diff --git "a/trainer_state.json" "b/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/trainer_state.json"
@@ -0,0 +1,7792 @@
+{
+  "best_global_step": 264710,
+  "best_metric": 0.870147919438821,
+  "best_model_checkpoint": "T:\\laupodteam\\AIOS\\Bram\\language_modeling\\Models\\language_models\\CardioCCC\\EuroBERT\\multilabel_3ldense_20epochs_40splits/fold_0\\checkpoint-264710",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 264710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009670960673945073,
+      "grad_norm": 1.4626084566116333,
+      "learning_rate": 1.9980733633032377e-05,
+      "loss": 1.326,
+      "step": 256
+    },
+    {
+      "epoch": 0.019341921347890145,
+      "grad_norm": 2.9422495365142822,
+      "learning_rate": 1.9961391711684486e-05,
+      "loss": 0.9436,
+      "step": 512
+    },
+    {
+      "epoch": 0.029012882021835214,
+      "grad_norm": 3.939150333404541,
+      "learning_rate": 1.9942049790336598e-05,
+      "loss": 0.8108,
+      "step": 768
+    },
+    {
+      "epoch": 0.03868384269578029,
+      "grad_norm": 3.260474681854248,
+      "learning_rate": 1.9922707868988706e-05,
+      "loss": 0.746,
+      "step": 1024
+    },
+    {
+      "epoch": 0.04835480336972536,
+      "grad_norm": 2.8487510681152344,
+      "learning_rate": 1.9903365947640814e-05,
+      "loss": 0.6876,
+      "step": 1280
+    },
+    {
+      "epoch": 0.05802576404367043,
+      "grad_norm": 3.7067031860351562,
+      "learning_rate": 1.9884024026292926e-05,
+      "loss": 0.6491,
+      "step": 1536
+    },
+    {
+      "epoch": 0.06769672471761551,
+      "grad_norm": 3.1346232891082764,
+      "learning_rate": 1.9864682104945038e-05,
+      "loss": 0.6117,
+      "step": 1792
+    },
+    {
+      "epoch": 0.07736768539156058,
+      "grad_norm": 3.9794366359710693,
+      "learning_rate": 1.9845340183597147e-05,
+      "loss": 0.584,
+      "step": 2048
+    },
+    {
+      "epoch": 0.08703864606550565,
+      "grad_norm": 3.7597267627716064,
+      "learning_rate": 1.9825998262249255e-05,
+      "loss": 0.5541,
+      "step": 2304
+    },
+    {
+      "epoch": 0.09670960673945073,
+      "grad_norm": 3.669264078140259,
+      "learning_rate": 1.9806656340901363e-05,
+      "loss": 0.5273,
+      "step": 2560
+    },
+    {
+      "epoch": 0.10638056741339579,
+      "grad_norm": 3.203001022338867,
+      "learning_rate": 1.9787314419553475e-05,
+      "loss": 0.5148,
+      "step": 2816
+    },
+    {
+      "epoch": 0.11605152808734086,
+      "grad_norm": 4.039089202880859,
+      "learning_rate": 1.9767972498205587e-05,
+      "loss": 0.4907,
+      "step": 3072
+    },
+    {
+      "epoch": 0.12572248876128594,
+      "grad_norm": 3.2784998416900635,
+      "learning_rate": 1.9748630576857695e-05,
+      "loss": 0.4825,
+      "step": 3328
+    },
+    {
+      "epoch": 0.13539344943523102,
+      "grad_norm": 3.981826066970825,
+      "learning_rate": 1.9729288655509804e-05,
+      "loss": 0.4639,
+      "step": 3584
+    },
+    {
+      "epoch": 0.1450644101091761,
+      "grad_norm": 4.3725690841674805,
+      "learning_rate": 1.9709946734161916e-05,
+      "loss": 0.4522,
+      "step": 3840
+    },
+    {
+      "epoch": 0.15473537078312116,
+      "grad_norm": 4.14705753326416,
+      "learning_rate": 1.969068036719429e-05,
+      "loss": 0.4452,
+      "step": 4096
+    },
+    {
+      "epoch": 0.16440633145706623,
+      "grad_norm": 3.336223840713501,
+      "learning_rate": 1.96713384458464e-05,
+      "loss": 0.4292,
+      "step": 4352
+    },
+    {
+      "epoch": 0.1740772921310113,
+      "grad_norm": 4.36456823348999,
+      "learning_rate": 1.9651996524498508e-05,
+      "loss": 0.4108,
+      "step": 4608
+    },
+    {
+      "epoch": 0.18374825280495638,
+      "grad_norm": 3.929685354232788,
+      "learning_rate": 1.9632654603150617e-05,
+      "loss": 0.403,
+      "step": 4864
+    },
+    {
+      "epoch": 0.19341921347890145,
+      "grad_norm": 4.6235671043396,
+      "learning_rate": 1.961331268180273e-05,
+      "loss": 0.3899,
+      "step": 5120
+    },
+    {
+      "epoch": 0.2030901741528465,
+      "grad_norm": 4.0524492263793945,
+      "learning_rate": 1.959397076045484e-05,
+      "loss": 0.3913,
+      "step": 5376
+    },
+    {
+      "epoch": 0.21276113482679157,
+      "grad_norm": 3.8945560455322266,
+      "learning_rate": 1.957462883910695e-05,
+      "loss": 0.3781,
+      "step": 5632
+    },
+    {
+      "epoch": 0.22243209550073664,
+      "grad_norm": 4.181601047515869,
+      "learning_rate": 1.9555286917759057e-05,
+      "loss": 0.3758,
+      "step": 5888
+    },
+    {
+      "epoch": 0.23210305617468172,
+      "grad_norm": 5.5385308265686035,
+      "learning_rate": 1.9536020550791436e-05,
+      "loss": 0.3646,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2417740168486268,
+      "grad_norm": 5.160412311553955,
+      "learning_rate": 1.9516678629443545e-05,
+      "loss": 0.3572,
+      "step": 6400
+    },
+    {
+      "epoch": 0.2514449775225719,
+      "grad_norm": 6.071929931640625,
+      "learning_rate": 1.9497336708095653e-05,
+      "loss": 0.3453,
+      "step": 6656
+    },
+    {
+      "epoch": 0.26111593819651696,
+      "grad_norm": 4.409694671630859,
+      "learning_rate": 1.947799478674776e-05,
+      "loss": 0.3504,
+      "step": 6912
+    },
+    {
+      "epoch": 0.27078689887046203,
+      "grad_norm": 4.06134033203125,
+      "learning_rate": 1.9458652865399873e-05,
+      "loss": 0.3404,
+      "step": 7168
+    },
+    {
+      "epoch": 0.2804578595444071,
+      "grad_norm": 3.8032515048980713,
+      "learning_rate": 1.9439310944051982e-05,
+      "loss": 0.34,
+      "step": 7424
+    },
+    {
+      "epoch": 0.2901288202183522,
+      "grad_norm": 4.95781135559082,
+      "learning_rate": 1.9419969022704094e-05,
+      "loss": 0.3249,
+      "step": 7680
+    },
+    {
+      "epoch": 0.29979978089229725,
+      "grad_norm": 3.898789167404175,
+      "learning_rate": 1.9400627101356202e-05,
+      "loss": 0.3218,
+      "step": 7936
+    },
+    {
+      "epoch": 0.3094707415662423,
+      "grad_norm": 4.6803717613220215,
+      "learning_rate": 1.9381285180008314e-05,
+      "loss": 0.3144,
+      "step": 8192
+    },
+    {
+      "epoch": 0.3191417022401874,
+      "grad_norm": 6.2057600021362305,
+      "learning_rate": 1.936201881304069e-05,
+      "loss": 0.3056,
+      "step": 8448
+    },
+    {
+      "epoch": 0.32881266291413247,
+      "grad_norm": 4.742001056671143,
+      "learning_rate": 1.9342676891692798e-05,
+      "loss": 0.3031,
+      "step": 8704
+    },
+    {
+      "epoch": 0.33848362358807754,
+      "grad_norm": 5.605335235595703,
+      "learning_rate": 1.9323334970344906e-05,
+      "loss": 0.2989,
+      "step": 8960
+    },
+    {
+      "epoch": 0.3481545842620226,
+      "grad_norm": 5.512292861938477,
+      "learning_rate": 1.9303993048997015e-05,
+      "loss": 0.2838,
+      "step": 9216
+    },
+    {
+      "epoch": 0.3578255449359677,
+      "grad_norm": 5.346792697906494,
+      "learning_rate": 1.9284651127649127e-05,
+      "loss": 0.2871,
+      "step": 9472
+    },
+    {
+      "epoch": 0.36749650560991276,
+      "grad_norm": 3.5019690990448,
+      "learning_rate": 1.926530920630124e-05,
+      "loss": 0.2794,
+      "step": 9728
+    },
+    {
+      "epoch": 0.37716746628385783,
+      "grad_norm": 4.682333946228027,
+      "learning_rate": 1.9245967284953347e-05,
+      "loss": 0.2736,
+      "step": 9984
+    },
+    {
+      "epoch": 0.3868384269578029,
+      "grad_norm": 7.038910865783691,
+      "learning_rate": 1.9226625363605455e-05,
+      "loss": 0.2786,
+      "step": 10240
+    },
+    {
+      "epoch": 0.396509387631748,
+      "grad_norm": 4.099844455718994,
+      "learning_rate": 1.9207283442257567e-05,
+      "loss": 0.2721,
+      "step": 10496
+    },
+    {
+      "epoch": 0.406180348305693,
+      "grad_norm": 3.918942928314209,
+      "learning_rate": 1.9187941520909676e-05,
+      "loss": 0.2704,
+      "step": 10752
+    },
+    {
+      "epoch": 0.41585130897963807,
+      "grad_norm": 5.411423683166504,
+      "learning_rate": 1.9168599599561784e-05,
+      "loss": 0.2604,
+      "step": 11008
+    },
+    {
+      "epoch": 0.42552226965358314,
+      "grad_norm": 7.702000617980957,
+      "learning_rate": 1.9149257678213896e-05,
+      "loss": 0.2618,
+      "step": 11264
+    },
+    {
+      "epoch": 0.4351932303275282,
+      "grad_norm": 4.103521347045898,
+      "learning_rate": 1.912999131124627e-05,
+      "loss": 0.2511,
+      "step": 11520
+    },
+    {
+      "epoch": 0.4448641910014733,
+      "grad_norm": 6.066595077514648,
+      "learning_rate": 1.911064938989838e-05,
+      "loss": 0.2551,
+      "step": 11776
+    },
+    {
+      "epoch": 0.45453515167541836,
+      "grad_norm": 6.25346565246582,
+      "learning_rate": 1.9091307468550492e-05,
+      "loss": 0.2499,
+      "step": 12032
+    },
+    {
+      "epoch": 0.46420611234936343,
+      "grad_norm": 4.310111045837402,
+      "learning_rate": 1.90719655472026e-05,
+      "loss": 0.2403,
+      "step": 12288
+    },
+    {
+      "epoch": 0.4738770730233085,
+      "grad_norm": 6.692182540893555,
+      "learning_rate": 1.9052623625854712e-05,
+      "loss": 0.24,
+      "step": 12544
+    },
+    {
+      "epoch": 0.4835480336972536,
+      "grad_norm": 4.0325751304626465,
+      "learning_rate": 1.903328170450682e-05,
+      "loss": 0.2383,
+      "step": 12800
+    },
+    {
+      "epoch": 0.49321899437119865,
+      "grad_norm": 4.97512149810791,
+      "learning_rate": 1.901393978315893e-05,
+      "loss": 0.2333,
+      "step": 13056
+    },
+    {
+      "epoch": 0.5028899550451438,
+      "grad_norm": 4.146473407745361,
+      "learning_rate": 1.899459786181104e-05,
+      "loss": 0.2342,
+      "step": 13312
+    },
+    {
+      "epoch": 0.5125609157190888,
+      "grad_norm": 6.477240562438965,
+      "learning_rate": 1.897525594046315e-05,
+      "loss": 0.23,
+      "step": 13568
+    },
+    {
+      "epoch": 0.5222318763930339,
+      "grad_norm": 5.060920715332031,
+      "learning_rate": 1.895591401911526e-05,
+      "loss": 0.2317,
+      "step": 13824
+    },
+    {
+      "epoch": 0.5319028370669789,
+      "grad_norm": 7.546407222747803,
+      "learning_rate": 1.893657209776737e-05,
+      "loss": 0.2235,
+      "step": 14080
+    },
+    {
+      "epoch": 0.5415737977409241,
+      "grad_norm": 6.76540994644165,
+      "learning_rate": 1.8917230176419478e-05,
+      "loss": 0.2189,
+      "step": 14336
+    },
+    {
+      "epoch": 0.5512447584148691,
+      "grad_norm": 6.734369277954102,
+      "learning_rate": 1.889788825507159e-05,
+      "loss": 0.2136,
+      "step": 14592
+    },
+    {
+      "epoch": 0.5609157190888142,
+      "grad_norm": 4.962408065795898,
+      "learning_rate": 1.8878546333723698e-05,
+      "loss": 0.2116,
+      "step": 14848
+    },
+    {
+      "epoch": 0.5705866797627592,
+      "grad_norm": 6.1386332511901855,
+      "learning_rate": 1.8859279966756074e-05,
+      "loss": 0.212,
+      "step": 15104
+    },
+    {
+      "epoch": 0.5802576404367044,
+      "grad_norm": 6.326384544372559,
+      "learning_rate": 1.8839938045408182e-05,
+      "loss": 0.2074,
+      "step": 15360
+    },
+    {
+      "epoch": 0.5899286011106494,
+      "grad_norm": 6.425912857055664,
+      "learning_rate": 1.8820596124060294e-05,
+      "loss": 0.2043,
+      "step": 15616
+    },
+    {
+      "epoch": 0.5995995617845945,
+      "grad_norm": 5.6023945808410645,
+      "learning_rate": 1.8801254202712406e-05,
+      "loss": 0.205,
+      "step": 15872
+    },
+    {
+      "epoch": 0.6092705224585395,
+      "grad_norm": 5.436675071716309,
+      "learning_rate": 1.8781912281364514e-05,
+      "loss": 0.2,
+      "step": 16128
+    },
+    {
+      "epoch": 0.6189414831324846,
+      "grad_norm": 3.5356578826904297,
+      "learning_rate": 1.8762570360016623e-05,
+      "loss": 0.1957,
+      "step": 16384
+    },
+    {
+      "epoch": 0.6286124438064297,
+      "grad_norm": 4.914231777191162,
+      "learning_rate": 1.874322843866873e-05,
+      "loss": 0.1957,
+      "step": 16640
+    },
+    {
+      "epoch": 0.6382834044803748,
+      "grad_norm": 5.829110145568848,
+      "learning_rate": 1.8723886517320843e-05,
+      "loss": 0.1936,
+      "step": 16896
+    },
+    {
+      "epoch": 0.6479543651543198,
+      "grad_norm": 9.775616645812988,
+      "learning_rate": 1.8704544595972955e-05,
+      "loss": 0.194,
+      "step": 17152
+    },
+    {
+      "epoch": 0.6576253258282649,
+      "grad_norm": 3.6314735412597656,
+      "learning_rate": 1.8685202674625063e-05,
+      "loss": 0.1862,
+      "step": 17408
+    },
+    {
+      "epoch": 0.66729628650221,
+      "grad_norm": 4.77644681930542,
+      "learning_rate": 1.8665860753277172e-05,
+      "loss": 0.1828,
+      "step": 17664
+    },
+    {
+      "epoch": 0.6769672471761551,
+      "grad_norm": 7.319884300231934,
+      "learning_rate": 1.8646518831929284e-05,
+      "loss": 0.1879,
+      "step": 17920
+    },
+    {
+      "epoch": 0.6866382078501001,
+      "grad_norm": 5.536057949066162,
+      "learning_rate": 1.8627176910581392e-05,
+      "loss": 0.1836,
+      "step": 18176
+    },
+    {
+      "epoch": 0.6963091685240452,
+      "grad_norm": 5.481319904327393,
+      "learning_rate": 1.86078349892335e-05,
+      "loss": 0.1802,
+      "step": 18432
+    },
+    {
+      "epoch": 0.7059801291979902,
+      "grad_norm": 6.011005401611328,
+      "learning_rate": 1.8588493067885612e-05,
+      "loss": 0.1824,
+      "step": 18688
+    },
+    {
+      "epoch": 0.7156510898719354,
+      "grad_norm": 5.187521457672119,
+      "learning_rate": 1.8569151146537724e-05,
+      "loss": 0.1763,
+      "step": 18944
+    },
+    {
+      "epoch": 0.7253220505458804,
+      "grad_norm": 6.904630661010742,
+      "learning_rate": 1.8549884779570096e-05,
+      "loss": 0.1719,
+      "step": 19200
+    },
+    {
+      "epoch": 0.7349930112198255,
+      "grad_norm": 7.806436538696289,
+      "learning_rate": 1.8530542858222208e-05,
+      "loss": 0.1707,
+      "step": 19456
+    },
+    {
+      "epoch": 0.7446639718937705,
+      "grad_norm": 3.597665548324585,
+      "learning_rate": 1.8511200936874317e-05,
+      "loss": 0.1706,
+      "step": 19712
+    },
+    {
+      "epoch": 0.7543349325677157,
+      "grad_norm": 4.756324291229248,
+      "learning_rate": 1.849185901552643e-05,
+      "loss": 0.1689,
+      "step": 19968
+    },
+    {
+      "epoch": 0.7640058932416607,
+      "grad_norm": 5.917934894561768,
+      "learning_rate": 1.8472517094178537e-05,
+      "loss": 0.1671,
+      "step": 20224
+    },
+    {
+      "epoch": 0.7736768539156058,
+      "grad_norm": 7.077094554901123,
+      "learning_rate": 1.8453175172830645e-05,
+      "loss": 0.1655,
+      "step": 20480
+    },
+    {
+      "epoch": 0.7833478145895508,
+      "grad_norm": 4.210581302642822,
+      "learning_rate": 1.8433833251482757e-05,
+      "loss": 0.1576,
+      "step": 20736
+    },
+    {
+      "epoch": 0.793018775263496,
+      "grad_norm": 4.523745059967041,
+      "learning_rate": 1.8414491330134866e-05,
+      "loss": 0.1601,
+      "step": 20992
+    },
+    {
+      "epoch": 0.802689735937441,
+      "grad_norm": 4.547347545623779,
+      "learning_rate": 1.8395149408786977e-05,
+      "loss": 0.1583,
+      "step": 21248
+    },
+    {
+      "epoch": 0.812360696611386,
+      "grad_norm": 4.029369831085205,
+      "learning_rate": 1.837588304181935e-05,
+      "loss": 0.1576,
+      "step": 21504
+    },
+    {
+      "epoch": 0.8220316572853311,
+      "grad_norm": 5.123602867126465,
+      "learning_rate": 1.835654112047146e-05,
+      "loss": 0.1514,
+      "step": 21760
+    },
+    {
+      "epoch": 0.8317026179592761,
+      "grad_norm": 6.265158176422119,
+      "learning_rate": 1.833719919912357e-05,
+      "loss": 0.157,
+      "step": 22016
+    },
+    {
+      "epoch": 0.8413735786332213,
+      "grad_norm": 8.210796356201172,
+      "learning_rate": 1.8317857277775682e-05,
+      "loss": 0.1503,
+      "step": 22272
+    },
+    {
+      "epoch": 0.8510445393071663,
+      "grad_norm": 10.078185081481934,
+      "learning_rate": 1.829851535642779e-05,
+      "loss": 0.15,
+      "step": 22528
+    },
+    {
+      "epoch": 0.8607154999811114,
+      "grad_norm": 6.486992359161377,
+      "learning_rate": 1.82791734350799e-05,
+      "loss": 0.1484,
+      "step": 22784
+    },
+    {
+      "epoch": 0.8703864606550564,
+      "grad_norm": 6.386577129364014,
+      "learning_rate": 1.825983151373201e-05,
+      "loss": 0.1476,
+      "step": 23040
+    },
+    {
+      "epoch": 0.8800574213290016,
+      "grad_norm": 7.5579328536987305,
+      "learning_rate": 1.8240489592384122e-05,
+      "loss": 0.1458,
+      "step": 23296
+    },
+    {
+      "epoch": 0.8897283820029466,
+      "grad_norm": 3.283404588699341,
+      "learning_rate": 1.8221223225416495e-05,
+      "loss": 0.144,
+      "step": 23552
+    },
+    {
+      "epoch": 0.8993993426768917,
+      "grad_norm": 7.462500095367432,
+      "learning_rate": 1.8201881304068606e-05,
+      "loss": 0.1475,
+      "step": 23808
+    },
+    {
+      "epoch": 0.9090703033508367,
+      "grad_norm": 4.219975471496582,
+      "learning_rate": 1.8182539382720715e-05,
+      "loss": 0.1415,
+      "step": 24064
+    },
+    {
+      "epoch": 0.9187412640247818,
+      "grad_norm": 5.009161949157715,
+      "learning_rate": 1.8163197461372823e-05,
+      "loss": 0.1395,
+      "step": 24320
+    },
+    {
+      "epoch": 0.9284122246987269,
+      "grad_norm": 5.921178340911865,
+      "learning_rate": 1.8143855540024935e-05,
+      "loss": 0.1381,
+      "step": 24576
+    },
+    {
+      "epoch": 0.938083185372672,
+      "grad_norm": 5.374543190002441,
+      "learning_rate": 1.8124513618677044e-05,
+      "loss": 0.1352,
+      "step": 24832
+    },
+    {
+      "epoch": 0.947754146046617,
+      "grad_norm": 3.8733317852020264,
+      "learning_rate": 1.8105171697329152e-05,
+      "loss": 0.1346,
+      "step": 25088
+    },
+    {
+      "epoch": 0.9574251067205621,
+      "grad_norm": 4.049707412719727,
+      "learning_rate": 1.8085829775981264e-05,
+      "loss": 0.1319,
+      "step": 25344
+    },
+    {
+      "epoch": 0.9670960673945072,
+      "grad_norm": 7.517127990722656,
+      "learning_rate": 1.806656340901364e-05,
+      "loss": 0.1271,
+      "step": 25600
+    },
+    {
+      "epoch": 0.9767670280684523,
+      "grad_norm": 4.687051773071289,
+      "learning_rate": 1.8047221487665748e-05,
+      "loss": 0.1279,
+      "step": 25856
+    },
+    {
+      "epoch": 0.9864379887423973,
+      "grad_norm": 4.79626989364624,
+      "learning_rate": 1.802787956631786e-05,
+      "loss": 0.1307,
+      "step": 26112
+    },
+    {
+      "epoch": 0.9961089494163424,
+      "grad_norm": 4.730831623077393,
+      "learning_rate": 1.8008537644969968e-05,
+      "loss": 0.1302,
+      "step": 26368
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1_B-DISEASE": 0.7781765393765878,
+      "eval_f1_B-MEDICATION": 0.9037345902828137,
+      "eval_f1_B-PROCEDURE": 0.7974038223998922,
+      "eval_f1_B-SYMPTOM": 0.7777604788347432,
+      "eval_f1_I-DISEASE": 0.8292819119234635,
+      "eval_f1_I-MEDICATION": 0.9226245076350295,
+      "eval_f1_I-PROCEDURE": 0.8287028141772023,
+      "eval_f1_I-SYMPTOM": 0.7961978076970171,
+      "eval_f1_O": 0.9184682391128007,
+      "eval_f1_macro": 0.8391500790488389,
+      "eval_f1_micro": 0.8767886171279684,
+      "eval_loss": 0.26655662059783936,
+      "eval_precision_B-DISEASE": 0.7914206036745407,
+      "eval_precision_B-MEDICATION": 0.9209310918159985,
+      "eval_precision_B-PROCEDURE": 0.839345657415725,
+      "eval_precision_B-SYMPTOM": 0.7863714275719733,
+      "eval_precision_I-DISEASE": 0.8204249990792915,
+      "eval_precision_I-MEDICATION": 0.9416267415606586,
+      "eval_precision_I-PROCEDURE": 0.8691026329930145,
+      "eval_precision_I-SYMPTOM": 0.7889775161164393,
+      "eval_precision_O": 0.9252825164715074,
+      "eval_precision_macro": 0.8537203540776832,
+      "eval_precision_micro": 0.8833806029697474,
+      "eval_rauc_macro": 0.9021063420010184,
+      "eval_rauc_micro": 0.9278253367848399,
+      "eval_recall_B-DISEASE": 0.7653684461013722,
+      "eval_recall_B-MEDICATION": 0.8871685353265706,
+      "eval_recall_B-PROCEDURE": 0.7594541409993155,
+      "eval_recall_B-SYMPTOM": 0.7693360711841205,
+      "eval_recall_I-DISEASE": 0.838332141647537,
+      "eval_recall_I-MEDICATION": 0.9043740413603427,
+      "eval_recall_I-PROCEDURE": 0.7918920903816495,
+      "eval_recall_I-SYMPTOM": 0.8035514721684934,
+      "eval_recall_O": 0.9117535959899989,
+      "eval_recall_macro": 0.8256922816843777,
+      "eval_recall_micro": 0.8702942843552489,
+      "eval_roc_auc_B-DISEASE": 0.8808075963149171,
+      "eval_roc_auc_B-MEDICATION": 0.9434285957498447,
+      "eval_roc_auc_B-PROCEDURE": 0.87847497845947,
+      "eval_roc_auc_B-SYMPTOM": 0.8824080001390723,
+      "eval_roc_auc_I-DISEASE": 0.9071844217170272,
+      "eval_roc_auc_I-MEDICATION": 0.9517977149811767,
+      "eval_roc_auc_I-PROCEDURE": 0.8901357064770181,
+      "eval_roc_auc_I-SYMPTOM": 0.8850274935590098,
+      "eval_roc_auc_O": 0.8996925706116287,
+      "eval_runtime": 61.1466,
+      "eval_samples_per_second": 177.818,
+      "eval_steps_per_second": 22.242,
+      "step": 26471
+    },
+    {
+      "epoch": 1.0057799100902876,
+      "grad_norm": 3.7280209064483643,
+      "learning_rate": 1.798919572362208e-05,
+      "loss": 0.1119,
+      "step": 26624
+    },
+    {
+      "epoch": 1.0154508707642325,
+      "grad_norm": 5.684998512268066,
+      "learning_rate": 1.796985380227419e-05,
+      "loss": 0.0936,
+      "step": 26880
+    },
+    {
+      "epoch": 1.0251218314381776,
+      "grad_norm": 3.695190191268921,
+      "learning_rate": 1.7950511880926297e-05,
+      "loss": 0.0955,
+      "step": 27136
+    },
+    {
+      "epoch": 1.0347927921121227,
+      "grad_norm": 4.493898868560791,
+      "learning_rate": 1.793116995957841e-05,
+      "loss": 0.0922,
+      "step": 27392
+    },
+    {
+      "epoch": 1.0444637527860678,
+      "grad_norm": 4.638331413269043,
+      "learning_rate": 1.7911828038230517e-05,
+      "loss": 0.0923,
+      "step": 27648
+    },
+    {
+      "epoch": 1.0541347134600128,
+      "grad_norm": 4.798746585845947,
+      "learning_rate": 1.7892561671262893e-05,
+      "loss": 0.0918,
+      "step": 27904
+    },
+    {
+      "epoch": 1.0638056741339579,
+      "grad_norm": 4.274206638336182,
+      "learning_rate": 1.7873219749915e-05,
+      "loss": 0.0945,
+      "step": 28160
+    },
+    {
+      "epoch": 1.073476634807903,
+      "grad_norm": 3.235424280166626,
+      "learning_rate": 1.7853877828567113e-05,
+      "loss": 0.0919,
+      "step": 28416
+    },
+    {
+      "epoch": 1.0831475954818481,
+      "grad_norm": 4.507290363311768,
+      "learning_rate": 1.783453590721922e-05,
+      "loss": 0.0932,
+      "step": 28672
+    },
+    {
+      "epoch": 1.092818556155793,
+      "grad_norm": 10.315567016601562,
+      "learning_rate": 1.7815193985871333e-05,
+      "loss": 0.0952,
+      "step": 28928
+    },
+    {
+      "epoch": 1.1024895168297382,
+      "grad_norm": 8.936885833740234,
+      "learning_rate": 1.7795852064523442e-05,
+      "loss": 0.0899,
+      "step": 29184
+    },
+    {
+      "epoch": 1.1121604775036833,
+      "grad_norm": 2.79886531829834,
+      "learning_rate": 1.777651014317555e-05,
+      "loss": 0.0901,
+      "step": 29440
+    },
+    {
+      "epoch": 1.1218314381776284,
+      "grad_norm": 3.2710986137390137,
+      "learning_rate": 1.7757168221827662e-05,
+      "loss": 0.0883,
+      "step": 29696
+    },
+    {
+      "epoch": 1.1315023988515733,
+      "grad_norm": 4.917572498321533,
+      "learning_rate": 1.7737826300479774e-05,
+      "loss": 0.0896,
+      "step": 29952
+    },
+    {
+      "epoch": 1.1411733595255185,
+      "grad_norm": 4.567966938018799,
+      "learning_rate": 1.7718484379131882e-05,
+      "loss": 0.0914,
+      "step": 30208
+    },
+    {
+      "epoch": 1.1508443201994636,
+      "grad_norm": 3.6949679851531982,
+      "learning_rate": 1.769914245778399e-05,
+      "loss": 0.0871,
+      "step": 30464
+    },
+    {
+      "epoch": 1.1605152808734087,
+      "grad_norm": 8.372673988342285,
+      "learning_rate": 1.7679876090816366e-05,
+      "loss": 0.0909,
+      "step": 30720
+    },
+    {
+      "epoch": 1.1701862415473536,
+      "grad_norm": 3.8434600830078125,
+      "learning_rate": 1.7660534169468478e-05,
+      "loss": 0.0849,
+      "step": 30976
+    },
+    {
+      "epoch": 1.1798572022212988,
+      "grad_norm": 4.115856647491455,
+      "learning_rate": 1.7641192248120587e-05,
+      "loss": 0.0904,
+      "step": 31232
+    },
+    {
+      "epoch": 1.1895281628952439,
+      "grad_norm": 3.246572971343994,
+      "learning_rate": 1.7621850326772695e-05,
+      "loss": 0.0907,
+      "step": 31488
+    },
+    {
+      "epoch": 1.199199123569189,
+      "grad_norm": 3.668151617050171,
+      "learning_rate": 1.7602508405424807e-05,
+      "loss": 0.0864,
+      "step": 31744
+    },
+    {
+      "epoch": 1.208870084243134,
+      "grad_norm": 3.0340752601623535,
+      "learning_rate": 1.7583166484076915e-05,
+      "loss": 0.0848,
+      "step": 32000
+    },
+    {
+      "epoch": 1.218541044917079,
+      "grad_norm": 4.029708385467529,
+      "learning_rate": 1.7563824562729027e-05,
+      "loss": 0.0857,
+      "step": 32256
+    },
+    {
+      "epoch": 1.2282120055910242,
+      "grad_norm": 5.181060791015625,
+      "learning_rate": 1.7544482641381136e-05,
+      "loss": 0.0863,
+      "step": 32512
+    },
+    {
+      "epoch": 1.2378829662649693,
+      "grad_norm": 5.2258124351501465,
+      "learning_rate": 1.752521627441351e-05,
+      "loss": 0.0867,
+      "step": 32768
+    },
+    {
+      "epoch": 1.2475539269389142,
+      "grad_norm": 10.210968017578125,
+      "learning_rate": 1.750587435306562e-05,
+      "loss": 0.0878,
+      "step": 33024
+    },
+    {
+      "epoch": 1.2572248876128593,
+      "grad_norm": 3.4898252487182617,
+      "learning_rate": 1.748653243171773e-05,
+      "loss": 0.0831,
+      "step": 33280
+    },
+    {
+      "epoch": 1.2668958482868045,
+      "grad_norm": 4.27427864074707,
+      "learning_rate": 1.746719051036984e-05,
+      "loss": 0.0864,
+      "step": 33536
+    },
+    {
+      "epoch": 1.2765668089607494,
+      "grad_norm": 5.286701679229736,
+      "learning_rate": 1.744784858902195e-05,
+      "loss": 0.0799,
+      "step": 33792
+    },
+    {
+      "epoch": 1.2862377696346945,
+      "grad_norm": 3.2482128143310547,
+      "learning_rate": 1.742850666767406e-05,
+      "loss": 0.084,
+      "step": 34048
+    },
+    {
+      "epoch": 1.2959087303086396,
+      "grad_norm": 2.9942526817321777,
+      "learning_rate": 1.7409164746326172e-05,
+      "loss": 0.0834,
+      "step": 34304
+    },
+    {
+      "epoch": 1.3055796909825848,
+      "grad_norm": 9.361547470092773,
+      "learning_rate": 1.738982282497828e-05,
+      "loss": 0.0851,
+      "step": 34560
+    },
+    {
+      "epoch": 1.3152506516565299,
+      "grad_norm": 5.259056568145752,
+      "learning_rate": 1.737048090363039e-05,
+      "loss": 0.0824,
+      "step": 34816
+    },
+    {
+      "epoch": 1.3249216123304748,
+      "grad_norm": 4.652898788452148,
+      "learning_rate": 1.7351138982282497e-05,
+      "loss": 0.0807,
+      "step": 35072
+    },
+    {
+      "epoch": 1.33459257300442,
+      "grad_norm": 3.225607395172119,
+      "learning_rate": 1.733179706093461e-05,
+      "loss": 0.0833,
+      "step": 35328
+    },
+    {
+      "epoch": 1.344263533678365,
+      "grad_norm": 4.242973804473877,
+      "learning_rate": 1.7312530693966985e-05,
+      "loss": 0.0785,
+      "step": 35584
+    },
+    {
+      "epoch": 1.35393449435231,
+      "grad_norm": 3.6310012340545654,
+      "learning_rate": 1.7293188772619093e-05,
+      "loss": 0.082,
+      "step": 35840
+    },
+    {
+      "epoch": 1.363605455026255,
+      "grad_norm": 4.149777412414551,
+      "learning_rate": 1.72738468512712e-05,
+      "loss": 0.0788,
+      "step": 36096
+    },
+    {
+      "epoch": 1.3732764157002002,
+      "grad_norm": 3.4874989986419678,
+      "learning_rate": 1.7254504929923313e-05,
+      "loss": 0.0813,
+      "step": 36352
+    },
+    {
+      "epoch": 1.3829473763741453,
+      "grad_norm": 4.847866535186768,
+      "learning_rate": 1.7235163008575425e-05,
+      "loss": 0.0762,
+      "step": 36608
+    },
+    {
+      "epoch": 1.3926183370480905,
+      "grad_norm": 6.0248332023620605,
+      "learning_rate": 1.7215821087227534e-05,
+      "loss": 0.084,
+      "step": 36864
+    },
+    {
+      "epoch": 1.4022892977220354,
+      "grad_norm": 12.932506561279297,
+      "learning_rate": 1.7196479165879642e-05,
+      "loss": 0.0774,
+      "step": 37120
+    },
+    {
+      "epoch": 1.4119602583959805,
+      "grad_norm": 4.421403884887695,
+      "learning_rate": 1.7177137244531754e-05,
+      "loss": 0.0745,
+      "step": 37376
+    },
+    {
+      "epoch": 1.4216312190699256,
+      "grad_norm": 4.352053165435791,
+      "learning_rate": 1.7157795323183862e-05,
+      "loss": 0.0766,
+      "step": 37632
+    },
+    {
+      "epoch": 1.4313021797438705,
+      "grad_norm": 3.0803287029266357,
+      "learning_rate": 1.7138528956216238e-05,
+      "loss": 0.0786,
+      "step": 37888
+    },
+    {
+      "epoch": 1.4409731404178157,
+      "grad_norm": 9.046032905578613,
+      "learning_rate": 1.7119187034868347e-05,
+      "loss": 0.0792,
+      "step": 38144
+    },
+    {
+      "epoch": 1.4506441010917608,
+      "grad_norm": 5.227222442626953,
+      "learning_rate": 1.709984511352046e-05,
+      "loss": 0.0782,
+      "step": 38400
+    },
+    {
+      "epoch": 1.460315061765706,
+      "grad_norm": 9.277040481567383,
+      "learning_rate": 1.7080503192172567e-05,
+      "loss": 0.0734,
+      "step": 38656
+    },
+    {
+      "epoch": 1.469986022439651,
+      "grad_norm": 6.931709289550781,
+      "learning_rate": 1.706116127082468e-05,
+      "loss": 0.0745,
+      "step": 38912
+    },
+    {
+      "epoch": 1.479656983113596,
+      "grad_norm": 2.403529167175293,
+      "learning_rate": 1.7041819349476787e-05,
+      "loss": 0.0713,
+      "step": 39168
+    },
+    {
+      "epoch": 1.489327943787541,
+      "grad_norm": 3.0608630180358887,
+      "learning_rate": 1.7022477428128895e-05,
+      "loss": 0.0724,
+      "step": 39424
+    },
+    {
+      "epoch": 1.4989989044614862,
+      "grad_norm": 2.9378268718719482,
+      "learning_rate": 1.7003135506781007e-05,
+      "loss": 0.0719,
+      "step": 39680
+    },
+    {
+      "epoch": 1.508669865135431,
+      "grad_norm": 4.745122909545898,
+      "learning_rate": 1.6983869139813383e-05,
+      "loss": 0.0755,
+      "step": 39936
+    },
+    {
+      "epoch": 1.5183408258093762,
+      "grad_norm": 7.573899745941162,
+      "learning_rate": 1.696452721846549e-05,
+      "loss": 0.0731,
+      "step": 40192
+    },
+    {
+      "epoch": 1.5280117864833214,
+      "grad_norm": 10.226018905639648,
+      "learning_rate": 1.69451852971176e-05,
+      "loss": 0.076,
+      "step": 40448
+    },
+    {
+      "epoch": 1.5376827471572665,
+      "grad_norm": 5.051877021789551,
+      "learning_rate": 1.692584337576971e-05,
+      "loss": 0.075,
+      "step": 40704
+    },
+    {
+      "epoch": 1.5473537078312116,
+      "grad_norm": 4.395775318145752,
+      "learning_rate": 1.6906501454421823e-05,
+      "loss": 0.0735,
+      "step": 40960
+    },
+    {
+      "epoch": 1.5570246685051568,
+      "grad_norm": 4.498766899108887,
+      "learning_rate": 1.6887159533073932e-05,
+      "loss": 0.0729,
+      "step": 41216
+    },
+    {
+      "epoch": 1.5666956291791017,
+      "grad_norm": 5.933803558349609,
+      "learning_rate": 1.686781761172604e-05,
+      "loss": 0.0748,
+      "step": 41472
+    },
+    {
+      "epoch": 1.5763665898530468,
+      "grad_norm": 2.9409236907958984,
+      "learning_rate": 1.6848475690378152e-05,
+      "loss": 0.07,
+      "step": 41728
+    },
+    {
+      "epoch": 1.5860375505269917,
+      "grad_norm": 8.31312370300293,
+      "learning_rate": 1.6829209323410528e-05,
+      "loss": 0.0703,
+      "step": 41984
+    },
+    {
+      "epoch": 1.5957085112009368,
+      "grad_norm": 1.95456862449646,
+      "learning_rate": 1.6809867402062636e-05,
+      "loss": 0.0709,
+      "step": 42240
+    },
+    {
+      "epoch": 1.605379471874882,
+      "grad_norm": 3.6376004219055176,
+      "learning_rate": 1.6790525480714745e-05,
+      "loss": 0.0656,
+      "step": 42496
+    },
+    {
+      "epoch": 1.615050432548827,
+      "grad_norm": 3.3740224838256836,
+      "learning_rate": 1.6771183559366853e-05,
+      "loss": 0.0728,
+      "step": 42752
+    },
+    {
+      "epoch": 1.6247213932227722,
+      "grad_norm": 2.608504295349121,
+      "learning_rate": 1.6751841638018965e-05,
+      "loss": 0.0723,
+      "step": 43008
+    },
+    {
+      "epoch": 1.634392353896717,
+      "grad_norm": 5.380160808563232,
+      "learning_rate": 1.6732499716671077e-05,
+      "loss": 0.0686,
+      "step": 43264
+    },
+    {
+      "epoch": 1.6440633145706622,
+      "grad_norm": 1.6728038787841797,
+      "learning_rate": 1.6713157795323185e-05,
+      "loss": 0.0668,
+      "step": 43520
+    },
+    {
+      "epoch": 1.6537342752446071,
+      "grad_norm": 7.20682430267334,
+      "learning_rate": 1.6693815873975294e-05,
+      "loss": 0.0689,
+      "step": 43776
+    },
+    {
+      "epoch": 1.6634052359185523,
+      "grad_norm": 9.442398071289062,
+      "learning_rate": 1.667454950700767e-05,
+      "loss": 0.0669,
+      "step": 44032
+    },
+    {
+      "epoch": 1.6730761965924974,
+      "grad_norm": 3.7477312088012695,
+      "learning_rate": 1.665520758565978e-05,
+      "loss": 0.0647,
+      "step": 44288
+    },
+    {
+      "epoch": 1.6827471572664425,
+      "grad_norm": 4.700344085693359,
+      "learning_rate": 1.663586566431189e-05,
+      "loss": 0.0712,
+      "step": 44544
+    },
+    {
+      "epoch": 1.6924181179403877,
+      "grad_norm": 3.5288517475128174,
+      "learning_rate": 1.6616523742963998e-05,
+      "loss": 0.0678,
+      "step": 44800
+    },
+    {
+      "epoch": 1.7020890786143328,
+      "grad_norm": 7.689276695251465,
+      "learning_rate": 1.659718182161611e-05,
+      "loss": 0.0668,
+      "step": 45056
+    },
+    {
+      "epoch": 1.7117600392882777,
+      "grad_norm": 4.36802339553833,
+      "learning_rate": 1.657783990026822e-05,
+      "loss": 0.0625,
+      "step": 45312
+    },
+    {
+      "epoch": 1.7214309999622228,
+      "grad_norm": 2.3436222076416016,
+      "learning_rate": 1.6558573533300594e-05,
+      "loss": 0.0655,
+      "step": 45568
+    },
+    {
+      "epoch": 1.7311019606361677,
+      "grad_norm": 1.5666533708572388,
+      "learning_rate": 1.6539231611952706e-05,
+      "loss": 0.0644,
+      "step": 45824
+    },
+    {
+      "epoch": 1.7407729213101129,
+      "grad_norm": 4.3904266357421875,
+      "learning_rate": 1.6519889690604814e-05,
+      "loss": 0.0634,
+      "step": 46080
+    },
+    {
+      "epoch": 1.750443881984058,
+      "grad_norm": 2.4941790103912354,
+      "learning_rate": 1.6500547769256926e-05,
+      "loss": 0.0641,
+      "step": 46336
+    },
+    {
+      "epoch": 1.760114842658003,
+      "grad_norm": 3.0806963443756104,
+      "learning_rate": 1.6481205847909034e-05,
+      "loss": 0.0664,
+      "step": 46592
+    },
+    {
+      "epoch": 1.7697858033319482,
+      "grad_norm": 6.179355621337891,
+      "learning_rate": 1.6461863926561143e-05,
+      "loss": 0.0626,
+      "step": 46848
+    },
+    {
+      "epoch": 1.7794567640058934,
+      "grad_norm": 1.792417287826538,
+      "learning_rate": 1.644252200521325e-05,
+      "loss": 0.0623,
+      "step": 47104
+    },
+    {
+      "epoch": 1.7891277246798383,
+      "grad_norm": 3.0433876514434814,
+      "learning_rate": 1.6423180083865363e-05,
+      "loss": 0.0629,
+      "step": 47360
+    },
+    {
+      "epoch": 1.7987986853537834,
+      "grad_norm": 8.955931663513184,
+      "learning_rate": 1.6403838162517475e-05,
+      "loss": 0.064,
+      "step": 47616
+    },
+    {
+      "epoch": 1.8084696460277283,
+      "grad_norm": 1.9222790002822876,
+      "learning_rate": 1.6384496241169583e-05,
+      "loss": 0.062,
+      "step": 47872
+    },
+    {
+      "epoch": 1.8181406067016734,
+      "grad_norm": 6.602641582489014,
+      "learning_rate": 1.6365154319821692e-05,
+      "loss": 0.0625,
+      "step": 48128
+    },
+    {
+      "epoch": 1.8278115673756186,
+      "grad_norm": 3.8623206615448,
+      "learning_rate": 1.6345812398473804e-05,
+      "loss": 0.0641,
+      "step": 48384
+    },
+    {
+      "epoch": 1.8374825280495637,
+      "grad_norm": 3.5689499378204346,
+      "learning_rate": 1.6326470477125912e-05,
+      "loss": 0.061,
+      "step": 48640
+    },
+    {
+      "epoch": 1.8471534887235088,
+      "grad_norm": 5.1966705322265625,
+      "learning_rate": 1.6307128555778024e-05,
+      "loss": 0.0603,
+      "step": 48896
+    },
+    {
+      "epoch": 1.856824449397454,
+      "grad_norm": 8.878084182739258,
+      "learning_rate": 1.6287862188810396e-05,
+      "loss": 0.0609,
+      "step": 49152
+    },
+    {
+      "epoch": 1.8664954100713989,
+      "grad_norm": 8.031649589538574,
+      "learning_rate": 1.6268520267462508e-05,
+      "loss": 0.0609,
+      "step": 49408
+    },
+    {
+      "epoch": 1.876166370745344,
+      "grad_norm": 5.966855525970459,
+      "learning_rate": 1.6249178346114616e-05,
+      "loss": 0.0603,
+      "step": 49664
+    },
+    {
+      "epoch": 1.8858373314192889,
+      "grad_norm": 5.956678867340088,
+      "learning_rate": 1.622983642476673e-05,
+      "loss": 0.0571,
+      "step": 49920
+    },
+    {
+      "epoch": 1.895508292093234,
+      "grad_norm": 4.6985650062561035,
+      "learning_rate": 1.6210494503418837e-05,
+      "loss": 0.0608,
+      "step": 50176
+    },
+    {
+      "epoch": 1.9051792527671791,
+      "grad_norm": 2.0274322032928467,
+      "learning_rate": 1.6191152582070945e-05,
+      "loss": 0.0601,
+      "step": 50432
+    },
+    {
+      "epoch": 1.9148502134411243,
+      "grad_norm": 2.5451152324676514,
+      "learning_rate": 1.6171810660723057e-05,
+      "loss": 0.0585,
+      "step": 50688
+    },
+    {
+      "epoch": 1.9245211741150694,
+      "grad_norm": 10.576590538024902,
+      "learning_rate": 1.6152468739375165e-05,
+      "loss": 0.0604,
+      "step": 50944
+    },
+    {
+      "epoch": 1.9341921347890145,
+      "grad_norm": 2.8857650756835938,
+      "learning_rate": 1.6133126818027277e-05,
+      "loss": 0.0577,
+      "step": 51200
+    },
+    {
+      "epoch": 1.9438630954629594,
+      "grad_norm": 3.5323078632354736,
+      "learning_rate": 1.6113784896679386e-05,
+      "loss": 0.0593,
+      "step": 51456
+    },
+    {
+      "epoch": 1.9535340561369046,
+      "grad_norm": 1.838157057762146,
+      "learning_rate": 1.6094442975331498e-05,
+      "loss": 0.0607,
+      "step": 51712
+    },
+    {
+      "epoch": 1.9632050168108495,
+      "grad_norm": 3.0781214237213135,
+      "learning_rate": 1.6075101053983606e-05,
+      "loss": 0.0579,
+      "step": 51968
+    },
+    {
+      "epoch": 1.9728759774847946,
+      "grad_norm": 3.3382725715637207,
+      "learning_rate": 1.6055759132635714e-05,
+      "loss": 0.0583,
+      "step": 52224
+    },
+    {
+      "epoch": 1.9825469381587397,
+      "grad_norm": 11.693552017211914,
+      "learning_rate": 1.6036417211287826e-05,
+      "loss": 0.06,
+      "step": 52480
+    },
+    {
+      "epoch": 1.9922178988326849,
+      "grad_norm": 2.506922960281372,
+      "learning_rate": 1.6017075289939935e-05,
+      "loss": 0.0565,
+      "step": 52736
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1_B-DISEASE": 0.795667459204617,
+      "eval_f1_B-MEDICATION": 0.921751878321422,
+      "eval_f1_B-PROCEDURE": 0.8160781701088163,
+      "eval_f1_B-SYMPTOM": 0.7897939991838038,
+      "eval_f1_I-DISEASE": 0.840603319768283,
+      "eval_f1_I-MEDICATION": 0.9362919771083036,
+      "eval_f1_I-PROCEDURE": 0.8357941949344769,
+      "eval_f1_I-SYMPTOM": 0.7996366525364875,
+      "eval_f1_O": 0.9230678952157123,
+      "eval_f1_macro": 0.8509650607091025,
+      "eval_f1_micro": 0.8840404124180135,
+      "eval_loss": 0.31923601031303406,
+      "eval_precision_B-DISEASE": 0.8158783079808294,
+      "eval_precision_B-MEDICATION": 0.9499527856468366,
+      "eval_precision_B-PROCEDURE": 0.848526831070472,
+      "eval_precision_B-SYMPTOM": 0.8200744316297579,
+      "eval_precision_I-DISEASE": 0.8429946510571731,
+      "eval_precision_I-MEDICATION": 0.9561669515355351,
+      "eval_precision_I-PROCEDURE": 0.8788058788058788,
+      "eval_precision_I-SYMPTOM": 0.8278156741398548,
+      "eval_precision_O": 0.9126516403530364,
+      "eval_precision_macro": 0.8725407946910416,
+      "eval_precision_micro": 0.8876748775758254,
+      "eval_rauc_macro": 0.904220184377927,
+      "eval_rauc_micro": 0.9331179355327206,
+      "eval_recall_B-DISEASE": 0.7764337272943602,
+      "eval_recall_B-MEDICATION": 0.8951770777718455,
+      "eval_recall_B-PROCEDURE": 0.7860198494182067,
+      "eval_recall_B-SYMPTOM": 0.7616700889801505,
+      "eval_recall_I-DISEASE": 0.8382255171289154,
+      "eval_recall_I-MEDICATION": 0.9172264240757392,
+      "eval_recall_I-PROCEDURE": 0.7967963312035382,
+      "eval_recall_I-SYMPTOM": 0.7733129163980228,
+      "eval_recall_O": 0.9337246601871894,
+      "eval_recall_macro": 0.8309540658286632,
+      "eval_recall_micro": 0.8804355875575709,
+      "eval_roc_auc_B-DISEASE": 0.8865867148232266,
+      "eval_roc_auc_B-MEDICATION": 0.9474921532385823,
+      "eval_roc_auc_B-PROCEDURE": 0.8918013132047432,
+      "eval_roc_auc_B-SYMPTOM": 0.8790279783173326,
+      "eval_roc_auc_I-DISEASE": 0.9089187734702582,
+      "eval_roc_auc_I-MEDICATION": 0.9583212327636237,
+      "eval_roc_auc_I-PROCEDURE": 0.8930449895535946,
+      "eval_roc_auc_I-SYMPTOM": 0.8741219681493123,
+      "eval_roc_auc_O": 0.8986665358806698,
+      "eval_runtime": 61.4999,
+      "eval_samples_per_second": 176.797,
+      "eval_steps_per_second": 22.114,
+      "step": 52942
+    },
+    {
+      "epoch": 2.00188885950663,
+      "grad_norm": 6.549783706665039,
+      "learning_rate": 1.5997733368592046e-05,
+      "loss": 0.0527,
+      "step": 52992
+    },
+    {
+      "epoch": 2.011559820180575,
+      "grad_norm": 17.193124771118164,
+      "learning_rate": 1.597846700162442e-05,
+      "loss": 0.0401,
+      "step": 53248
+    },
+    {
+      "epoch": 2.0212307808545202,
+      "grad_norm": 9.684758186340332,
+      "learning_rate": 1.595912508027653e-05,
+      "loss": 0.0405,
+      "step": 53504
+    },
+    {
+      "epoch": 2.030901741528465,
+      "grad_norm": 2.453227996826172,
+      "learning_rate": 1.5939783158928642e-05,
+      "loss": 0.0412,
+      "step": 53760
+    },
+    {
+      "epoch": 2.04057270220241,
+      "grad_norm": 5.099764347076416,
+      "learning_rate": 1.592044123758075e-05,
+      "loss": 0.0392,
+      "step": 54016
+    },
+    {
+      "epoch": 2.050243662876355,
+      "grad_norm": 2.8053245544433594,
+      "learning_rate": 1.590109931623286e-05,
+      "loss": 0.0388,
+      "step": 54272
+    },
+    {
+      "epoch": 2.0599146235503003,
+      "grad_norm": 1.1759517192840576,
+      "learning_rate": 1.5881832949265235e-05,
+      "loss": 0.0411,
+      "step": 54528
+    },
+    {
+      "epoch": 2.0695855842242454,
+      "grad_norm": 5.915517330169678,
+      "learning_rate": 1.5862491027917343e-05,
+      "loss": 0.0389,
+      "step": 54784
+    },
+    {
+      "epoch": 2.0792565448981906,
+      "grad_norm": 8.0426664352417,
+      "learning_rate": 1.5843149106569455e-05,
+      "loss": 0.0382,
+      "step": 55040
+    },
+    {
+      "epoch": 2.0889275055721357,
+      "grad_norm": 10.392659187316895,
+      "learning_rate": 1.5823807185221564e-05,
+      "loss": 0.0421,
+      "step": 55296
+    },
+    {
+      "epoch": 2.098598466246081,
+      "grad_norm": 7.73749303817749,
+      "learning_rate": 1.5804465263873675e-05,
+      "loss": 0.0389,
+      "step": 55552
+    },
+    {
+      "epoch": 2.1082694269200255,
+      "grad_norm": 5.712843418121338,
+      "learning_rate": 1.5785123342525784e-05,
+      "loss": 0.0403,
+      "step": 55808
+    },
+    {
+      "epoch": 2.1179403875939706,
+      "grad_norm": 2.4857349395751953,
+      "learning_rate": 1.5765781421177896e-05,
+      "loss": 0.0389,
+      "step": 56064
+    },
+    {
+      "epoch": 2.1276113482679158,
+      "grad_norm": 2.2378458976745605,
+      "learning_rate": 1.5746439499830004e-05,
+      "loss": 0.0395,
+      "step": 56320
+    },
+    {
+      "epoch": 2.137282308941861,
+      "grad_norm": 5.0309739112854,
+      "learning_rate": 1.5727097578482113e-05,
+      "loss": 0.0407,
+      "step": 56576
+    },
+    {
+      "epoch": 2.146953269615806,
+      "grad_norm": 3.6221115589141846,
+      "learning_rate": 1.570775565713422e-05,
+      "loss": 0.0413,
+      "step": 56832
+    },
+    {
+      "epoch": 2.156624230289751,
+      "grad_norm": 4.810079574584961,
+      "learning_rate": 1.5688413735786333e-05,
+      "loss": 0.04,
+      "step": 57088
+    },
+    {
+      "epoch": 2.1662951909636963,
+      "grad_norm": 2.51513671875,
+      "learning_rate": 1.5669071814438445e-05,
+      "loss": 0.0404,
+      "step": 57344
+    },
+    {
+      "epoch": 2.1759661516376414,
+      "grad_norm": 2.1976306438446045,
+      "learning_rate": 1.5649805447470817e-05,
+      "loss": 0.0418,
+      "step": 57600
+    },
+    {
+      "epoch": 2.185637112311586,
+      "grad_norm": 2.1660706996917725,
+      "learning_rate": 1.563046352612293e-05,
+      "loss": 0.0379,
+      "step": 57856
+    },
+    {
+      "epoch": 2.195308072985531,
+      "grad_norm": 3.0370383262634277,
+      "learning_rate": 1.561112160477504e-05,
+      "loss": 0.0386,
+      "step": 58112
+    },
+    {
+      "epoch": 2.2049790336594763,
+      "grad_norm": 2.958423614501953,
+      "learning_rate": 1.5591855237807413e-05,
+      "loss": 0.0395,
+      "step": 58368
+    },
+    {
+      "epoch": 2.2146499943334215,
+      "grad_norm": 0.8426064848899841,
+      "learning_rate": 1.5572513316459525e-05,
+      "loss": 0.0396,
+      "step": 58624
+    },
+    {
+      "epoch": 2.2243209550073666,
+      "grad_norm": 2.25600528717041,
+      "learning_rate": 1.5553171395111633e-05,
+      "loss": 0.0405,
+      "step": 58880
+    },
+    {
+      "epoch": 2.2339919156813117,
+      "grad_norm": 2.133103609085083,
+      "learning_rate": 1.553382947376374e-05,
+      "loss": 0.0391,
+      "step": 59136
+    },
+    {
+      "epoch": 2.243662876355257,
+      "grad_norm": 27.295085906982422,
+      "learning_rate": 1.5514487552415853e-05,
+      "loss": 0.0382,
+      "step": 59392
+    },
+    {
+      "epoch": 2.253333837029202,
+      "grad_norm": 3.368842840194702,
+      "learning_rate": 1.5495145631067962e-05,
+      "loss": 0.0407,
+      "step": 59648
+    },
+    {
+      "epoch": 2.2630047977031467,
+      "grad_norm": 1.4239710569381714,
+      "learning_rate": 1.5475803709720074e-05,
+      "loss": 0.0376,
+      "step": 59904
+    },
+    {
+      "epoch": 2.272675758377092,
+      "grad_norm": 4.708951473236084,
+      "learning_rate": 1.5456461788372182e-05,
+      "loss": 0.0378,
+      "step": 60160
+    },
+    {
+      "epoch": 2.282346719051037,
+      "grad_norm": 11.830906867980957,
+      "learning_rate": 1.5437119867024294e-05,
+      "loss": 0.0391,
+      "step": 60416
+    },
+    {
+      "epoch": 2.292017679724982,
+      "grad_norm": 2.8490591049194336,
+      "learning_rate": 1.5417777945676402e-05,
+      "loss": 0.0395,
+      "step": 60672
+    },
+    {
+      "epoch": 2.301688640398927,
+      "grad_norm": 3.398808240890503,
+      "learning_rate": 1.539843602432851e-05,
+      "loss": 0.0407,
+      "step": 60928
+    },
+    {
+      "epoch": 2.3113596010728723,
+      "grad_norm": 4.087090492248535,
+      "learning_rate": 1.537909410298062e-05,
+      "loss": 0.0361,
+      "step": 61184
+    },
+    {
+      "epoch": 2.3210305617468174,
+      "grad_norm": 2.446629762649536,
+      "learning_rate": 1.535975218163273e-05,
+      "loss": 0.0361,
+      "step": 61440
+    },
+    {
+      "epoch": 2.330701522420762,
+      "grad_norm": 1.8066984415054321,
+      "learning_rate": 1.5340410260284843e-05,
+      "loss": 0.0399,
+      "step": 61696
+    },
+    {
+      "epoch": 2.3403724830947072,
+      "grad_norm": 2.6665291786193848,
+      "learning_rate": 1.532106833893695e-05,
+      "loss": 0.0396,
+      "step": 61952
+    },
+    {
+      "epoch": 2.3500434437686524,
+      "grad_norm": 0.9438909292221069,
+      "learning_rate": 1.530172641758906e-05,
+      "loss": 0.0385,
+      "step": 62208
+    },
+    {
+      "epoch": 2.3597144044425975,
+      "grad_norm": 1.689215898513794,
+      "learning_rate": 1.528238449624117e-05,
+      "loss": 0.0399,
+      "step": 62464
+    },
+    {
+      "epoch": 2.3693853651165426,
+      "grad_norm": 2.397761583328247,
+      "learning_rate": 1.526304257489328e-05,
+      "loss": 0.0363,
+      "step": 62720
+    },
+    {
+      "epoch": 2.3790563257904878,
+      "grad_norm": 17.148651123046875,
+      "learning_rate": 1.524370065354539e-05,
+      "loss": 0.0379,
+      "step": 62976
+    },
+    {
+      "epoch": 2.388727286464433,
+      "grad_norm": 7.684645652770996,
+      "learning_rate": 1.52243587321975e-05,
+      "loss": 0.038,
+      "step": 63232
+    },
+    {
+      "epoch": 2.398398247138378,
+      "grad_norm": 2.3121824264526367,
+      "learning_rate": 1.520501681084961e-05,
+      "loss": 0.0363,
+      "step": 63488
+    },
+    {
+      "epoch": 2.408069207812323,
+      "grad_norm": 4.012951374053955,
+      "learning_rate": 1.518567488950172e-05,
+      "loss": 0.0369,
+      "step": 63744
+    },
+    {
+      "epoch": 2.417740168486268,
+      "grad_norm": 3.992743730545044,
+      "learning_rate": 1.5166332968153829e-05,
+      "loss": 0.037,
+      "step": 64000
+    },
+    {
+      "epoch": 2.427411129160213,
+      "grad_norm": 2.0966529846191406,
+      "learning_rate": 1.5147066601186205e-05,
+      "loss": 0.0398,
+      "step": 64256
+    },
+    {
+      "epoch": 2.437082089834158,
+      "grad_norm": 4.283209800720215,
+      "learning_rate": 1.5127724679838316e-05,
+      "loss": 0.0375,
+      "step": 64512
+    },
+    {
+      "epoch": 2.446753050508103,
+      "grad_norm": 7.317829608917236,
+      "learning_rate": 1.5108382758490425e-05,
+      "loss": 0.0385,
+      "step": 64768
+    },
+    {
+      "epoch": 2.4564240111820483,
+      "grad_norm": 2.1492598056793213,
+      "learning_rate": 1.5089040837142535e-05,
+      "loss": 0.038,
+      "step": 65024
+    },
+    {
+      "epoch": 2.4660949718559935,
+      "grad_norm": 4.824232578277588,
+      "learning_rate": 1.5069698915794643e-05,
+      "loss": 0.0404,
+      "step": 65280
+    },
+    {
+      "epoch": 2.4757659325299386,
+      "grad_norm": 2.757894992828369,
+      "learning_rate": 1.5050356994446755e-05,
+      "loss": 0.0379,
+      "step": 65536
+    },
+    {
+      "epoch": 2.4854368932038833,
+      "grad_norm": 3.4582314491271973,
+      "learning_rate": 1.5031015073098865e-05,
+      "loss": 0.0352,
+      "step": 65792
+    },
+    {
+      "epoch": 2.4951078538778284,
+      "grad_norm": 2.4710917472839355,
+      "learning_rate": 1.5011673151750974e-05,
+      "loss": 0.0363,
+      "step": 66048
+    },
+    {
+      "epoch": 2.5047788145517735,
+      "grad_norm": 2.776700973510742,
+      "learning_rate": 1.4992331230403084e-05,
+      "loss": 0.0358,
+      "step": 66304
+    },
+    {
+      "epoch": 2.5144497752257187,
+      "grad_norm": 3.758176326751709,
+      "learning_rate": 1.4972989309055194e-05,
+      "loss": 0.0356,
+      "step": 66560
+    },
+    {
+      "epoch": 2.524120735899664,
+      "grad_norm": 2.5761642456054688,
+      "learning_rate": 1.4953647387707304e-05,
+      "loss": 0.0404,
+      "step": 66816
+    },
+    {
+      "epoch": 2.533791696573609,
+      "grad_norm": 1.3668540716171265,
+      "learning_rate": 1.4934381020739678e-05,
+      "loss": 0.0366,
+      "step": 67072
+    },
+    {
+      "epoch": 2.543462657247554,
+      "grad_norm": 3.8430099487304688,
+      "learning_rate": 1.4915039099391788e-05,
+      "loss": 0.0372,
+      "step": 67328
+    },
+    {
+      "epoch": 2.5531336179214987,
+      "grad_norm": 5.29500675201416,
+      "learning_rate": 1.4895697178043897e-05,
+      "loss": 0.0358,
+      "step": 67584
+    },
+    {
+      "epoch": 2.5628045785954443,
+      "grad_norm": 0.8562812805175781,
+      "learning_rate": 1.4876355256696009e-05,
+      "loss": 0.0374,
+      "step": 67840
+    },
+    {
+      "epoch": 2.572475539269389,
+      "grad_norm": 4.466825008392334,
+      "learning_rate": 1.4857013335348119e-05,
+      "loss": 0.0359,
+      "step": 68096
+    },
+    {
+      "epoch": 2.582146499943334,
+      "grad_norm": 12.638843536376953,
+      "learning_rate": 1.4837746968380493e-05,
+      "loss": 0.0362,
+      "step": 68352
+    },
+    {
+      "epoch": 2.5918174606172792,
+      "grad_norm": 4.4277119636535645,
+      "learning_rate": 1.4818405047032603e-05,
+      "loss": 0.036,
+      "step": 68608
+    },
+    {
+      "epoch": 2.6014884212912244,
+      "grad_norm": 1.1809728145599365,
+      "learning_rate": 1.4799063125684711e-05,
+      "loss": 0.035,
+      "step": 68864
+    },
+    {
+      "epoch": 2.6111593819651695,
+      "grad_norm": 4.5768327713012695,
+      "learning_rate": 1.4779721204336823e-05,
+      "loss": 0.0374,
+      "step": 69120
+    },
+    {
+      "epoch": 2.6208303426391146,
+      "grad_norm": 4.537430763244629,
+      "learning_rate": 1.4760379282988933e-05,
+      "loss": 0.0344,
+      "step": 69376
+    },
+    {
+      "epoch": 2.6305013033130598,
+      "grad_norm": 1.4762442111968994,
+      "learning_rate": 1.4741037361641042e-05,
+      "loss": 0.0374,
+      "step": 69632
+    },
+    {
+      "epoch": 2.6401722639870044,
+      "grad_norm": 1.5577633380889893,
+      "learning_rate": 1.4721695440293152e-05,
+      "loss": 0.0353,
+      "step": 69888
+    },
+    {
+      "epoch": 2.6498432246609496,
+      "grad_norm": 4.222722053527832,
+      "learning_rate": 1.4702353518945262e-05,
+      "loss": 0.0359,
+      "step": 70144
+    },
+    {
+      "epoch": 2.6595141853348947,
+      "grad_norm": 1.9563344717025757,
+      "learning_rate": 1.4683011597597372e-05,
+      "loss": 0.0379,
+      "step": 70400
+    },
+    {
+      "epoch": 2.66918514600884,
+      "grad_norm": 5.85068416595459,
+      "learning_rate": 1.466366967624948e-05,
+      "loss": 0.0344,
+      "step": 70656
+    },
+    {
+      "epoch": 2.678856106682785,
+      "grad_norm": 2.2116239070892334,
+      "learning_rate": 1.464432775490159e-05,
+      "loss": 0.039,
+      "step": 70912
+    },
+    {
+      "epoch": 2.68852706735673,
+      "grad_norm": 4.683871269226074,
+      "learning_rate": 1.4624985833553702e-05,
+      "loss": 0.0343,
+      "step": 71168
+    },
+    {
+      "epoch": 2.698198028030675,
+      "grad_norm": 1.9998408555984497,
+      "learning_rate": 1.460564391220581e-05,
+      "loss": 0.0367,
+      "step": 71424
+    },
+    {
+      "epoch": 2.70786898870462,
+      "grad_norm": 1.950804352760315,
+      "learning_rate": 1.4586301990857921e-05,
+      "loss": 0.0354,
+      "step": 71680
+    },
+    {
+      "epoch": 2.7175399493785655,
+      "grad_norm": 2.9149844646453857,
+      "learning_rate": 1.456696006951003e-05,
+      "loss": 0.0339,
+      "step": 71936
+    },
+    {
+      "epoch": 2.72721091005251,
+      "grad_norm": 4.158403396606445,
+      "learning_rate": 1.4547618148162141e-05,
+      "loss": 0.0358,
+      "step": 72192
+    },
+    {
+      "epoch": 2.7368818707264553,
+      "grad_norm": 1.9110437631607056,
+      "learning_rate": 1.4528351781194517e-05,
+      "loss": 0.0363,
+      "step": 72448
+    },
+    {
+      "epoch": 2.7465528314004004,
+      "grad_norm": 4.942687034606934,
+      "learning_rate": 1.4509009859846625e-05,
+      "loss": 0.0331,
+      "step": 72704
+    },
+    {
+      "epoch": 2.7562237920743455,
+      "grad_norm": 4.669269561767578,
+      "learning_rate": 1.4489667938498735e-05,
+      "loss": 0.0339,
+      "step": 72960
+    },
+    {
+      "epoch": 2.7658947527482907,
+      "grad_norm": 2.782804012298584,
+      "learning_rate": 1.4470326017150846e-05,
+      "loss": 0.0337,
+      "step": 73216
+    },
+    {
+      "epoch": 2.775565713422236,
+      "grad_norm": 0.8589828014373779,
+      "learning_rate": 1.4450984095802956e-05,
+      "loss": 0.0348,
+      "step": 73472
+    },
+    {
+      "epoch": 2.785236674096181,
+      "grad_norm": 6.355395793914795,
+      "learning_rate": 1.4431642174455066e-05,
+      "loss": 0.0347,
+      "step": 73728
+    },
+    {
+      "epoch": 2.7949076347701256,
+      "grad_norm": 1.7806596755981445,
+      "learning_rate": 1.4412300253107174e-05,
+      "loss": 0.035,
+      "step": 73984
+    },
+    {
+      "epoch": 2.8045785954440707,
+      "grad_norm": 5.5398850440979,
+      "learning_rate": 1.4392958331759286e-05,
+      "loss": 0.0309,
+      "step": 74240
+    },
+    {
+      "epoch": 2.814249556118016,
+      "grad_norm": 1.2205835580825806,
+      "learning_rate": 1.437369196479166e-05,
+      "loss": 0.0318,
+      "step": 74496
+    },
+    {
+      "epoch": 2.823920516791961,
+      "grad_norm": 4.248105525970459,
+      "learning_rate": 1.435435004344377e-05,
+      "loss": 0.0347,
+      "step": 74752
+    },
+    {
+      "epoch": 2.833591477465906,
+      "grad_norm": 1.5058479309082031,
+      "learning_rate": 1.4335083676476144e-05,
+      "loss": 0.0338,
+      "step": 75008
+    },
+    {
+      "epoch": 2.8432624381398512,
+      "grad_norm": 3.8759660720825195,
+      "learning_rate": 1.4315741755128254e-05,
+      "loss": 0.0343,
+      "step": 75264
+    },
+    {
+      "epoch": 2.8529333988137964,
+      "grad_norm": 16.488771438598633,
+      "learning_rate": 1.4296399833780366e-05,
+      "loss": 0.0338,
+      "step": 75520
+    },
+    {
+      "epoch": 2.862604359487741,
+      "grad_norm": 6.564029693603516,
+      "learning_rate": 1.4277057912432475e-05,
+      "loss": 0.0312,
+      "step": 75776
+    },
+    {
+      "epoch": 2.8722753201616866,
+      "grad_norm": 1.345203161239624,
+      "learning_rate": 1.4257715991084585e-05,
+      "loss": 0.0332,
+      "step": 76032
+    },
+    {
+      "epoch": 2.8819462808356313,
+      "grad_norm": 2.0033822059631348,
+      "learning_rate": 1.4238374069736693e-05,
+      "loss": 0.0322,
+      "step": 76288
+    },
+    {
+      "epoch": 2.8916172415095764,
+      "grad_norm": 6.844017505645752,
+      "learning_rate": 1.4219032148388805e-05,
+      "loss": 0.0319,
+      "step": 76544
+    },
+    {
+      "epoch": 2.9012882021835216,
+      "grad_norm": 4.2425150871276855,
+      "learning_rate": 1.4199690227040915e-05,
+      "loss": 0.0322,
+      "step": 76800
+    },
+    {
+      "epoch": 2.9109591628574667,
+      "grad_norm": 1.8265749216079712,
+      "learning_rate": 1.4180348305693024e-05,
+      "loss": 0.0322,
+      "step": 77056
+    },
+    {
+      "epoch": 2.920630123531412,
+      "grad_norm": 3.0552210807800293,
+      "learning_rate": 1.4161006384345134e-05,
+      "loss": 0.033,
+      "step": 77312
+    },
+    {
+      "epoch": 2.930301084205357,
+      "grad_norm": 2.102796792984009,
+      "learning_rate": 1.4141664462997244e-05,
+      "loss": 0.0346,
+      "step": 77568
+    },
+    {
+      "epoch": 2.939972044879302,
+      "grad_norm": 1.903757929801941,
+      "learning_rate": 1.4122322541649354e-05,
+      "loss": 0.0315,
+      "step": 77824
+    },
+    {
+      "epoch": 2.9496430055532468,
+      "grad_norm": 9.322936058044434,
+      "learning_rate": 1.4102980620301462e-05,
+      "loss": 0.0336,
+      "step": 78080
+    },
+    {
+      "epoch": 2.959313966227192,
+      "grad_norm": 1.862209677696228,
+      "learning_rate": 1.4083714253333838e-05,
+      "loss": 0.0328,
+      "step": 78336
+    },
+    {
+      "epoch": 2.968984926901137,
+      "grad_norm": 3.4806630611419678,
+      "learning_rate": 1.4064372331985946e-05,
+      "loss": 0.0321,
+      "step": 78592
+    },
+    {
+      "epoch": 2.978655887575082,
+      "grad_norm": 7.490905284881592,
+      "learning_rate": 1.4045030410638058e-05,
+      "loss": 0.0321,
+      "step": 78848
+    },
+    {
+      "epoch": 2.9883268482490273,
+      "grad_norm": 2.008312940597534,
+      "learning_rate": 1.4025688489290168e-05,
+      "loss": 0.032,
+      "step": 79104
+    },
+    {
+      "epoch": 2.9979978089229724,
+      "grad_norm": 5.4629645347595215,
+      "learning_rate": 1.4006346567942277e-05,
+      "loss": 0.0316,
+      "step": 79360
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1_B-DISEASE": 0.8058758050409478,
+      "eval_f1_B-MEDICATION": 0.9331298806211291,
+      "eval_f1_B-PROCEDURE": 0.8246479186103336,
+      "eval_f1_B-SYMPTOM": 0.7958159437899519,
+      "eval_f1_I-DISEASE": 0.8446797498113607,
+      "eval_f1_I-MEDICATION": 0.9445428820775924,
+      "eval_f1_I-PROCEDURE": 0.8431497703012539,
+      "eval_f1_I-SYMPTOM": 0.8064467139982535,
+      "eval_f1_O": 0.9242880224344192,
+      "eval_f1_macro": 0.8580640762983602,
+      "eval_f1_micro": 0.8867284724320147,
+      "eval_loss": 0.346194326877594,
+      "eval_precision_B-DISEASE": 0.8078026619909142,
+      "eval_precision_B-MEDICATION": 0.9413256066642521,
+      "eval_precision_B-PROCEDURE": 0.8576841327049256,
+      "eval_precision_B-SYMPTOM": 0.8196756992055719,
+      "eval_precision_I-DISEASE": 0.8398561507936508,
+      "eval_precision_I-MEDICATION": 0.9445678620543743,
+      "eval_precision_I-PROCEDURE": 0.8685191753683246,
+      "eval_precision_I-SYMPTOM": 0.8141611818689563,
+      "eval_precision_O": 0.922143895574372,
+      "eval_precision_macro": 0.8684151518028158,
+      "eval_precision_micro": 0.8893727212165927,
+      "eval_rauc_macro": 0.9135258778318731,
+      "eval_rauc_micro": 0.9350417116157864,
+      "eval_recall_B-DISEASE": 0.8039581185055922,
+      "eval_recall_B-MEDICATION": 0.9250756362342054,
+      "eval_recall_B-PROCEDURE": 0.7940622861054073,
+      "eval_recall_B-SYMPTOM": 0.773305954825462,
+      "eval_recall_I-DISEASE": 0.8495590762553469,
+      "eval_recall_I-MEDICATION": 0.944517903422013,
+      "eval_recall_I-PROCEDURE": 0.8192203807518748,
+      "eval_recall_I-SYMPTOM": 0.7988770685579196,
+      "eval_recall_O": 0.9264421433839181,
+      "eval_recall_macro": 0.8483353964490822,
+      "eval_recall_micro": 0.8840999005950059,
+      "eval_roc_auc_B-DISEASE": 0.9001994739703317,
+      "eval_roc_auc_B-MEDICATION": 0.9624199730237505,
+      "eval_roc_auc_B-PROCEDURE": 0.89589622737178,
+      "eval_roc_auc_B-SYMPTOM": 0.8848133448211472,
+      "eval_roc_auc_I-DISEASE": 0.914201809349682,
+      "eval_roc_auc_I-MEDICATION": 0.9718740532463399,
+      "eval_roc_auc_I-PROCEDURE": 0.9035684876000457,
+      "eval_roc_auc_I-SYMPTOM": 0.8852284244551051,
+      "eval_roc_auc_O": 0.903531106648675,
+      "eval_runtime": 61.221,
+      "eval_samples_per_second": 177.602,
+      "eval_steps_per_second": 22.215,
+      "step": 79413
+    },
+    {
+      "epoch": 3.0076687695969175,
+      "grad_norm": 4.327937602996826,
+      "learning_rate": 1.3987004646594387e-05,
+      "loss": 0.0237,
+      "step": 79616
+    },
+    {
+      "epoch": 3.0173397302708627,
+      "grad_norm": 1.6373872756958008,
+      "learning_rate": 1.3967662725246499e-05,
+      "loss": 0.022,
+      "step": 79872
+    },
+    {
+      "epoch": 3.0270106909448073,
+      "grad_norm": 3.250305652618408,
+      "learning_rate": 1.3948320803898607e-05,
+      "loss": 0.0246,
+      "step": 80128
+    },
+    {
+      "epoch": 3.0366816516187525,
+      "grad_norm": 1.6971690654754639,
+      "learning_rate": 1.3928978882550717e-05,
+      "loss": 0.0236,
+      "step": 80384
+    },
+    {
+      "epoch": 3.0463526122926976,
+      "grad_norm": 5.478879451751709,
+      "learning_rate": 1.3909636961202826e-05,
+      "loss": 0.0219,
+      "step": 80640
+    },
+    {
+      "epoch": 3.0560235729666427,
+      "grad_norm": 2.4806175231933594,
+      "learning_rate": 1.3890295039854938e-05,
+      "loss": 0.0236,
+      "step": 80896
+    },
+    {
+      "epoch": 3.065694533640588,
+      "grad_norm": 1.5560436248779297,
+      "learning_rate": 1.3870953118507046e-05,
+      "loss": 0.0229,
+      "step": 81152
+    },
+    {
+      "epoch": 3.075365494314533,
+      "grad_norm": 10.51571273803711,
+      "learning_rate": 1.3851611197159156e-05,
+      "loss": 0.0246,
+      "step": 81408
+    },
+    {
+      "epoch": 3.085036454988478,
+      "grad_norm": 4.828140735626221,
+      "learning_rate": 1.3832269275811265e-05,
+      "loss": 0.0225,
+      "step": 81664
+    },
+    {
+      "epoch": 3.0947074156624232,
+      "grad_norm": 0.9167439937591553,
+      "learning_rate": 1.3812927354463376e-05,
+      "loss": 0.0241,
+      "step": 81920
+    },
+    {
+      "epoch": 3.104378376336368,
+      "grad_norm": 4.8147454261779785,
+      "learning_rate": 1.3793585433115487e-05,
+      "loss": 0.0226,
+      "step": 82176
+    },
+    {
+      "epoch": 3.114049337010313,
+      "grad_norm": 5.181445121765137,
+      "learning_rate": 1.3774243511767595e-05,
+      "loss": 0.0202,
+      "step": 82432
+    },
+    {
+      "epoch": 3.123720297684258,
+      "grad_norm": 1.4374691247940063,
+      "learning_rate": 1.375497714479997e-05,
+      "loss": 0.0221,
+      "step": 82688
+    },
+    {
+      "epoch": 3.1333912583582033,
+      "grad_norm": 3.805264949798584,
+      "learning_rate": 1.3735635223452082e-05,
+      "loss": 0.0241,
+      "step": 82944
+    },
+    {
+      "epoch": 3.1430622190321484,
+      "grad_norm": 3.3050577640533447,
+      "learning_rate": 1.3716368856484456e-05,
+      "loss": 0.0225,
+      "step": 83200
+    },
+    {
+      "epoch": 3.1527331797060936,
+      "grad_norm": 1.6958988904953003,
+      "learning_rate": 1.3697026935136567e-05,
+      "loss": 0.0233,
+      "step": 83456
+    },
+    {
+      "epoch": 3.1624041403800387,
+      "grad_norm": 2.1749958992004395,
+      "learning_rate": 1.3677685013788675e-05,
+      "loss": 0.024,
+      "step": 83712
+    },
+    {
+      "epoch": 3.1720751010539834,
+      "grad_norm": 1.0387561321258545,
+      "learning_rate": 1.3658343092440785e-05,
+      "loss": 0.0235,
+      "step": 83968
+    },
+    {
+      "epoch": 3.1817460617279285,
+      "grad_norm": 4.311033248901367,
+      "learning_rate": 1.3639001171092895e-05,
+      "loss": 0.025,
+      "step": 84224
+    },
+    {
+      "epoch": 3.1914170224018736,
+      "grad_norm": 1.0629218816757202,
+      "learning_rate": 1.3619659249745005e-05,
+      "loss": 0.0242,
+      "step": 84480
+    },
+    {
+      "epoch": 3.2010879830758188,
+      "grad_norm": 4.607676029205322,
+      "learning_rate": 1.3600317328397114e-05,
+      "loss": 0.0218,
+      "step": 84736
+    },
+    {
+      "epoch": 3.210758943749764,
+      "grad_norm": 1.2249504327774048,
+      "learning_rate": 1.3580975407049224e-05,
+      "loss": 0.0217,
+      "step": 84992
+    },
+    {
+      "epoch": 3.220429904423709,
+      "grad_norm": 3.8173789978027344,
+      "learning_rate": 1.3561633485701336e-05,
+      "loss": 0.0212,
+      "step": 85248
+    },
+    {
+      "epoch": 3.230100865097654,
+      "grad_norm": 5.286001205444336,
+      "learning_rate": 1.3542291564353444e-05,
+      "loss": 0.0234,
+      "step": 85504
+    },
+    {
+      "epoch": 3.2397718257715993,
+      "grad_norm": 0.9266921281814575,
+      "learning_rate": 1.3522949643005554e-05,
+      "loss": 0.0227,
+      "step": 85760
+    },
+    {
+      "epoch": 3.2494427864455444,
+      "grad_norm": 1.9286329746246338,
+      "learning_rate": 1.3503607721657663e-05,
+      "loss": 0.0216,
+      "step": 86016
+    },
+    {
+      "epoch": 3.259113747119489,
+      "grad_norm": 7.073780536651611,
+      "learning_rate": 1.3484265800309775e-05,
+      "loss": 0.0229,
+      "step": 86272
+    },
+    {
+      "epoch": 3.268784707793434,
+      "grad_norm": 11.505043983459473,
+      "learning_rate": 1.3464923878961885e-05,
+      "loss": 0.0216,
+      "step": 86528
+    },
+    {
+      "epoch": 3.2784556684673793,
+      "grad_norm": 2.463899850845337,
+      "learning_rate": 1.3445581957613993e-05,
+      "loss": 0.0238,
+      "step": 86784
+    },
+    {
+      "epoch": 3.2881266291413245,
+      "grad_norm": 2.2217423915863037,
+      "learning_rate": 1.3426240036266103e-05,
+      "loss": 0.0244,
+      "step": 87040
+    },
+    {
+      "epoch": 3.2977975898152696,
+      "grad_norm": 2.690162181854248,
+      "learning_rate": 1.3406898114918213e-05,
+      "loss": 0.0233,
+      "step": 87296
+    },
+    {
+      "epoch": 3.3074685504892147,
+      "grad_norm": 0.6873595118522644,
+      "learning_rate": 1.3387631747950589e-05,
+      "loss": 0.0212,
+      "step": 87552
+    },
+    {
+      "epoch": 3.31713951116316,
+      "grad_norm": 12.570816040039062,
+      "learning_rate": 1.3368289826602698e-05,
+      "loss": 0.021,
+      "step": 87808
+    },
+    {
+      "epoch": 3.3268104718371045,
+      "grad_norm": 1.3393861055374146,
+      "learning_rate": 1.3348947905254808e-05,
+      "loss": 0.0204,
+      "step": 88064
+    },
+    {
+      "epoch": 3.3364814325110497,
+      "grad_norm": 0.6096575856208801,
+      "learning_rate": 1.332960598390692e-05,
+      "loss": 0.0218,
+      "step": 88320
+    },
+    {
+      "epoch": 3.346152393184995,
+      "grad_norm": 4.549058437347412,
+      "learning_rate": 1.3310264062559028e-05,
+      "loss": 0.0232,
+      "step": 88576
+    },
+    {
+      "epoch": 3.35582335385894,
+      "grad_norm": 2.827040195465088,
+      "learning_rate": 1.3290922141211138e-05,
+      "loss": 0.023,
+      "step": 88832
+    },
+    {
+      "epoch": 3.365494314532885,
+      "grad_norm": 4.081531524658203,
+      "learning_rate": 1.3271580219863246e-05,
+      "loss": 0.0202,
+      "step": 89088
+    },
+    {
+      "epoch": 3.37516527520683,
+      "grad_norm": 16.549381256103516,
+      "learning_rate": 1.3252238298515358e-05,
+      "loss": 0.023,
+      "step": 89344
+    },
+    {
+      "epoch": 3.3848362358807753,
+      "grad_norm": 1.166902780532837,
+      "learning_rate": 1.3232896377167468e-05,
+      "loss": 0.0217,
+      "step": 89600
+    },
+    {
+      "epoch": 3.3945071965547204,
+      "grad_norm": 1.8393259048461914,
+      "learning_rate": 1.3213554455819577e-05,
+      "loss": 0.0226,
+      "step": 89856
+    },
+    {
+      "epoch": 3.4041781572286656,
+      "grad_norm": 3.180155038833618,
+      "learning_rate": 1.3194288088851953e-05,
+      "loss": 0.0216,
+      "step": 90112
+    },
+    {
+      "epoch": 3.4138491179026103,
+      "grad_norm": 0.5230717658996582,
+      "learning_rate": 1.3174946167504061e-05,
+      "loss": 0.022,
+      "step": 90368
+    },
+    {
+      "epoch": 3.4235200785765554,
+      "grad_norm": 15.037604331970215,
+      "learning_rate": 1.3155604246156173e-05,
+      "loss": 0.0234,
+      "step": 90624
+    },
+    {
+      "epoch": 3.4331910392505005,
+      "grad_norm": 11.155952453613281,
+      "learning_rate": 1.3136262324808283e-05,
+      "loss": 0.0224,
+      "step": 90880
+    },
+    {
+      "epoch": 3.4428619999244456,
+      "grad_norm": 2.1080737113952637,
+      "learning_rate": 1.3116920403460391e-05,
+      "loss": 0.023,
+      "step": 91136
+    },
+    {
+      "epoch": 3.4525329605983908,
+      "grad_norm": 0.7303668856620789,
+      "learning_rate": 1.3097578482112501e-05,
+      "loss": 0.0217,
+      "step": 91392
+    },
+    {
+      "epoch": 3.462203921272336,
+      "grad_norm": 0.6222452521324158,
+      "learning_rate": 1.3078236560764612e-05,
+      "loss": 0.0219,
+      "step": 91648
+    },
+    {
+      "epoch": 3.471874881946281,
+      "grad_norm": 0.8807787299156189,
+      "learning_rate": 1.3058894639416722e-05,
+      "loss": 0.0236,
+      "step": 91904
+    },
+    {
+      "epoch": 3.4815458426202257,
+      "grad_norm": 0.9494552612304688,
+      "learning_rate": 1.3039628272449096e-05,
+      "loss": 0.0208,
+      "step": 92160
+    },
+    {
+      "epoch": 3.491216803294171,
+      "grad_norm": 14.498435020446777,
+      "learning_rate": 1.3020286351101206e-05,
+      "loss": 0.0241,
+      "step": 92416
+    },
+    {
+      "epoch": 3.500887763968116,
+      "grad_norm": 1.3170123100280762,
+      "learning_rate": 1.3000944429753314e-05,
+      "loss": 0.0213,
+      "step": 92672
+    },
+    {
+      "epoch": 3.510558724642061,
+      "grad_norm": 1.3304574489593506,
+      "learning_rate": 1.2981602508405426e-05,
+      "loss": 0.0216,
+      "step": 92928
+    },
+    {
+      "epoch": 3.520229685316006,
+      "grad_norm": 0.5469146966934204,
+      "learning_rate": 1.2962260587057536e-05,
+      "loss": 0.0198,
+      "step": 93184
+    },
+    {
+      "epoch": 3.5299006459899513,
+      "grad_norm": 1.7149643898010254,
+      "learning_rate": 1.2942918665709645e-05,
+      "loss": 0.0197,
+      "step": 93440
+    },
+    {
+      "epoch": 3.5395716066638965,
+      "grad_norm": 2.092782974243164,
+      "learning_rate": 1.292365229874202e-05,
+      "loss": 0.0225,
+      "step": 93696
+    },
+    {
+      "epoch": 3.549242567337841,
+      "grad_norm": 1.180370807647705,
+      "learning_rate": 1.2904310377394132e-05,
+      "loss": 0.0204,
+      "step": 93952
+    },
+    {
+      "epoch": 3.5589135280117867,
+      "grad_norm": 16.842605590820312,
+      "learning_rate": 1.288496845604624e-05,
+      "loss": 0.0214,
+      "step": 94208
+    },
+    {
+      "epoch": 3.5685844886857314,
+      "grad_norm": 3.62001895904541,
+      "learning_rate": 1.286562653469835e-05,
+      "loss": 0.0241,
+      "step": 94464
+    },
+    {
+      "epoch": 3.5782554493596765,
+      "grad_norm": 2.4327309131622314,
+      "learning_rate": 1.284628461335046e-05,
+      "loss": 0.0192,
+      "step": 94720
+    },
+    {
+      "epoch": 3.5879264100336217,
+      "grad_norm": 5.820268154144287,
+      "learning_rate": 1.2826942692002571e-05,
+      "loss": 0.0223,
+      "step": 94976
+    },
+    {
+      "epoch": 3.597597370707567,
+      "grad_norm": 3.0629537105560303,
+      "learning_rate": 1.280760077065468e-05,
+      "loss": 0.02,
+      "step": 95232
+    },
+    {
+      "epoch": 3.607268331381512,
+      "grad_norm": 2.9143710136413574,
+      "learning_rate": 1.278825884930679e-05,
+      "loss": 0.0198,
+      "step": 95488
+    },
+    {
+      "epoch": 3.616939292055457,
+      "grad_norm": 1.7662220001220703,
+      "learning_rate": 1.2768916927958898e-05,
+      "loss": 0.0225,
+      "step": 95744
+    },
+    {
+      "epoch": 3.626610252729402,
+      "grad_norm": 3.5561130046844482,
+      "learning_rate": 1.274957500661101e-05,
+      "loss": 0.0228,
+      "step": 96000
+    },
+    {
+      "epoch": 3.636281213403347,
+      "grad_norm": 5.7032470703125,
+      "learning_rate": 1.273023308526312e-05,
+      "loss": 0.0208,
+      "step": 96256
+    },
+    {
+      "epoch": 3.645952174077292,
+      "grad_norm": 1.8125163316726685,
+      "learning_rate": 1.2710891163915228e-05,
+      "loss": 0.0212,
+      "step": 96512
+    },
+    {
+      "epoch": 3.655623134751237,
+      "grad_norm": 4.229706764221191,
+      "learning_rate": 1.2691549242567338e-05,
+      "loss": 0.0238,
+      "step": 96768
+    },
+    {
+      "epoch": 3.6652940954251823,
+      "grad_norm": 1.200060486793518,
+      "learning_rate": 1.267220732121945e-05,
+      "loss": 0.0189,
+      "step": 97024
+    },
+    {
+      "epoch": 3.6749650560991274,
+      "grad_norm": 3.1629979610443115,
+      "learning_rate": 1.2652865399871559e-05,
+      "loss": 0.0207,
+      "step": 97280
+    },
+    {
+      "epoch": 3.6846360167730725,
+      "grad_norm": 3.1145436763763428,
+      "learning_rate": 1.2633523478523669e-05,
+      "loss": 0.0201,
+      "step": 97536
+    },
+    {
+      "epoch": 3.6943069774470176,
+      "grad_norm": 2.600019693374634,
+      "learning_rate": 1.2614181557175777e-05,
+      "loss": 0.0208,
+      "step": 97792
+    },
+    {
+      "epoch": 3.7039779381209623,
+      "grad_norm": 3.338853120803833,
+      "learning_rate": 1.2594915190208153e-05,
+      "loss": 0.0209,
+      "step": 98048
+    },
+    {
+      "epoch": 3.713648898794908,
+      "grad_norm": 6.754782676696777,
+      "learning_rate": 1.2575573268860263e-05,
+      "loss": 0.0187,
+      "step": 98304
+    },
+    {
+      "epoch": 3.7233198594688526,
+      "grad_norm": 3.4177420139312744,
+      "learning_rate": 1.2556231347512373e-05,
+      "loss": 0.0216,
+      "step": 98560
+    },
+    {
+      "epoch": 3.7329908201427977,
+      "grad_norm": 1.6833980083465576,
+      "learning_rate": 1.2536889426164482e-05,
+      "loss": 0.0202,
+      "step": 98816
+    },
+    {
+      "epoch": 3.742661780816743,
+      "grad_norm": 2.7053074836730957,
+      "learning_rate": 1.2517547504816592e-05,
+      "loss": 0.0191,
+      "step": 99072
+    },
+    {
+      "epoch": 3.752332741490688,
+      "grad_norm": 2.020542621612549,
+      "learning_rate": 1.2498205583468704e-05,
+      "loss": 0.0195,
+      "step": 99328
+    },
+    {
+      "epoch": 3.762003702164633,
+      "grad_norm": 4.648097515106201,
+      "learning_rate": 1.2478863662120812e-05,
+      "loss": 0.0208,
+      "step": 99584
+    },
+    {
+      "epoch": 3.771674662838578,
+      "grad_norm": 1.1168490648269653,
+      "learning_rate": 1.2459521740772922e-05,
+      "loss": 0.0194,
+      "step": 99840
+    },
+    {
+      "epoch": 3.7813456235125233,
+      "grad_norm": 0.9811049103736877,
+      "learning_rate": 1.2440255373805296e-05,
+      "loss": 0.0207,
+      "step": 100096
+    },
+    {
+      "epoch": 3.791016584186468,
+      "grad_norm": 3.2866318225860596,
+      "learning_rate": 1.2420913452457408e-05,
+      "loss": 0.0208,
+      "step": 100352
+    },
+    {
+      "epoch": 3.800687544860413,
+      "grad_norm": 1.0944135189056396,
+      "learning_rate": 1.2401571531109518e-05,
+      "loss": 0.0216,
+      "step": 100608
+    },
+    {
+      "epoch": 3.8103585055343583,
+      "grad_norm": 1.5802284479141235,
+      "learning_rate": 1.2382229609761627e-05,
+      "loss": 0.0215,
+      "step": 100864
+    },
+    {
+      "epoch": 3.8200294662083034,
+      "grad_norm": 15.70626163482666,
+      "learning_rate": 1.2362887688413737e-05,
+      "loss": 0.0224,
+      "step": 101120
+    },
+    {
+      "epoch": 3.8297004268822485,
+      "grad_norm": 2.241199016571045,
+      "learning_rate": 1.2343545767065847e-05,
+      "loss": 0.0203,
+      "step": 101376
+    },
+    {
+      "epoch": 3.8393713875561937,
+      "grad_norm": 1.7189942598342896,
+      "learning_rate": 1.2324203845717957e-05,
+      "loss": 0.0202,
+      "step": 101632
+    },
+    {
+      "epoch": 3.849042348230139,
+      "grad_norm": 3.025250196456909,
+      "learning_rate": 1.2304861924370065e-05,
+      "loss": 0.0214,
+      "step": 101888
+    },
+    {
+      "epoch": 3.8587133089040835,
+      "grad_norm": 0.44517338275909424,
+      "learning_rate": 1.2285595557402441e-05,
+      "loss": 0.0213,
+      "step": 102144
+    },
+    {
+      "epoch": 3.868384269578029,
+      "grad_norm": 1.4796372652053833,
+      "learning_rate": 1.226625363605455e-05,
+      "loss": 0.0214,
+      "step": 102400
+    },
+    {
+      "epoch": 3.8780552302519737,
+      "grad_norm": 3.5950703620910645,
+      "learning_rate": 1.2246911714706661e-05,
+      "loss": 0.0195,
+      "step": 102656
+    },
+    {
+      "epoch": 3.887726190925919,
+      "grad_norm": 3.87646222114563,
+      "learning_rate": 1.2227569793358771e-05,
+      "loss": 0.0194,
+      "step": 102912
+    },
+    {
+      "epoch": 3.897397151599864,
+      "grad_norm": 6.18682336807251,
+      "learning_rate": 1.220822787201088e-05,
+      "loss": 0.0186,
+      "step": 103168
+    },
+    {
+      "epoch": 3.907068112273809,
+      "grad_norm": 4.5957207679748535,
+      "learning_rate": 1.218888595066299e-05,
+      "loss": 0.0193,
+      "step": 103424
+    },
+    {
+      "epoch": 3.9167390729477543,
+      "grad_norm": 11.035417556762695,
+      "learning_rate": 1.2169544029315102e-05,
+      "loss": 0.0193,
+      "step": 103680
+    },
+    {
+      "epoch": 3.9264100336216994,
+      "grad_norm": 1.2352112531661987,
+      "learning_rate": 1.215020210796721e-05,
+      "loss": 0.0181,
+      "step": 103936
+    },
+    {
+      "epoch": 3.9360809942956445,
+      "grad_norm": 0.506557047367096,
+      "learning_rate": 1.213086018661932e-05,
+      "loss": 0.0187,
+      "step": 104192
+    },
+    {
+      "epoch": 3.945751954969589,
+      "grad_norm": 2.8846030235290527,
+      "learning_rate": 1.2111593819651694e-05,
+      "loss": 0.0196,
+      "step": 104448
+    },
+    {
+      "epoch": 3.9554229156435343,
+      "grad_norm": 1.4602288007736206,
+      "learning_rate": 1.2092251898303806e-05,
+      "loss": 0.0192,
+      "step": 104704
+    },
+    {
+      "epoch": 3.9650938763174794,
+      "grad_norm": 13.7206392288208,
+      "learning_rate": 1.207298553133618e-05,
+      "loss": 0.0191,
+      "step": 104960
+    },
+    {
+      "epoch": 3.9747648369914246,
+      "grad_norm": 1.7238157987594604,
+      "learning_rate": 1.205364360998829e-05,
+      "loss": 0.0201,
+      "step": 105216
+    },
+    {
+      "epoch": 3.9844357976653697,
+      "grad_norm": 2.0438215732574463,
+      "learning_rate": 1.20343016886404e-05,
+      "loss": 0.0182,
+      "step": 105472
+    },
+    {
+      "epoch": 3.994106758339315,
+      "grad_norm": 1.2184364795684814,
+      "learning_rate": 1.2014959767292509e-05,
+      "loss": 0.019,
+      "step": 105728
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1_B-DISEASE": 0.808675320486979,
+      "eval_f1_B-MEDICATION": 0.9266381766381766,
+      "eval_f1_B-PROCEDURE": 0.8295174204717594,
+      "eval_f1_B-SYMPTOM": 0.7980295566502463,
+      "eval_f1_I-DISEASE": 0.8489476041200179,
+      "eval_f1_I-MEDICATION": 0.9397869262133368,
+      "eval_f1_I-PROCEDURE": 0.847453216112688,
+      "eval_f1_I-SYMPTOM": 0.8079173624618605,
+      "eval_f1_O": 0.9249064875950979,
+      "eval_f1_macro": 0.8590968967500181,
+      "eval_f1_micro": 0.8881361203919136,
+      "eval_loss": 0.4215824604034424,
+      "eval_precision_B-DISEASE": 0.8221985408640052,
+      "eval_precision_B-MEDICATION": 0.927133440228042,
+      "eval_precision_B-PROCEDURE": 0.8393623543838136,
+      "eval_precision_B-SYMPTOM": 0.8061812467260345,
+      "eval_precision_I-DISEASE": 0.8662832447676619,
+      "eval_precision_I-MEDICATION": 0.9348440443793176,
+      "eval_precision_I-PROCEDURE": 0.8446231286120726,
+      "eval_precision_I-SYMPTOM": 0.8113340449395586,
+      "eval_precision_O": 0.9229153657042629,
+      "eval_precision_macro": 0.8638750456227521,
+      "eval_precision_micro": 0.88976580540172,
+      "eval_rauc_macro": 0.9166627680103409,
+      "eval_rauc_micro": 0.9362568980657558,
+      "eval_recall_B-DISEASE": 0.795589751725232,
+      "eval_recall_B-MEDICATION": 0.9261434418935753,
+      "eval_recall_B-PROCEDURE": 0.8199007529089665,
+      "eval_recall_B-SYMPTOM": 0.7900410677618069,
+      "eval_recall_I-DISEASE": 0.8322921762691454,
+      "eval_recall_I-MEDICATION": 0.9447823557412599,
+      "eval_recall_I-PROCEDURE": 0.8503023329824475,
+      "eval_recall_I-SYMPTOM": 0.8045293359123147,
+      "eval_recall_O": 0.9269062194588178,
+      "eval_recall_macro": 0.8544986038503963,
+      "eval_recall_micro": 0.886512394293185,
+      "eval_roc_auc_B-DISEASE": 0.8961942453514548,
+      "eval_roc_auc_B-MEDICATION": 0.9629229597024016,
+      "eval_roc_auc_B-PROCEDURE": 0.9085987950526558,
+      "eval_roc_auc_B-SYMPTOM": 0.8929666290562625,
+      "eval_roc_auc_I-DISEASE": 0.9077573774887775,
+      "eval_roc_auc_I-MEDICATION": 0.9719339273090749,
+      "eval_roc_auc_I-PROCEDURE": 0.9175308611542671,
+      "eval_roc_auc_I-SYMPTOM": 0.8876856873124548,
+      "eval_roc_auc_O": 0.9043744296657181,
+      "eval_runtime": 61.4869,
+      "eval_samples_per_second": 176.835,
+      "eval_steps_per_second": 22.119,
+      "step": 105884
+    },
+    {
+      "epoch": 4.00377771901326,
+      "grad_norm": 0.7948421835899353,
+      "learning_rate": 1.199561784594462e-05,
+      "loss": 0.0178,
+      "step": 105984
+    },
+    {
+      "epoch": 4.013448679687205,
+      "grad_norm": 0.8098104596138,
+      "learning_rate": 1.1976275924596729e-05,
+      "loss": 0.0143,
+      "step": 106240
+    },
+    {
+      "epoch": 4.02311964036115,
+      "grad_norm": 3.08135724067688,
+      "learning_rate": 1.195693400324884e-05,
+      "loss": 0.0134,
+      "step": 106496
+    },
+    {
+      "epoch": 4.032790601035095,
+      "grad_norm": 1.1449787616729736,
+      "learning_rate": 1.1937592081900948e-05,
+      "loss": 0.0133,
+      "step": 106752
+    },
+    {
+      "epoch": 4.0424615617090405,
+      "grad_norm": 2.6626508235931396,
+      "learning_rate": 1.1918325714933323e-05,
+      "loss": 0.0136,
+      "step": 107008
+    },
+    {
+      "epoch": 4.052132522382985,
+      "grad_norm": 1.2061920166015625,
+      "learning_rate": 1.1898983793585435e-05,
+      "loss": 0.0145,
+      "step": 107264
+    },
+    {
+      "epoch": 4.06180348305693,
+      "grad_norm": 0.4288395941257477,
+      "learning_rate": 1.1879641872237544e-05,
+      "loss": 0.0127,
+      "step": 107520
+    },
+    {
+      "epoch": 4.071474443730875,
+      "grad_norm": 3.4469873905181885,
+      "learning_rate": 1.1860299950889654e-05,
+      "loss": 0.0143,
+      "step": 107776
+    },
+    {
+      "epoch": 4.08114540440482,
+      "grad_norm": 3.4651808738708496,
+      "learning_rate": 1.1840958029541762e-05,
+      "loss": 0.0137,
+      "step": 108032
+    },
+    {
+      "epoch": 4.090816365078766,
+      "grad_norm": 4.205618381500244,
+      "learning_rate": 1.1821616108193874e-05,
+      "loss": 0.0136,
+      "step": 108288
+    },
+    {
+      "epoch": 4.10048732575271,
+      "grad_norm": 0.8337300419807434,
+      "learning_rate": 1.1802274186845984e-05,
+      "loss": 0.0126,
+      "step": 108544
+    },
+    {
+      "epoch": 4.110158286426656,
+      "grad_norm": 5.309538841247559,
+      "learning_rate": 1.1782932265498093e-05,
+      "loss": 0.0137,
+      "step": 108800
+    },
+    {
+      "epoch": 4.119829247100601,
+      "grad_norm": 0.6177698969841003,
+      "learning_rate": 1.1763590344150204e-05,
+      "loss": 0.0147,
+      "step": 109056
+    },
+    {
+      "epoch": 4.129500207774546,
+      "grad_norm": 2.2366254329681396,
+      "learning_rate": 1.1744248422802313e-05,
+      "loss": 0.0144,
+      "step": 109312
+    },
+    {
+      "epoch": 4.139171168448491,
+      "grad_norm": 1.5923917293548584,
+      "learning_rate": 1.1724906501454423e-05,
+      "loss": 0.0124,
+      "step": 109568
+    },
+    {
+      "epoch": 4.1488421291224356,
+      "grad_norm": 0.6197337508201599,
+      "learning_rate": 1.1705564580106531e-05,
+      "loss": 0.0128,
+      "step": 109824
+    },
+    {
+      "epoch": 4.158513089796381,
+      "grad_norm": 1.5513421297073364,
+      "learning_rate": 1.1686222658758643e-05,
+      "loss": 0.0133,
+      "step": 110080
+    },
+    {
+      "epoch": 4.168184050470326,
+      "grad_norm": 0.4733668863773346,
+      "learning_rate": 1.1666880737410753e-05,
+      "loss": 0.013,
+      "step": 110336
+    },
+    {
+      "epoch": 4.177855011144271,
+      "grad_norm": 0.9195311069488525,
+      "learning_rate": 1.1647538816062862e-05,
+      "loss": 0.0147,
+      "step": 110592
+    },
+    {
+      "epoch": 4.187525971818216,
+      "grad_norm": 0.4619844853878021,
+      "learning_rate": 1.1628272449095237e-05,
+      "loss": 0.0149,
+      "step": 110848
+    },
+    {
+      "epoch": 4.197196932492162,
+      "grad_norm": 0.4427216351032257,
+      "learning_rate": 1.1608930527747346e-05,
+      "loss": 0.0146,
+      "step": 111104
+    },
+    {
+      "epoch": 4.206867893166106,
+      "grad_norm": 2.1087565422058105,
+      "learning_rate": 1.1589588606399458e-05,
+      "loss": 0.0141,
+      "step": 111360
+    },
+    {
+      "epoch": 4.216538853840051,
+      "grad_norm": 1.2194585800170898,
+      "learning_rate": 1.1570246685051568e-05,
+      "loss": 0.0164,
+      "step": 111616
+    },
+    {
+      "epoch": 4.226209814513997,
+      "grad_norm": 1.4488071203231812,
+      "learning_rate": 1.1550904763703676e-05,
+      "loss": 0.0158,
+      "step": 111872
+    },
+    {
+      "epoch": 4.235880775187941,
+      "grad_norm": 5.222316265106201,
+      "learning_rate": 1.1531562842355786e-05,
+      "loss": 0.0144,
+      "step": 112128
+    },
+    {
+      "epoch": 4.245551735861887,
+      "grad_norm": 0.9832548499107361,
+      "learning_rate": 1.1512220921007897e-05,
+      "loss": 0.0148,
+      "step": 112384
+    },
+    {
+      "epoch": 4.2552226965358315,
+      "grad_norm": 3.2491071224212646,
+      "learning_rate": 1.1492878999660007e-05,
+      "loss": 0.0141,
+      "step": 112640
+    },
+    {
+      "epoch": 4.264893657209777,
+      "grad_norm": 0.40463200211524963,
+      "learning_rate": 1.1473537078312115e-05,
+      "loss": 0.0153,
+      "step": 112896
+    },
+    {
+      "epoch": 4.274564617883722,
+      "grad_norm": 0.7759467363357544,
+      "learning_rate": 1.1454195156964225e-05,
+      "loss": 0.0137,
+      "step": 113152
+    },
+    {
+      "epoch": 4.2842355785576665,
+      "grad_norm": 5.856504917144775,
+      "learning_rate": 1.1434853235616337e-05,
+      "loss": 0.0154,
+      "step": 113408
+    },
+    {
+      "epoch": 4.293906539231612,
+      "grad_norm": 1.3605588674545288,
+      "learning_rate": 1.1415586868648711e-05,
+      "loss": 0.0154,
+      "step": 113664
+    },
+    {
+      "epoch": 4.303577499905557,
+      "grad_norm": 0.4841889441013336,
+      "learning_rate": 1.1396244947300821e-05,
+      "loss": 0.0143,
+      "step": 113920
+    },
+    {
+      "epoch": 4.313248460579502,
+      "grad_norm": 2.290330171585083,
+      "learning_rate": 1.137690302595293e-05,
+      "loss": 0.0124,
+      "step": 114176
+    },
+    {
+      "epoch": 4.322919421253447,
+      "grad_norm": 0.6299089193344116,
+      "learning_rate": 1.135756110460504e-05,
+      "loss": 0.015,
+      "step": 114432
+    },
+    {
+      "epoch": 4.3325903819273925,
+      "grad_norm": 2.6966304779052734,
+      "learning_rate": 1.1338219183257152e-05,
+      "loss": 0.0147,
+      "step": 114688
+    },
+    {
+      "epoch": 4.342261342601337,
+      "grad_norm": 3.5934536457061768,
+      "learning_rate": 1.131887726190926e-05,
+      "loss": 0.0135,
+      "step": 114944
+    },
+    {
+      "epoch": 4.351932303275283,
+      "grad_norm": 2.391207218170166,
+      "learning_rate": 1.129953534056137e-05,
+      "loss": 0.0127,
+      "step": 115200
+    },
+    {
+      "epoch": 4.3616032639492275,
+      "grad_norm": 7.104966640472412,
+      "learning_rate": 1.1280193419213479e-05,
+      "loss": 0.0127,
+      "step": 115456
+    },
+    {
+      "epoch": 4.371274224623172,
+      "grad_norm": 4.91796875,
+      "learning_rate": 1.126085149786559e-05,
+      "loss": 0.0136,
+      "step": 115712
+    },
+    {
+      "epoch": 4.380945185297118,
+      "grad_norm": 0.9888034462928772,
+      "learning_rate": 1.1241509576517699e-05,
+      "loss": 0.0143,
+      "step": 115968
+    },
+    {
+      "epoch": 4.390616145971062,
+      "grad_norm": 5.1639018058776855,
+      "learning_rate": 1.1222167655169809e-05,
+      "loss": 0.0127,
+      "step": 116224
+    },
+    {
+      "epoch": 4.400287106645008,
+      "grad_norm": 8.415788650512695,
+      "learning_rate": 1.1202825733821917e-05,
+      "loss": 0.0145,
+      "step": 116480
+    },
+    {
+      "epoch": 4.409958067318953,
+      "grad_norm": 4.235672950744629,
+      "learning_rate": 1.118348381247403e-05,
+      "loss": 0.0154,
+      "step": 116736
+    },
+    {
+      "epoch": 4.419629027992898,
+      "grad_norm": 1.2345690727233887,
+      "learning_rate": 1.116414189112614e-05,
+      "loss": 0.0143,
+      "step": 116992
+    },
+    {
+      "epoch": 4.429299988666843,
+      "grad_norm": 8.792167663574219,
+      "learning_rate": 1.1144799969778248e-05,
+      "loss": 0.0162,
+      "step": 117248
+    },
+    {
+      "epoch": 4.438970949340788,
+      "grad_norm": 2.2384276390075684,
+      "learning_rate": 1.1125533602810623e-05,
+      "loss": 0.0141,
+      "step": 117504
+    },
+    {
+      "epoch": 4.448641910014733,
+      "grad_norm": 1.041791558265686,
+      "learning_rate": 1.1106191681462735e-05,
+      "loss": 0.0136,
+      "step": 117760
+    },
+    {
+      "epoch": 4.458312870688678,
+      "grad_norm": 4.7409515380859375,
+      "learning_rate": 1.1086849760114844e-05,
+      "loss": 0.0136,
+      "step": 118016
+    },
+    {
+      "epoch": 4.4679838313626234,
+      "grad_norm": 0.2378958761692047,
+      "learning_rate": 1.1067507838766954e-05,
+      "loss": 0.0147,
+      "step": 118272
+    },
+    {
+      "epoch": 4.477654792036568,
+      "grad_norm": 0.31944742798805237,
+      "learning_rate": 1.1048165917419062e-05,
+      "loss": 0.0135,
+      "step": 118528
+    },
+    {
+      "epoch": 4.487325752710514,
+      "grad_norm": 1.0051418542861938,
+      "learning_rate": 1.1028899550451438e-05,
+      "loss": 0.0137,
+      "step": 118784
+    },
+    {
+      "epoch": 4.496996713384458,
+      "grad_norm": 1.6819483041763306,
+      "learning_rate": 1.1009557629103548e-05,
+      "loss": 0.0156,
+      "step": 119040
+    },
+    {
+      "epoch": 4.506667674058404,
+      "grad_norm": 0.40426477789878845,
+      "learning_rate": 1.0990215707755658e-05,
+      "loss": 0.0146,
+      "step": 119296
+    },
+    {
+      "epoch": 4.516338634732349,
+      "grad_norm": 3.140392303466797,
+      "learning_rate": 1.0970873786407768e-05,
+      "loss": 0.0129,
+      "step": 119552
+    },
+    {
+      "epoch": 4.526009595406293,
+      "grad_norm": 4.579553604125977,
+      "learning_rate": 1.0951531865059877e-05,
+      "loss": 0.0124,
+      "step": 119808
+    },
+    {
+      "epoch": 4.535680556080239,
+      "grad_norm": 5.144607067108154,
+      "learning_rate": 1.0932189943711989e-05,
+      "loss": 0.0153,
+      "step": 120064
+    },
+    {
+      "epoch": 4.545351516754184,
+      "grad_norm": 0.48044607043266296,
+      "learning_rate": 1.0912848022364097e-05,
+      "loss": 0.013,
+      "step": 120320
+    },
+    {
+      "epoch": 4.555022477428129,
+      "grad_norm": 42.02862548828125,
+      "learning_rate": 1.0893506101016207e-05,
+      "loss": 0.0137,
+      "step": 120576
+    },
+    {
+      "epoch": 4.564693438102074,
+      "grad_norm": 6.357956886291504,
+      "learning_rate": 1.0874239734048581e-05,
+      "loss": 0.0154,
+      "step": 120832
+    },
+    {
+      "epoch": 4.574364398776019,
+      "grad_norm": 1.7824290990829468,
+      "learning_rate": 1.0854897812700693e-05,
+      "loss": 0.0127,
+      "step": 121088
+    },
+    {
+      "epoch": 4.584035359449964,
+      "grad_norm": 1.5723809003829956,
+      "learning_rate": 1.0835555891352803e-05,
+      "loss": 0.0129,
+      "step": 121344
+    },
+    {
+      "epoch": 4.593706320123909,
+      "grad_norm": 0.8262581825256348,
+      "learning_rate": 1.0816213970004911e-05,
+      "loss": 0.0151,
+      "step": 121600
+    },
+    {
+      "epoch": 4.603377280797854,
+      "grad_norm": 0.8032371401786804,
+      "learning_rate": 1.0796872048657022e-05,
+      "loss": 0.0158,
+      "step": 121856
+    },
+    {
+      "epoch": 4.613048241471799,
+      "grad_norm": 0.9602940082550049,
+      "learning_rate": 1.0777530127309133e-05,
+      "loss": 0.0142,
+      "step": 122112
+    },
+    {
+      "epoch": 4.622719202145745,
+      "grad_norm": 1.9872223138809204,
+      "learning_rate": 1.0758188205961242e-05,
+      "loss": 0.0134,
+      "step": 122368
+    },
+    {
+      "epoch": 4.632390162819689,
+      "grad_norm": 5.095240116119385,
+      "learning_rate": 1.0738846284613352e-05,
+      "loss": 0.014,
+      "step": 122624
+    },
+    {
+      "epoch": 4.642061123493635,
+      "grad_norm": 5.41306209564209,
+      "learning_rate": 1.071950436326546e-05,
+      "loss": 0.0124,
+      "step": 122880
+    },
+    {
+      "epoch": 4.6517320841675796,
+      "grad_norm": 10.439872741699219,
+      "learning_rate": 1.0700162441917572e-05,
+      "loss": 0.0148,
+      "step": 123136
+    },
+    {
+      "epoch": 4.661403044841524,
+      "grad_norm": 0.26815417408943176,
+      "learning_rate": 1.068082052056968e-05,
+      "loss": 0.0132,
+      "step": 123392
+    },
+    {
+      "epoch": 4.67107400551547,
+      "grad_norm": 0.6603275537490845,
+      "learning_rate": 1.0661554153602056e-05,
+      "loss": 0.0116,
+      "step": 123648
+    },
+    {
+      "epoch": 4.6807449661894145,
+      "grad_norm": 7.041431903839111,
+      "learning_rate": 1.0642212232254165e-05,
+      "loss": 0.0129,
+      "step": 123904
+    },
+    {
+      "epoch": 4.69041592686336,
+      "grad_norm": 0.7987198233604431,
+      "learning_rate": 1.0622870310906275e-05,
+      "loss": 0.0129,
+      "step": 124160
+    },
+    {
+      "epoch": 4.700086887537305,
+      "grad_norm": 0.14286652207374573,
+      "learning_rate": 1.0603528389558387e-05,
+      "loss": 0.0124,
+      "step": 124416
+    },
+    {
+      "epoch": 4.70975784821125,
+      "grad_norm": 0.9553490877151489,
+      "learning_rate": 1.0584186468210495e-05,
+      "loss": 0.0124,
+      "step": 124672
+    },
+    {
+      "epoch": 4.719428808885195,
+      "grad_norm": 0.6493328809738159,
+      "learning_rate": 1.0564844546862605e-05,
+      "loss": 0.012,
+      "step": 124928
+    },
+    {
+      "epoch": 4.729099769559141,
+      "grad_norm": 0.2133503556251526,
+      "learning_rate": 1.0545502625514714e-05,
+      "loss": 0.014,
+      "step": 125184
+    },
+    {
+      "epoch": 4.738770730233085,
+      "grad_norm": 2.6697592735290527,
+      "learning_rate": 1.0526160704166826e-05,
+      "loss": 0.013,
+      "step": 125440
+    },
+    {
+      "epoch": 4.748441690907031,
+      "grad_norm": 0.8658607602119446,
+      "learning_rate": 1.0506894337199201e-05,
+      "loss": 0.0131,
+      "step": 125696
+    },
+    {
+      "epoch": 4.7581126515809755,
+      "grad_norm": 1.9833451509475708,
+      "learning_rate": 1.048755241585131e-05,
+      "loss": 0.013,
+      "step": 125952
+    },
+    {
+      "epoch": 4.76778361225492,
+      "grad_norm": 0.19457457959651947,
+      "learning_rate": 1.046821049450342e-05,
+      "loss": 0.0142,
+      "step": 126208
+    },
+    {
+      "epoch": 4.777454572928866,
+      "grad_norm": 0.9841840863227844,
+      "learning_rate": 1.044886857315553e-05,
+      "loss": 0.0123,
+      "step": 126464
+    },
+    {
+      "epoch": 4.7871255336028105,
+      "grad_norm": 1.9175962209701538,
+      "learning_rate": 1.042952665180764e-05,
+      "loss": 0.0136,
+      "step": 126720
+    },
+    {
+      "epoch": 4.796796494276756,
+      "grad_norm": 1.7247178554534912,
+      "learning_rate": 1.0410184730459748e-05,
+      "loss": 0.0136,
+      "step": 126976
+    },
+    {
+      "epoch": 4.806467454950701,
+      "grad_norm": 2.0652236938476562,
+      "learning_rate": 1.0390842809111859e-05,
+      "loss": 0.0112,
+      "step": 127232
+    },
+    {
+      "epoch": 4.816138415624646,
+      "grad_norm": 1.1892759799957275,
+      "learning_rate": 1.037150088776397e-05,
+      "loss": 0.0125,
+      "step": 127488
+    },
+    {
+      "epoch": 4.825809376298591,
+      "grad_norm": 29.004505157470703,
+      "learning_rate": 1.0352158966416079e-05,
+      "loss": 0.0112,
+      "step": 127744
+    },
+    {
+      "epoch": 4.835480336972536,
+      "grad_norm": 0.5393902659416199,
+      "learning_rate": 1.0332817045068189e-05,
+      "loss": 0.0124,
+      "step": 128000
+    },
+    {
+      "epoch": 4.845151297646481,
+      "grad_norm": 0.9426546096801758,
+      "learning_rate": 1.0313475123720297e-05,
+      "loss": 0.011,
+      "step": 128256
+    },
+    {
+      "epoch": 4.854822258320426,
+      "grad_norm": 1.1209189891815186,
+      "learning_rate": 1.029413320237241e-05,
+      "loss": 0.0117,
+      "step": 128512
+    },
+    {
+      "epoch": 4.8644932189943715,
+      "grad_norm": 0.8620722889900208,
+      "learning_rate": 1.027479128102452e-05,
+      "loss": 0.0121,
+      "step": 128768
+    },
+    {
+      "epoch": 4.874164179668316,
+      "grad_norm": 0.14039096236228943,
+      "learning_rate": 1.0255524914056893e-05,
+      "loss": 0.0145,
+      "step": 129024
+    },
+    {
+      "epoch": 4.883835140342262,
+      "grad_norm": 0.5701342821121216,
+      "learning_rate": 1.0236182992709003e-05,
+      "loss": 0.0114,
+      "step": 129280
+    },
+    {
+      "epoch": 4.893506101016206,
+      "grad_norm": 0.802097499370575,
+      "learning_rate": 1.0216841071361112e-05,
+      "loss": 0.0124,
+      "step": 129536
+    },
+    {
+      "epoch": 4.903177061690151,
+      "grad_norm": 0.49824589490890503,
+      "learning_rate": 1.0197499150013224e-05,
+      "loss": 0.0133,
+      "step": 129792
+    },
+    {
+      "epoch": 4.912848022364097,
+      "grad_norm": 1.2195169925689697,
+      "learning_rate": 1.0178157228665332e-05,
+      "loss": 0.0134,
+      "step": 130048
+    },
+    {
+      "epoch": 4.922518983038041,
+      "grad_norm": 23.420486450195312,
+      "learning_rate": 1.0158815307317442e-05,
+      "loss": 0.0125,
+      "step": 130304
+    },
+    {
+      "epoch": 4.932189943711987,
+      "grad_norm": 0.8538005948066711,
+      "learning_rate": 1.013947338596955e-05,
+      "loss": 0.0124,
+      "step": 130560
+    },
+    {
+      "epoch": 4.941860904385932,
+      "grad_norm": 3.506213903427124,
+      "learning_rate": 1.0120131464621663e-05,
+      "loss": 0.0125,
+      "step": 130816
+    },
+    {
+      "epoch": 4.951531865059877,
+      "grad_norm": 0.5479403734207153,
+      "learning_rate": 1.0100789543273773e-05,
+      "loss": 0.0137,
+      "step": 131072
+    },
+    {
+      "epoch": 4.961202825733822,
+      "grad_norm": 0.24773092567920685,
+      "learning_rate": 1.0081447621925881e-05,
+      "loss": 0.011,
+      "step": 131328
+    },
+    {
+      "epoch": 4.970873786407767,
+      "grad_norm": 0.3392595946788788,
+      "learning_rate": 1.0062105700577991e-05,
+      "loss": 0.0113,
+      "step": 131584
+    },
+    {
+      "epoch": 4.980544747081712,
+      "grad_norm": 9.13214111328125,
+      "learning_rate": 1.0042763779230103e-05,
+      "loss": 0.0103,
+      "step": 131840
+    },
+    {
+      "epoch": 4.990215707755657,
+      "grad_norm": 0.6798635721206665,
+      "learning_rate": 1.0023421857882212e-05,
+      "loss": 0.0112,
+      "step": 132096
+    },
+    {
+      "epoch": 4.999886668429602,
+      "grad_norm": 3.8642024993896484,
+      "learning_rate": 1.0004155490914587e-05,
+      "loss": 0.0132,
+      "step": 132352
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1_B-DISEASE": 0.8076930929582066,
+      "eval_f1_B-MEDICATION": 0.9320128479657388,
+      "eval_f1_B-PROCEDURE": 0.8299265901797881,
+      "eval_f1_B-SYMPTOM": 0.802206734344465,
+      "eval_f1_I-DISEASE": 0.8443607103813086,
+      "eval_f1_I-MEDICATION": 0.9473012496676416,
+      "eval_f1_I-PROCEDURE": 0.8478063590704366,
+      "eval_f1_I-SYMPTOM": 0.8098297732572185,
+      "eval_f1_O": 0.9250181548686375,
+      "eval_f1_macro": 0.8606839458548268,
+      "eval_f1_micro": 0.8883442580707792,
+      "eval_loss": 0.4413922429084778,
+      "eval_precision_B-DISEASE": 0.83231643172733,
+      "eval_precision_B-MEDICATION": 0.9345142243692969,
+      "eval_precision_B-PROCEDURE": 0.8534490552391285,
+      "eval_precision_B-SYMPTOM": 0.8108590008041114,
+      "eval_precision_I-DISEASE": 0.8482866891605315,
+      "eval_precision_I-MEDICATION": 0.952467518579907,
+      "eval_precision_I-PROCEDURE": 0.8695185973099094,
+      "eval_precision_I-SYMPTOM": 0.8183803238035672,
+      "eval_precision_O": 0.9206075463451251,
+      "eval_precision_macro": 0.8711554874821008,
+      "eval_precision_micro": 0.8905099095411801,
+      "eval_rauc_macro": 0.9146732071749695,
+      "eval_rauc_micro": 0.9361508470284178,
+      "eval_recall_B-DISEASE": 0.784484810026176,
+      "eval_recall_B-MEDICATION": 0.9295248264815803,
+      "eval_recall_B-PROCEDURE": 0.8076659822039699,
+      "eval_recall_B-SYMPTOM": 0.7937371663244354,
+      "eval_recall_I-DISEASE": 0.8404709040504773,
+      "eval_recall_I-MEDICATION": 0.9421907230126408,
+      "eval_recall_I-PROCEDURE": 0.8271520314654786,
+      "eval_recall_I-SYMPTOM": 0.8014560498603052,
+      "eval_recall_O": 0.9294712290821007,
+      "eval_recall_macro": 0.8506837469452404,
+      "eval_recall_micro": 0.8861891144410676,
+      "eval_roc_auc_B-DISEASE": 0.8907720240571226,
+      "eval_roc_auc_B-MEDICATION": 0.964629291931633,
+      "eval_roc_auc_B-PROCEDURE": 0.9026383818040776,
+      "eval_roc_auc_B-SYMPTOM": 0.8948664885493695,
+      "eval_roc_auc_I-DISEASE": 0.9104202960745905,
+      "eval_roc_auc_I-MEDICATION": 0.9707688588965032,
+      "eval_roc_auc_I-PROCEDURE": 0.9075291450310622,
+      "eval_roc_auc_I-SYMPTOM": 0.8868675259287415,
+      "eval_roc_auc_O": 0.9035668523016245,
+      "eval_runtime": 61.1266,
+      "eval_samples_per_second": 177.877,
+      "eval_steps_per_second": 22.249,
+      "step": 132355
+    },
+    {
+      "epoch": 5.009557629103547,
+      "grad_norm": 0.4311939775943756,
+      "learning_rate": 9.984813569566696e-06,
+      "loss": 0.0071,
+      "step": 132608
+    },
+    {
+      "epoch": 5.019228589777493,
+      "grad_norm": 1.0362738370895386,
+      "learning_rate": 9.965471648218806e-06,
+      "loss": 0.0086,
+      "step": 132864
+    },
+    {
+      "epoch": 5.028899550451437,
+      "grad_norm": 1.9174968004226685,
+      "learning_rate": 9.946129726870916e-06,
+      "loss": 0.0069,
+      "step": 133120
+    },
+    {
+      "epoch": 5.038570511125383,
+      "grad_norm": 0.2945270240306854,
+      "learning_rate": 9.926787805523026e-06,
+      "loss": 0.0086,
+      "step": 133376
+    },
+    {
+      "epoch": 5.048241471799328,
+      "grad_norm": 0.024452047422528267,
+      "learning_rate": 9.907445884175136e-06,
+      "loss": 0.0068,
+      "step": 133632
+    },
+    {
+      "epoch": 5.057912432473272,
+      "grad_norm": 0.9929279088973999,
+      "learning_rate": 9.888179517207512e-06,
+      "loss": 0.0077,
+      "step": 133888
+    },
+    {
+      "epoch": 5.067583393147218,
+      "grad_norm": 3.7908236980438232,
+      "learning_rate": 9.86883759585962e-06,
+      "loss": 0.0088,
+      "step": 134144
+    },
+    {
+      "epoch": 5.0772543538211625,
+      "grad_norm": 1.9607737064361572,
+      "learning_rate": 9.84949567451173e-06,
+      "loss": 0.0077,
+      "step": 134400
+    },
+    {
+      "epoch": 5.086925314495108,
+      "grad_norm": 4.287957668304443,
+      "learning_rate": 9.83015375316384e-06,
+      "loss": 0.0091,
+      "step": 134656
+    },
+    {
+      "epoch": 5.096596275169053,
+      "grad_norm": 0.9552005529403687,
+      "learning_rate": 9.81081183181595e-06,
+      "loss": 0.0081,
+      "step": 134912
+    },
+    {
+      "epoch": 5.106267235842998,
+      "grad_norm": 3.186450481414795,
+      "learning_rate": 9.79146991046806e-06,
+      "loss": 0.0074,
+      "step": 135168
+    },
+    {
+      "epoch": 5.115938196516943,
+      "grad_norm": 0.3131207525730133,
+      "learning_rate": 9.772127989120171e-06,
+      "loss": 0.0076,
+      "step": 135424
+    },
+    {
+      "epoch": 5.125609157190888,
+      "grad_norm": 0.2811489701271057,
+      "learning_rate": 9.75278606777228e-06,
+      "loss": 0.009,
+      "step": 135680
+    },
+    {
+      "epoch": 5.135280117864833,
+      "grad_norm": 0.3740166127681732,
+      "learning_rate": 9.73344414642439e-06,
+      "loss": 0.0078,
+      "step": 135936
+    },
+    {
+      "epoch": 5.144951078538778,
+      "grad_norm": 1.3230619430541992,
+      "learning_rate": 9.7141022250765e-06,
+      "loss": 0.008,
+      "step": 136192
+    },
+    {
+      "epoch": 5.1546220392127235,
+      "grad_norm": 0.6120270490646362,
+      "learning_rate": 9.694835858108874e-06,
+      "loss": 0.0073,
+      "step": 136448
+    },
+    {
+      "epoch": 5.164292999886668,
+      "grad_norm": 4.456196308135986,
+      "learning_rate": 9.675493936760985e-06,
+      "loss": 0.01,
+      "step": 136704
+    },
+    {
+      "epoch": 5.173963960560614,
+      "grad_norm": 0.2429385632276535,
+      "learning_rate": 9.656152015413094e-06,
+      "loss": 0.0088,
+      "step": 136960
+    },
+    {
+      "epoch": 5.1836349212345585,
+      "grad_norm": 1.2598743438720703,
+      "learning_rate": 9.636810094065204e-06,
+      "loss": 0.0103,
+      "step": 137216
+    },
+    {
+      "epoch": 5.193305881908504,
+      "grad_norm": 1.915220022201538,
+      "learning_rate": 9.617468172717314e-06,
+      "loss": 0.0098,
+      "step": 137472
+    },
+    {
+      "epoch": 5.202976842582449,
+      "grad_norm": 0.8882638812065125,
+      "learning_rate": 9.598126251369424e-06,
+      "loss": 0.0094,
+      "step": 137728
+    },
+    {
+      "epoch": 5.212647803256393,
+      "grad_norm": 0.10290802270174026,
+      "learning_rate": 9.578784330021533e-06,
+      "loss": 0.0085,
+      "step": 137984
+    },
+    {
+      "epoch": 5.222318763930339,
+      "grad_norm": 3.6905243396759033,
+      "learning_rate": 9.559442408673644e-06,
+      "loss": 0.0105,
+      "step": 138240
+    },
+    {
+      "epoch": 5.231989724604284,
+      "grad_norm": 0.27331113815307617,
+      "learning_rate": 9.540100487325753e-06,
+      "loss": 0.0096,
+      "step": 138496
+    },
+    {
+      "epoch": 5.241660685278229,
+      "grad_norm": 0.3453868627548218,
+      "learning_rate": 9.520758565977863e-06,
+      "loss": 0.0093,
+      "step": 138752
+    },
+    {
+      "epoch": 5.251331645952174,
+      "grad_norm": 6.686705589294434,
+      "learning_rate": 9.501416644629973e-06,
+      "loss": 0.0103,
+      "step": 139008
+    },
+    {
+      "epoch": 5.2610026066261195,
+      "grad_norm": 6.24531364440918,
+      "learning_rate": 9.482074723282083e-06,
+      "loss": 0.0089,
+      "step": 139264
+    },
+    {
+      "epoch": 5.270673567300064,
+      "grad_norm": 5.73491907119751,
+      "learning_rate": 9.462732801934192e-06,
+      "loss": 0.0099,
+      "step": 139520
+    },
+    {
+      "epoch": 5.280344527974009,
+      "grad_norm": 3.492011308670044,
+      "learning_rate": 9.443390880586304e-06,
+      "loss": 0.0078,
+      "step": 139776
+    },
+    {
+      "epoch": 5.2900154886479545,
+      "grad_norm": 0.5170190930366516,
+      "learning_rate": 9.424048959238412e-06,
+      "loss": 0.0078,
+      "step": 140032
+    },
+    {
+      "epoch": 5.299686449321899,
+      "grad_norm": 0.07176166027784348,
+      "learning_rate": 9.404707037890522e-06,
+      "loss": 0.008,
+      "step": 140288
+    },
+    {
+      "epoch": 5.309357409995845,
+      "grad_norm": 1.4914041757583618,
+      "learning_rate": 9.385440670922898e-06,
+      "loss": 0.009,
+      "step": 140544
+    },
+    {
+      "epoch": 5.319028370669789,
+      "grad_norm": 2.964844226837158,
+      "learning_rate": 9.366098749575008e-06,
+      "loss": 0.0085,
+      "step": 140800
+    },
+    {
+      "epoch": 5.328699331343735,
+      "grad_norm": 0.2556954324245453,
+      "learning_rate": 9.346756828227116e-06,
+      "loss": 0.0091,
+      "step": 141056
+    },
+    {
+      "epoch": 5.33837029201768,
+      "grad_norm": 3.6987621784210205,
+      "learning_rate": 9.327414906879228e-06,
+      "loss": 0.0079,
+      "step": 141312
+    },
+    {
+      "epoch": 5.348041252691624,
+      "grad_norm": 4.68747615814209,
+      "learning_rate": 9.308072985531337e-06,
+      "loss": 0.0087,
+      "step": 141568
+    },
+    {
+      "epoch": 5.35771221336557,
+      "grad_norm": 0.4118718206882477,
+      "learning_rate": 9.288731064183447e-06,
+      "loss": 0.0096,
+      "step": 141824
+    },
+    {
+      "epoch": 5.367383174039515,
+      "grad_norm": 0.3415529429912567,
+      "learning_rate": 9.269389142835557e-06,
+      "loss": 0.0088,
+      "step": 142080
+    },
+    {
+      "epoch": 5.37705413471346,
+      "grad_norm": 0.10233204811811447,
+      "learning_rate": 9.250047221487667e-06,
+      "loss": 0.0082,
+      "step": 142336
+    },
+    {
+      "epoch": 5.386725095387405,
+      "grad_norm": 0.2785378396511078,
+      "learning_rate": 9.230705300139775e-06,
+      "loss": 0.0107,
+      "step": 142592
+    },
+    {
+      "epoch": 5.39639605606135,
+      "grad_norm": 1.3955039978027344,
+      "learning_rate": 9.211438933172151e-06,
+      "loss": 0.0081,
+      "step": 142848
+    },
+    {
+      "epoch": 5.406067016735295,
+      "grad_norm": 6.009440898895264,
+      "learning_rate": 9.192097011824261e-06,
+      "loss": 0.0078,
+      "step": 143104
+    },
+    {
+      "epoch": 5.415737977409241,
+      "grad_norm": 0.10272625833749771,
+      "learning_rate": 9.172755090476371e-06,
+      "loss": 0.0097,
+      "step": 143360
+    },
+    {
+      "epoch": 5.425408938083185,
+      "grad_norm": 5.104133605957031,
+      "learning_rate": 9.153413169128481e-06,
+      "loss": 0.0079,
+      "step": 143616
+    },
+    {
+      "epoch": 5.43507989875713,
+      "grad_norm": 0.218174010515213,
+      "learning_rate": 9.13407124778059e-06,
+      "loss": 0.0088,
+      "step": 143872
+    },
+    {
+      "epoch": 5.444750859431076,
+      "grad_norm": 4.509812355041504,
+      "learning_rate": 9.1147293264327e-06,
+      "loss": 0.0088,
+      "step": 144128
+    },
+    {
+      "epoch": 5.45442182010502,
+      "grad_norm": 0.9697214961051941,
+      "learning_rate": 9.09538740508481e-06,
+      "loss": 0.0088,
+      "step": 144384
+    },
+    {
+      "epoch": 5.464092780778966,
+      "grad_norm": 1.000596046447754,
+      "learning_rate": 9.07604548373692e-06,
+      "loss": 0.0089,
+      "step": 144640
+    },
+    {
+      "epoch": 5.473763741452911,
+      "grad_norm": 0.22552327811717987,
+      "learning_rate": 9.05670356238903e-06,
+      "loss": 0.009,
+      "step": 144896
+    },
+    {
+      "epoch": 5.483434702126856,
+      "grad_norm": 0.7269870042800903,
+      "learning_rate": 9.03736164104114e-06,
+      "loss": 0.0097,
+      "step": 145152
+    },
+    {
+      "epoch": 5.493105662800801,
+      "grad_norm": 0.3465439975261688,
+      "learning_rate": 9.018095274073515e-06,
+      "loss": 0.0102,
+      "step": 145408
+    },
+    {
+      "epoch": 5.502776623474746,
+      "grad_norm": 0.6706210970878601,
+      "learning_rate": 8.998753352725625e-06,
+      "loss": 0.009,
+      "step": 145664
+    },
+    {
+      "epoch": 5.512447584148691,
+      "grad_norm": 36.635414123535156,
+      "learning_rate": 8.979411431377735e-06,
+      "loss": 0.0084,
+      "step": 145920
+    },
+    {
+      "epoch": 5.522118544822636,
+      "grad_norm": 1.6504905223846436,
+      "learning_rate": 8.960069510029845e-06,
+      "loss": 0.008,
+      "step": 146176
+    },
+    {
+      "epoch": 5.531789505496581,
+      "grad_norm": 0.5836831331253052,
+      "learning_rate": 8.940727588681955e-06,
+      "loss": 0.0087,
+      "step": 146432
+    },
+    {
+      "epoch": 5.541460466170526,
+      "grad_norm": 0.684615433216095,
+      "learning_rate": 8.921385667334065e-06,
+      "loss": 0.0076,
+      "step": 146688
+    },
+    {
+      "epoch": 5.551131426844472,
+      "grad_norm": 2.892833709716797,
+      "learning_rate": 8.902043745986174e-06,
+      "loss": 0.0085,
+      "step": 146944
+    },
+    {
+      "epoch": 5.560802387518416,
+      "grad_norm": 20.16980743408203,
+      "learning_rate": 8.882701824638284e-06,
+      "loss": 0.0084,
+      "step": 147200
+    },
+    {
+      "epoch": 5.570473348192362,
+      "grad_norm": 3.590690851211548,
+      "learning_rate": 8.86343545767066e-06,
+      "loss": 0.008,
+      "step": 147456
+    },
+    {
+      "epoch": 5.5801443088663065,
+      "grad_norm": 0.8185898661613464,
+      "learning_rate": 8.844093536322768e-06,
+      "loss": 0.0074,
+      "step": 147712
+    },
+    {
+      "epoch": 5.589815269540251,
+      "grad_norm": 0.3533550202846527,
+      "learning_rate": 8.82475161497488e-06,
+      "loss": 0.0079,
+      "step": 147968
+    },
+    {
+      "epoch": 5.599486230214197,
+      "grad_norm": 1.9578065872192383,
+      "learning_rate": 8.805409693626988e-06,
+      "loss": 0.0077,
+      "step": 148224
+    },
+    {
+      "epoch": 5.6091571908881415,
+      "grad_norm": 0.17547504603862762,
+      "learning_rate": 8.786067772279098e-06,
+      "loss": 0.0086,
+      "step": 148480
+    },
+    {
+      "epoch": 5.618828151562087,
+      "grad_norm": 1.6071051359176636,
+      "learning_rate": 8.766725850931208e-06,
+      "loss": 0.0085,
+      "step": 148736
+    },
+    {
+      "epoch": 5.628499112236032,
+      "grad_norm": 0.8156256079673767,
+      "learning_rate": 8.747383929583318e-06,
+      "loss": 0.007,
+      "step": 148992
+    },
+    {
+      "epoch": 5.638170072909977,
+      "grad_norm": 11.689854621887207,
+      "learning_rate": 8.728042008235429e-06,
+      "loss": 0.0096,
+      "step": 149248
+    },
+    {
+      "epoch": 5.647841033583922,
+      "grad_norm": 0.9380402565002441,
+      "learning_rate": 8.708700086887539e-06,
+      "loss": 0.0082,
+      "step": 149504
+    },
+    {
+      "epoch": 5.657511994257867,
+      "grad_norm": 0.5615717172622681,
+      "learning_rate": 8.689433719919913e-06,
+      "loss": 0.0079,
+      "step": 149760
+    },
+    {
+      "epoch": 5.667182954931812,
+      "grad_norm": 1.7645057439804077,
+      "learning_rate": 8.670091798572023e-06,
+      "loss": 0.0103,
+      "step": 150016
+    },
+    {
+      "epoch": 5.676853915605757,
+      "grad_norm": 4.009266376495361,
+      "learning_rate": 8.650749877224133e-06,
+      "loss": 0.0089,
+      "step": 150272
+    },
+    {
+      "epoch": 5.6865248762797025,
+      "grad_norm": 0.6033828854560852,
+      "learning_rate": 8.631407955876243e-06,
+      "loss": 0.0074,
+      "step": 150528
+    },
+    {
+      "epoch": 5.696195836953647,
+      "grad_norm": 5.695953369140625,
+      "learning_rate": 8.612066034528353e-06,
+      "loss": 0.0087,
+      "step": 150784
+    },
+    {
+      "epoch": 5.705866797627593,
+      "grad_norm": 2.7361793518066406,
+      "learning_rate": 8.592724113180463e-06,
+      "loss": 0.0083,
+      "step": 151040
+    },
+    {
+      "epoch": 5.715537758301537,
+      "grad_norm": 0.26094111800193787,
+      "learning_rate": 8.573382191832572e-06,
+      "loss": 0.0083,
+      "step": 151296
+    },
+    {
+      "epoch": 5.725208718975482,
+      "grad_norm": 0.7956266403198242,
+      "learning_rate": 8.554040270484682e-06,
+      "loss": 0.0098,
+      "step": 151552
+    },
+    {
+      "epoch": 5.734879679649428,
+      "grad_norm": 0.28114378452301025,
+      "learning_rate": 8.534698349136792e-06,
+      "loss": 0.0093,
+      "step": 151808
+    },
+    {
+      "epoch": 5.744550640323372,
+      "grad_norm": 2.0160458087921143,
+      "learning_rate": 8.515356427788902e-06,
+      "loss": 0.0099,
+      "step": 152064
+    },
+    {
+      "epoch": 5.754221600997318,
+      "grad_norm": 1.1137139797210693,
+      "learning_rate": 8.496014506441012e-06,
+      "loss": 0.0082,
+      "step": 152320
+    },
+    {
+      "epoch": 5.763892561671263,
+      "grad_norm": 3.6147210597991943,
+      "learning_rate": 8.476672585093122e-06,
+      "loss": 0.0083,
+      "step": 152576
+    },
+    {
+      "epoch": 5.773563522345208,
+      "grad_norm": 4.814803123474121,
+      "learning_rate": 8.457330663745231e-06,
+      "loss": 0.007,
+      "step": 152832
+    },
+    {
+      "epoch": 5.783234483019153,
+      "grad_norm": 0.7147836089134216,
+      "learning_rate": 8.437988742397341e-06,
+      "loss": 0.0088,
+      "step": 153088
+    },
+    {
+      "epoch": 5.7929054436930985,
+      "grad_norm": 1.4864364862442017,
+      "learning_rate": 8.418646821049451e-06,
+      "loss": 0.0063,
+      "step": 153344
+    },
+    {
+      "epoch": 5.802576404367043,
+      "grad_norm": 0.7108877301216125,
+      "learning_rate": 8.399304899701561e-06,
+      "loss": 0.0076,
+      "step": 153600
+    },
+    {
+      "epoch": 5.812247365040989,
+      "grad_norm": 2.6084437370300293,
+      "learning_rate": 8.379962978353671e-06,
+      "loss": 0.0086,
+      "step": 153856
+    },
+    {
+      "epoch": 5.821918325714933,
+      "grad_norm": 0.09771878272294998,
+      "learning_rate": 8.360696611386045e-06,
+      "loss": 0.009,
+      "step": 154112
+    },
+    {
+      "epoch": 5.831589286388878,
+      "grad_norm": 0.6635453104972839,
+      "learning_rate": 8.341354690038155e-06,
+      "loss": 0.0071,
+      "step": 154368
+    },
+    {
+      "epoch": 5.841260247062824,
+      "grad_norm": 1.141113042831421,
+      "learning_rate": 8.322088323070531e-06,
+      "loss": 0.0076,
+      "step": 154624
+    },
+    {
+      "epoch": 5.850931207736768,
+      "grad_norm": 0.8303898572921753,
+      "learning_rate": 8.30274640172264e-06,
+      "loss": 0.0096,
+      "step": 154880
+    },
+    {
+      "epoch": 5.860602168410714,
+      "grad_norm": 0.5006212592124939,
+      "learning_rate": 8.28340448037475e-06,
+      "loss": 0.0076,
+      "step": 155136
+    },
+    {
+      "epoch": 5.870273129084659,
+      "grad_norm": 1.09455406665802,
+      "learning_rate": 8.26406255902686e-06,
+      "loss": 0.007,
+      "step": 155392
+    },
+    {
+      "epoch": 5.879944089758604,
+      "grad_norm": 0.5454290509223938,
+      "learning_rate": 8.24472063767897e-06,
+      "loss": 0.0081,
+      "step": 155648
+    },
+    {
+      "epoch": 5.889615050432549,
+      "grad_norm": 14.345696449279785,
+      "learning_rate": 8.22537871633108e-06,
+      "loss": 0.0097,
+      "step": 155904
+    },
+    {
+      "epoch": 5.8992860111064935,
+      "grad_norm": 2.6186184883117676,
+      "learning_rate": 8.20603679498319e-06,
+      "loss": 0.0089,
+      "step": 156160
+    },
+    {
+      "epoch": 5.908956971780439,
+      "grad_norm": 1.894392967224121,
+      "learning_rate": 8.186694873635299e-06,
+      "loss": 0.0078,
+      "step": 156416
+    },
+    {
+      "epoch": 5.918627932454384,
+      "grad_norm": 0.8504657745361328,
+      "learning_rate": 8.167352952287409e-06,
+      "loss": 0.0089,
+      "step": 156672
+    },
+    {
+      "epoch": 5.928298893128329,
+      "grad_norm": 1.3975979089736938,
+      "learning_rate": 8.148011030939519e-06,
+      "loss": 0.0076,
+      "step": 156928
+    },
+    {
+      "epoch": 5.937969853802274,
+      "grad_norm": 0.12042956799268723,
+      "learning_rate": 8.128669109591629e-06,
+      "loss": 0.0073,
+      "step": 157184
+    },
+    {
+      "epoch": 5.94764081447622,
+      "grad_norm": 0.7101040482521057,
+      "learning_rate": 8.10932718824374e-06,
+      "loss": 0.0084,
+      "step": 157440
+    },
+    {
+      "epoch": 5.957311775150164,
+      "grad_norm": 0.049012139439582825,
+      "learning_rate": 8.08998526689585e-06,
+      "loss": 0.0078,
+      "step": 157696
+    },
+    {
+      "epoch": 5.966982735824109,
+      "grad_norm": 3.6799347400665283,
+      "learning_rate": 8.070643345547958e-06,
+      "loss": 0.0069,
+      "step": 157952
+    },
+    {
+      "epoch": 5.976653696498055,
+      "grad_norm": 5.190356731414795,
+      "learning_rate": 8.051301424200068e-06,
+      "loss": 0.0083,
+      "step": 158208
+    },
+    {
+      "epoch": 5.986324657171999,
+      "grad_norm": 0.405319482088089,
+      "learning_rate": 8.031959502852178e-06,
+      "loss": 0.0076,
+      "step": 158464
+    },
+    {
+      "epoch": 5.995995617845945,
+      "grad_norm": 7.220467567443848,
+      "learning_rate": 8.012617581504288e-06,
+      "loss": 0.0076,
+      "step": 158720
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1_B-DISEASE": 0.8137172062733137,
+      "eval_f1_B-MEDICATION": 0.9366835994194485,
+      "eval_f1_B-PROCEDURE": 0.8338765045843654,
+      "eval_f1_B-SYMPTOM": 0.802911592516026,
+      "eval_f1_I-DISEASE": 0.8454658855143709,
+      "eval_f1_I-MEDICATION": 0.9528172976448839,
+      "eval_f1_I-PROCEDURE": 0.8516517120332436,
+      "eval_f1_I-SYMPTOM": 0.8137056001030496,
+      "eval_f1_O": 0.9249487903086626,
+      "eval_f1_macro": 0.8639753542663738,
+      "eval_f1_micro": 0.8895774266140277,
+      "eval_loss": 0.4695410430431366,
+      "eval_precision_B-DISEASE": 0.846968981938307,
+      "eval_precision_B-MEDICATION": 0.9552266419981499,
+      "eval_precision_B-PROCEDURE": 0.8472406181015453,
+      "eval_precision_B-SYMPTOM": 0.8153335920685884,
+      "eval_precision_I-DISEASE": 0.8649620429239743,
+      "eval_precision_I-MEDICATION": 0.9655191138140747,
+      "eval_precision_I-PROCEDURE": 0.8750075317409081,
+      "eval_precision_I-SYMPTOM": 0.8128417937335135,
+      "eval_precision_O": 0.9181102771519474,
+      "eval_precision_macro": 0.8779122881634454,
+      "eval_precision_micro": 0.8910716505650682,
+      "eval_rauc_macro": 0.9145927366341076,
+      "eval_rauc_micro": 0.9371255777552341,
+      "eval_recall_B-DISEASE": 0.7829777107955898,
+      "eval_recall_B-MEDICATION": 0.9188467698878804,
+      "eval_recall_B-PROCEDURE": 0.820927446954141,
+      "eval_recall_B-SYMPTOM": 0.7908624229979466,
+      "eval_recall_I-DISEASE": 0.8268292376974121,
+      "eval_recall_I-MEDICATION": 0.9404453377056117,
+      "eval_recall_I-PROCEDURE": 0.8295103103299143,
+      "eval_recall_I-SYMPTOM": 0.8145712443584784,
+      "eval_recall_O": 0.9318899408213067,
+      "eval_recall_macro": 0.8507622690609201,
+      "eval_recall_micro": 0.8880882055547169,
+      "eval_roc_auc_B-DISEASE": 0.8901727076261692,
+      "eval_roc_auc_B-MEDICATION": 0.9593353648433499,
+      "eval_roc_auc_B-PROCEDURE": 0.9091887857316173,
+      "eval_roc_auc_B-SYMPTOM": 0.8934942497238074,
+      "eval_roc_auc_I-DISEASE": 0.9049857727909453,
+      "eval_roc_auc_I-MEDICATION": 0.9699894527029364,
+      "eval_roc_auc_I-PROCEDURE": 0.9089825820626593,
+      "eval_roc_auc_I-SYMPTOM": 0.8926697963231113,
+      "eval_roc_auc_O": 0.9025159179023717,
+      "eval_runtime": 60.8686,
+      "eval_samples_per_second": 178.631,
+      "eval_steps_per_second": 22.343,
+      "step": 158826
+    },
+    {
+      "epoch": 6.0056665785198895,
+      "grad_norm": 2.5522048473358154,
+      "learning_rate": 7.993275660156398e-06,
+      "loss": 0.0067,
+      "step": 158976
+    },
+    {
+      "epoch": 6.015337539193835,
+      "grad_norm": 0.1445242464542389,
+      "learning_rate": 7.973933738808508e-06,
+      "loss": 0.0056,
+      "step": 159232
+    },
+    {
+      "epoch": 6.02500849986778,
+      "grad_norm": 0.8560025095939636,
+      "learning_rate": 7.954591817460619e-06,
+      "loss": 0.004,
+      "step": 159488
+    },
+    {
+      "epoch": 6.034679460541725,
+      "grad_norm": 0.5683347582817078,
+      "learning_rate": 7.935249896112727e-06,
+      "loss": 0.0048,
+      "step": 159744
+    },
+    {
+      "epoch": 6.04435042121567,
+      "grad_norm": 0.10347987711429596,
+      "learning_rate": 7.916059083525368e-06,
+      "loss": 0.0048,
+      "step": 160000
+    },
+    {
+      "epoch": 6.054021381889615,
+      "grad_norm": 0.765963613986969,
+      "learning_rate": 7.896717162177477e-06,
+      "loss": 0.0044,
+      "step": 160256
+    },
+    {
+      "epoch": 6.06369234256356,
+      "grad_norm": 0.23950816690921783,
+      "learning_rate": 7.877375240829588e-06,
+      "loss": 0.0039,
+      "step": 160512
+    },
+    {
+      "epoch": 6.073363303237505,
+      "grad_norm": 1.28322434425354,
+      "learning_rate": 7.858033319481697e-06,
+      "loss": 0.0058,
+      "step": 160768
+    },
+    {
+      "epoch": 6.0830342639114505,
+      "grad_norm": 0.0957738608121872,
+      "learning_rate": 7.838691398133807e-06,
+      "loss": 0.0051,
+      "step": 161024
+    },
+    {
+      "epoch": 6.092705224585395,
+      "grad_norm": 0.09481767565011978,
+      "learning_rate": 7.819349476785917e-06,
+      "loss": 0.006,
+      "step": 161280
+    },
+    {
+      "epoch": 6.102376185259341,
+      "grad_norm": 1.084963321685791,
+      "learning_rate": 7.800007555438027e-06,
+      "loss": 0.0052,
+      "step": 161536
+    },
+    {
+      "epoch": 6.1120471459332855,
+      "grad_norm": 0.19962504506111145,
+      "learning_rate": 7.780665634090136e-06,
+      "loss": 0.0063,
+      "step": 161792
+    },
+    {
+      "epoch": 6.12171810660723,
+      "grad_norm": 0.44316428899765015,
+      "learning_rate": 7.761323712742248e-06,
+      "loss": 0.0055,
+      "step": 162048
+    },
+    {
+      "epoch": 6.131389067281176,
+      "grad_norm": 0.096375972032547,
+      "learning_rate": 7.741981791394356e-06,
+      "loss": 0.0046,
+      "step": 162304
+    },
+    {
+      "epoch": 6.14106002795512,
+      "grad_norm": 0.06923657655715942,
+      "learning_rate": 7.722639870046466e-06,
+      "loss": 0.0065,
+      "step": 162560
+    },
+    {
+      "epoch": 6.150730988629066,
+      "grad_norm": 0.05641581490635872,
+      "learning_rate": 7.703373503078842e-06,
+      "loss": 0.0053,
+      "step": 162816
+    },
+    {
+      "epoch": 6.160401949303011,
+      "grad_norm": 0.10804527252912521,
+      "learning_rate": 7.684031581730952e-06,
+      "loss": 0.0049,
+      "step": 163072
+    },
+    {
+      "epoch": 6.170072909976956,
+      "grad_norm": 0.3508886694908142,
+      "learning_rate": 7.664689660383062e-06,
+      "loss": 0.0057,
+      "step": 163328
+    },
+    {
+      "epoch": 6.179743870650901,
+      "grad_norm": 0.19692179560661316,
+      "learning_rate": 7.645347739035172e-06,
+      "loss": 0.0051,
+      "step": 163584
+    },
+    {
+      "epoch": 6.1894148313248465,
+      "grad_norm": 7.462360382080078,
+      "learning_rate": 7.6260058176872806e-06,
+      "loss": 0.0052,
+      "step": 163840
+    },
+    {
+      "epoch": 6.199085791998791,
+      "grad_norm": 0.0778375118970871,
+      "learning_rate": 7.6066638963393915e-06,
+      "loss": 0.0057,
+      "step": 164096
+    },
+    {
+      "epoch": 6.208756752672736,
+      "grad_norm": 3.7269153594970703,
+      "learning_rate": 7.587321974991501e-06,
+      "loss": 0.0066,
+      "step": 164352
+    },
+    {
+      "epoch": 6.218427713346681,
+      "grad_norm": 0.3314465582370758,
+      "learning_rate": 7.567980053643611e-06,
+      "loss": 0.0066,
+      "step": 164608
+    },
+    {
+      "epoch": 6.228098674020626,
+      "grad_norm": 0.4546041786670685,
+      "learning_rate": 7.548713686675986e-06,
+      "loss": 0.0054,
+      "step": 164864
+    },
+    {
+      "epoch": 6.237769634694572,
+      "grad_norm": 0.1140669584274292,
+      "learning_rate": 7.529371765328095e-06,
+      "loss": 0.0053,
+      "step": 165120
+    },
+    {
+      "epoch": 6.247440595368516,
+      "grad_norm": 0.03010609745979309,
+      "learning_rate": 7.510029843980205e-06,
+      "loss": 0.0045,
+      "step": 165376
+    },
+    {
+      "epoch": 6.257111556042462,
+      "grad_norm": 0.015513704158365726,
+      "learning_rate": 7.4906879226323145e-06,
+      "loss": 0.0056,
+      "step": 165632
+    },
+    {
+      "epoch": 6.266782516716407,
+      "grad_norm": 0.09134875982999802,
+      "learning_rate": 7.4713460012844255e-06,
+      "loss": 0.0066,
+      "step": 165888
+    },
+    {
+      "epoch": 6.276453477390351,
+      "grad_norm": 0.016765909269452095,
+      "learning_rate": 7.452004079936535e-06,
+      "loss": 0.0053,
+      "step": 166144
+    },
+    {
+      "epoch": 6.286124438064297,
+      "grad_norm": 0.5640433430671692,
+      "learning_rate": 7.432662158588645e-06,
+      "loss": 0.0049,
+      "step": 166400
+    },
+    {
+      "epoch": 6.295795398738242,
+      "grad_norm": 0.21902374923229218,
+      "learning_rate": 7.413320237240754e-06,
+      "loss": 0.0064,
+      "step": 166656
+    },
+    {
+      "epoch": 6.305466359412187,
+      "grad_norm": 5.544469833374023,
+      "learning_rate": 7.393978315892864e-06,
+      "loss": 0.0052,
+      "step": 166912
+    },
+    {
+      "epoch": 6.315137320086132,
+      "grad_norm": 0.7227392792701721,
+      "learning_rate": 7.3746363945449736e-06,
+      "loss": 0.0054,
+      "step": 167168
+    },
+    {
+      "epoch": 6.324808280760077,
+      "grad_norm": 5.256189346313477,
+      "learning_rate": 7.3552944731970845e-06,
+      "loss": 0.0057,
+      "step": 167424
+    },
+    {
+      "epoch": 6.334479241434022,
+      "grad_norm": 4.659141540527344,
+      "learning_rate": 7.335952551849194e-06,
+      "loss": 0.0048,
+      "step": 167680
+    },
+    {
+      "epoch": 6.344150202107967,
+      "grad_norm": 0.9072468876838684,
+      "learning_rate": 7.316610630501304e-06,
+      "loss": 0.0046,
+      "step": 167936
+    },
+    {
+      "epoch": 6.353821162781912,
+      "grad_norm": 0.14295679330825806,
+      "learning_rate": 7.297268709153413e-06,
+      "loss": 0.0052,
+      "step": 168192
+    },
+    {
+      "epoch": 6.363492123455857,
+      "grad_norm": 0.07267609983682632,
+      "learning_rate": 7.277926787805523e-06,
+      "loss": 0.0044,
+      "step": 168448
+    },
+    {
+      "epoch": 6.373163084129803,
+      "grad_norm": 0.5884820818901062,
+      "learning_rate": 7.258584866457633e-06,
+      "loss": 0.0059,
+      "step": 168704
+    },
+    {
+      "epoch": 6.382834044803747,
+      "grad_norm": 0.9420909881591797,
+      "learning_rate": 7.239318499490009e-06,
+      "loss": 0.0063,
+      "step": 168960
+    },
+    {
+      "epoch": 6.392505005477693,
+      "grad_norm": 0.13994884490966797,
+      "learning_rate": 7.2199765781421184e-06,
+      "loss": 0.0047,
+      "step": 169216
+    },
+    {
+      "epoch": 6.4021759661516375,
+      "grad_norm": 0.12359564751386642,
+      "learning_rate": 7.2006346567942286e-06,
+      "loss": 0.0052,
+      "step": 169472
+    },
+    {
+      "epoch": 6.411846926825583,
+      "grad_norm": 2.2115604877471924,
+      "learning_rate": 7.181292735446338e-06,
+      "loss": 0.0057,
+      "step": 169728
+    },
+    {
+      "epoch": 6.421517887499528,
+      "grad_norm": 0.019372638314962387,
+      "learning_rate": 7.162101922858978e-06,
+      "loss": 0.0058,
+      "step": 169984
+    },
+    {
+      "epoch": 6.4311888481734725,
+      "grad_norm": 0.07033487409353256,
+      "learning_rate": 7.142760001511088e-06,
+      "loss": 0.007,
+      "step": 170240
+    },
+    {
+      "epoch": 6.440859808847418,
+      "grad_norm": 0.0495685413479805,
+      "learning_rate": 7.123418080163198e-06,
+      "loss": 0.004,
+      "step": 170496
+    },
+    {
+      "epoch": 6.450530769521363,
+      "grad_norm": 5.647730350494385,
+      "learning_rate": 7.104076158815309e-06,
+      "loss": 0.0056,
+      "step": 170752
+    },
+    {
+      "epoch": 6.460201730195308,
+      "grad_norm": 0.04144500568509102,
+      "learning_rate": 7.084734237467418e-06,
+      "loss": 0.0045,
+      "step": 171008
+    },
+    {
+      "epoch": 6.469872690869253,
+      "grad_norm": 0.04790091514587402,
+      "learning_rate": 7.065392316119528e-06,
+      "loss": 0.005,
+      "step": 171264
+    },
+    {
+      "epoch": 6.479543651543199,
+      "grad_norm": 0.5807636976242065,
+      "learning_rate": 7.046050394771637e-06,
+      "loss": 0.006,
+      "step": 171520
+    },
+    {
+      "epoch": 6.489214612217143,
+      "grad_norm": 0.04957037419080734,
+      "learning_rate": 7.026708473423747e-06,
+      "loss": 0.0055,
+      "step": 171776
+    },
+    {
+      "epoch": 6.498885572891089,
+      "grad_norm": 0.29678839445114136,
+      "learning_rate": 7.0073665520758576e-06,
+      "loss": 0.0055,
+      "step": 172032
+    },
+    {
+      "epoch": 6.5085565335650335,
+      "grad_norm": 0.12547393143177032,
+      "learning_rate": 6.988024630727968e-06,
+      "loss": 0.004,
+      "step": 172288
+    },
+    {
+      "epoch": 6.518227494238978,
+      "grad_norm": 0.032738201320171356,
+      "learning_rate": 6.9687582637603425e-06,
+      "loss": 0.0062,
+      "step": 172544
+    },
+    {
+      "epoch": 6.527898454912924,
+      "grad_norm": 0.013363759964704514,
+      "learning_rate": 6.949416342412452e-06,
+      "loss": 0.0053,
+      "step": 172800
+    },
+    {
+      "epoch": 6.537569415586868,
+      "grad_norm": 0.12095487862825394,
+      "learning_rate": 6.930074421064562e-06,
+      "loss": 0.0059,
+      "step": 173056
+    },
+    {
+      "epoch": 6.547240376260814,
+      "grad_norm": 1.4809820652008057,
+      "learning_rate": 6.910732499716671e-06,
+      "loss": 0.0045,
+      "step": 173312
+    },
+    {
+      "epoch": 6.556911336934759,
+      "grad_norm": 0.11994415521621704,
+      "learning_rate": 6.891390578368782e-06,
+      "loss": 0.0045,
+      "step": 173568
+    },
+    {
+      "epoch": 6.566582297608704,
+      "grad_norm": 0.5074435472488403,
+      "learning_rate": 6.8720486570208915e-06,
+      "loss": 0.0047,
+      "step": 173824
+    },
+    {
+      "epoch": 6.576253258282649,
+      "grad_norm": 1.6332694292068481,
+      "learning_rate": 6.852706735673002e-06,
+      "loss": 0.0035,
+      "step": 174080
+    },
+    {
+      "epoch": 6.585924218956594,
+      "grad_norm": 0.6540184020996094,
+      "learning_rate": 6.833364814325111e-06,
+      "loss": 0.005,
+      "step": 174336
+    },
+    {
+      "epoch": 6.595595179630539,
+      "grad_norm": 4.0721588134765625,
+      "learning_rate": 6.814022892977221e-06,
+      "loss": 0.0043,
+      "step": 174592
+    },
+    {
+      "epoch": 6.605266140304484,
+      "grad_norm": 0.34634193778038025,
+      "learning_rate": 6.79468097162933e-06,
+      "loss": 0.0063,
+      "step": 174848
+    },
+    {
+      "epoch": 6.6149371009784295,
+      "grad_norm": 0.140211820602417,
+      "learning_rate": 6.775339050281441e-06,
+      "loss": 0.0036,
+      "step": 175104
+    },
+    {
+      "epoch": 6.624608061652374,
+      "grad_norm": 1.9943935871124268,
+      "learning_rate": 6.7559971289335505e-06,
+      "loss": 0.0067,
+      "step": 175360
+    },
+    {
+      "epoch": 6.63427902232632,
+      "grad_norm": 10.475574493408203,
+      "learning_rate": 6.736655207585661e-06,
+      "loss": 0.0054,
+      "step": 175616
+    },
+    {
+      "epoch": 6.643949983000264,
+      "grad_norm": 12.580154418945312,
+      "learning_rate": 6.71731328623777e-06,
+      "loss": 0.0065,
+      "step": 175872
+    },
+    {
+      "epoch": 6.653620943674209,
+      "grad_norm": 0.5796445608139038,
+      "learning_rate": 6.69797136488988e-06,
+      "loss": 0.0047,
+      "step": 176128
+    },
+    {
+      "epoch": 6.663291904348155,
+      "grad_norm": 0.03411826118826866,
+      "learning_rate": 6.678629443541989e-06,
+      "loss": 0.0038,
+      "step": 176384
+    },
+    {
+      "epoch": 6.672962865022099,
+      "grad_norm": 0.3479785621166229,
+      "learning_rate": 6.6592875221941e-06,
+      "loss": 0.0059,
+      "step": 176640
+    },
+    {
+      "epoch": 6.682633825696045,
+      "grad_norm": 0.37940141558647156,
+      "learning_rate": 6.63994560084621e-06,
+      "loss": 0.0053,
+      "step": 176896
+    },
+    {
+      "epoch": 6.69230478636999,
+      "grad_norm": 0.2881454527378082,
+      "learning_rate": 6.62060367949832e-06,
+      "loss": 0.0043,
+      "step": 177152
+    },
+    {
+      "epoch": 6.701975747043935,
+      "grad_norm": 0.32211869955062866,
+      "learning_rate": 6.601261758150429e-06,
+      "loss": 0.0071,
+      "step": 177408
+    },
+    {
+      "epoch": 6.71164670771788,
+      "grad_norm": 0.0830293819308281,
+      "learning_rate": 6.581919836802539e-06,
+      "loss": 0.0047,
+      "step": 177664
+    },
+    {
+      "epoch": 6.7213176683918245,
+      "grad_norm": 0.6374879479408264,
+      "learning_rate": 6.5625779154546484e-06,
+      "loss": 0.005,
+      "step": 177920
+    },
+    {
+      "epoch": 6.73098862906577,
+      "grad_norm": 0.42339634895324707,
+      "learning_rate": 6.543235994106759e-06,
+      "loss": 0.0057,
+      "step": 178176
+    },
+    {
+      "epoch": 6.740659589739715,
+      "grad_norm": 0.21855546534061432,
+      "learning_rate": 6.523894072758869e-06,
+      "loss": 0.0044,
+      "step": 178432
+    },
+    {
+      "epoch": 6.75033055041366,
+      "grad_norm": 0.17506131529808044,
+      "learning_rate": 6.5046277057912435e-06,
+      "loss": 0.0048,
+      "step": 178688
+    },
+    {
+      "epoch": 6.760001511087605,
+      "grad_norm": 0.11796054244041443,
+      "learning_rate": 6.485285784443354e-06,
+      "loss": 0.0055,
+      "step": 178944
+    },
+    {
+      "epoch": 6.769672471761551,
+      "grad_norm": 0.7898224592208862,
+      "learning_rate": 6.465943863095463e-06,
+      "loss": 0.0042,
+      "step": 179200
+    },
+    {
+      "epoch": 6.779343432435495,
+      "grad_norm": 0.18970559537410736,
+      "learning_rate": 6.446677496127839e-06,
+      "loss": 0.0044,
+      "step": 179456
+    },
+    {
+      "epoch": 6.789014393109441,
+      "grad_norm": 1.1956768035888672,
+      "learning_rate": 6.427335574779948e-06,
+      "loss": 0.0049,
+      "step": 179712
+    },
+    {
+      "epoch": 6.798685353783386,
+      "grad_norm": 0.6470310688018799,
+      "learning_rate": 6.407993653432059e-06,
+      "loss": 0.005,
+      "step": 179968
+    },
+    {
+      "epoch": 6.808356314457331,
+      "grad_norm": 4.411340236663818,
+      "learning_rate": 6.388651732084168e-06,
+      "loss": 0.0043,
+      "step": 180224
+    },
+    {
+      "epoch": 6.818027275131276,
+      "grad_norm": 0.09347503632307053,
+      "learning_rate": 6.369309810736278e-06,
+      "loss": 0.0043,
+      "step": 180480
+    },
+    {
+      "epoch": 6.8276982358052205,
+      "grad_norm": 0.007505136076360941,
+      "learning_rate": 6.3499678893883875e-06,
+      "loss": 0.0055,
+      "step": 180736
+    },
+    {
+      "epoch": 6.837369196479166,
+      "grad_norm": 0.286432683467865,
+      "learning_rate": 6.330625968040498e-06,
+      "loss": 0.0039,
+      "step": 180992
+    },
+    {
+      "epoch": 6.847040157153111,
+      "grad_norm": 0.2944409251213074,
+      "learning_rate": 6.311284046692607e-06,
+      "loss": 0.004,
+      "step": 181248
+    },
+    {
+      "epoch": 6.856711117827056,
+      "grad_norm": 0.32838645577430725,
+      "learning_rate": 6.291942125344718e-06,
+      "loss": 0.0046,
+      "step": 181504
+    },
+    {
+      "epoch": 6.866382078501001,
+      "grad_norm": 0.04531640559434891,
+      "learning_rate": 6.272600203996827e-06,
+      "loss": 0.0048,
+      "step": 181760
+    },
+    {
+      "epoch": 6.876053039174947,
+      "grad_norm": 0.060415927320718765,
+      "learning_rate": 6.253258282648937e-06,
+      "loss": 0.0038,
+      "step": 182016
+    },
+    {
+      "epoch": 6.885723999848891,
+      "grad_norm": 0.0581819973886013,
+      "learning_rate": 6.233916361301047e-06,
+      "loss": 0.004,
+      "step": 182272
+    },
+    {
+      "epoch": 6.895394960522836,
+      "grad_norm": 0.0427870936691761,
+      "learning_rate": 6.214574439953157e-06,
+      "loss": 0.005,
+      "step": 182528
+    },
+    {
+      "epoch": 6.9050659211967815,
+      "grad_norm": 1.7197208404541016,
+      "learning_rate": 6.195232518605266e-06,
+      "loss": 0.0043,
+      "step": 182784
+    },
+    {
+      "epoch": 6.914736881870726,
+      "grad_norm": 0.09247897565364838,
+      "learning_rate": 6.175890597257377e-06,
+      "loss": 0.0056,
+      "step": 183040
+    },
+    {
+      "epoch": 6.924407842544672,
+      "grad_norm": 0.019822193309664726,
+      "learning_rate": 6.156548675909486e-06,
+      "loss": 0.0055,
+      "step": 183296
+    },
+    {
+      "epoch": 6.9340788032186165,
+      "grad_norm": 1.541544795036316,
+      "learning_rate": 6.137282308941861e-06,
+      "loss": 0.0057,
+      "step": 183552
+    },
+    {
+      "epoch": 6.943749763892562,
+      "grad_norm": 1.1010373830795288,
+      "learning_rate": 6.117940387593971e-06,
+      "loss": 0.0048,
+      "step": 183808
+    },
+    {
+      "epoch": 6.953420724566507,
+      "grad_norm": 0.32369253039360046,
+      "learning_rate": 6.0985984662460805e-06,
+      "loss": 0.0044,
+      "step": 184064
+    },
+    {
+      "epoch": 6.963091685240451,
+      "grad_norm": 0.36643514037132263,
+      "learning_rate": 6.079332099278456e-06,
+      "loss": 0.0052,
+      "step": 184320
+    },
+    {
+      "epoch": 6.972762645914397,
+      "grad_norm": 4.76845645904541,
+      "learning_rate": 6.0599901779305655e-06,
+      "loss": 0.0055,
+      "step": 184576
+    },
+    {
+      "epoch": 6.982433606588342,
+      "grad_norm": 0.9248315095901489,
+      "learning_rate": 6.0406482565826765e-06,
+      "loss": 0.0057,
+      "step": 184832
+    },
+    {
+      "epoch": 6.992104567262287,
+      "grad_norm": 7.52930212020874,
+      "learning_rate": 6.021306335234786e-06,
+      "loss": 0.0057,
+      "step": 185088
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1_B-DISEASE": 0.8170322475036831,
+      "eval_f1_B-MEDICATION": 0.9388233174159835,
+      "eval_f1_B-PROCEDURE": 0.839606661240293,
+      "eval_f1_B-SYMPTOM": 0.8083601954871582,
+      "eval_f1_I-DISEASE": 0.8508488239606706,
+      "eval_f1_I-MEDICATION": 0.9480509127627348,
+      "eval_f1_I-PROCEDURE": 0.8557830786803291,
+      "eval_f1_I-SYMPTOM": 0.8172193160347818,
+      "eval_f1_O": 0.9271939022229883,
+      "eval_f1_macro": 0.8669909394787357,
+      "eval_f1_micro": 0.8922796408524778,
+      "eval_loss": 0.4217996597290039,
+      "eval_precision_B-DISEASE": 0.8439005833121989,
+      "eval_precision_B-MEDICATION": 0.9507299270072993,
+      "eval_precision_B-PROCEDURE": 0.8642271636248359,
+      "eval_precision_B-SYMPTOM": 0.8188329471244997,
+      "eval_precision_I-DISEASE": 0.8612162292396158,
+      "eval_precision_I-MEDICATION": 0.9526327031934209,
+      "eval_precision_I-PROCEDURE": 0.8682078109649086,
+      "eval_precision_I-SYMPTOM": 0.8107099237044831,
+      "eval_precision_O": 0.9254912549627295,
+      "eval_precision_macro": 0.8773276159037767,
+      "eval_precision_micro": 0.8938970887232961,
+      "eval_rauc_macro": 0.9183518246652276,
+      "eval_rauc_micro": 0.9385967353145594,
+      "eval_recall_B-DISEASE": 0.7918220036487665,
+      "eval_recall_B-MEDICATION": 0.9272112475529454,
+      "eval_recall_B-PROCEDURE": 0.8163501026694046,
+      "eval_recall_B-SYMPTOM": 0.7981519507186858,
+      "eval_recall_I-DISEASE": 0.8407280573012708,
+      "eval_recall_I-MEDICATION": 0.943512984608875,
+      "eval_recall_I-PROCEDURE": 0.8437089443234025,
+      "eval_recall_I-SYMPTOM": 0.8238340855362132,
+      "eval_recall_O": 0.9289028258275723,
+      "eval_recall_macro": 0.8571358002430152,
+      "eval_recall_micro": 0.8906680357402255,
+      "eval_roc_auc_B-DISEASE": 0.8945483627101096,
+      "eval_roc_auc_B-MEDICATION": 0.9635074195320126,
+      "eval_roc_auc_B-PROCEDURE": 0.9070703509413875,
+      "eval_roc_auc_B-SYMPTOM": 0.897166398981839,
+      "eval_roc_auc_I-DISEASE": 0.9115174466724183,
+      "eval_roc_auc_I-MEDICATION": 0.9714307242336749,
+      "eval_roc_auc_I-PROCEDURE": 0.9156151956077059,
+      "eval_roc_auc_I-SYMPTOM": 0.896927321744982,
+      "eval_roc_auc_O": 0.9073832015629196,
+      "eval_runtime": 61.0949,
+      "eval_samples_per_second": 177.969,
+      "eval_steps_per_second": 22.26,
+      "step": 185297
+    },
+    {
+      "epoch": 7.001775527936232,
+      "grad_norm": 0.7092540860176086,
+      "learning_rate": 6.001964413886896e-06,
+      "loss": 0.0041,
+      "step": 185344
+    },
+    {
+      "epoch": 7.0114464886101775,
+      "grad_norm": 0.18654197454452515,
+      "learning_rate": 5.982622492539005e-06,
+      "loss": 0.0024,
+      "step": 185600
+    },
+    {
+      "epoch": 7.021117449284122,
+      "grad_norm": 0.8840870261192322,
+      "learning_rate": 5.963280571191115e-06,
+      "loss": 0.0023,
+      "step": 185856
+    },
+    {
+      "epoch": 7.030788409958068,
+      "grad_norm": 0.08226889371871948,
+      "learning_rate": 5.943938649843225e-06,
+      "loss": 0.0041,
+      "step": 186112
+    },
+    {
+      "epoch": 7.040459370632012,
+      "grad_norm": 0.1381804347038269,
+      "learning_rate": 5.9245967284953355e-06,
+      "loss": 0.0031,
+      "step": 186368
+    },
+    {
+      "epoch": 7.050130331305957,
+      "grad_norm": 2.1430623531341553,
+      "learning_rate": 5.905254807147445e-06,
+      "loss": 0.0022,
+      "step": 186624
+    },
+    {
+      "epoch": 7.059801291979903,
+      "grad_norm": 0.060144223272800446,
+      "learning_rate": 5.885912885799555e-06,
+      "loss": 0.0022,
+      "step": 186880
+    },
+    {
+      "epoch": 7.069472252653847,
+      "grad_norm": 0.06146460771560669,
+      "learning_rate": 5.866570964451664e-06,
+      "loss": 0.0035,
+      "step": 187136
+    },
+    {
+      "epoch": 7.079143213327793,
+      "grad_norm": 1.6876006126403809,
+      "learning_rate": 5.847229043103775e-06,
+      "loss": 0.0034,
+      "step": 187392
+    },
+    {
+      "epoch": 7.088814174001738,
+      "grad_norm": 2.21935772895813,
+      "learning_rate": 5.8278871217558845e-06,
+      "loss": 0.0045,
+      "step": 187648
+    },
+    {
+      "epoch": 7.098485134675683,
+      "grad_norm": 0.2139071524143219,
+      "learning_rate": 5.808545200407995e-06,
+      "loss": 0.0028,
+      "step": 187904
+    },
+    {
+      "epoch": 7.108156095349628,
+      "grad_norm": 0.2530527710914612,
+      "learning_rate": 5.789203279060104e-06,
+      "loss": 0.0029,
+      "step": 188160
+    },
+    {
+      "epoch": 7.117827056023573,
+      "grad_norm": 0.06350823491811752,
+      "learning_rate": 5.769861357712214e-06,
+      "loss": 0.0028,
+      "step": 188416
+    },
+    {
+      "epoch": 7.127498016697518,
+      "grad_norm": 0.3266438841819763,
+      "learning_rate": 5.750519436364323e-06,
+      "loss": 0.0057,
+      "step": 188672
+    },
+    {
+      "epoch": 7.137168977371463,
+      "grad_norm": 0.02727964147925377,
+      "learning_rate": 5.731253069396698e-06,
+      "loss": 0.0042,
+      "step": 188928
+    },
+    {
+      "epoch": 7.146839938045408,
+      "grad_norm": 0.007432880811393261,
+      "learning_rate": 5.711911148048809e-06,
+      "loss": 0.0035,
+      "step": 189184
+    },
+    {
+      "epoch": 7.156510898719353,
+      "grad_norm": 0.09012371301651001,
+      "learning_rate": 5.692569226700918e-06,
+      "loss": 0.0039,
+      "step": 189440
+    },
+    {
+      "epoch": 7.166181859393299,
+      "grad_norm": 0.19539253413677216,
+      "learning_rate": 5.6732273053530285e-06,
+      "loss": 0.0039,
+      "step": 189696
+    },
+    {
+      "epoch": 7.175852820067243,
+      "grad_norm": 3.682310104370117,
+      "learning_rate": 5.653885384005138e-06,
+      "loss": 0.0031,
+      "step": 189952
+    },
+    {
+      "epoch": 7.185523780741189,
+      "grad_norm": 0.4140027165412903,
+      "learning_rate": 5.634543462657248e-06,
+      "loss": 0.0044,
+      "step": 190208
+    },
+    {
+      "epoch": 7.195194741415134,
+      "grad_norm": 0.047425903379917145,
+      "learning_rate": 5.615201541309357e-06,
+      "loss": 0.0032,
+      "step": 190464
+    },
+    {
+      "epoch": 7.204865702089078,
+      "grad_norm": 0.08099602907896042,
+      "learning_rate": 5.595859619961468e-06,
+      "loss": 0.0027,
+      "step": 190720
+    },
+    {
+      "epoch": 7.214536662763024,
+      "grad_norm": 2.0335052013397217,
+      "learning_rate": 5.5765176986135775e-06,
+      "loss": 0.0038,
+      "step": 190976
+    },
+    {
+      "epoch": 7.2242076234369685,
+      "grad_norm": 0.7074165940284729,
+      "learning_rate": 5.557251331645953e-06,
+      "loss": 0.0033,
+      "step": 191232
+    },
+    {
+      "epoch": 7.233878584110914,
+      "grad_norm": 0.00729184877127409,
+      "learning_rate": 5.537909410298062e-06,
+      "loss": 0.0033,
+      "step": 191488
+    },
+    {
+      "epoch": 7.243549544784859,
+      "grad_norm": 0.2962284982204437,
+      "learning_rate": 5.518643043330437e-06,
+      "loss": 0.0033,
+      "step": 191744
+    },
+    {
+      "epoch": 7.253220505458804,
+      "grad_norm": 0.03666882589459419,
+      "learning_rate": 5.499301121982547e-06,
+      "loss": 0.0032,
+      "step": 192000
+    },
+    {
+      "epoch": 7.262891466132749,
+      "grad_norm": 2.278210163116455,
+      "learning_rate": 5.479959200634657e-06,
+      "loss": 0.0026,
+      "step": 192256
+    },
+    {
+      "epoch": 7.272562426806694,
+      "grad_norm": 0.6450464129447937,
+      "learning_rate": 5.460617279286768e-06,
+      "loss": 0.0031,
+      "step": 192512
+    },
+    {
+      "epoch": 7.282233387480639,
+      "grad_norm": 0.011020343750715256,
+      "learning_rate": 5.441275357938877e-06,
+      "loss": 0.0026,
+      "step": 192768
+    },
+    {
+      "epoch": 7.291904348154584,
+      "grad_norm": 0.848145604133606,
+      "learning_rate": 5.421933436590987e-06,
+      "loss": 0.0031,
+      "step": 193024
+    },
+    {
+      "epoch": 7.30157530882853,
+      "grad_norm": 0.47598353028297424,
+      "learning_rate": 5.402591515243096e-06,
+      "loss": 0.0035,
+      "step": 193280
+    },
+    {
+      "epoch": 7.311246269502474,
+      "grad_norm": 0.08850053697824478,
+      "learning_rate": 5.3832495938952064e-06,
+      "loss": 0.0028,
+      "step": 193536
+    },
+    {
+      "epoch": 7.32091723017642,
+      "grad_norm": 0.14100511372089386,
+      "learning_rate": 5.363907672547316e-06,
+      "loss": 0.0028,
+      "step": 193792
+    },
+    {
+      "epoch": 7.3305881908503645,
+      "grad_norm": 0.0643409714102745,
+      "learning_rate": 5.344565751199427e-06,
+      "loss": 0.0034,
+      "step": 194048
+    },
+    {
+      "epoch": 7.340259151524309,
+      "grad_norm": 0.02023415081202984,
+      "learning_rate": 5.325223829851536e-06,
+      "loss": 0.0034,
+      "step": 194304
+    },
+    {
+      "epoch": 7.349930112198255,
+      "grad_norm": 0.2690616846084595,
+      "learning_rate": 5.305881908503646e-06,
+      "loss": 0.0036,
+      "step": 194560
+    },
+    {
+      "epoch": 7.3596010728721994,
+      "grad_norm": 1.2020032405853271,
+      "learning_rate": 5.286539987155755e-06,
+      "loss": 0.0021,
+      "step": 194816
+    },
+    {
+      "epoch": 7.369272033546145,
+      "grad_norm": 0.49315980076789856,
+      "learning_rate": 5.2671980658078655e-06,
+      "loss": 0.0033,
+      "step": 195072
+    },
+    {
+      "epoch": 7.37894299422009,
+      "grad_norm": 0.03424458205699921,
+      "learning_rate": 5.247856144459975e-06,
+      "loss": 0.0034,
+      "step": 195328
+    },
+    {
+      "epoch": 7.388613954894035,
+      "grad_norm": 0.5558503270149231,
+      "learning_rate": 5.228514223112086e-06,
+      "loss": 0.0039,
+      "step": 195584
+    },
+    {
+      "epoch": 7.39828491556798,
+      "grad_norm": 0.1527431756258011,
+      "learning_rate": 5.209172301764195e-06,
+      "loss": 0.0025,
+      "step": 195840
+    },
+    {
+      "epoch": 7.4079558762419255,
+      "grad_norm": 0.03023804910480976,
+      "learning_rate": 5.189830380416305e-06,
+      "loss": 0.0029,
+      "step": 196096
+    },
+    {
+      "epoch": 7.41762683691587,
+      "grad_norm": 0.006813144311308861,
+      "learning_rate": 5.1704884590684145e-06,
+      "loss": 0.002,
+      "step": 196352
+    },
+    {
+      "epoch": 7.427297797589815,
+      "grad_norm": 0.06950301676988602,
+      "learning_rate": 5.151146537720525e-06,
+      "loss": 0.0035,
+      "step": 196608
+    },
+    {
+      "epoch": 7.4369687582637605,
+      "grad_norm": 0.12590453028678894,
+      "learning_rate": 5.131804616372634e-06,
+      "loss": 0.0027,
+      "step": 196864
+    },
+    {
+      "epoch": 7.446639718937705,
+      "grad_norm": 1.1601083278656006,
+      "learning_rate": 5.112462695024745e-06,
+      "loss": 0.0025,
+      "step": 197120
+    },
+    {
+      "epoch": 7.456310679611651,
+      "grad_norm": 1.2641323804855347,
+      "learning_rate": 5.093120773676854e-06,
+      "loss": 0.0031,
+      "step": 197376
+    },
+    {
+      "epoch": 7.465981640285595,
+      "grad_norm": 0.9254095554351807,
+      "learning_rate": 5.073778852328964e-06,
+      "loss": 0.003,
+      "step": 197632
+    },
+    {
+      "epoch": 7.475652600959541,
+      "grad_norm": 0.05598944053053856,
+      "learning_rate": 5.0544369309810736e-06,
+      "loss": 0.003,
+      "step": 197888
+    },
+    {
+      "epoch": 7.485323561633486,
+      "grad_norm": 0.040579646825790405,
+      "learning_rate": 5.035170564013449e-06,
+      "loss": 0.0028,
+      "step": 198144
+    },
+    {
+      "epoch": 7.494994522307431,
+      "grad_norm": 8.562992095947266,
+      "learning_rate": 5.0158286426655585e-06,
+      "loss": 0.0043,
+      "step": 198400
+    },
+    {
+      "epoch": 7.504665482981376,
+      "grad_norm": 0.09161358326673508,
+      "learning_rate": 4.996562275697933e-06,
+      "loss": 0.0028,
+      "step": 198656
+    },
+    {
+      "epoch": 7.514336443655321,
+      "grad_norm": 0.06476159393787384,
+      "learning_rate": 4.9772203543500435e-06,
+      "loss": 0.0029,
+      "step": 198912
+    },
+    {
+      "epoch": 7.524007404329266,
+      "grad_norm": 0.025177879258990288,
+      "learning_rate": 4.957878433002154e-06,
+      "loss": 0.0041,
+      "step": 199168
+    },
+    {
+      "epoch": 7.533678365003211,
+      "grad_norm": 0.06914424151182175,
+      "learning_rate": 4.938536511654263e-06,
+      "loss": 0.0036,
+      "step": 199424
+    },
+    {
+      "epoch": 7.543349325677156,
+      "grad_norm": 0.007711977697908878,
+      "learning_rate": 4.919194590306373e-06,
+      "loss": 0.0037,
+      "step": 199680
+    },
+    {
+      "epoch": 7.553020286351101,
+      "grad_norm": 0.5741889476776123,
+      "learning_rate": 4.899852668958483e-06,
+      "loss": 0.0021,
+      "step": 199936
+    },
+    {
+      "epoch": 7.562691247025047,
+      "grad_norm": 0.017532778903841972,
+      "learning_rate": 4.880510747610593e-06,
+      "loss": 0.0039,
+      "step": 200192
+    },
+    {
+      "epoch": 7.572362207698991,
+      "grad_norm": 0.013444333337247372,
+      "learning_rate": 4.8611688262627025e-06,
+      "loss": 0.0032,
+      "step": 200448
+    },
+    {
+      "epoch": 7.582033168372936,
+      "grad_norm": 0.1252066045999527,
+      "learning_rate": 4.8418269049148135e-06,
+      "loss": 0.0026,
+      "step": 200704
+    },
+    {
+      "epoch": 7.591704129046882,
+      "grad_norm": 0.16216708719730377,
+      "learning_rate": 4.822560537947188e-06,
+      "loss": 0.0028,
+      "step": 200960
+    },
+    {
+      "epoch": 7.601375089720826,
+      "grad_norm": 0.20117320120334625,
+      "learning_rate": 4.803218616599298e-06,
+      "loss": 0.0026,
+      "step": 201216
+    },
+    {
+      "epoch": 7.611046050394772,
+      "grad_norm": 0.4220730662345886,
+      "learning_rate": 4.783876695251408e-06,
+      "loss": 0.0033,
+      "step": 201472
+    },
+    {
+      "epoch": 7.620717011068717,
+      "grad_norm": 0.04324984550476074,
+      "learning_rate": 4.764534773903518e-06,
+      "loss": 0.0032,
+      "step": 201728
+    },
+    {
+      "epoch": 7.630387971742662,
+      "grad_norm": 0.24287299811840057,
+      "learning_rate": 4.745192852555627e-06,
+      "loss": 0.0029,
+      "step": 201984
+    },
+    {
+      "epoch": 7.640058932416607,
+      "grad_norm": 0.01797611638903618,
+      "learning_rate": 4.725850931207737e-06,
+      "loss": 0.0023,
+      "step": 202240
+    },
+    {
+      "epoch": 7.6497298930905515,
+      "grad_norm": 0.027291102334856987,
+      "learning_rate": 4.706509009859847e-06,
+      "loss": 0.0037,
+      "step": 202496
+    },
+    {
+      "epoch": 7.659400853764497,
+      "grad_norm": 0.015763144940137863,
+      "learning_rate": 4.687167088511957e-06,
+      "loss": 0.0024,
+      "step": 202752
+    },
+    {
+      "epoch": 7.669071814438442,
+      "grad_norm": 2.068912982940674,
+      "learning_rate": 4.6679007215443315e-06,
+      "loss": 0.0027,
+      "step": 203008
+    },
+    {
+      "epoch": 7.678742775112387,
+      "grad_norm": 0.1518033742904663,
+      "learning_rate": 4.648558800196442e-06,
+      "loss": 0.0025,
+      "step": 203264
+    },
+    {
+      "epoch": 7.688413735786332,
+      "grad_norm": 0.7454547882080078,
+      "learning_rate": 4.629216878848552e-06,
+      "loss": 0.0027,
+      "step": 203520
+    },
+    {
+      "epoch": 7.698084696460278,
+      "grad_norm": 0.04685609042644501,
+      "learning_rate": 4.609874957500661e-06,
+      "loss": 0.0034,
+      "step": 203776
+    },
+    {
+      "epoch": 7.707755657134222,
+      "grad_norm": 0.012423527427017689,
+      "learning_rate": 4.590533036152771e-06,
+      "loss": 0.002,
+      "step": 204032
+    },
+    {
+      "epoch": 7.717426617808167,
+      "grad_norm": 0.5419167876243591,
+      "learning_rate": 4.571191114804881e-06,
+      "loss": 0.0025,
+      "step": 204288
+    },
+    {
+      "epoch": 7.7270975784821125,
+      "grad_norm": 0.3725039064884186,
+      "learning_rate": 4.551849193456991e-06,
+      "loss": 0.0028,
+      "step": 204544
+    },
+    {
+      "epoch": 7.736768539156057,
+      "grad_norm": 0.09141060709953308,
+      "learning_rate": 4.532507272109101e-06,
+      "loss": 0.0024,
+      "step": 204800
+    },
+    {
+      "epoch": 7.746439499830003,
+      "grad_norm": 0.13550949096679688,
+      "learning_rate": 4.513165350761211e-06,
+      "loss": 0.0025,
+      "step": 205056
+    },
+    {
+      "epoch": 7.7561104605039475,
+      "grad_norm": 0.005226655397564173,
+      "learning_rate": 4.49382342941332e-06,
+      "loss": 0.0027,
+      "step": 205312
+    },
+    {
+      "epoch": 7.765781421177893,
+      "grad_norm": 1.0764216184616089,
+      "learning_rate": 4.47448150806543e-06,
+      "loss": 0.0029,
+      "step": 205568
+    },
+    {
+      "epoch": 7.775452381851838,
+      "grad_norm": 0.019114414229989052,
+      "learning_rate": 4.45513958671754e-06,
+      "loss": 0.0023,
+      "step": 205824
+    },
+    {
+      "epoch": 7.785123342525783,
+      "grad_norm": 0.214304581284523,
+      "learning_rate": 4.43579766536965e-06,
+      "loss": 0.0028,
+      "step": 206080
+    },
+    {
+      "epoch": 7.794794303199728,
+      "grad_norm": 0.9313531517982483,
+      "learning_rate": 4.41645574402176e-06,
+      "loss": 0.0027,
+      "step": 206336
+    },
+    {
+      "epoch": 7.804465263873674,
+      "grad_norm": 0.04551494121551514,
+      "learning_rate": 4.3971893770541355e-06,
+      "loss": 0.0025,
+      "step": 206592
+    },
+    {
+      "epoch": 7.814136224547618,
+      "grad_norm": 0.25390639901161194,
+      "learning_rate": 4.377847455706245e-06,
+      "loss": 0.0028,
+      "step": 206848
+    },
+    {
+      "epoch": 7.823807185221563,
+      "grad_norm": 0.4188549816608429,
+      "learning_rate": 4.358505534358355e-06,
+      "loss": 0.0035,
+      "step": 207104
+    },
+    {
+      "epoch": 7.8334781458955085,
+      "grad_norm": 5.584123134613037,
+      "learning_rate": 4.339163613010465e-06,
+      "loss": 0.0029,
+      "step": 207360
+    },
+    {
+      "epoch": 7.843149106569453,
+      "grad_norm": 0.09376902878284454,
+      "learning_rate": 4.319821691662574e-06,
+      "loss": 0.0025,
+      "step": 207616
+    },
+    {
+      "epoch": 7.852820067243399,
+      "grad_norm": 0.007881022058427334,
+      "learning_rate": 4.3004797703146844e-06,
+      "loss": 0.0031,
+      "step": 207872
+    },
+    {
+      "epoch": 7.8624910279173434,
+      "grad_norm": 0.053988266736269,
+      "learning_rate": 4.2811378489667946e-06,
+      "loss": 0.0031,
+      "step": 208128
+    },
+    {
+      "epoch": 7.872161988591289,
+      "grad_norm": 0.37332120537757874,
+      "learning_rate": 4.261795927618904e-06,
+      "loss": 0.0021,
+      "step": 208384
+    },
+    {
+      "epoch": 7.881832949265234,
+      "grad_norm": 0.10056313127279282,
+      "learning_rate": 4.242454006271014e-06,
+      "loss": 0.003,
+      "step": 208640
+    },
+    {
+      "epoch": 7.891503909939178,
+      "grad_norm": 0.021642550826072693,
+      "learning_rate": 4.223187639303389e-06,
+      "loss": 0.003,
+      "step": 208896
+    },
+    {
+      "epoch": 7.901174870613124,
+      "grad_norm": 0.15152160823345184,
+      "learning_rate": 4.203845717955499e-06,
+      "loss": 0.0028,
+      "step": 209152
+    },
+    {
+      "epoch": 7.910845831287069,
+      "grad_norm": 0.05597339943051338,
+      "learning_rate": 4.184503796607608e-06,
+      "loss": 0.0026,
+      "step": 209408
+    },
+    {
+      "epoch": 7.920516791961014,
+      "grad_norm": 0.026413604617118835,
+      "learning_rate": 4.165161875259718e-06,
+      "loss": 0.0027,
+      "step": 209664
+    },
+    {
+      "epoch": 7.930187752634959,
+      "grad_norm": 0.086790531873703,
+      "learning_rate": 4.1458199539118285e-06,
+      "loss": 0.0018,
+      "step": 209920
+    },
+    {
+      "epoch": 7.9398587133089045,
+      "grad_norm": 0.40138956904411316,
+      "learning_rate": 4.126478032563938e-06,
+      "loss": 0.0026,
+      "step": 210176
+    },
+    {
+      "epoch": 7.949529673982849,
+      "grad_norm": 0.504784107208252,
+      "learning_rate": 4.107136111216048e-06,
+      "loss": 0.003,
+      "step": 210432
+    },
+    {
+      "epoch": 7.959200634656794,
+      "grad_norm": 0.5855137705802917,
+      "learning_rate": 4.087794189868158e-06,
+      "loss": 0.0038,
+      "step": 210688
+    },
+    {
+      "epoch": 7.968871595330739,
+      "grad_norm": 0.23986396193504333,
+      "learning_rate": 4.068452268520267e-06,
+      "loss": 0.0027,
+      "step": 210944
+    },
+    {
+      "epoch": 7.978542556004684,
+      "grad_norm": 0.08508482575416565,
+      "learning_rate": 4.049110347172377e-06,
+      "loss": 0.0039,
+      "step": 211200
+    },
+    {
+      "epoch": 7.98821351667863,
+      "grad_norm": 2.018085241317749,
+      "learning_rate": 4.0297684258244875e-06,
+      "loss": 0.0018,
+      "step": 211456
+    },
+    {
+      "epoch": 7.997884477352574,
+      "grad_norm": 0.023388510569930077,
+      "learning_rate": 4.010502058856862e-06,
+      "loss": 0.0022,
+      "step": 211712
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1_B-DISEASE": 0.8192092717409173,
+      "eval_f1_B-MEDICATION": 0.9423820224719102,
+      "eval_f1_B-PROCEDURE": 0.8420637009739406,
+      "eval_f1_B-SYMPTOM": 0.8127123442808607,
+      "eval_f1_I-DISEASE": 0.850955341029534,
+      "eval_f1_I-MEDICATION": 0.949058663755226,
+      "eval_f1_I-PROCEDURE": 0.8554017038172543,
+      "eval_f1_I-SYMPTOM": 0.8136104891443594,
+      "eval_f1_O": 0.9274238987873996,
+      "eval_f1_macro": 0.868090826222378,
+      "eval_f1_micro": 0.8928833447754752,
+      "eval_loss": 0.4737370014190674,
+      "eval_precision_B-DISEASE": 0.8500213219616205,
+      "eval_precision_B-MEDICATION": 0.9520523065746458,
+      "eval_precision_B-PROCEDURE": 0.8641274986493788,
+      "eval_precision_B-SYMPTOM": 0.8414187307635937,
+      "eval_precision_I-DISEASE": 0.8638646013066827,
+      "eval_precision_I-MEDICATION": 0.9557009546283385,
+      "eval_precision_I-PROCEDURE": 0.8787206030410202,
+      "eval_precision_I-SYMPTOM": 0.8445731862439002,
+      "eval_precision_O": 0.9156305475079966,
+      "eval_precision_macro": 0.8851233056307976,
+      "eval_precision_micro": 0.895332761029088,
+      "eval_rauc_macro": 0.9153957194153303,
+      "eval_rauc_micro": 0.9385898278409849,
+      "eval_recall_B-DISEASE": 0.7905528674545887,
+      "eval_recall_B-MEDICATION": 0.9329062110695854,
+      "eval_recall_B-PROCEDURE": 0.8210985626283368,
+      "eval_recall_B-SYMPTOM": 0.7859000684462697,
+      "eval_recall_I-DISEASE": 0.8384262221051443,
+      "eval_recall_I-MEDICATION": 0.942508065795737,
+      "eval_recall_I-PROCEDURE": 0.8332884525936988,
+      "eval_recall_I-SYMPTOM": 0.7848377390930582,
+      "eval_recall_O": 0.9395250115419437,
+      "eval_recall_macro": 0.8521159111920403,
+      "eval_recall_micro": 0.8904472939909823,
+      "eval_roc_auc_B-DISEASE": 0.8939787349011639,
+      "eval_roc_auc_B-MEDICATION": 0.966357083606876,
+      "eval_roc_auc_B-PROCEDURE": 0.9094372113385102,
+      "eval_roc_auc_B-SYMPTOM": 0.8913483585328563,
+      "eval_roc_auc_I-DISEASE": 0.9105856356600845,
+      "eval_roc_auc_I-MEDICATION": 0.9709506682682745,
+      "eval_roc_auc_I-PROCEDURE": 0.9110413996799644,
+      "eval_roc_auc_I-SYMPTOM": 0.8811634945418189,
+      "eval_roc_auc_O": 0.9036988882084248,
+      "eval_runtime": 61.2016,
+      "eval_samples_per_second": 177.659,
+      "eval_steps_per_second": 22.222,
+      "step": 211768
+    },
+    {
+      "epoch": 8.00755543802652,
+      "grad_norm": 0.04221045598387718,
+      "learning_rate": 3.9911601375089725e-06,
+      "loss": 0.0014,
+      "step": 211968
+    },
+    {
+      "epoch": 8.017226398700465,
+      "grad_norm": 0.10489369928836823,
+      "learning_rate": 3.971818216161083e-06,
+      "loss": 0.0014,
+      "step": 212224
+    },
+    {
+      "epoch": 8.02689735937441,
+      "grad_norm": 0.005116314627230167,
+      "learning_rate": 3.952476294813192e-06,
+      "loss": 0.0017,
+      "step": 212480
+    },
+    {
+      "epoch": 8.036568320048355,
+      "grad_norm": 0.013480676338076591,
+      "learning_rate": 3.933134373465302e-06,
+      "loss": 0.0015,
+      "step": 212736
+    },
+    {
+      "epoch": 8.0462392807223,
+      "grad_norm": 0.009527523070573807,
+      "learning_rate": 3.913792452117412e-06,
+      "loss": 0.0017,
+      "step": 212992
+    },
+    {
+      "epoch": 8.055910241396244,
+      "grad_norm": 0.06975742429494858,
+      "learning_rate": 3.8944505307695214e-06,
+      "loss": 0.0018,
+      "step": 213248
+    },
+    {
+      "epoch": 8.06558120207019,
+      "grad_norm": 1.0523467063903809,
+      "learning_rate": 3.8751086094216316e-06,
+      "loss": 0.0008,
+      "step": 213504
+    },
+    {
+      "epoch": 8.075252162744135,
+      "grad_norm": 0.021572506055235863,
+      "learning_rate": 3.855766688073742e-06,
+      "loss": 0.0015,
+      "step": 213760
+    },
+    {
+      "epoch": 8.084923123418081,
+      "grad_norm": 0.004556609317660332,
+      "learning_rate": 3.8365003211061165e-06,
+      "loss": 0.0025,
+      "step": 214016
+    },
+    {
+      "epoch": 8.094594084092025,
+      "grad_norm": 0.01564151607453823,
+      "learning_rate": 3.817158399758226e-06,
+      "loss": 0.002,
+      "step": 214272
+    },
+    {
+      "epoch": 8.10426504476597,
+      "grad_norm": 0.02460288256406784,
+      "learning_rate": 3.797816478410336e-06,
+      "loss": 0.0023,
+      "step": 214528
+    },
+    {
+      "epoch": 8.113936005439916,
+      "grad_norm": 0.19753815233707428,
+      "learning_rate": 3.778474557062446e-06,
+      "loss": 0.0022,
+      "step": 214784
+    },
+    {
+      "epoch": 8.12360696611386,
+      "grad_norm": 0.0022627103608101606,
+      "learning_rate": 3.7591326357145558e-06,
+      "loss": 0.0027,
+      "step": 215040
+    },
+    {
+      "epoch": 8.133277926787805,
+      "grad_norm": 0.027415508404374123,
+      "learning_rate": 3.7397907143666655e-06,
+      "loss": 0.0013,
+      "step": 215296
+    },
+    {
+      "epoch": 8.14294888746175,
+      "grad_norm": 0.13008584082126617,
+      "learning_rate": 3.7204487930187756e-06,
+      "loss": 0.0023,
+      "step": 215552
+    },
+    {
+      "epoch": 8.152619848135696,
+      "grad_norm": 0.03469686210155487,
+      "learning_rate": 3.7011068716708853e-06,
+      "loss": 0.0017,
+      "step": 215808
+    },
+    {
+      "epoch": 8.16229080880964,
+      "grad_norm": 0.27707692980766296,
+      "learning_rate": 3.681764950322995e-06,
+      "loss": 0.0016,
+      "step": 216064
+    },
+    {
+      "epoch": 8.171961769483586,
+      "grad_norm": 0.001276107388548553,
+      "learning_rate": 3.662423028975105e-06,
+      "loss": 0.0019,
+      "step": 216320
+    },
+    {
+      "epoch": 8.181632730157531,
+      "grad_norm": 0.1010005995631218,
+      "learning_rate": 3.6431566620074804e-06,
+      "loss": 0.0017,
+      "step": 216576
+    },
+    {
+      "epoch": 8.191303690831475,
+      "grad_norm": 0.0014761561760678887,
+      "learning_rate": 3.62381474065959e-06,
+      "loss": 0.0012,
+      "step": 216832
+    },
+    {
+      "epoch": 8.20097465150542,
+      "grad_norm": 0.01065876055508852,
+      "learning_rate": 3.6044728193117002e-06,
+      "loss": 0.0018,
+      "step": 217088
+    },
+    {
+      "epoch": 8.210645612179366,
+      "grad_norm": 0.013767397962510586,
+      "learning_rate": 3.58513089796381e-06,
+      "loss": 0.0019,
+      "step": 217344
+    },
+    {
+      "epoch": 8.220316572853312,
+      "grad_norm": 0.06974133104085922,
+      "learning_rate": 3.5657889766159196e-06,
+      "loss": 0.0016,
+      "step": 217600
+    },
+    {
+      "epoch": 8.229987533527256,
+      "grad_norm": 0.0005238667945377529,
+      "learning_rate": 3.5464470552680298e-06,
+      "loss": 0.002,
+      "step": 217856
+    },
+    {
+      "epoch": 8.239658494201201,
+      "grad_norm": 0.0016113127348944545,
+      "learning_rate": 3.5271051339201395e-06,
+      "loss": 0.0021,
+      "step": 218112
+    },
+    {
+      "epoch": 8.249329454875147,
+      "grad_norm": 0.006277918349951506,
+      "learning_rate": 3.5077632125722496e-06,
+      "loss": 0.002,
+      "step": 218368
+    },
+    {
+      "epoch": 8.259000415549092,
+      "grad_norm": 6.543371200561523,
+      "learning_rate": 3.4884212912243593e-06,
+      "loss": 0.0032,
+      "step": 218624
+    },
+    {
+      "epoch": 8.268671376223036,
+      "grad_norm": 0.002728199353441596,
+      "learning_rate": 3.469154924256734e-06,
+      "loss": 0.0017,
+      "step": 218880
+    },
+    {
+      "epoch": 8.278342336896982,
+      "grad_norm": 0.0380263552069664,
+      "learning_rate": 3.449813002908844e-06,
+      "loss": 0.0015,
+      "step": 219136
+    },
+    {
+      "epoch": 8.288013297570927,
+      "grad_norm": 0.09521731734275818,
+      "learning_rate": 3.430471081560954e-06,
+      "loss": 0.0014,
+      "step": 219392
+    },
+    {
+      "epoch": 8.297684258244871,
+      "grad_norm": 0.05859646946191788,
+      "learning_rate": 3.4111291602130637e-06,
+      "loss": 0.0016,
+      "step": 219648
+    },
+    {
+      "epoch": 8.307355218918817,
+      "grad_norm": 0.057360127568244934,
+      "learning_rate": 3.3917872388651734e-06,
+      "loss": 0.0015,
+      "step": 219904
+    },
+    {
+      "epoch": 8.317026179592762,
+      "grad_norm": 0.005022614262998104,
+      "learning_rate": 3.3724453175172835e-06,
+      "loss": 0.0018,
+      "step": 220160
+    },
+    {
+      "epoch": 8.326697140266708,
+      "grad_norm": 0.009211408905684948,
+      "learning_rate": 3.353103396169393e-06,
+      "loss": 0.0019,
+      "step": 220416
+    },
+    {
+      "epoch": 8.336368100940652,
+      "grad_norm": 0.8216173052787781,
+      "learning_rate": 3.333761474821503e-06,
+      "loss": 0.0015,
+      "step": 220672
+    },
+    {
+      "epoch": 8.346039061614597,
+      "grad_norm": 0.036033984273672104,
+      "learning_rate": 3.314419553473613e-06,
+      "loss": 0.0019,
+      "step": 220928
+    },
+    {
+      "epoch": 8.355710022288543,
+      "grad_norm": 0.28528496623039246,
+      "learning_rate": 3.295153186505988e-06,
+      "loss": 0.0016,
+      "step": 221184
+    },
+    {
+      "epoch": 8.365380982962487,
+      "grad_norm": 0.21900594234466553,
+      "learning_rate": 3.2758112651580976e-06,
+      "loss": 0.0011,
+      "step": 221440
+    },
+    {
+      "epoch": 8.375051943636432,
+      "grad_norm": 0.1995537430047989,
+      "learning_rate": 3.2564693438102073e-06,
+      "loss": 0.0011,
+      "step": 221696
+    },
+    {
+      "epoch": 8.384722904310378,
+      "grad_norm": 0.05183367431163788,
+      "learning_rate": 3.2371274224623174e-06,
+      "loss": 0.0016,
+      "step": 221952
+    },
+    {
+      "epoch": 8.394393864984323,
+      "grad_norm": 0.8787815570831299,
+      "learning_rate": 3.217785501114427e-06,
+      "loss": 0.0016,
+      "step": 222208
+    },
+    {
+      "epoch": 8.404064825658267,
+      "grad_norm": 0.013117530383169651,
+      "learning_rate": 3.198443579766537e-06,
+      "loss": 0.0017,
+      "step": 222464
+    },
+    {
+      "epoch": 8.413735786332213,
+      "grad_norm": 0.005170230288058519,
+      "learning_rate": 3.179101658418647e-06,
+      "loss": 0.0018,
+      "step": 222720
+    },
+    {
+      "epoch": 8.423406747006158,
+      "grad_norm": 0.07186521589756012,
+      "learning_rate": 3.1597597370707567e-06,
+      "loss": 0.0024,
+      "step": 222976
+    },
+    {
+      "epoch": 8.433077707680102,
+      "grad_norm": 0.4515911042690277,
+      "learning_rate": 3.1404178157228664e-06,
+      "loss": 0.0023,
+      "step": 223232
+    },
+    {
+      "epoch": 8.442748668354048,
+      "grad_norm": 0.05934571474790573,
+      "learning_rate": 3.121151448755242e-06,
+      "loss": 0.0024,
+      "step": 223488
+    },
+    {
+      "epoch": 8.452419629027993,
+      "grad_norm": 0.5439963936805725,
+      "learning_rate": 3.1018095274073517e-06,
+      "loss": 0.0015,
+      "step": 223744
+    },
+    {
+      "epoch": 8.462090589701939,
+      "grad_norm": 0.002186891855672002,
+      "learning_rate": 3.0824676060594614e-06,
+      "loss": 0.0012,
+      "step": 224000
+    },
+    {
+      "epoch": 8.471761550375883,
+      "grad_norm": 0.005363143049180508,
+      "learning_rate": 3.0631256847115716e-06,
+      "loss": 0.0019,
+      "step": 224256
+    },
+    {
+      "epoch": 8.481432511049828,
+      "grad_norm": 0.8389096856117249,
+      "learning_rate": 3.0437837633636813e-06,
+      "loss": 0.0014,
+      "step": 224512
+    },
+    {
+      "epoch": 8.491103471723774,
+      "grad_norm": 0.009227742440998554,
+      "learning_rate": 3.024441842015791e-06,
+      "loss": 0.0015,
+      "step": 224768
+    },
+    {
+      "epoch": 8.500774432397717,
+      "grad_norm": 0.021440809592604637,
+      "learning_rate": 3.005099920667901e-06,
+      "loss": 0.0012,
+      "step": 225024
+    },
+    {
+      "epoch": 8.510445393071663,
+      "grad_norm": 0.053202465176582336,
+      "learning_rate": 2.985757999320011e-06,
+      "loss": 0.0021,
+      "step": 225280
+    },
+    {
+      "epoch": 8.520116353745609,
+      "grad_norm": 0.09795872122049332,
+      "learning_rate": 2.9664160779721205e-06,
+      "loss": 0.0011,
+      "step": 225536
+    },
+    {
+      "epoch": 8.529787314419554,
+      "grad_norm": 0.07053809612989426,
+      "learning_rate": 2.9470741566242306e-06,
+      "loss": 0.002,
+      "step": 225792
+    },
+    {
+      "epoch": 8.539458275093498,
+      "grad_norm": 0.015584302134811878,
+      "learning_rate": 2.9277322352763403e-06,
+      "loss": 0.0017,
+      "step": 226048
+    },
+    {
+      "epoch": 8.549129235767444,
+      "grad_norm": 0.014636941254138947,
+      "learning_rate": 2.9083903139284505e-06,
+      "loss": 0.002,
+      "step": 226304
+    },
+    {
+      "epoch": 8.55880019644139,
+      "grad_norm": 0.002259760396555066,
+      "learning_rate": 2.88904839258056e-06,
+      "loss": 0.0022,
+      "step": 226560
+    },
+    {
+      "epoch": 8.568471157115333,
+      "grad_norm": 0.1187112033367157,
+      "learning_rate": 2.86970647123267e-06,
+      "loss": 0.0019,
+      "step": 226816
+    },
+    {
+      "epoch": 8.578142117789278,
+      "grad_norm": 1.316362738609314,
+      "learning_rate": 2.85036454988478e-06,
+      "loss": 0.0018,
+      "step": 227072
+    },
+    {
+      "epoch": 8.587813078463224,
+      "grad_norm": 0.02268380858004093,
+      "learning_rate": 2.8310226285368897e-06,
+      "loss": 0.0015,
+      "step": 227328
+    },
+    {
+      "epoch": 8.59748403913717,
+      "grad_norm": 0.11864591389894485,
+      "learning_rate": 2.8117562615692645e-06,
+      "loss": 0.0016,
+      "step": 227584
+    },
+    {
+      "epoch": 8.607154999811113,
+      "grad_norm": 0.1629875749349594,
+      "learning_rate": 2.7924143402213743e-06,
+      "loss": 0.0013,
+      "step": 227840
+    },
+    {
+      "epoch": 8.616825960485059,
+      "grad_norm": 0.0012598687317222357,
+      "learning_rate": 2.7730724188734844e-06,
+      "loss": 0.0015,
+      "step": 228096
+    },
+    {
+      "epoch": 8.626496921159005,
+      "grad_norm": 0.012492740526795387,
+      "learning_rate": 2.753730497525594e-06,
+      "loss": 0.0017,
+      "step": 228352
+    },
+    {
+      "epoch": 8.63616788183295,
+      "grad_norm": 0.14352132380008698,
+      "learning_rate": 2.734388576177704e-06,
+      "loss": 0.0013,
+      "step": 228608
+    },
+    {
+      "epoch": 8.645838842506894,
+      "grad_norm": 0.022044667974114418,
+      "learning_rate": 2.715046654829814e-06,
+      "loss": 0.0015,
+      "step": 228864
+    },
+    {
+      "epoch": 8.65550980318084,
+      "grad_norm": 0.28277599811553955,
+      "learning_rate": 2.6957047334819236e-06,
+      "loss": 0.0024,
+      "step": 229120
+    },
+    {
+      "epoch": 8.665180763854785,
+      "grad_norm": 0.005805708467960358,
+      "learning_rate": 2.6763628121340333e-06,
+      "loss": 0.0018,
+      "step": 229376
+    },
+    {
+      "epoch": 8.674851724528729,
+      "grad_norm": 0.042201265692710876,
+      "learning_rate": 2.6570208907861435e-06,
+      "loss": 0.0013,
+      "step": 229632
+    },
+    {
+      "epoch": 8.684522685202674,
+      "grad_norm": 0.5332639813423157,
+      "learning_rate": 2.637678969438253e-06,
+      "loss": 0.001,
+      "step": 229888
+    },
+    {
+      "epoch": 8.69419364587662,
+      "grad_norm": 0.001226294320076704,
+      "learning_rate": 2.618337048090363e-06,
+      "loss": 0.0021,
+      "step": 230144
+    },
+    {
+      "epoch": 8.703864606550566,
+      "grad_norm": 0.008391711860895157,
+      "learning_rate": 2.598995126742473e-06,
+      "loss": 0.0018,
+      "step": 230400
+    },
+    {
+      "epoch": 8.71353556722451,
+      "grad_norm": 0.005565817467868328,
+      "learning_rate": 2.5797287597748482e-06,
+      "loss": 0.0014,
+      "step": 230656
+    },
+    {
+      "epoch": 8.723206527898455,
+      "grad_norm": 0.004753118846565485,
+      "learning_rate": 2.560386838426958e-06,
+      "loss": 0.0012,
+      "step": 230912
+    },
+    {
+      "epoch": 8.7328774885724,
+      "grad_norm": 0.0013271772768348455,
+      "learning_rate": 2.541044917079068e-06,
+      "loss": 0.0021,
+      "step": 231168
+    },
+    {
+      "epoch": 8.742548449246344,
+      "grad_norm": 0.06540732830762863,
+      "learning_rate": 2.5217029957311778e-06,
+      "loss": 0.0017,
+      "step": 231424
+    },
+    {
+      "epoch": 8.75221940992029,
+      "grad_norm": 0.16908077895641327,
+      "learning_rate": 2.5023610743832875e-06,
+      "loss": 0.002,
+      "step": 231680
+    },
+    {
+      "epoch": 8.761890370594235,
+      "grad_norm": 0.29503974318504333,
+      "learning_rate": 2.4830191530353976e-06,
+      "loss": 0.0016,
+      "step": 231936
+    },
+    {
+      "epoch": 8.771561331268181,
+      "grad_norm": 9.24250316619873,
+      "learning_rate": 2.4636772316875073e-06,
+      "loss": 0.0019,
+      "step": 232192
+    },
+    {
+      "epoch": 8.781232291942125,
+      "grad_norm": 0.09708067774772644,
+      "learning_rate": 2.444335310339617e-06,
+      "loss": 0.0011,
+      "step": 232448
+    },
+    {
+      "epoch": 8.79090325261607,
+      "grad_norm": 0.001615343731828034,
+      "learning_rate": 2.425068943371992e-06,
+      "loss": 0.0017,
+      "step": 232704
+    },
+    {
+      "epoch": 8.800574213290016,
+      "grad_norm": 0.21001236140727997,
+      "learning_rate": 2.405727022024102e-06,
+      "loss": 0.0021,
+      "step": 232960
+    },
+    {
+      "epoch": 8.81024517396396,
+      "grad_norm": 0.014585831202566624,
+      "learning_rate": 2.3863851006762117e-06,
+      "loss": 0.001,
+      "step": 233216
+    },
+    {
+      "epoch": 8.819916134637905,
+      "grad_norm": 0.6824801564216614,
+      "learning_rate": 2.367043179328322e-06,
+      "loss": 0.0016,
+      "step": 233472
+    },
+    {
+      "epoch": 8.829587095311851,
+      "grad_norm": 0.014681616798043251,
+      "learning_rate": 2.3477012579804315e-06,
+      "loss": 0.002,
+      "step": 233728
+    },
+    {
+      "epoch": 8.839258055985797,
+      "grad_norm": 0.010957110673189163,
+      "learning_rate": 2.3283593366325417e-06,
+      "loss": 0.0013,
+      "step": 233984
+    },
+    {
+      "epoch": 8.84892901665974,
+      "grad_norm": 1.2413954734802246,
+      "learning_rate": 2.3090174152846514e-06,
+      "loss": 0.0011,
+      "step": 234240
+    },
+    {
+      "epoch": 8.858599977333686,
+      "grad_norm": 0.1283838450908661,
+      "learning_rate": 2.289751048317026e-06,
+      "loss": 0.0011,
+      "step": 234496
+    },
+    {
+      "epoch": 8.868270938007631,
+      "grad_norm": 0.030070781707763672,
+      "learning_rate": 2.2704846813494014e-06,
+      "loss": 0.0013,
+      "step": 234752
+    },
+    {
+      "epoch": 8.877941898681575,
+      "grad_norm": 0.10878092795610428,
+      "learning_rate": 2.251142760001511e-06,
+      "loss": 0.0012,
+      "step": 235008
+    },
+    {
+      "epoch": 8.88761285935552,
+      "grad_norm": 0.0010157637298107147,
+      "learning_rate": 2.2318008386536213e-06,
+      "loss": 0.001,
+      "step": 235264
+    },
+    {
+      "epoch": 8.897283820029466,
+      "grad_norm": 0.0011938668321818113,
+      "learning_rate": 2.212458917305731e-06,
+      "loss": 0.0012,
+      "step": 235520
+    },
+    {
+      "epoch": 8.906954780703412,
+      "grad_norm": 0.0009772476041689515,
+      "learning_rate": 2.1931169959578407e-06,
+      "loss": 0.0012,
+      "step": 235776
+    },
+    {
+      "epoch": 8.916625741377356,
+      "grad_norm": 0.02653772011399269,
+      "learning_rate": 2.173775074609951e-06,
+      "loss": 0.0011,
+      "step": 236032
+    },
+    {
+      "epoch": 8.926296702051301,
+      "grad_norm": 0.002025567227974534,
+      "learning_rate": 2.1544331532620605e-06,
+      "loss": 0.0011,
+      "step": 236288
+    },
+    {
+      "epoch": 8.935967662725247,
+      "grad_norm": 0.07364089787006378,
+      "learning_rate": 2.1350912319141702e-06,
+      "loss": 0.0017,
+      "step": 236544
+    },
+    {
+      "epoch": 8.94563862339919,
+      "grad_norm": 0.000813729246146977,
+      "learning_rate": 2.1157493105662803e-06,
+      "loss": 0.0012,
+      "step": 236800
+    },
+    {
+      "epoch": 8.955309584073136,
+      "grad_norm": 0.3964155912399292,
+      "learning_rate": 2.09640738921839e-06,
+      "loss": 0.0013,
+      "step": 237056
+    },
+    {
+      "epoch": 8.964980544747082,
+      "grad_norm": 0.02675843983888626,
+      "learning_rate": 2.0770654678704998e-06,
+      "loss": 0.0013,
+      "step": 237312
+    },
+    {
+      "epoch": 8.974651505421027,
+      "grad_norm": 0.45542263984680176,
+      "learning_rate": 2.05772354652261e-06,
+      "loss": 0.0009,
+      "step": 237568
+    },
+    {
+      "epoch": 8.984322466094971,
+      "grad_norm": 0.004206574056297541,
+      "learning_rate": 2.0383816251747196e-06,
+      "loss": 0.0011,
+      "step": 237824
+    },
+    {
+      "epoch": 8.993993426768917,
+      "grad_norm": 0.029356837272644043,
+      "learning_rate": 2.0190397038268293e-06,
+      "loss": 0.0011,
+      "step": 238080
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1_B-DISEASE": 0.820265182517597,
+      "eval_f1_B-MEDICATION": 0.9411343069617418,
+      "eval_f1_B-PROCEDURE": 0.8432354734732991,
+      "eval_f1_B-SYMPTOM": 0.8137595552466991,
+      "eval_f1_I-DISEASE": 0.853021119122057,
+      "eval_f1_I-MEDICATION": 0.95037530170013,
+      "eval_f1_I-PROCEDURE": 0.8561874578893519,
+      "eval_f1_I-SYMPTOM": 0.8206522616146783,
+      "eval_f1_O": 0.9278188308044935,
+      "eval_f1_macro": 0.8696054988144497,
+      "eval_f1_micro": 0.8938386961399782,
+      "eval_loss": 0.507999837398529,
+      "eval_precision_B-DISEASE": 0.8472398343055203,
+      "eval_precision_B-MEDICATION": 0.9476723204619271,
+      "eval_precision_B-PROCEDURE": 0.8588731144631766,
+      "eval_precision_B-SYMPTOM": 0.826393789696542,
+      "eval_precision_I-DISEASE": 0.8680188544493643,
+      "eval_precision_I-MEDICATION": 0.9531815279846776,
+      "eval_precision_I-PROCEDURE": 0.8730946382675522,
+      "eval_precision_I-SYMPTOM": 0.8215935894536173,
+      "eval_precision_O": 0.9236782838636837,
+      "eval_precision_macro": 0.8799717725495623,
+      "eval_precision_micro": 0.895900159381018,
+      "eval_rauc_macro": 0.9196513344131847,
+      "eval_rauc_micro": 0.9392897520293723,
+      "eval_recall_B-DISEASE": 0.7949551836281431,
+      "eval_recall_B-MEDICATION": 0.9346858871685353,
+      "eval_recall_B-PROCEDURE": 0.8281570841889117,
+      "eval_recall_B-SYMPTOM": 0.8015058179329226,
+      "eval_recall_I-DISEASE": 0.8385328466237659,
+      "eval_recall_I-MEDICATION": 0.9475855503252764,
+      "eval_recall_I-PROCEDURE": 0.8399226419251389,
+      "eval_recall_I-SYMPTOM": 0.8197130883301096,
+      "eval_recall_O": 0.9319966663269038,
+      "eval_recall_macro": 0.8596727518277453,
+      "eval_recall_micro": 0.8917866979597766,
+      "eval_roc_auc_B-DISEASE": 0.8961441020336804,
+      "eval_roc_auc_B-MEDICATION": 0.9672374649513288,
+      "eval_roc_auc_B-PROCEDURE": 0.9129064100226968,
+      "eval_roc_auc_B-SYMPTOM": 0.8989321500948878,
+      "eval_roc_auc_I-DISEASE": 0.9109411921441964,
+      "eval_roc_auc_I-MEDICATION": 0.973469577978567,
+      "eval_roc_auc_I-PROCEDURE": 0.9140138334490733,
+      "eval_roc_auc_I-SYMPTOM": 0.8959855777737502,
+      "eval_roc_auc_O": 0.9072317012704816,
+      "eval_runtime": 61.1454,
+      "eval_samples_per_second": 177.822,
+      "eval_steps_per_second": 22.242,
+      "step": 238239
+    },
+    {
+      "epoch": 9.003664387442862,
+      "grad_norm": 0.0012333148624747992,
+      "learning_rate": 1.9996977824789394e-06,
+      "loss": 0.0009,
+      "step": 238336
+    },
+    {
+      "epoch": 9.013335348116808,
+      "grad_norm": 0.05198514088988304,
+      "learning_rate": 1.980355861131049e-06,
+      "loss": 0.0013,
+      "step": 238592
+    },
+    {
+      "epoch": 9.023006308790752,
+      "grad_norm": 0.002556259511038661,
+      "learning_rate": 1.9610894941634244e-06,
+      "loss": 0.0007,
+      "step": 238848
+    },
+    {
+      "epoch": 9.032677269464697,
+      "grad_norm": 0.017605243250727654,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 0.0003,
+      "step": 239104
+    },
+    {
+      "epoch": 9.042348230138643,
+      "grad_norm": 0.2546218931674957,
+      "learning_rate": 1.9224056514676438e-06,
+      "loss": 0.0011,
+      "step": 239360
+    },
+    {
+      "epoch": 9.052019190812587,
+      "grad_norm": 0.005463745910674334,
+      "learning_rate": 1.903063730119754e-06,
+      "loss": 0.0007,
+      "step": 239616
+    },
+    {
+      "epoch": 9.061690151486532,
+      "grad_norm": 0.013387962244451046,
+      "learning_rate": 1.8837218087718636e-06,
+      "loss": 0.0009,
+      "step": 239872
+    },
+    {
+      "epoch": 9.071361112160478,
+      "grad_norm": 0.0036850119940936565,
+      "learning_rate": 1.8643798874239735e-06,
+      "loss": 0.0008,
+      "step": 240128
+    },
+    {
+      "epoch": 9.081032072834423,
+      "grad_norm": 0.002097562188282609,
+      "learning_rate": 1.8450379660760835e-06,
+      "loss": 0.0006,
+      "step": 240384
+    },
+    {
+      "epoch": 9.090703033508367,
+      "grad_norm": 0.009374704211950302,
+      "learning_rate": 1.8256960447281932e-06,
+      "loss": 0.0007,
+      "step": 240640
+    },
+    {
+      "epoch": 9.100373994182313,
+      "grad_norm": 0.009544138796627522,
+      "learning_rate": 1.806354123380303e-06,
+      "loss": 0.001,
+      "step": 240896
+    },
+    {
+      "epoch": 9.110044954856258,
+      "grad_norm": 0.014574944972991943,
+      "learning_rate": 1.787012202032413e-06,
+      "loss": 0.001,
+      "step": 241152
+    },
+    {
+      "epoch": 9.119715915530202,
+      "grad_norm": 0.0014770117122679949,
+      "learning_rate": 1.7676702806845227e-06,
+      "loss": 0.001,
+      "step": 241408
+    },
+    {
+      "epoch": 9.129386876204148,
+      "grad_norm": 0.00023075766512192786,
+      "learning_rate": 1.7483283593366326e-06,
+      "loss": 0.0006,
+      "step": 241664
+    },
+    {
+      "epoch": 9.139057836878093,
+      "grad_norm": 0.036480896174907684,
+      "learning_rate": 1.7289864379887425e-06,
+      "loss": 0.0007,
+      "step": 241920
+    },
+    {
+      "epoch": 9.148728797552039,
+      "grad_norm": 0.005274293944239616,
+      "learning_rate": 1.7096445166408524e-06,
+      "loss": 0.0008,
+      "step": 242176
+    },
+    {
+      "epoch": 9.158399758225983,
+      "grad_norm": 0.0636928603053093,
+      "learning_rate": 1.6903025952929622e-06,
+      "loss": 0.0005,
+      "step": 242432
+    },
+    {
+      "epoch": 9.168070718899928,
+      "grad_norm": 0.007083303295075893,
+      "learning_rate": 1.670960673945072e-06,
+      "loss": 0.0012,
+      "step": 242688
+    },
+    {
+      "epoch": 9.177741679573874,
+      "grad_norm": 0.0029853142332285643,
+      "learning_rate": 1.651618752597182e-06,
+      "loss": 0.0013,
+      "step": 242944
+    },
+    {
+      "epoch": 9.187412640247818,
+      "grad_norm": 0.004745794460177422,
+      "learning_rate": 1.6322768312492917e-06,
+      "loss": 0.0008,
+      "step": 243200
+    },
+    {
+      "epoch": 9.197083600921763,
+      "grad_norm": 0.029157089069485664,
+      "learning_rate": 1.6129349099014016e-06,
+      "loss": 0.0009,
+      "step": 243456
+    },
+    {
+      "epoch": 9.206754561595709,
+      "grad_norm": 0.09862171113491058,
+      "learning_rate": 1.5935929885535115e-06,
+      "loss": 0.001,
+      "step": 243712
+    },
+    {
+      "epoch": 9.216425522269654,
+      "grad_norm": 0.02549828216433525,
+      "learning_rate": 1.5742510672056212e-06,
+      "loss": 0.0013,
+      "step": 243968
+    },
+    {
+      "epoch": 9.226096482943598,
+      "grad_norm": 0.0003341349947731942,
+      "learning_rate": 1.5549091458577311e-06,
+      "loss": 0.0011,
+      "step": 244224
+    },
+    {
+      "epoch": 9.235767443617544,
+      "grad_norm": 0.00141440168954432,
+      "learning_rate": 1.535567224509841e-06,
+      "loss": 0.0007,
+      "step": 244480
+    },
+    {
+      "epoch": 9.24543840429149,
+      "grad_norm": 0.0013356832787394524,
+      "learning_rate": 1.516225303161951e-06,
+      "loss": 0.0014,
+      "step": 244736
+    },
+    {
+      "epoch": 9.255109364965433,
+      "grad_norm": 0.06080584600567818,
+      "learning_rate": 1.4968833818140607e-06,
+      "loss": 0.0006,
+      "step": 244992
+    },
+    {
+      "epoch": 9.264780325639379,
+      "grad_norm": 0.11237218230962753,
+      "learning_rate": 1.4775414604661706e-06,
+      "loss": 0.0012,
+      "step": 245248
+    },
+    {
+      "epoch": 9.274451286313324,
+      "grad_norm": 0.23928683996200562,
+      "learning_rate": 1.4581995391182805e-06,
+      "loss": 0.0005,
+      "step": 245504
+    },
+    {
+      "epoch": 9.28412224698727,
+      "grad_norm": 0.001771116629242897,
+      "learning_rate": 1.4388576177703902e-06,
+      "loss": 0.0011,
+      "step": 245760
+    },
+    {
+      "epoch": 9.293793207661214,
+      "grad_norm": 0.0017612532246857882,
+      "learning_rate": 1.4195156964225001e-06,
+      "loss": 0.0007,
+      "step": 246016
+    },
+    {
+      "epoch": 9.303464168335159,
+      "grad_norm": 0.00843687541782856,
+      "learning_rate": 1.4002493294548752e-06,
+      "loss": 0.0018,
+      "step": 246272
+    },
+    {
+      "epoch": 9.313135129009105,
+      "grad_norm": 0.07218307256698608,
+      "learning_rate": 1.380907408106985e-06,
+      "loss": 0.0007,
+      "step": 246528
+    },
+    {
+      "epoch": 9.322806089683048,
+      "grad_norm": 0.00684273662045598,
+      "learning_rate": 1.361565486759095e-06,
+      "loss": 0.0005,
+      "step": 246784
+    },
+    {
+      "epoch": 9.332477050356994,
+      "grad_norm": 0.0004243789007887244,
+      "learning_rate": 1.34229911979147e-06,
+      "loss": 0.0005,
+      "step": 247040
+    },
+    {
+      "epoch": 9.34214801103094,
+      "grad_norm": 0.000982985831797123,
+      "learning_rate": 1.32295719844358e-06,
+      "loss": 0.0009,
+      "step": 247296
+    },
+    {
+      "epoch": 9.351818971704885,
+      "grad_norm": 0.008006760850548744,
+      "learning_rate": 1.3036152770956897e-06,
+      "loss": 0.0008,
+      "step": 247552
+    },
+    {
+      "epoch": 9.361489932378829,
+      "grad_norm": 0.0012839402770623565,
+      "learning_rate": 1.2842733557477996e-06,
+      "loss": 0.0012,
+      "step": 247808
+    },
+    {
+      "epoch": 9.371160893052775,
+      "grad_norm": 0.0076642511412501335,
+      "learning_rate": 1.2649314343999095e-06,
+      "loss": 0.0007,
+      "step": 248064
+    },
+    {
+      "epoch": 9.38083185372672,
+      "grad_norm": 0.0976879671216011,
+      "learning_rate": 1.2455895130520192e-06,
+      "loss": 0.0006,
+      "step": 248320
+    },
+    {
+      "epoch": 9.390502814400666,
+      "grad_norm": 2.341963291168213,
+      "learning_rate": 1.2262475917041291e-06,
+      "loss": 0.0009,
+      "step": 248576
+    },
+    {
+      "epoch": 9.40017377507461,
+      "grad_norm": 0.002288688672706485,
+      "learning_rate": 1.206905670356239e-06,
+      "loss": 0.0007,
+      "step": 248832
+    },
+    {
+      "epoch": 9.409844735748555,
+      "grad_norm": 0.0005827232380397618,
+      "learning_rate": 1.187563749008349e-06,
+      "loss": 0.0009,
+      "step": 249088
+    },
+    {
+      "epoch": 9.4195156964225,
+      "grad_norm": 0.00030542805325239897,
+      "learning_rate": 1.1682218276604587e-06,
+      "loss": 0.0007,
+      "step": 249344
+    },
+    {
+      "epoch": 9.429186657096444,
+      "grad_norm": 0.00033465458545833826,
+      "learning_rate": 1.1488799063125686e-06,
+      "loss": 0.0007,
+      "step": 249600
+    },
+    {
+      "epoch": 9.43885761777039,
+      "grad_norm": 0.0005558193661272526,
+      "learning_rate": 1.1295379849646785e-06,
+      "loss": 0.001,
+      "step": 249856
+    },
+    {
+      "epoch": 9.448528578444336,
+      "grad_norm": 0.008819201961159706,
+      "learning_rate": 1.1101960636167882e-06,
+      "loss": 0.0008,
+      "step": 250112
+    },
+    {
+      "epoch": 9.458199539118281,
+      "grad_norm": 0.011124982498586178,
+      "learning_rate": 1.0908541422688981e-06,
+      "loss": 0.001,
+      "step": 250368
+    },
+    {
+      "epoch": 9.467870499792225,
+      "grad_norm": 0.07561460882425308,
+      "learning_rate": 1.071512220921008e-06,
+      "loss": 0.001,
+      "step": 250624
+    },
+    {
+      "epoch": 9.47754146046617,
+      "grad_norm": 0.00775932939723134,
+      "learning_rate": 1.0521702995731177e-06,
+      "loss": 0.0008,
+      "step": 250880
+    },
+    {
+      "epoch": 9.487212421140116,
+      "grad_norm": 0.0026791319251060486,
+      "learning_rate": 1.032903932605493e-06,
+      "loss": 0.0009,
+      "step": 251136
+    },
+    {
+      "epoch": 9.49688338181406,
+      "grad_norm": 0.0014814439928159118,
+      "learning_rate": 1.0135620112576027e-06,
+      "loss": 0.0009,
+      "step": 251392
+    },
+    {
+      "epoch": 9.506554342488005,
+      "grad_norm": 0.17079958319664001,
+      "learning_rate": 9.942200899097126e-07,
+      "loss": 0.0008,
+      "step": 251648
+    },
+    {
+      "epoch": 9.516225303161951,
+      "grad_norm": 0.006455567199736834,
+      "learning_rate": 9.748781685618225e-07,
+      "loss": 0.0008,
+      "step": 251904
+    },
+    {
+      "epoch": 9.525896263835897,
+      "grad_norm": 0.0035214037634432316,
+      "learning_rate": 9.555362472139324e-07,
+      "loss": 0.0003,
+      "step": 252160
+    },
+    {
+      "epoch": 9.53556722450984,
+      "grad_norm": 0.0005882234545424581,
+      "learning_rate": 9.361943258660422e-07,
+      "loss": 0.0004,
+      "step": 252416
+    },
+    {
+      "epoch": 9.545238185183786,
+      "grad_norm": 0.00487788300961256,
+      "learning_rate": 9.168524045181521e-07,
+      "loss": 0.0011,
+      "step": 252672
+    },
+    {
+      "epoch": 9.554909145857732,
+      "grad_norm": 0.0005454017664305866,
+      "learning_rate": 8.975104831702619e-07,
+      "loss": 0.0009,
+      "step": 252928
+    },
+    {
+      "epoch": 9.564580106531675,
+      "grad_norm": 0.0002963479782920331,
+      "learning_rate": 8.782441162026368e-07,
+      "loss": 0.0008,
+      "step": 253184
+    },
+    {
+      "epoch": 9.574251067205621,
+      "grad_norm": 0.014803556725382805,
+      "learning_rate": 8.589021948547467e-07,
+      "loss": 0.0007,
+      "step": 253440
+    },
+    {
+      "epoch": 9.583922027879566,
+      "grad_norm": 0.0010204812278971076,
+      "learning_rate": 8.395602735068565e-07,
+      "loss": 0.0006,
+      "step": 253696
+    },
+    {
+      "epoch": 9.593592988553512,
+      "grad_norm": 0.000603766180574894,
+      "learning_rate": 8.202183521589665e-07,
+      "loss": 0.0005,
+      "step": 253952
+    },
+    {
+      "epoch": 9.603263949227456,
+      "grad_norm": 0.0006934937555342913,
+      "learning_rate": 8.008764308110763e-07,
+      "loss": 0.0004,
+      "step": 254208
+    },
+    {
+      "epoch": 9.612934909901401,
+      "grad_norm": 0.002163499826565385,
+      "learning_rate": 7.815345094631861e-07,
+      "loss": 0.0012,
+      "step": 254464
+    },
+    {
+      "epoch": 9.622605870575347,
+      "grad_norm": 0.009007874876260757,
+      "learning_rate": 7.62192588115296e-07,
+      "loss": 0.0009,
+      "step": 254720
+    },
+    {
+      "epoch": 9.632276831249293,
+      "grad_norm": 0.001189779955893755,
+      "learning_rate": 7.42850666767406e-07,
+      "loss": 0.0007,
+      "step": 254976
+    },
+    {
+      "epoch": 9.641947791923236,
+      "grad_norm": 0.006172012072056532,
+      "learning_rate": 7.235087454195158e-07,
+      "loss": 0.0008,
+      "step": 255232
+    },
+    {
+      "epoch": 9.651618752597182,
+      "grad_norm": 0.0028820731677114964,
+      "learning_rate": 7.041668240716256e-07,
+      "loss": 0.0009,
+      "step": 255488
+    },
+    {
+      "epoch": 9.661289713271128,
+      "grad_norm": 0.002549013588577509,
+      "learning_rate": 6.848249027237356e-07,
+      "loss": 0.0005,
+      "step": 255744
+    },
+    {
+      "epoch": 9.670960673945071,
+      "grad_norm": 0.0011592130176723003,
+      "learning_rate": 6.654829813758454e-07,
+      "loss": 0.0005,
+      "step": 256000
+    },
+    {
+      "epoch": 9.680631634619017,
+      "grad_norm": 0.009473592974245548,
+      "learning_rate": 6.461410600279553e-07,
+      "loss": 0.0006,
+      "step": 256256
+    },
+    {
+      "epoch": 9.690302595292962,
+      "grad_norm": 0.013225371949374676,
+      "learning_rate": 6.267991386800651e-07,
+      "loss": 0.0006,
+      "step": 256512
+    },
+    {
+      "epoch": 9.699973555966906,
+      "grad_norm": 0.0005315671442076564,
+      "learning_rate": 6.0753277171244e-07,
+      "loss": 0.0009,
+      "step": 256768
+    },
+    {
+      "epoch": 9.709644516640852,
+      "grad_norm": 0.07691678404808044,
+      "learning_rate": 5.881908503645499e-07,
+      "loss": 0.001,
+      "step": 257024
+    },
+    {
+      "epoch": 9.719315477314797,
+      "grad_norm": 0.00017236363783013076,
+      "learning_rate": 5.688489290166599e-07,
+      "loss": 0.0007,
+      "step": 257280
+    },
+    {
+      "epoch": 9.728986437988743,
+      "grad_norm": 0.00099793984554708,
+      "learning_rate": 5.495070076687697e-07,
+      "loss": 0.0016,
+      "step": 257536
+    },
+    {
+      "epoch": 9.738657398662687,
+      "grad_norm": 0.0005514703807421029,
+      "learning_rate": 5.301650863208795e-07,
+      "loss": 0.0004,
+      "step": 257792
+    },
+    {
+      "epoch": 9.748328359336632,
+      "grad_norm": 0.0029203654266893864,
+      "learning_rate": 5.108231649729894e-07,
+      "loss": 0.0007,
+      "step": 258048
+    },
+    {
+      "epoch": 9.757999320010578,
+      "grad_norm": 0.0004254644736647606,
+      "learning_rate": 4.914812436250992e-07,
+      "loss": 0.0016,
+      "step": 258304
+    },
+    {
+      "epoch": 9.767670280684523,
+      "grad_norm": 0.0031043547205626965,
+      "learning_rate": 4.721393222772091e-07,
+      "loss": 0.0005,
+      "step": 258560
+    },
+    {
+      "epoch": 9.777341241358467,
+      "grad_norm": 0.002943431492894888,
+      "learning_rate": 4.5279740092931894e-07,
+      "loss": 0.0008,
+      "step": 258816
+    },
+    {
+      "epoch": 9.787012202032413,
+      "grad_norm": 0.00015551786054857075,
+      "learning_rate": 4.334554795814288e-07,
+      "loss": 0.0011,
+      "step": 259072
+    },
+    {
+      "epoch": 9.796683162706358,
+      "grad_norm": 0.0021992865949869156,
+      "learning_rate": 4.1411355823353867e-07,
+      "loss": 0.0011,
+      "step": 259328
+    },
+    {
+      "epoch": 9.806354123380302,
+      "grad_norm": 0.3576786518096924,
+      "learning_rate": 3.947716368856485e-07,
+      "loss": 0.0011,
+      "step": 259584
+    },
+    {
+      "epoch": 9.816025084054248,
+      "grad_norm": 0.001682179281488061,
+      "learning_rate": 3.7542971553775834e-07,
+      "loss": 0.0007,
+      "step": 259840
+    },
+    {
+      "epoch": 9.825696044728193,
+      "grad_norm": 0.0001894651068141684,
+      "learning_rate": 3.560877941898682e-07,
+      "loss": 0.0007,
+      "step": 260096
+    },
+    {
+      "epoch": 9.835367005402139,
+      "grad_norm": 0.11490330845117569,
+      "learning_rate": 3.3674587284197807e-07,
+      "loss": 0.0006,
+      "step": 260352
+    },
+    {
+      "epoch": 9.845037966076083,
+      "grad_norm": 0.00011810084106400609,
+      "learning_rate": 3.1740395149408793e-07,
+      "loss": 0.0005,
+      "step": 260608
+    },
+    {
+      "epoch": 9.854708926750028,
+      "grad_norm": 0.0006803704309277236,
+      "learning_rate": 2.9806203014619774e-07,
+      "loss": 0.0005,
+      "step": 260864
+    },
+    {
+      "epoch": 9.864379887423974,
+      "grad_norm": 0.0036548932548612356,
+      "learning_rate": 2.787201087983076e-07,
+      "loss": 0.0007,
+      "step": 261120
+    },
+    {
+      "epoch": 9.874050848097918,
+      "grad_norm": 0.0011051982874050736,
+      "learning_rate": 2.5937818745041747e-07,
+      "loss": 0.0009,
+      "step": 261376
+    },
+    {
+      "epoch": 9.883721808771863,
+      "grad_norm": 0.010463064536452293,
+      "learning_rate": 2.4003626610252733e-07,
+      "loss": 0.0006,
+      "step": 261632
+    },
+    {
+      "epoch": 9.893392769445809,
+      "grad_norm": 0.0015552444383502007,
+      "learning_rate": 2.2069434475463717e-07,
+      "loss": 0.0004,
+      "step": 261888
+    },
+    {
+      "epoch": 9.903063730119754,
+      "grad_norm": 0.00023192820663098246,
+      "learning_rate": 2.0135242340674704e-07,
+      "loss": 0.0005,
+      "step": 262144
+    },
+    {
+      "epoch": 9.912734690793698,
+      "grad_norm": 2.180852174758911,
+      "learning_rate": 1.8201050205885687e-07,
+      "loss": 0.0008,
+      "step": 262400
+    },
+    {
+      "epoch": 9.922405651467644,
+      "grad_norm": 0.2690439820289612,
+      "learning_rate": 1.6266858071096674e-07,
+      "loss": 0.0005,
+      "step": 262656
+    },
+    {
+      "epoch": 9.93207661214159,
+      "grad_norm": 0.0014845479745417833,
+      "learning_rate": 1.4340221374334178e-07,
+      "loss": 0.0007,
+      "step": 262912
+    },
+    {
+      "epoch": 9.941747572815533,
+      "grad_norm": 0.0010751072550192475,
+      "learning_rate": 1.2406029239545164e-07,
+      "loss": 0.0017,
+      "step": 263168
+    },
+    {
+      "epoch": 9.951418533489479,
+      "grad_norm": 0.005477603990584612,
+      "learning_rate": 1.0479392542782669e-07,
+      "loss": 0.0003,
+      "step": 263424
+    },
+    {
+      "epoch": 9.961089494163424,
+      "grad_norm": 0.003662185976281762,
+      "learning_rate": 8.545200407993654e-08,
+      "loss": 0.001,
+      "step": 263680
+    },
+    {
+      "epoch": 9.97076045483737,
+      "grad_norm": 0.0006105359643697739,
+      "learning_rate": 6.611008273204639e-08,
+      "loss": 0.001,
+      "step": 263936
+    },
+    {
+      "epoch": 9.980431415511314,
+      "grad_norm": 0.0005147479241713881,
+      "learning_rate": 4.676816138415625e-08,
+      "loss": 0.0006,
+      "step": 264192
+    },
+    {
+      "epoch": 9.99010237618526,
+      "grad_norm": 0.002465909579768777,
+      "learning_rate": 2.7426240036266103e-08,
+      "loss": 0.0007,
+      "step": 264448
+    },
+    {
+      "epoch": 9.999773336859205,
+      "grad_norm": 0.0049901618622243404,
+      "learning_rate": 8.084318688375959e-09,
+      "loss": 0.0008,
+      "step": 264704
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1_B-DISEASE": 0.8212511199804513,
+      "eval_f1_B-MEDICATION": 0.9441194996850535,
+      "eval_f1_B-PROCEDURE": 0.8438837081733407,
+      "eval_f1_B-SYMPTOM": 0.8142008132624335,
+      "eval_f1_I-DISEASE": 0.8531332420369243,
+      "eval_f1_I-MEDICATION": 0.9504971609841921,
+      "eval_f1_I-PROCEDURE": 0.855959918699867,
+      "eval_f1_I-SYMPTOM": 0.8203061784176257,
+      "eval_f1_O": 0.9279796337095003,
+      "eval_f1_macro": 0.870147919438821,
+      "eval_f1_micro": 0.8940428457113243,
+      "eval_loss": 0.5246506333351135,
+      "eval_precision_B-DISEASE": 0.8439357160793505,
+      "eval_precision_B-MEDICATION": 0.9548598471059337,
+      "eval_precision_B-PROCEDURE": 0.8662552367223749,
+      "eval_precision_B-SYMPTOM": 0.8270493539504342,
+      "eval_precision_I-DISEASE": 0.8624838159699522,
+      "eval_precision_I-MEDICATION": 0.9581855315489627,
+      "eval_precision_I-PROCEDURE": 0.8779157051309547,
+      "eval_precision_I-SYMPTOM": 0.8292179488587081,
+      "eval_precision_O": 0.9223528464068083,
+      "eval_precision_macro": 0.8824728890859421,
+      "eval_precision_micro": 0.8962622493770654,
+      "eval_rauc_macro": 0.918932582829971,
+      "eval_rauc_micro": 0.9393388823070546,
+      "eval_recall_B-DISEASE": 0.7997541048623781,
+      "eval_recall_B-MEDICATION": 0.9336180815091654,
+      "eval_recall_B-PROCEDURE": 0.8226386036960985,
+      "eval_recall_B-SYMPTOM": 0.8017453798767967,
+      "eval_recall_I-DISEASE": 0.8439832411344849,
+      "eval_recall_I-MEDICATION": 0.942931189506532,
+      "eval_recall_I-PROCEDURE": 0.8350755220446033,
+      "eval_recall_I-SYMPTOM": 0.8115839243498818,
+      "eval_recall_O": 0.9336754945048357,
+      "eval_recall_macro": 0.858333949053864,
+      "eval_recall_micro": 0.8918344066604195,
+      "eval_roc_auc_B-DISEASE": 0.898501130076159,
+      "eval_roc_auc_B-MEDICATION": 0.9667188383374489,
+      "eval_roc_auc_B-PROCEDURE": 0.9102252873491329,
+      "eval_roc_auc_B-SYMPTOM": 0.8990597025985936,
+      "eval_roc_auc_I-DISEASE": 0.9132048321619536,
+      "eval_roc_auc_I-MEDICATION": 0.9711798590609849,
+      "eval_roc_auc_I-PROCEDURE": 0.9118804724182935,
+      "eval_roc_auc_I-SYMPTOM": 0.8927663421914375,
+      "eval_roc_auc_O": 0.9068567812757345,
+      "eval_runtime": 60.9219,
+      "eval_samples_per_second": 178.474,
+      "eval_steps_per_second": 22.324,
+      "step": 264710
+    }
+  ],
+  "logging_steps": 256,
+  "max_steps": 264710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5034084397459712e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}