Training in progress, epoch 1, checkpoint

checkpoint-555/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f74f9f4ff34b668f2cf1ed044080969a05f7c00ad80383c44ef509f68df306
+oid sha256:73390260de79e2c8629bcd13a704a7b0a9571a7b60fb682f4a2233bfce71939b
 size 1629432864

checkpoint-555/trainer_state.json

@@ -10,398 +10,402 @@
   "log_history": [
     {
       "epoch": 0.018026137899954935,
-      "grad_norm": 21.723926544189453,
+      "grad_norm": 37.54188919067383,
       "learning_rate": 4.981949458483755e-05,
-      "loss": 0.8104,
+      "loss": 0.8911,
       "step": 10
     },
     {
       "epoch": 0.03605227579990987,
-      "grad_norm": 55.4254035949707,
+      "grad_norm": 15.440231323242188,
       "learning_rate": 4.963898916967509e-05,
-      "loss": 0.5178,
+      "loss": 0.6165,
       "step": 20
     },
     {
       "epoch": 0.054078413699864804,
-      "grad_norm": 41.4888801574707,
+      "grad_norm": 226.8269500732422,
       "learning_rate": 4.945848375451264e-05,
-      "loss": 0.5092,
+      "loss": 0.5151,
       "step": 30
     },
     {
       "epoch": 0.07210455159981974,
-      "grad_norm": 25.77608299255371,
+      "grad_norm": 21.70491600036621,
       "learning_rate": 4.927797833935018e-05,
-      "loss": 0.5581,
+      "loss": 0.5669,
       "step": 40
     },
     {
       "epoch": 0.09013068949977468,
-      "grad_norm": 61.5268669128418,
+      "grad_norm": 79.27781677246094,
       "learning_rate": 4.909747292418773e-05,
-      "loss": 0.5132,
+      "loss": 0.5119,
       "step": 50
     },
     {
       "epoch": 0.10815682739972961,
-      "grad_norm": 18.218244552612305,
+      "grad_norm": 15.314950942993164,
       "learning_rate": 4.891696750902527e-05,
-      "loss": 0.4614,
+      "loss": 0.474,
       "step": 60
     },
     {
       "epoch": 0.12618296529968454,
-      "grad_norm": 30.51982879638672,
+      "grad_norm": 25.575763702392578,
       "learning_rate": 4.873646209386282e-05,
-      "loss": 0.4648,
+      "loss": 0.478,
       "step": 70
     },
     {
       "epoch": 0.14420910319963948,
-      "grad_norm": 20.707260131835938,
+      "grad_norm": 27.453636169433594,
       "learning_rate": 4.855595667870036e-05,
-      "loss": 0.4317,
+      "loss": 0.4285,
       "step": 80
     },
     {
       "epoch": 0.16223524109959442,
-      "grad_norm": 21.699357986450195,
+      "grad_norm": 34.88062286376953,
       "learning_rate": 4.837545126353791e-05,
-      "loss": 0.4226,
+      "loss": 0.4317,
       "step": 90
     },
     {
       "epoch": 0.18026137899954936,
-      "grad_norm": 51.80731201171875,
+      "grad_norm": 46.823577880859375,
       "learning_rate": 4.819494584837546e-05,
-      "loss": 0.5002,
+      "loss": 0.4899,
       "step": 100
     },
     {
       "epoch": 0.19828751689950427,
-      "grad_norm": 44.694942474365234,
+      "grad_norm": 36.73914337158203,
       "learning_rate": 4.8014440433213e-05,
-      "loss": 0.4933,
+      "loss": 0.4839,
       "step": 110
     },
     {
       "epoch": 0.21631365479945922,
-      "grad_norm": 22.704530715942383,
+      "grad_norm": 102.61051940917969,
       "learning_rate": 4.783393501805055e-05,
-      "loss": 0.4399,
+      "loss": 0.4795,
       "step": 120
     },
     {
       "epoch": 0.23433979269941416,
-      "grad_norm": 26.04544448852539,
+      "grad_norm": 24.9108829498291,
       "learning_rate": 4.765342960288809e-05,
-      "loss": 0.438,
+      "loss": 0.4332,
       "step": 130
     },
     {
       "epoch": 0.25236593059936907,
-      "grad_norm": 14.642335891723633,
+      "grad_norm": 14.366719245910645,
       "learning_rate": 4.747292418772563e-05,
-      "loss": 0.4591,
+      "loss": 0.4811,
       "step": 140
     },
     {
       "epoch": 0.270392068499324,
-      "grad_norm": 16.13884162902832,
+      "grad_norm": 19.95521354675293,
       "learning_rate": 4.7292418772563177e-05,
-      "loss": 0.4546,
+      "loss": 0.4544,
       "step": 150
     },
     {
       "epoch": 0.28841820639927895,
-      "grad_norm": 29.33772087097168,
+      "grad_norm": 20.914020538330078,
       "learning_rate": 4.711191335740072e-05,
-      "loss": 0.4665,
+      "loss": 0.4646,
       "step": 160
     },
     {
       "epoch": 0.3064443442992339,
-      "grad_norm": 15.900433540344238,
+      "grad_norm": 154.6277313232422,
       "learning_rate": 4.693140794223827e-05,
-      "loss": 0.4703,
+      "loss": 0.47,
       "step": 170
     },
     {
       "epoch": 0.32447048219918884,
-      "grad_norm": 17.246356964111328,
+      "grad_norm": 30.73076820373535,
       "learning_rate": 4.675090252707581e-05,
-      "loss": 0.426,
+      "loss": 0.4341,
       "step": 180
     },
     {
       "epoch": 0.3424966200991438,
-      "grad_norm": 25.457477569580078,
+      "grad_norm": 14.621489524841309,
       "learning_rate": 4.657039711191336e-05,
-      "loss": 0.4711,
+      "loss": 0.5163,
       "step": 190
     },
     {
       "epoch": 0.3605227579990987,
-      "grad_norm": 25.43963050842285,
+      "grad_norm": 25.546030044555664,
       "learning_rate": 4.63898916967509e-05,
-      "loss": 0.4547,
+      "loss": 0.4601,
       "step": 200
     },
     {
       "epoch": 0.3785488958990536,
-      "grad_norm": 32.49702072143555,
+      "grad_norm": 18.222177505493164,
       "learning_rate": 4.620938628158845e-05,
-      "loss": 0.4603,
+      "loss": 0.4398,
       "step": 210
     },
     {
       "epoch": 0.39657503379900855,
-      "grad_norm": 52.78520965576172,
+      "grad_norm": 20.1109676361084,
       "learning_rate": 4.602888086642599e-05,
-      "loss": 0.4471,
+      "loss": 0.432,
       "step": 220
     },
     {
       "epoch": 0.4146011716989635,
-      "grad_norm": 16.70362663269043,
+      "grad_norm": 13.729535102844238,
       "learning_rate": 4.584837545126354e-05,
-      "loss": 0.4393,
+      "loss": 0.4327,
       "step": 230
     },
     {
       "epoch": 0.43262730959891843,
-      "grad_norm": 23.55246353149414,
+      "grad_norm": 32.50856018066406,
       "learning_rate": 4.566787003610109e-05,
-      "loss": 0.4256,
+      "loss": 0.4208,
       "step": 240
     },
     {
       "epoch": 0.45065344749887337,
-      "grad_norm": 18.868804931640625,
+      "grad_norm": 15.05933666229248,
       "learning_rate": 4.548736462093863e-05,
-      "loss": 0.4324,
+      "loss": 0.4451,
       "step": 250
     },
     {
       "epoch": 0.4686795853988283,
-      "grad_norm": 19.074827194213867,
+      "grad_norm": 31.787078857421875,
       "learning_rate": 4.530685920577618e-05,
-      "loss": 0.4419,
+      "loss": 0.4376,
       "step": 260
     },
     {
       "epoch": 0.48670572329878325,
-      "grad_norm": 29.232803344726562,
+      "grad_norm": 25.446210861206055,
       "learning_rate": 4.5126353790613716e-05,
-      "loss": 0.4179,
+      "loss": 0.4131,
       "step": 270
     },
     {
       "epoch": 0.5047318611987381,
-      "grad_norm": 17.780059814453125,
+      "grad_norm": 31.328969955444336,
       "learning_rate": 4.494584837545127e-05,
-      "loss": 0.3917,
+      "loss": 0.4194,
       "step": 280
     },
     {
       "epoch": 0.5227579990986931,
-      "grad_norm": 13.99399471282959,
+      "grad_norm": 255.53672790527344,
       "learning_rate": 4.4765342960288806e-05,
-      "loss": 0.4321,
+      "loss": 0.4984,
       "step": 290
     },
     {
       "epoch": 0.540784136998648,
-      "grad_norm": 14.700942039489746,
+      "grad_norm": 14.31953239440918,
       "learning_rate": 4.458483754512636e-05,
-      "loss": 0.4163,
+      "loss": 0.4417,
       "step": 300
     },
     {
       "epoch": 0.558810274898603,
-      "grad_norm": 17.43704605102539,
+      "grad_norm": 26.942129135131836,
       "learning_rate": 4.44043321299639e-05,
-      "loss": 0.4268,
+      "loss": 0.4527,
       "step": 310
     },
     {
       "epoch": 0.5768364127985579,
-      "grad_norm": 28.500301361083984,
+      "grad_norm": 36.217586517333984,
       "learning_rate": 4.422382671480145e-05,
-      "loss": 0.4229,
+      "loss": 0.4485,
       "step": 320
     },
     {
       "epoch": 0.5948625506985128,
-      "grad_norm": 36.14088439941406,
+      "grad_norm": 38.54646682739258,
       "learning_rate": 4.404332129963899e-05,
-      "loss": 0.4559,
+      "loss": 0.4579,
       "step": 330
     },
     {
       "epoch": 0.6128886885984678,
-      "grad_norm": 15.279230117797852,
+      "grad_norm": 21.504106521606445,
       "learning_rate": 4.386281588447654e-05,
-      "loss": 0.4067,
+      "loss": 0.4117,
       "step": 340
     },
     {
       "epoch": 0.6309148264984227,
-      "grad_norm": 21.569740295410156,
+      "grad_norm": 16.283788681030273,
       "learning_rate": 4.368231046931408e-05,
-      "loss": 0.4298,
+      "loss": 0.438,
       "step": 350
     },
     {
       "epoch": 0.6489409643983777,
-      "grad_norm": 20.630115509033203,
+      "grad_norm": 33.57164001464844,
       "learning_rate": 4.350180505415163e-05,
-      "loss": 0.4173,
+      "loss": 0.4043,
       "step": 360
     },
     {
       "epoch": 0.6669671022983326,
-      "grad_norm": 15.515020370483398,
+      "grad_norm": 12.821700096130371,
       "learning_rate": 4.332129963898917e-05,
-      "loss": 0.4063,
+      "loss": 0.4119,
       "step": 370
     },
     {
       "epoch": 0.6849932401982876,
-      "grad_norm": 16.33180046081543,
+      "grad_norm": 23.477996826171875,
       "learning_rate": 4.314079422382672e-05,
-      "loss": 0.3651,
+      "loss": 0.3783,
       "step": 380
     },
     {
       "epoch": 0.7030193780982424,
-      "grad_norm": 16.77664566040039,
+      "grad_norm": 18.2862548828125,
       "learning_rate": 4.296028880866426e-05,
-      "loss": 0.3879,
+      "loss": 0.4023,
       "step": 390
     },
     {
       "epoch": 0.7210455159981974,
-      "grad_norm": 11.113824844360352,
+      "grad_norm": 19.799530029296875,
       "learning_rate": 4.277978339350181e-05,
-      "loss": 0.4205,
+      "loss": 0.419,
       "step": 400
     },
     {
       "epoch": 0.7390716538981523,
-      "grad_norm": 17.835678100585938,
+      "grad_norm": 17.081830978393555,
       "learning_rate": 4.259927797833935e-05,
-      "loss": 0.4466,
+      "loss": 0.467,
       "step": 410
     },
     {
       "epoch": 0.7570977917981072,
-      "grad_norm": 24.48379135131836,
+      "grad_norm": 24.008344650268555,
       "learning_rate": 4.24187725631769e-05,
-      "loss": 0.4084,
+      "loss": 0.4302,
       "step": 420
     },
     {
       "epoch": 0.7751239296980622,
-      "grad_norm": 29.183530807495117,
+      "grad_norm": 40.07936477661133,
       "learning_rate": 4.223826714801444e-05,
-      "loss": 0.3588,
+      "loss": 0.3622,
       "step": 430
     },
     {
       "epoch": 0.7931500675980171,
-      "grad_norm": 16.398386001586914,
+      "grad_norm": 19.614171981811523,
       "learning_rate": 4.205776173285199e-05,
-      "loss": 0.4594,
+      "loss": 0.4645,
       "step": 440
     },
     {
       "epoch": 0.8111762054979721,
-      "grad_norm": 24.11660385131836,
+      "grad_norm": 32.0594596862793,
       "learning_rate": 4.187725631768953e-05,
-      "loss": 0.376,
+      "loss": 0.3755,
       "step": 450
     },
     {
       "epoch": 0.829202343397927,
-      "grad_norm": 21.480924606323242,
+      "grad_norm": 15.177023887634277,
       "learning_rate": 4.169675090252708e-05,
-      "loss": 0.4035,
+      "loss": 0.4275,
       "step": 460
     },
     {
       "epoch": 0.847228481297882,
-      "grad_norm": 11.91422176361084,
+      "grad_norm": 11.258400917053223,
       "learning_rate": 4.151624548736462e-05,
-      "loss": 0.4074,
+      "loss": 0.4137,
       "step": 470
     },
     {
       "epoch": 0.8652546191978369,
-      "grad_norm": 17.17136001586914,
+      "grad_norm": 13.211421012878418,
       "learning_rate": 4.1335740072202167e-05,
-      "loss": 0.4259,
+      "loss": 0.4337,
       "step": 480
     },
     {
       "epoch": 0.8832807570977917,
-      "grad_norm": 15.024781227111816,
+      "grad_norm": 14.50296401977539,
       "learning_rate": 4.115523465703972e-05,
-      "loss": 0.413,
+      "loss": 0.4318,
       "step": 490
     },
     {
       "epoch": 0.9013068949977467,
-      "grad_norm": 15.877848625183105,
+      "grad_norm": 21.239362716674805,
       "learning_rate": 4.0974729241877256e-05,
-      "loss": 0.4013,
+      "loss": 0.3939,
       "step": 500
     },
     {
       "epoch": 0.9193330328977016,
-      "grad_norm": 20.711393356323242,
+      "grad_norm": 18.6204891204834,
       "learning_rate": 4.079422382671481e-05,
-      "loss": 0.3875,
+      "loss": 0.3838,
       "step": 510
     },
     {
       "epoch": 0.9373591707976566,
-      "grad_norm": 14.360701560974121,
+      "grad_norm": 21.722551345825195,
       "learning_rate": 4.0613718411552346e-05,
-      "loss": 0.4025,
+      "loss": 0.4236,
       "step": 520
     },
     {
       "epoch": 0.9553853086976115,
-      "grad_norm": 16.94271469116211,
+      "grad_norm": 23.824357986450195,
       "learning_rate": 4.043321299638989e-05,
-      "loss": 0.3971,
+      "loss": 0.4062,
       "step": 530
     },
     {
       "epoch": 0.9734114465975665,
-      "grad_norm": 23.218050003051758,
+      "grad_norm": 18.93727684020996,
       "learning_rate": 4.0252707581227436e-05,
-      "loss": 0.4305,
+      "loss": 0.4412,
       "step": 540
     },
     {
       "epoch": 0.9914375844975214,
-      "grad_norm": 25.439455032348633,
+      "grad_norm": 16.050817489624023,
       "learning_rate": 4.007220216606498e-05,
-      "loss": 0.3969,
+      "loss": 0.4142,
       "step": 550
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.8410362694300518,
-      "eval_loss": 0.36654186248779297,
-      "eval_precision": 0.7994483845547675,
-      "eval_recall": 0.8871884564932225,
-      "eval_runtime": 77.9824,
-      "eval_samples_per_second": 59.924,
-      "eval_steps_per_second": 7.502,
+      "eval_f1": 0.8390086641144469,
+      "eval_fn": 205,
+      "eval_fp": 594,
+      "eval_loss": 0.3744712173938751,
+      "eval_precision": 0.7780269058295964,
+      "eval_recall": 0.910362920857018,
+      "eval_runtime": 73.1391,
+      "eval_samples_per_second": 63.892,
+      "eval_steps_per_second": 7.998,
+      "eval_tn": 1792,
+      "eval_tp": 2082,
       "step": 555
     }
   ],

checkpoint-555/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd360ff6566a7421740b08164da56480ee843ecd9962d79899c9150e4be0d68e
+oid sha256:810629f6569bf22bd4122bdaa88d9cc0d6cea1b331667027a3cd4891b919dd14
 size 5432