning_rate": 1.0533333333333333e-05,
      "loss": 0.4952,
      "step": 80
    },
    {
      "epoch": 0.5027932960893855,
      "grad_norm": 3.1345021724700928,
      "learning_rate": 1.186666666666667e-05,
      "loss": 0.5234,
      "step": 90
    },
    {
      "epoch": 0.5586592178770949,
      "grad_norm": 5.645432949066162,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 0.5089,
      "step": 100
    },
    {
      "epoch": 0.6145251396648045,
      "grad_norm": 3.7119741439819336,
      "learning_rate": 1.4533333333333335e-05,
      "loss": 0.4735,
      "step": 110
    },
    {
      "epoch": 0.6703910614525139,
      "grad_norm": 8.215346336364746,
      "learning_rate": 1.586666666666667e-05,
      "loss": 0.5003,
      "step": 120
    },
    {
      "epoch": 0.7262569832402235,
      "grad_norm": 5.145977020263672,
      "learning_rate": 1.72e-05,
      "loss": 0.4147,
      "step": 130
    },
    {
      "epoch": 0.7821229050279329,
      "grad_norm": 2.537804126739502,
      "learning_rate": 1.8533333333333334e-05,
      "loss": 0.3685,
      "step": 140
    },
    {
      "epoch": 0.8379888268156425,
      "grad_norm": 4.58748722076416,
      "learning_rate": 1.9866666666666667e-05,
      "loss": 0.3349,
      "step": 150
    },
    {
      "epoch": 0.8938547486033519,
      "grad_norm": 5.2894134521484375,
      "learning_rate": 1.9836808703535813e-05,
      "loss": 0.294,
      "step": 160
    },
    {
      "epoch": 0.9497206703910615,
      "grad_norm": 19.09000015258789,
      "learning_rate": 1.9655485040797827e-05,
      "loss": 0.288,
      "step": 170
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8775510204081632,
      "eval_f1": 0.8773557452999963,
      "eval_loss": 0.30696821212768555,
      "eval_precision": 0.8774895500368822,
      "eval_recall": 0.8775510204081632,
      "eval_runtime": 44.9376,
      "eval_samples_per_second": 3.271,
      "eval_steps_per_second": 0.111,
      "step": 179
    },
    {
      "epoch": 1.005586592178771,
      "grad_norm": 5.151806354522705,
      "learning_rate": 1.9474161378059838e-05,
      "loss": 0.2949,
      "step": 180
    },
    {
      "epoch": 1.0614525139664805,
      "grad_norm": 5.022265911102295,
      "learning_rate": 1.9292837715321852e-05,
      "loss": 0.165,
      "step": 190
    },
    {
      "epoch": 1.1173184357541899,
      "grad_norm": 9.743254661560059,
      "learning_rate": 1.9111514052583863e-05,
      "loss": 0.2579,
      "step": 200
    },
    {
      "epoch": 1.1731843575418994,
      "grad_norm": 12.344402313232422,
      "learning_rate": 1.8930190389845877e-05,
      "loss": 0.283,
      "step": 210
    },
    {
      "epoch": 1.229050279329609,
      "grad_norm": 6.7589111328125,
      "learning_rate": 1.8748866727107888e-05,
      "loss": 0.2604,
      "step": 220
    },
    {
      "epoch": 1.2849162011173183,
      "grad_norm": 3.3086533546447754,
      "learning_rate": 1.8567543064369902e-05,
      "loss": 0.1972,
      "step": 230
    },
    {
      "epoch": 1.3407821229050279,
      "grad_norm": 5.3050923347473145,
      "learning_rate": 1.8386219401631916e-05,
      "loss": 0.2585,
      "step": 240
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 4.015077590942383,
      "learning_rate": 1.8204895738893927e-05,
      "loss": 0.2061,
      "step": 250
    },
    {
      "epoch": 1.452513966480447,
      "grad_norm": 3.9509942531585693,
      "learning_rate": 1.802357207615594e-05,
      "loss": 0.2497,
      "step": 260
    },
    {
      "epoch": 1.5083798882681565,
      "grad_norm": 5.380828857421875,
      "learning_rate": 1.784224841341795e-05,
      "loss": 0.2784,
      "step": 270
    },
    {
      "epoch": 1.564245810055866,
      "grad_norm": 3.400120973587036,
      "learning_rate": 1.7660924750679966e-05,
      "loss": 0.2659,
      "step": 280
    },
    {
      "epoch": 1.6201117318435754,
      "grad_norm": 1.753212809562683,
      "learning_rate": 1.7479601087941977e-05,
      "loss": 0.2076,
      "step": 290
    },
    {
      "epoch": 1.675977653631285,
      "grad_norm": 5.839695930480957,
      "learning_rate": 1.729827742520399e-05,
      "loss": 0.2168,
      "step": 300
    },
    {
      "epoch": 1.7318435754189943,
      "grad_norm": 3.75396466255188,
      "learning_rate": 1.7116953762466005e-05,
      "loss": 0.1925,
      "step": 310
    },
    {
      "epoch": 1.7877094972067038,
      "grad_norm": 4.7805986404418945,
      "learning_rate": 1.6935630099728016e-05,
      "loss": 0.2179,
      "step": 320
    },
    {
      "epoch": 1.8435754189944134,
      "grad_norm": 15.363788604736328,
      "learning_rate": 1.675430643699003e-05,
      "loss": 0.2328,
      "step": 330
    },
    {
      "epoch": 1.899441340782123,
      "grad_norm": 4.211331844329834,
      "learning_rate": 1.657298277425204e-05,
      "loss": 0.1723,
      "step": 340
    },
    {
      "epoch": 1.9553072625698324,
      "grad_norm": 2.37222957611084,
      "learning_rate": 1.6391659111514055e-05,
      "loss": 0.263,
      "step": 350
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9047619047619048,
      "eval_f1": 0.9036272534175698,
      "eval_loss": 0.2916606664657593,
      "eval_precision": 0.9113029827315541,
      "eval_recall": 0.9047619047619048,
      "eval_runtime": 43.0995,
      "eval_samples_per_second": 3.411,
      "eval_steps_per_second": 0.116,
      "step": 358
    },
    {
      "epoch": 2.011173184357542,
      "grad_norm": 3.767514228820801,
      "learning_rate": 1.6210335448776065e-05,
      "loss": 0.1492,
      "step": 360
    },
    {
      "epoch": 2.0670391061452515,
      "grad_norm": 6.10928201675415,
      "learning_rate": 1.602901178603808e-05,
      "loss": 0.164,
      "step": 370
    },
    {
      "epoch": 2.122905027932961,
      "grad_norm": 5.148931503295898,
      "learning_rate": 1.584768812330009e-05,
      "loss": 0.1319,
      "step": 380
    },
    {
      "epoch": 2.17877094972067,
      "grad_norm": 3.880173683166504,
      "learning_rate": 1.5666364460562104e-05,
      "loss": 0.1354,
      "step": 390
    },
    {
      "epoch": 2.2346368715083798,
      "grad_norm": 3.432164192199707,
      "learning_rate": 1.548504079782412e-05,
      "loss": 0.1028,
      "step": 400
    },
    {
      "epoch": 2.2905027932960893,
      "grad_norm": 8.787654876708984,
      "learning_rate": 1.530371713508613e-05,
      "loss": 0.1777,
      "step": 410
    },
    {
      "epoch": 2.346368715083799,
      "grad_norm": 4.742533206939697,
      "learning_rate": 1.5122393472348142e-05,
      "loss": 0.1124,
      "step": 420
    },
    {
      "epoch": 2.4022346368715084,
      "grad_norm": 4.186207294464111,
      "learning_rate": 1.4941069809610156e-05,
      "loss": 0.1848,
      "step": 430
    },
    {
      "epoch": 2.458100558659218,
      "grad_norm": 1.7014570236206055,
      "learning_rate": 1.4759746146872167e-05,
      "loss": 0.1311,
      "step": 440
    },
    {
      "epoch": 2.5139664804469275,
      "grad_norm": 5.445011615753174,
      "learning_rate": 1.4578422484134181e-05,
      "loss": 0.1633,
      "step": 450
    },
    {
      "epoch": 2.5698324022346366,
      "grad_norm": 5.768681049346924,
      "learning_rate": 1.4397098821396193e-05,
      "loss": 0.1426,
      "step": 460
    },
    {
      "epoch": 2.6256983240223466,
      "grad_norm": 9.130986213684082,
      "learning_rate": 1.4215775158658207e-05,
      "loss": 0.0882,
      "step": 470
    },
    {
      "epoch": 2.6815642458100557,
      "grad_norm": 2.656816244125366,
      "learning_rate": 1.4034451495920218e-05,
      "loss": 0.1253,
      "step": 480
    },
    {
      "epoch": 2.7374301675977653,
      "grad_norm": 4.939051628112793,
      "learning_rate": 1.3853127833182232e-05,
      "loss": 0.176,
      "step": 490
    },
    {
      "epoch": 2.793296089385475,
      "grad_norm": 8.688886642456055,
      "learning_rate": 1.3671804170444245e-05,
      "loss": 0.1189,
      "step": 500
    },
    {
      "epoch": 2.8491620111731844,
      "grad_norm": 4.239016056060791,
      "learning_rate": 1.3490480507706256e-05,
      "loss": 0.1324,
      "step": 510
    },
    {
      "epoch": 2.905027932960894,
      "grad_norm": 9.253652572631836,
      "learning_rate": 1.330915684496827e-05,
      "loss": 0.2247,
      "step": 520
    },
    {
      "epoch": 2.9608938547486034,
      "grad_norm": 8.102351188659668,
      "learning_rate": 1.3127833182230282e-05,
      "loss": 0.144,
      "step": 530
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_f1": 0.8978827235479027,
      "eval_loss": 0.30465707182884216,
      "eval_precision": 0.8978902630470574,
      "eval_recall": 0.8979591836734694,
      "eval_runtime": 42.2881,
      "eval_samples_per_second": 3.476,
      "eval_steps_per_second": 0.118,
      "step": 537
    },
    {
      "epoch": 3.016759776536313,
      "grad_norm": 2.3151211738586426,
      "learning_rate": 1.2946509519492295e-05,
      "loss": 0.0805,
      "step": 540
    },
    {
      "epoch": 3.0726256983240225,
      "grad_norm": 0.773265540599823,
      "learning_rate": 1.2765185856754307e-05,
      "loss": 0.0878,
      "step": 550
    },
    {
      "epoch": 3.1284916201117317,
      "grad_norm": 2.0086417198181152,
      "learning_rate": 1.2583862194016321e-05,
      "loss": 0.1024,
      "step": 560
    },
    {
      "epoch": 3.184357541899441,
      "grad_norm": 4.90833854675293,
      "learning_rate": 1.2402538531278332e-05,
      "loss": 0.0831,
      "step": 570
    },
    {
      "epoch": 3.2402234636871508,
      "grad_norm": 3.742814064025879,
      "learning_rate": 1.2221214868540346e-05,
      "loss": 0.1213,
      "step": 580
    },
    {
      "epoch": 3.2960893854748603,
      "grad_norm": 1.9768400192260742,
      "learning_rate": 1.2039891205802359e-05,
      "loss": 0.077,
      "step": 590
    },
    {
      "epoch": 3.35195530726257,
      "grad_norm": 0.833071768283844,
      "learning_rate": 1.185856754306437e-05,
      "loss": 0.094,
      "step": 600
    },
    {
      "epoch": 3.4078212290502794,
      "grad_norm": 1.4159188270568848,
      "learning_rate": 1.1677243880326384e-05,
      "loss": 0.1288,
      "step": 610
    },
    {
      "epoch": 3.463687150837989,
      "grad_norm": 7.14526891708374,
      "learning_rate": 1.1495920217588396e-05,
      "loss": 0.0656,
      "step": 620
    },
    {
      "epoch": 3.5195530726256985,
      "grad_norm": 6.060492038726807,
      "learning_rate": 1.131459655485041e-05,
      "loss": 0.0598,
      "step": 630
    },
    {
      "epoch": 3.5754189944134076,
      "grad_norm": 4.400679111480713,
      "learning_rate": 1.1133272892112421e-05,
      "loss": 0.0919,
      "step": 640
    },
    {
      "epoch": 3.631284916201117,
      "grad_norm": 9.306907653808594,
      "learning_rate": 1.0951949229374435e-05,
      "loss": 0.0754,
      "step": 650
    },
    {
      "epoch": 3.6871508379888267,
      "grad_norm": 1.2165876626968384,
      "learning_rate": 1.0770625566636447e-05,
      "loss": 0.1537,
      "step": 660
    },
    {
      "epoch": 3.7430167597765363,
      "grad_norm": 4.806360244750977,
      "learning_rate": 1.0589301903898458e-05,
      "loss": 0.0336,
      "step": 670
    },
    {
      "epoch": 3.798882681564246,
      "grad_norm": 4.607973098754883,
      "learning_rate": 1.0407978241160472e-05,
      "loss": 0.0667,
      "step": 680
    },
    {
      "epoch": 3.8547486033519553,
      "grad_norm": 6.711869239807129,
      "learning_rate": 1.0226654578422487e-05,
      "loss": 0.1215,
      "step": 690
    },
    {
      "epoch": 3.910614525139665,
      "grad_norm": 8.619525909423828,
      "learning_rate": 1.0045330915684497e-05,
      "loss": 0.0875,
      "step": 700
    },
    {
      "epoch": 3.9664804469273744,
      "grad_norm": 4.532635688781738,
      "learning_rate": 9.86400725294651e-06,
      "loss": 0.088,
      "step": 710
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9047619047619048,
      "eval_f1": 0.9046100241222194,
      "eval_loss": 0.34424835443496704,
      "eval_precision": 0.9047977624784854,
      "eval_recall": 0.9047619047619048,
      "eval_runtime": 42.5788,
      "eval_samples_per_second": 3.452,
      "eval_steps_per_second": 0.117,
      "step": 716
    },
    {
      "epoch": 4.022346368715084,
      "grad_norm": 3.24448561668396,
      "learning_rate": 9.682683590208522e-06,
      "loss": 0.1583,
      "step": 720
    },
    {
      "epoch": 4.078212290502793,
      "grad_norm": 8.842151641845703,
      "learning_rate": 9.501359927470536e-06,
      "loss": 0.0533,
      "step": 730
    },
    {
      "epoch": 4.134078212290503,
      "grad_norm": 1.76890230178833,
      "learning_rate": 9.320036264732549e-06,
      "loss": 0.0312,
      "step": 740
    },
    {
      "epoch": 4.189944134078212,
      "grad_norm": 2.4802823066711426,
      "learning_rate": 9.138712601994561e-06,
      "loss": 0.0176,
      "step": 750
    },
    {
      "epoch": 4.245810055865922,
      "grad_norm": 1.202589750289917,
      "learning_rate": 8.957388939256574e-06,
      "loss": 0.0912,
      "step": 760
    },
    {
      "epoch": 4.301675977653631,
      "grad_norm": 0.26222002506256104,
      "learning_rate": 8.776065276518586e-06,
      "loss": 0.0501,
      "step": 770
    },
    {
      "epoch": 4.35754189944134,
      "grad_norm": 12.392189979553223,
      "learning_rate": 8.5947416137806e-06,
      "loss": 0.0433,
      "step": 780
    },
    {
      "epoch": 4.41340782122905,
      "grad_norm": 8.532198905944824,
      "learning_rate": 8.413417951042611e-06,
      "loss": 0.096,
      "step": 790
    },
    {
      "epoch": 4.4692737430167595,
      "grad_norm": 3.229271411895752,
      "learning_rate": 8.232094288304623e-06,
      "loss": 0.0743,
      "step": 800
    },
    {
      "epoch": 4.5251396648044695,
      "grad_norm": 0.5314301252365112,
      "learning_rate": 8.050770625566638e-06,
      "loss": 0.0588,
      "step": 810
    },
    {
      "epoch": 4.581005586592179,
      "grad_norm": 12.809399604797363,
      "learning_rate": 7.86944696282865e-06,
      "loss": 0.0761,
      "step": 820
    },
    {
      "epoch": 4.636871508379889,
      "grad_norm": 9.645480155944824,
      "learning_rate": 7.688123300090663e-06,
      "loss": 0.0666,
      "step": 830
    },
    {
      "epoch": 4.692737430167598,
      "grad_norm": 2.1018457412719727,
      "learning_rate": 7.506799637352675e-06,
      "loss": 0.0437,
      "step": 840
    },
    {
      "epoch": 4.748603351955307,
      "grad_norm": 11.410074234008789,
      "learning_rate": 7.3254759746146875e-06,
      "loss": 0.0753,
      "step": 850
    },
    {
      "epoch": 4.804469273743017,
      "grad_norm": 8.368203163146973,
      "learning_rate": 7.144152311876701e-06,
      "loss": 0.0743,
      "step": 860
    },
    {
      "epoch": 4.860335195530726,
      "grad_norm": 4.603096008300781,
      "learning_rate": 6.962828649138713e-06,
      "loss": 0.058,
      "step": 870
    },
    {
      "epoch": 4.916201117318436,
      "grad_norm": 1.7863306999206543,
      "learning_rate": 6.781504986400726e-06,
      "loss": 0.0089,
      "step": 880
    },
    {
      "epoch": 4.972067039106145,
      "grad_norm": 5.33497953414917,
      "learning_rate": 6.600181323662739e-06,
      "loss": 0.0941,
      "step": 890
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_f1": 0.8978827235479027,
      "eval_loss": 0.4454677999019623,
      "eval_precision": 0.8978902630470574,
      "eval_recall": 0.8979591836734694,
      "eval_runtime": 44.1091,
      "eval_samples_per_second": 3.333,
      "eval_steps_per_second": 0.113,
      "step": 895
    },
    {
      "epoch": 5.027932960893855,
      "grad_norm": 13.331377029418945,
      "learning_rate": 6.418857660924751e-06,
      "loss": 0.0554,
      "step": 900
    },
    {
      "epoch": 5.083798882681564,
      "grad_norm": 43.700767517089844,
      "learning_rate": 6.237533998186765e-06,
      "loss": 0.0662,
      "step": 910
    },
    {
      "epoch": 5.139664804469274,
      "grad_norm": 3.050325393676758,
      "learning_rate": 6.056210335448776e-06,
      "loss": 0.0361,
      "step": 920
    },
    {
      "epoch": 5.195530726256983,
      "grad_norm": 3.3658792972564697,
      "learning_rate": 5.874886672710789e-06,
      "loss": 0.0293,
      "step": 930
    },
    {
      "epoch": 5.251396648044693,
      "grad_norm": 0.4701756238937378,
      "learning_rate": 5.693563009972802e-06,
      "loss": 0.0193,
      "step": 940
    },
    {
      "epoch": 5.307262569832402,
      "grad_norm": 0.5358762741088867,
      "learning_rate": 5.5122393472348145e-06,
      "loss": 0.0507,
      "step": 950
    },
    {
      "epoch": 5.363128491620111,
      "grad_norm": 2.983640193939209,
      "learning_rate": 5.330915684496827e-06,
      "loss": 0.0208,
      "step": 960
    },
    {
      "epoch": 5.418994413407821,
      "grad_norm": 18.32625389099121,
      "learning_rate": 5.14959202175884e-06,
      "loss": 0.0702,
      "step": 970
    },
    {
      "epoch": 5.4748603351955305,
      "grad_norm": 8.444658279418945,
      "learning_rate": 4.968268359020853e-06,
      "loss": 0.0374,
      "step": 980
    },
    {
      "epoch": 5.5307262569832405,
      "grad_norm": 0.7589412927627563,
      "learning_rate": 4.786944696282865e-06,
      "loss": 0.0412,
      "step": 990
    },
    {
      "epoch": 5.58659217877095,
      "grad_norm": 3.848323106765747,
      "learning_rate": 4.6056210335448785e-06,
      "loss": 0.0623,
      "step": 1000
    },
    {
      "epoch": 5.64245810055866,
      "grad_norm": 8.687700271606445,
      "learning_rate": 4.424297370806891e-06,
      "loss": 0.0595,
      "step": 1010
    },
    {
      "epoch": 5.698324022346369,
      "grad_norm": 0.09025302529335022,
      "learning_rate": 4.242973708068903e-06,
      "loss": 0.0087,
      "step": 1020
    },
    {
      "epoch": 5.754189944134078,
      "grad_norm": 0.11568494141101837,
      "learning_rate": 4.061650045330916e-06,
      "loss": 0.0241,
      "step": 1030
    },
    {
      "epoch": 5.810055865921788,
      "grad_norm": 1.0072994232177734,
      "learning_rate": 3.880326382592929e-06,
      "loss": 0.0196,
      "step": 1040
    },
    {
      "epoch": 5.865921787709497,
      "grad_norm": 2.54008150100708,
      "learning_rate": 3.6990027198549416e-06,
      "loss": 0.033,
      "step": 1050
    },
    {
      "epoch": 5.921787709497207,
      "grad_norm": 0.12731680274009705,
      "learning_rate": 3.517679057116954e-06,
      "loss": 0.0568,
      "step": 1060
    },
    {
      "epoch": 5.977653631284916,
      "grad_norm": 14.050686836242676,
      "learning_rate": 3.336355394378967e-06,
      "loss": 0.0479,
      "step": 1070
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_f1": 0.8978827235479027,
      "eval_loss": 0.4888676702976227,
      "eval_precision": 0.8978902630470574,
      "eval_recall": 0.8979591836734694,
      "eval_runtime": 43.2366,
      "eval_samples_per_second": 3.4,
      "eval_steps_per_second": 0.116,
      "step": 1074
    }
  ],
  "logging_steps": 10,
  "max_steps": 1253,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 8699999323206960.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}