Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e25373df5edc238dbf538c9d6b0eeeb1d527cd776721216fef2c7d314232c2
+oid sha256:177e0b34b90401023e43089ae9758dc71eba73077227428059afc4d40b5fb2cf
 size 343230128

tmp-checkpoint-3344/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:679b8a720834f32a37a026843f6ba683c0b8ce557938fc12081fe935cd4db184
+oid sha256:177e0b34b90401023e43089ae9758dc71eba73077227428059afc4d40b5fb2cf
 size 343230128

tmp-checkpoint-3344/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f317cfd8349e8ee2d029f9aa88d2e4339ce123e13bf0841c1d01b7e89692de
+oid sha256:946b371afd81e4ae0577536945428e4811abda8e8b6b531621f969f2f6f503c8
 size 686581178

tmp-checkpoint-3344/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:990a9bc979f688068fc78acf887df48beba53924abcc2be46c815a142d69552d
+oid sha256:da81a52c24335a33bd7e915e12750c356e870f34ad1240d2be346252e1f2316b
 size 14244

tmp-checkpoint-3344/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.18664708733558655,
+  "best_metric": 0.18490658700466156,
   "best_model_checkpoint": "vit-base-patch16-224-in21k-crack-detectorVITmain50epochs\\checkpoint-3344",
   "epoch": 2.999775734469612,
   "eval_steps": 500,
@@ -11,2065 +11,2065 @@
     {
       "epoch": 0.01,
       "learning_rate": 8.976660682226213e-08,
-      "loss": 1.3944,
+      "loss": 1.3961,
       "step": 10
     },
     {
       "epoch": 0.02,
       "learning_rate": 1.7953321364452426e-07,
-      "loss": 1.3875,
+      "loss": 1.395,
       "step": 20
     },
     {
       "epoch": 0.03,
       "learning_rate": 2.692998204667864e-07,
-      "loss": 1.3999,
+      "loss": 1.3978,
       "step": 30
     },
     {
       "epoch": 0.04,
       "learning_rate": 3.590664272890485e-07,
-      "loss": 1.3915,
+      "loss": 1.3963,
       "step": 40
     },
     {
       "epoch": 0.04,
       "learning_rate": 4.4883303411131064e-07,
-      "loss": 1.3856,
+      "loss": 1.3907,
       "step": 50
     },
     {
       "epoch": 0.05,
       "learning_rate": 5.385996409335728e-07,
-      "loss": 1.3912,
+      "loss": 1.396,
       "step": 60
     },
     {
       "epoch": 0.06,
       "learning_rate": 6.283662477558349e-07,
-      "loss": 1.3902,
+      "loss": 1.3885,
       "step": 70
     },
     {
       "epoch": 0.07,
       "learning_rate": 7.18132854578097e-07,
-      "loss": 1.3851,
+      "loss": 1.387,
       "step": 80
     },
     {
       "epoch": 0.08,
       "learning_rate": 8.078994614003591e-07,
-      "loss": 1.3755,
+      "loss": 1.3894,
       "step": 90
     },
     {
       "epoch": 0.09,
       "learning_rate": 8.976660682226213e-07,
-      "loss": 1.3793,
+      "loss": 1.3806,
       "step": 100
     },
     {
       "epoch": 0.1,
       "learning_rate": 9.874326750448833e-07,
-      "loss": 1.3737,
+      "loss": 1.383,
       "step": 110
     },
     {
       "epoch": 0.11,
       "learning_rate": 1.0771992818671456e-06,
-      "loss": 1.3736,
+      "loss": 1.3764,
       "step": 120
     },
     {
       "epoch": 0.12,
       "learning_rate": 1.1669658886894075e-06,
-      "loss": 1.3678,
+      "loss": 1.3688,
       "step": 130
     },
     {
       "epoch": 0.13,
       "learning_rate": 1.2567324955116697e-06,
-      "loss": 1.3637,
+      "loss": 1.3708,
       "step": 140
     },
     {
       "epoch": 0.13,
       "learning_rate": 1.3464991023339318e-06,
-      "loss": 1.357,
+      "loss": 1.366,
       "step": 150
     },
     {
       "epoch": 0.14,
       "learning_rate": 1.436265709156194e-06,
-      "loss": 1.3583,
+      "loss": 1.371,
       "step": 160
     },
     {
       "epoch": 0.15,
       "learning_rate": 1.5260323159784561e-06,
-      "loss": 1.361,
+      "loss": 1.3558,
       "step": 170
     },
     {
       "epoch": 0.16,
       "learning_rate": 1.6157989228007182e-06,
-      "loss": 1.3517,
+      "loss": 1.3584,
       "step": 180
     },
     {
       "epoch": 0.17,
       "learning_rate": 1.7055655296229805e-06,
-      "loss": 1.3543,
+      "loss": 1.3409,
       "step": 190
     },
     {
       "epoch": 0.18,
       "learning_rate": 1.7953321364452425e-06,
-      "loss": 1.3497,
+      "loss": 1.346,
       "step": 200
     },
     {
       "epoch": 0.19,
       "learning_rate": 1.8850987432675046e-06,
-      "loss": 1.3436,
+      "loss": 1.3355,
       "step": 210
     },
     {
       "epoch": 0.2,
       "learning_rate": 1.9748653500897667e-06,
-      "loss": 1.3304,
+      "loss": 1.3323,
       "step": 220
     },
     {
       "epoch": 0.21,
       "learning_rate": 2.064631956912029e-06,
-      "loss": 1.3262,
+      "loss": 1.3231,
       "step": 230
     },
     {
       "epoch": 0.22,
       "learning_rate": 2.1543985637342912e-06,
-      "loss": 1.3209,
+      "loss": 1.3129,
       "step": 240
     },
     {
       "epoch": 0.22,
       "learning_rate": 2.244165170556553e-06,
-      "loss": 1.3054,
+      "loss": 1.3178,
       "step": 250
     },
     {
       "epoch": 0.23,
       "learning_rate": 2.333931777378815e-06,
-      "loss": 1.3028,
+      "loss": 1.2953,
       "step": 260
     },
     {
       "epoch": 0.24,
       "learning_rate": 2.423698384201077e-06,
-      "loss": 1.2939,
+      "loss": 1.2938,
       "step": 270
     },
     {
       "epoch": 0.25,
       "learning_rate": 2.5134649910233395e-06,
-      "loss": 1.2894,
+      "loss": 1.2849,
       "step": 280
     },
     {
       "epoch": 0.26,
       "learning_rate": 2.6032315978456015e-06,
-      "loss": 1.2838,
+      "loss": 1.2813,
       "step": 290
     },
     {
       "epoch": 0.27,
       "learning_rate": 2.6929982046678636e-06,
-      "loss": 1.2625,
+      "loss": 1.2811,
       "step": 300
     },
     {
       "epoch": 0.28,
       "learning_rate": 2.7827648114901257e-06,
-      "loss": 1.2727,
+      "loss": 1.2526,
       "step": 310
     },
     {
       "epoch": 0.29,
       "learning_rate": 2.872531418312388e-06,
-      "loss": 1.2398,
+      "loss": 1.2438,
       "step": 320
     },
     {
       "epoch": 0.3,
       "learning_rate": 2.9622980251346502e-06,
-      "loss": 1.2267,
+      "loss": 1.2145,
       "step": 330
     },
     {
       "epoch": 0.31,
       "learning_rate": 3.0520646319569123e-06,
-      "loss": 1.2359,
+      "loss": 1.2146,
       "step": 340
     },
     {
       "epoch": 0.31,
       "learning_rate": 3.1418312387791743e-06,
-      "loss": 1.218,
+      "loss": 1.1883,
       "step": 350
     },
     {
       "epoch": 0.32,
       "learning_rate": 3.2315978456014364e-06,
-      "loss": 1.1877,
+      "loss": 1.1891,
       "step": 360
     },
     {
       "epoch": 0.33,
       "learning_rate": 3.321364452423698e-06,
-      "loss": 1.1764,
+      "loss": 1.1723,
       "step": 370
     },
     {
       "epoch": 0.34,
       "learning_rate": 3.411131059245961e-06,
-      "loss": 1.151,
+      "loss": 1.1417,
       "step": 380
     },
     {
       "epoch": 0.35,
       "learning_rate": 3.500897666068223e-06,
-      "loss": 1.1334,
+      "loss": 1.1338,
       "step": 390
     },
     {
       "epoch": 0.36,
       "learning_rate": 3.590664272890485e-06,
-      "loss": 1.1272,
+      "loss": 1.1004,
       "step": 400
     },
     {
       "epoch": 0.37,
       "learning_rate": 3.680430879712747e-06,
-      "loss": 1.1077,
+      "loss": 1.0873,
       "step": 410
     },
     {
       "epoch": 0.38,
       "learning_rate": 3.770197486535009e-06,
-      "loss": 1.1021,
+      "loss": 1.0358,
       "step": 420
     },
     {
       "epoch": 0.39,
       "learning_rate": 3.859964093357271e-06,
-      "loss": 1.0583,
+      "loss": 1.0517,
       "step": 430
     },
     {
       "epoch": 0.39,
       "learning_rate": 3.949730700179533e-06,
-      "loss": 1.0482,
+      "loss": 1.0139,
       "step": 440
     },
     {
       "epoch": 0.4,
       "learning_rate": 4.039497307001795e-06,
-      "loss": 1.0214,
+      "loss": 1.0294,
       "step": 450
     },
     {
       "epoch": 0.41,
       "learning_rate": 4.129263913824058e-06,
-      "loss": 1.0114,
+      "loss": 1.0171,
       "step": 460
     },
     {
       "epoch": 0.42,
       "learning_rate": 4.21903052064632e-06,
-      "loss": 1.0237,
+      "loss": 0.9827,
       "step": 470
     },
     {
       "epoch": 0.43,
       "learning_rate": 4.3087971274685824e-06,
-      "loss": 0.969,
+      "loss": 0.9382,
       "step": 480
     },
     {
       "epoch": 0.44,
       "learning_rate": 4.3985637342908445e-06,
-      "loss": 0.966,
+      "loss": 0.9145,
       "step": 490
     },
     {
       "epoch": 0.45,
       "learning_rate": 4.488330341113106e-06,
-      "loss": 0.9518,
+      "loss": 0.9276,
       "step": 500
     },
     {
       "epoch": 0.46,
       "learning_rate": 4.578096947935368e-06,
-      "loss": 0.9545,
+      "loss": 0.8801,
       "step": 510
     },
     {
       "epoch": 0.47,
       "learning_rate": 4.66786355475763e-06,
-      "loss": 0.9473,
+      "loss": 0.8906,
       "step": 520
     },
     {
       "epoch": 0.48,
       "learning_rate": 4.757630161579892e-06,
-      "loss": 0.9026,
+      "loss": 0.9025,
       "step": 530
     },
     {
       "epoch": 0.48,
       "learning_rate": 4.847396768402154e-06,
-      "loss": 0.8535,
+      "loss": 0.8621,
       "step": 540
     },
     {
       "epoch": 0.49,
       "learning_rate": 4.937163375224417e-06,
-      "loss": 0.8598,
+      "loss": 0.8653,
       "step": 550
     },
     {
       "epoch": 0.5,
       "learning_rate": 5.026929982046679e-06,
-      "loss": 0.8154,
+      "loss": 0.8292,
       "step": 560
     },
     {
       "epoch": 0.51,
       "learning_rate": 5.116696588868941e-06,
-      "loss": 0.8561,
+      "loss": 0.8195,
       "step": 570
     },
     {
       "epoch": 0.52,
       "learning_rate": 5.206463195691203e-06,
-      "loss": 0.7924,
+      "loss": 0.8026,
       "step": 580
     },
     {
       "epoch": 0.53,
       "learning_rate": 5.296229802513465e-06,
-      "loss": 0.7947,
+      "loss": 0.841,
       "step": 590
     },
     {
       "epoch": 0.54,
       "learning_rate": 5.385996409335727e-06,
-      "loss": 0.7999,
+      "loss": 0.778,
       "step": 600
     },
     {
       "epoch": 0.55,
       "learning_rate": 5.475763016157989e-06,
-      "loss": 0.7771,
+      "loss": 0.7706,
       "step": 610
     },
     {
       "epoch": 0.56,
       "learning_rate": 5.565529622980251e-06,
-      "loss": 0.7826,
+      "loss": 0.733,
       "step": 620
     },
     {
       "epoch": 0.57,
       "learning_rate": 5.655296229802514e-06,
-      "loss": 0.7321,
+      "loss": 0.7437,
       "step": 630
     },
     {
       "epoch": 0.57,
       "learning_rate": 5.745062836624776e-06,
-      "loss": 0.7689,
+      "loss": 0.7644,
       "step": 640
     },
     {
       "epoch": 0.58,
       "learning_rate": 5.834829443447038e-06,
-      "loss": 0.7546,
+      "loss": 0.7125,
       "step": 650
     },
     {
       "epoch": 0.59,
       "learning_rate": 5.9245960502693004e-06,
-      "loss": 0.7336,
+      "loss": 0.7146,
       "step": 660
     },
     {
       "epoch": 0.6,
       "learning_rate": 6.0143626570915625e-06,
-      "loss": 0.6889,
+      "loss": 0.7201,
       "step": 670
     },
     {
       "epoch": 0.61,
       "learning_rate": 6.1041292639138246e-06,
-      "loss": 0.6996,
+      "loss": 0.6851,
       "step": 680
     },
     {
       "epoch": 0.62,
       "learning_rate": 6.193895870736087e-06,
-      "loss": 0.6994,
+      "loss": 0.6417,
       "step": 690
     },
     {
       "epoch": 0.63,
       "learning_rate": 6.283662477558349e-06,
-      "loss": 0.74,
+      "loss": 0.6656,
       "step": 700
     },
     {
       "epoch": 0.64,
       "learning_rate": 6.373429084380611e-06,
-      "loss": 0.711,
+      "loss": 0.6122,
       "step": 710
     },
     {
       "epoch": 0.65,
       "learning_rate": 6.463195691202873e-06,
-      "loss": 0.6765,
+      "loss": 0.6536,
       "step": 720
     },
     {
       "epoch": 0.65,
       "learning_rate": 6.552962298025135e-06,
-      "loss": 0.6717,
+      "loss": 0.6315,
       "step": 730
     },
     {
       "epoch": 0.66,
       "learning_rate": 6.642728904847396e-06,
-      "loss": 0.6776,
+      "loss": 0.6618,
       "step": 740
     },
     {
       "epoch": 0.67,
       "learning_rate": 6.732495511669659e-06,
-      "loss": 0.62,
+      "loss": 0.6346,
       "step": 750
     },
     {
       "epoch": 0.68,
       "learning_rate": 6.822262118491922e-06,
-      "loss": 0.6392,
+      "loss": 0.6866,
       "step": 760
     },
     {
       "epoch": 0.69,
       "learning_rate": 6.912028725314183e-06,
-      "loss": 0.62,
+      "loss": 0.6093,
       "step": 770
     },
     {
       "epoch": 0.7,
       "learning_rate": 7.001795332136446e-06,
-      "loss": 0.6103,
+      "loss": 0.6116,
       "step": 780
     },
     {
       "epoch": 0.71,
       "learning_rate": 7.091561938958707e-06,
-      "loss": 0.6504,
+      "loss": 0.602,
       "step": 790
     },
     {
       "epoch": 0.72,
       "learning_rate": 7.18132854578097e-06,
-      "loss": 0.6126,
+      "loss": 0.6266,
       "step": 800
     },
     {
       "epoch": 0.73,
       "learning_rate": 7.271095152603231e-06,
-      "loss": 0.5707,
+      "loss": 0.6082,
       "step": 810
     },
     {
       "epoch": 0.74,
       "learning_rate": 7.360861759425494e-06,
-      "loss": 0.587,
+      "loss": 0.6194,
       "step": 820
     },
     {
       "epoch": 0.74,
       "learning_rate": 7.4506283662477555e-06,
-      "loss": 0.5684,
+      "loss": 0.6277,
       "step": 830
     },
     {
       "epoch": 0.75,
       "learning_rate": 7.540394973070018e-06,
-      "loss": 0.5586,
+      "loss": 0.609,
       "step": 840
     },
     {
       "epoch": 0.76,
       "learning_rate": 7.630161579892281e-06,
-      "loss": 0.6074,
+      "loss": 0.6252,
       "step": 850
     },
     {
       "epoch": 0.77,
       "learning_rate": 7.719928186714543e-06,
-      "loss": 0.5638,
+      "loss": 0.5813,
       "step": 860
     },
     {
       "epoch": 0.78,
       "learning_rate": 7.809694793536805e-06,
-      "loss": 0.5952,
+      "loss": 0.5799,
       "step": 870
     },
     {
       "epoch": 0.79,
       "learning_rate": 7.899461400359067e-06,
-      "loss": 0.5647,
+      "loss": 0.6398,
       "step": 880
     },
     {
       "epoch": 0.8,
       "learning_rate": 7.98922800718133e-06,
-      "loss": 0.6049,
+      "loss": 0.5549,
       "step": 890
     },
     {
       "epoch": 0.81,
       "learning_rate": 8.07899461400359e-06,
-      "loss": 0.5525,
+      "loss": 0.6023,
       "step": 900
     },
     {
       "epoch": 0.82,
       "learning_rate": 8.168761220825854e-06,
-      "loss": 0.522,
+      "loss": 0.582,
       "step": 910
     },
     {
       "epoch": 0.83,
       "learning_rate": 8.258527827648117e-06,
-      "loss": 0.5489,
+      "loss": 0.544,
       "step": 920
     },
     {
       "epoch": 0.83,
       "learning_rate": 8.348294434470378e-06,
-      "loss": 0.5394,
+      "loss": 0.5912,
       "step": 930
     },
     {
       "epoch": 0.84,
       "learning_rate": 8.43806104129264e-06,
-      "loss": 0.5707,
+      "loss": 0.5461,
       "step": 940
     },
     {
       "epoch": 0.85,
       "learning_rate": 8.527827648114902e-06,
-      "loss": 0.5322,
+      "loss": 0.5238,
       "step": 950
     },
     {
       "epoch": 0.86,
       "learning_rate": 8.617594254937165e-06,
-      "loss": 0.5637,
+      "loss": 0.5558,
       "step": 960
     },
     {
       "epoch": 0.87,
       "learning_rate": 8.707360861759426e-06,
-      "loss": 0.529,
+      "loss": 0.5371,
       "step": 970
     },
     {
       "epoch": 0.88,
       "learning_rate": 8.797127468581689e-06,
-      "loss": 0.51,
+      "loss": 0.5529,
       "step": 980
     },
     {
       "epoch": 0.89,
       "learning_rate": 8.88689407540395e-06,
-      "loss": 0.4844,
+      "loss": 0.5691,
       "step": 990
     },
     {
       "epoch": 0.9,
       "learning_rate": 8.976660682226211e-06,
-      "loss": 0.5349,
+      "loss": 0.5567,
       "step": 1000
     },
     {
       "epoch": 0.91,
       "learning_rate": 9.066427289048474e-06,
-      "loss": 0.5377,
+      "loss": 0.5135,
       "step": 1010
     },
     {
       "epoch": 0.92,
       "learning_rate": 9.156193895870736e-06,
-      "loss": 0.4985,
+      "loss": 0.5099,
       "step": 1020
     },
     {
       "epoch": 0.92,
       "learning_rate": 9.245960502692998e-06,
-      "loss": 0.5533,
+      "loss": 0.5422,
       "step": 1030
     },
     {
       "epoch": 0.93,
       "learning_rate": 9.33572710951526e-06,
-      "loss": 0.4955,
+      "loss": 0.5106,
       "step": 1040
     },
     {
       "epoch": 0.94,
       "learning_rate": 9.425493716337523e-06,
-      "loss": 0.541,
+      "loss": 0.4892,
       "step": 1050
     },
     {
       "epoch": 0.95,
       "learning_rate": 9.515260323159784e-06,
-      "loss": 0.4757,
+      "loss": 0.4541,
       "step": 1060
     },
     {
       "epoch": 0.96,
       "learning_rate": 9.605026929982047e-06,
-      "loss": 0.5478,
+      "loss": 0.4675,
       "step": 1070
     },
     {
       "epoch": 0.97,
       "learning_rate": 9.694793536804308e-06,
-      "loss": 0.5281,
+      "loss": 0.5123,
       "step": 1080
     },
     {
       "epoch": 0.98,
       "learning_rate": 9.784560143626571e-06,
-      "loss": 0.5187,
+      "loss": 0.5089,
       "step": 1090
     },
     {
       "epoch": 0.99,
       "learning_rate": 9.874326750448834e-06,
-      "loss": 0.4591,
+      "loss": 0.5233,
       "step": 1100
     },
     {
       "epoch": 1.0,
       "learning_rate": 9.964093357271095e-06,
-      "loss": 0.5344,
+      "loss": 0.5622,
       "step": 1110
     },
     {
       "epoch": 1.0,
       "eval_accuracy": {
-        "accuracy": 0.8744113029827315
+        "accuracy": 0.8736263736263736
       },
       "eval_f1": {
-        "f1": 0.8645201833830978
+        "f1": 0.8653360894930927
       },
-      "eval_loss": 0.40481075644493103,
+      "eval_loss": 0.4108576774597168,
       "eval_precision": {
-        "precision": 0.8668175457367389
+        "precision": 0.8669392826942903
       },
       "eval_recall": {
-        "recall": 0.8631211355155497
+        "recall": 0.8641606609285752
       },
-      "eval_runtime": 243.6123,
-      "eval_samples_per_second": 73.215,
-      "eval_steps_per_second": 4.577,
+      "eval_runtime": 236.9507,
+      "eval_samples_per_second": 75.273,
+      "eval_steps_per_second": 4.706,
       "step": 1114
     },
     {
       "epoch": 1.0,
       "learning_rate": 1.0053859964093358e-05,
-      "loss": 0.5092,
+      "loss": 0.4957,
       "step": 1120
     },
     {
       "epoch": 1.01,
       "learning_rate": 1.0143626570915619e-05,
-      "loss": 0.4834,
+      "loss": 0.5729,
       "step": 1130
     },
     {
       "epoch": 1.02,
       "learning_rate": 1.0233393177737882e-05,
-      "loss": 0.5403,
+      "loss": 0.4884,
       "step": 1140
     },
     {
       "epoch": 1.03,
       "learning_rate": 1.0323159784560143e-05,
-      "loss": 0.5109,
+      "loss": 0.4744,
       "step": 1150
     },
     {
       "epoch": 1.04,
       "learning_rate": 1.0412926391382406e-05,
-      "loss": 0.5002,
+      "loss": 0.4683,
       "step": 1160
     },
     {
       "epoch": 1.05,
       "learning_rate": 1.0502692998204669e-05,
-      "loss": 0.5052,
+      "loss": 0.5,
       "step": 1170
     },
     {
       "epoch": 1.06,
       "learning_rate": 1.059245960502693e-05,
-      "loss": 0.4642,
+      "loss": 0.4649,
       "step": 1180
     },
     {
       "epoch": 1.07,
       "learning_rate": 1.0682226211849193e-05,
-      "loss": 0.4479,
+      "loss": 0.508,
       "step": 1190
     },
     {
       "epoch": 1.08,
       "learning_rate": 1.0771992818671454e-05,
-      "loss": 0.4944,
+      "loss": 0.4898,
       "step": 1200
     },
     {
       "epoch": 1.09,
       "learning_rate": 1.0861759425493717e-05,
-      "loss": 0.4583,
+      "loss": 0.4722,
       "step": 1210
     },
     {
       "epoch": 1.09,
       "learning_rate": 1.0951526032315979e-05,
-      "loss": 0.4779,
+      "loss": 0.4814,
       "step": 1220
     },
     {
       "epoch": 1.1,
       "learning_rate": 1.1041292639138241e-05,
-      "loss": 0.5038,
+      "loss": 0.4505,
       "step": 1230
     },
     {
       "epoch": 1.11,
       "learning_rate": 1.1131059245960503e-05,
-      "loss": 0.4831,
+      "loss": 0.4505,
       "step": 1240
     },
     {
       "epoch": 1.12,
       "learning_rate": 1.1220825852782766e-05,
-      "loss": 0.4999,
+      "loss": 0.4187,
       "step": 1250
     },
     {
       "epoch": 1.13,
       "learning_rate": 1.1310592459605028e-05,
-      "loss": 0.4611,
+      "loss": 0.4603,
       "step": 1260
     },
     {
       "epoch": 1.14,
       "learning_rate": 1.140035906642729e-05,
-      "loss": 0.4775,
+      "loss": 0.4721,
       "step": 1270
     },
     {
       "epoch": 1.15,
       "learning_rate": 1.1490125673249553e-05,
-      "loss": 0.4388,
+      "loss": 0.4368,
       "step": 1280
     },
     {
       "epoch": 1.16,
       "learning_rate": 1.1579892280071814e-05,
-      "loss": 0.4374,
+      "loss": 0.4722,
       "step": 1290
     },
     {
       "epoch": 1.17,
       "learning_rate": 1.1669658886894077e-05,
-      "loss": 0.4608,
+      "loss": 0.4718,
       "step": 1300
     },
     {
       "epoch": 1.18,
       "learning_rate": 1.1759425493716338e-05,
-      "loss": 0.4973,
+      "loss": 0.4899,
       "step": 1310
     },
     {
       "epoch": 1.18,
       "learning_rate": 1.1849192100538601e-05,
-      "loss": 0.4387,
+      "loss": 0.4758,
       "step": 1320
     },
     {
       "epoch": 1.19,
       "learning_rate": 1.1938958707360862e-05,
-      "loss": 0.4617,
+      "loss": 0.4523,
       "step": 1330
     },
     {
       "epoch": 1.2,
       "learning_rate": 1.2028725314183125e-05,
-      "loss": 0.4631,
+      "loss": 0.485,
       "step": 1340
     },
     {
       "epoch": 1.21,
       "learning_rate": 1.2118491921005388e-05,
-      "loss": 0.4869,
+      "loss": 0.4977,
       "step": 1350
     },
     {
       "epoch": 1.22,
       "learning_rate": 1.2208258527827649e-05,
-      "loss": 0.4699,
+      "loss": 0.4305,
       "step": 1360
     },
     {
       "epoch": 1.23,
       "learning_rate": 1.2298025134649912e-05,
-      "loss": 0.482,
+      "loss": 0.4221,
       "step": 1370
     },
     {
       "epoch": 1.24,
       "learning_rate": 1.2387791741472173e-05,
-      "loss": 0.4067,
+      "loss": 0.4975,
       "step": 1380
     },
     {
       "epoch": 1.25,
       "learning_rate": 1.2477558348294434e-05,
-      "loss": 0.4218,
+      "loss": 0.4506,
       "step": 1390
     },
     {
       "epoch": 1.26,
       "learning_rate": 1.2567324955116697e-05,
-      "loss": 0.4643,
+      "loss": 0.4326,
       "step": 1400
     },
     {
       "epoch": 1.26,
       "learning_rate": 1.2657091561938959e-05,
-      "loss": 0.4317,
+      "loss": 0.4479,
       "step": 1410
     },
     {
       "epoch": 1.27,
       "learning_rate": 1.2746858168761221e-05,
-      "loss": 0.4303,
+      "loss": 0.4468,
       "step": 1420
     },
     {
       "epoch": 1.28,
       "learning_rate": 1.2836624775583483e-05,
-      "loss": 0.4247,
+      "loss": 0.402,
       "step": 1430
     },
     {
       "epoch": 1.29,
       "learning_rate": 1.2926391382405746e-05,
-      "loss": 0.4553,
+      "loss": 0.4711,
       "step": 1440
     },
     {
       "epoch": 1.3,
       "learning_rate": 1.3016157989228009e-05,
-      "loss": 0.4527,
+      "loss": 0.4686,
       "step": 1450
     },
     {
       "epoch": 1.31,
       "learning_rate": 1.310592459605027e-05,
-      "loss": 0.4216,
+      "loss": 0.4639,
       "step": 1460
     },
     {
       "epoch": 1.32,
       "learning_rate": 1.3195691202872531e-05,
-      "loss": 0.4481,
+      "loss": 0.435,
       "step": 1470
     },
     {
       "epoch": 1.33,
       "learning_rate": 1.3285457809694792e-05,
-      "loss": 0.3926,
+      "loss": 0.3868,
       "step": 1480
     },
     {
       "epoch": 1.34,
       "learning_rate": 1.3375224416517057e-05,
-      "loss": 0.4644,
+      "loss": 0.4303,
       "step": 1490
     },
     {
       "epoch": 1.35,
       "learning_rate": 1.3464991023339318e-05,
-      "loss": 0.4156,
+      "loss": 0.432,
       "step": 1500
     },
     {
       "epoch": 1.35,
       "learning_rate": 1.355475763016158e-05,
-      "loss": 0.4165,
+      "loss": 0.4206,
       "step": 1510
     },
     {
       "epoch": 1.36,
       "learning_rate": 1.3644524236983844e-05,
-      "loss": 0.427,
+      "loss": 0.4282,
       "step": 1520
     },
     {
       "epoch": 1.37,
       "learning_rate": 1.3734290843806105e-05,
-      "loss": 0.4229,
+      "loss": 0.4284,
       "step": 1530
     },
     {
       "epoch": 1.38,
       "learning_rate": 1.3824057450628366e-05,
-      "loss": 0.3961,
+      "loss": 0.4096,
       "step": 1540
     },
     {
       "epoch": 1.39,
       "learning_rate": 1.3913824057450627e-05,
-      "loss": 0.4438,
+      "loss": 0.4259,
       "step": 1550
     },
     {
       "epoch": 1.4,
       "learning_rate": 1.4003590664272892e-05,
-      "loss": 0.4037,
+      "loss": 0.4436,
       "step": 1560
     },
     {
       "epoch": 1.41,
       "learning_rate": 1.4093357271095153e-05,
-      "loss": 0.4341,
+      "loss": 0.4453,
       "step": 1570
     },
     {
       "epoch": 1.42,
       "learning_rate": 1.4183123877917415e-05,
-      "loss": 0.3715,
+      "loss": 0.4065,
       "step": 1580
     },
     {
       "epoch": 1.43,
       "learning_rate": 1.4272890484739679e-05,
-      "loss": 0.4292,
+      "loss": 0.4011,
       "step": 1590
     },
     {
       "epoch": 1.44,
       "learning_rate": 1.436265709156194e-05,
-      "loss": 0.4539,
+      "loss": 0.4488,
       "step": 1600
     },
     {
       "epoch": 1.44,
       "learning_rate": 1.4452423698384202e-05,
-      "loss": 0.409,
+      "loss": 0.4122,
       "step": 1610
     },
     {
       "epoch": 1.45,
       "learning_rate": 1.4542190305206463e-05,
-      "loss": 0.4473,
+      "loss": 0.429,
       "step": 1620
     },
     {
       "epoch": 1.46,
       "learning_rate": 1.4631956912028727e-05,
-      "loss": 0.4202,
+      "loss": 0.4377,
       "step": 1630
     },
     {
       "epoch": 1.47,
       "learning_rate": 1.4721723518850989e-05,
-      "loss": 0.3701,
+      "loss": 0.4186,
       "step": 1640
     },
     {
       "epoch": 1.48,
       "learning_rate": 1.481149012567325e-05,
-      "loss": 0.4451,
+      "loss": 0.4063,
       "step": 1650
     },
     {
       "epoch": 1.49,
       "learning_rate": 1.4901256732495511e-05,
-      "loss": 0.4216,
+      "loss": 0.4055,
       "step": 1660
     },
     {
       "epoch": 1.5,
       "learning_rate": 1.4991023339317776e-05,
-      "loss": 0.4116,
+      "loss": 0.4173,
       "step": 1670
     },
     {
       "epoch": 1.51,
       "learning_rate": 1.5080789946140037e-05,
-      "loss": 0.4006,
+      "loss": 0.4361,
       "step": 1680
     },
     {
       "epoch": 1.52,
       "learning_rate": 1.5170556552962298e-05,
-      "loss": 0.4303,
+      "loss": 0.4528,
       "step": 1690
     },
     {
       "epoch": 1.53,
       "learning_rate": 1.5260323159784563e-05,
-      "loss": 0.441,
+      "loss": 0.3665,
       "step": 1700
     },
     {
       "epoch": 1.53,
       "learning_rate": 1.5350089766606824e-05,
-      "loss": 0.4248,
+      "loss": 0.3913,
       "step": 1710
     },
     {
       "epoch": 1.54,
       "learning_rate": 1.5439856373429085e-05,
-      "loss": 0.3771,
+      "loss": 0.4002,
       "step": 1720
     },
     {
       "epoch": 1.55,
       "learning_rate": 1.5529622980251346e-05,
-      "loss": 0.4158,
+      "loss": 0.4004,
       "step": 1730
     },
     {
       "epoch": 1.56,
       "learning_rate": 1.561938958707361e-05,
-      "loss": 0.3815,
+      "loss": 0.4432,
       "step": 1740
     },
     {
       "epoch": 1.57,
       "learning_rate": 1.5709156193895872e-05,
-      "loss": 0.4204,
+      "loss": 0.3743,
       "step": 1750
     },
     {
       "epoch": 1.58,
       "learning_rate": 1.5798922800718133e-05,
-      "loss": 0.4886,
+      "loss": 0.3972,
       "step": 1760
     },
     {
       "epoch": 1.59,
       "learning_rate": 1.5888689407540398e-05,
-      "loss": 0.4382,
+      "loss": 0.368,
       "step": 1770
     },
     {
       "epoch": 1.6,
       "learning_rate": 1.597845601436266e-05,
-      "loss": 0.4502,
+      "loss": 0.4525,
       "step": 1780
     },
     {
       "epoch": 1.61,
       "learning_rate": 1.606822262118492e-05,
-      "loss": 0.4155,
+      "loss": 0.3962,
       "step": 1790
     },
     {
       "epoch": 1.61,
       "learning_rate": 1.615798922800718e-05,
-      "loss": 0.3801,
+      "loss": 0.3888,
       "step": 1800
     },
     {
       "epoch": 1.62,
       "learning_rate": 1.6247755834829446e-05,
-      "loss": 0.3968,
+      "loss": 0.4111,
       "step": 1810
     },
     {
       "epoch": 1.63,
       "learning_rate": 1.6337522441651707e-05,
-      "loss": 0.365,
+      "loss": 0.4084,
       "step": 1820
     },
     {
       "epoch": 1.64,
       "learning_rate": 1.642728904847397e-05,
-      "loss": 0.3638,
+      "loss": 0.4181,
       "step": 1830
     },
     {
       "epoch": 1.65,
       "learning_rate": 1.6517055655296233e-05,
-      "loss": 0.3935,
+      "loss": 0.4022,
       "step": 1840
     },
     {
       "epoch": 1.66,
       "learning_rate": 1.6606822262118494e-05,
-      "loss": 0.4092,
+      "loss": 0.3886,
       "step": 1850
     },
     {
       "epoch": 1.67,
       "learning_rate": 1.6696588868940756e-05,
-      "loss": 0.3617,
+      "loss": 0.4092,
       "step": 1860
     },
     {
       "epoch": 1.68,
       "learning_rate": 1.6786355475763017e-05,
-      "loss": 0.389,
+      "loss": 0.3843,
       "step": 1870
     },
     {
       "epoch": 1.69,
       "learning_rate": 1.687612208258528e-05,
-      "loss": 0.3357,
+      "loss": 0.4237,
       "step": 1880
     },
     {
       "epoch": 1.7,
       "learning_rate": 1.6965888689407543e-05,
-      "loss": 0.3925,
+      "loss": 0.3801,
       "step": 1890
     },
     {
       "epoch": 1.7,
       "learning_rate": 1.7055655296229804e-05,
-      "loss": 0.4186,
+      "loss": 0.385,
       "step": 1900
     },
     {
       "epoch": 1.71,
       "learning_rate": 1.7145421903052065e-05,
-      "loss": 0.3913,
+      "loss": 0.4452,
       "step": 1910
     },
     {
       "epoch": 1.72,
       "learning_rate": 1.723518850987433e-05,
-      "loss": 0.3679,
+      "loss": 0.5147,
       "step": 1920
     },
     {
       "epoch": 1.73,
       "learning_rate": 1.732495511669659e-05,
-      "loss": 0.4476,
+      "loss": 0.353,
       "step": 1930
     },
     {
       "epoch": 1.74,
       "learning_rate": 1.7414721723518852e-05,
-      "loss": 0.4065,
+      "loss": 0.3816,
       "step": 1940
     },
     {
       "epoch": 1.75,
       "learning_rate": 1.7504488330341113e-05,
-      "loss": 0.4079,
+      "loss": 0.361,
       "step": 1950
     },
     {
       "epoch": 1.76,
       "learning_rate": 1.7594254937163378e-05,
-      "loss": 0.3831,
+      "loss": 0.3884,
       "step": 1960
     },
     {
       "epoch": 1.77,
       "learning_rate": 1.768402154398564e-05,
-      "loss": 0.3985,
+      "loss": 0.3391,
       "step": 1970
     },
     {
       "epoch": 1.78,
       "learning_rate": 1.77737881508079e-05,
-      "loss": 0.3705,
+      "loss": 0.4211,
       "step": 1980
     },
     {
       "epoch": 1.79,
       "learning_rate": 1.786355475763016e-05,
-      "loss": 0.3742,
+      "loss": 0.3796,
       "step": 1990
     },
     {
       "epoch": 1.79,
       "learning_rate": 1.7953321364452423e-05,
-      "loss": 0.3517,
+      "loss": 0.3881,
       "step": 2000
     },
     {
       "epoch": 1.8,
       "learning_rate": 1.8043087971274687e-05,
-      "loss": 0.3871,
+      "loss": 0.3904,
       "step": 2010
     },
     {
       "epoch": 1.81,
       "learning_rate": 1.813285457809695e-05,
-      "loss": 0.3416,
+      "loss": 0.3845,
       "step": 2020
     },
     {
       "epoch": 1.82,
       "learning_rate": 1.822262118491921e-05,
-      "loss": 0.3856,
+      "loss": 0.3721,
       "step": 2030
     },
     {
       "epoch": 1.83,
       "learning_rate": 1.831238779174147e-05,
-      "loss": 0.4245,
+      "loss": 0.4141,
       "step": 2040
     },
     {
       "epoch": 1.84,
       "learning_rate": 1.8402154398563732e-05,
-      "loss": 0.3645,
+      "loss": 0.3682,
       "step": 2050
     },
     {
       "epoch": 1.85,
       "learning_rate": 1.8491921005385997e-05,
-      "loss": 0.3505,
+      "loss": 0.3826,
       "step": 2060
     },
     {
       "epoch": 1.86,
       "learning_rate": 1.8581687612208258e-05,
-      "loss": 0.3746,
+      "loss": 0.3588,
       "step": 2070
     },
     {
       "epoch": 1.87,
       "learning_rate": 1.867145421903052e-05,
-      "loss": 0.352,
+      "loss": 0.3663,
       "step": 2080
     },
     {
       "epoch": 1.87,
       "learning_rate": 1.8761220825852784e-05,
-      "loss": 0.4295,
+      "loss": 0.4186,
       "step": 2090
     },
     {
       "epoch": 1.88,
       "learning_rate": 1.8850987432675045e-05,
-      "loss": 0.387,
+      "loss": 0.3756,
       "step": 2100
     },
     {
       "epoch": 1.89,
       "learning_rate": 1.8940754039497306e-05,
-      "loss": 0.4056,
+      "loss": 0.3655,
       "step": 2110
     },
     {
       "epoch": 1.9,
       "learning_rate": 1.9030520646319568e-05,
-      "loss": 0.3913,
+      "loss": 0.4158,
       "step": 2120
     },
     {
       "epoch": 1.91,
       "learning_rate": 1.9120287253141832e-05,
-      "loss": 0.3789,
+      "loss": 0.3985,
       "step": 2130
     },
     {
       "epoch": 1.92,
       "learning_rate": 1.9210053859964093e-05,
-      "loss": 0.3688,
+      "loss": 0.3955,
       "step": 2140
     },
     {
       "epoch": 1.93,
       "learning_rate": 1.9299820466786355e-05,
-      "loss": 0.3499,
+      "loss": 0.3757,
       "step": 2150
     },
     {
       "epoch": 1.94,
       "learning_rate": 1.9389587073608616e-05,
-      "loss": 0.3153,
+      "loss": 0.3712,
       "step": 2160
     },
     {
       "epoch": 1.95,
       "learning_rate": 1.947935368043088e-05,
-      "loss": 0.3558,
+      "loss": 0.3723,
       "step": 2170
     },
     {
       "epoch": 1.96,
       "learning_rate": 1.9569120287253142e-05,
-      "loss": 0.3001,
+      "loss": 0.367,
       "step": 2180
     },
     {
       "epoch": 1.96,
       "learning_rate": 1.9658886894075403e-05,
-      "loss": 0.3109,
+      "loss": 0.3659,
       "step": 2190
     },
     {
       "epoch": 1.97,
       "learning_rate": 1.9748653500897668e-05,
-      "loss": 0.3377,
+      "loss": 0.3752,
       "step": 2200
     },
     {
       "epoch": 1.98,
       "learning_rate": 1.983842010771993e-05,
-      "loss": 0.3888,
+      "loss": 0.318,
       "step": 2210
     },
     {
       "epoch": 1.99,
       "learning_rate": 1.992818671454219e-05,
-      "loss": 0.3536,
+      "loss": 0.3696,
       "step": 2220
     },
     {
       "epoch": 2.0,
       "eval_accuracy": {
-        "accuracy": 0.9219555954249832
+        "accuracy": 0.9249271137026239
       },
       "eval_f1": {
-        "f1": 0.9164276462698699
+        "f1": 0.9207602119769538
       },
-      "eval_loss": 0.2440667599439621,
+      "eval_loss": 0.2492757886648178,
       "eval_precision": {
-        "precision": 0.9196643633917082
+        "precision": 0.9199949527238288
       },
       "eval_recall": {
-        "recall": 0.913748377704386
+        "recall": 0.9219224853720074
       },
-      "eval_runtime": 164.5475,
-      "eval_samples_per_second": 108.394,
-      "eval_steps_per_second": 6.776,
+      "eval_runtime": 166.1808,
+      "eval_samples_per_second": 107.329,
+      "eval_steps_per_second": 6.71,
       "step": 2229
     },
     {
       "epoch": 2.0,
       "learning_rate": 2.001795332136445e-05,
-      "loss": 0.3716,
+      "loss": 0.3681,
       "step": 2230
     },
     {
       "epoch": 2.01,
       "learning_rate": 2.0107719928186716e-05,
-      "loss": 0.3336,
+      "loss": 0.321,
       "step": 2240
     },
     {
       "epoch": 2.02,
       "learning_rate": 2.0197486535008977e-05,
-      "loss": 0.3309,
+      "loss": 0.332,
       "step": 2250
     },
     {
       "epoch": 2.03,
       "learning_rate": 2.0287253141831238e-05,
-      "loss": 0.4064,
+      "loss": 0.3343,
       "step": 2260
     },
     {
       "epoch": 2.04,
       "learning_rate": 2.0377019748653503e-05,
-      "loss": 0.33,
+      "loss": 0.3341,
       "step": 2270
     },
     {
       "epoch": 2.05,
       "learning_rate": 2.0466786355475764e-05,
-      "loss": 0.3911,
+      "loss": 0.3473,
       "step": 2280
     },
     {
       "epoch": 2.05,
       "learning_rate": 2.0556552962298025e-05,
-      "loss": 0.3405,
+      "loss": 0.3479,
       "step": 2290
     },
     {
       "epoch": 2.06,
       "learning_rate": 2.0646319569120286e-05,
-      "loss": 0.317,
+      "loss": 0.3235,
       "step": 2300
     },
     {
       "epoch": 2.07,
       "learning_rate": 2.073608617594255e-05,
-      "loss": 0.3305,
+      "loss": 0.3455,
       "step": 2310
     },
     {
       "epoch": 2.08,
       "learning_rate": 2.0825852782764812e-05,
-      "loss": 0.3201,
+      "loss": 0.3675,
       "step": 2320
     },
     {
       "epoch": 2.09,
       "learning_rate": 2.0915619389587073e-05,
-      "loss": 0.3107,
+      "loss": 0.3267,
       "step": 2330
     },
     {
       "epoch": 2.1,
       "learning_rate": 2.1005385996409338e-05,
-      "loss": 0.351,
+      "loss": 0.3588,
       "step": 2340
     },
     {
       "epoch": 2.11,
       "learning_rate": 2.10951526032316e-05,
-      "loss": 0.3181,
+      "loss": 0.3762,
       "step": 2350
     },
     {
       "epoch": 2.12,
       "learning_rate": 2.118491921005386e-05,
-      "loss": 0.3494,
+      "loss": 0.3474,
       "step": 2360
     },
     {
       "epoch": 2.13,
       "learning_rate": 2.1274685816876122e-05,
-      "loss": 0.3718,
+      "loss": 0.3614,
       "step": 2370
     },
     {
       "epoch": 2.14,
       "learning_rate": 2.1364452423698386e-05,
-      "loss": 0.34,
+      "loss": 0.3611,
       "step": 2380
     },
     {
       "epoch": 2.14,
       "learning_rate": 2.1454219030520648e-05,
-      "loss": 0.306,
+      "loss": 0.4051,
       "step": 2390
     },
     {
       "epoch": 2.15,
       "learning_rate": 2.154398563734291e-05,
-      "loss": 0.3147,
+      "loss": 0.3314,
       "step": 2400
     },
     {
       "epoch": 2.16,
       "learning_rate": 2.163375224416517e-05,
-      "loss": 0.2842,
+      "loss": 0.3427,
       "step": 2410
     },
     {
       "epoch": 2.17,
       "learning_rate": 2.1723518850987435e-05,
-      "loss": 0.3461,
+      "loss": 0.2886,
       "step": 2420
     },
     {
       "epoch": 2.18,
       "learning_rate": 2.1813285457809696e-05,
-      "loss": 0.3161,
+      "loss": 0.3262,
       "step": 2430
     },
     {
       "epoch": 2.19,
       "learning_rate": 2.1903052064631957e-05,
-      "loss": 0.3152,
+      "loss": 0.3516,
       "step": 2440
     },
     {
       "epoch": 2.2,
       "learning_rate": 2.199281867145422e-05,
-      "loss": 0.3104,
+      "loss": 0.3744,
       "step": 2450
     },
     {
       "epoch": 2.21,
       "learning_rate": 2.2082585278276483e-05,
-      "loss": 0.3485,
+      "loss": 0.3545,
       "step": 2460
     },
     {
       "epoch": 2.22,
       "learning_rate": 2.2172351885098744e-05,
-      "loss": 0.3682,
+      "loss": 0.2993,
       "step": 2470
     },
     {
       "epoch": 2.22,
       "learning_rate": 2.2262118491921005e-05,
-      "loss": 0.2831,
+      "loss": 0.3412,
       "step": 2480
     },
     {
       "epoch": 2.23,
       "learning_rate": 2.235188509874327e-05,
-      "loss": 0.3097,
+      "loss": 0.3823,
       "step": 2490
     },
     {
       "epoch": 2.24,
       "learning_rate": 2.244165170556553e-05,
-      "loss": 0.3433,
+      "loss": 0.3206,
       "step": 2500
     },
     {
       "epoch": 2.25,
       "learning_rate": 2.2531418312387792e-05,
-      "loss": 0.3319,
+      "loss": 0.2969,
       "step": 2510
     },
     {
       "epoch": 2.26,
       "learning_rate": 2.2621184919210057e-05,
-      "loss": 0.3236,
+      "loss": 0.3306,
       "step": 2520
     },
     {
       "epoch": 2.27,
       "learning_rate": 2.2710951526032318e-05,
-      "loss": 0.3531,
+      "loss": 0.3641,
       "step": 2530
     },
     {
       "epoch": 2.28,
       "learning_rate": 2.280071813285458e-05,
-      "loss": 0.2737,
+      "loss": 0.3588,
       "step": 2540
     },
     {
       "epoch": 2.29,
       "learning_rate": 2.289048473967684e-05,
-      "loss": 0.3774,
+      "loss": 0.3632,
       "step": 2550
     },
     {
       "epoch": 2.3,
       "learning_rate": 2.2980251346499105e-05,
-      "loss": 0.2936,
+      "loss": 0.3072,
       "step": 2560
     },
     {
       "epoch": 2.31,
       "learning_rate": 2.3070017953321366e-05,
-      "loss": 0.3015,
+      "loss": 0.3606,
       "step": 2570
     },
     {
       "epoch": 2.31,
       "learning_rate": 2.3159784560143628e-05,
-      "loss": 0.2933,
+      "loss": 0.4114,
       "step": 2580
     },
     {
       "epoch": 2.32,
       "learning_rate": 2.3249551166965892e-05,
-      "loss": 0.3348,
+      "loss": 0.282,
       "step": 2590
     },
     {
       "epoch": 2.33,
       "learning_rate": 2.3339317773788153e-05,
-      "loss": 0.3249,
+      "loss": 0.3336,
       "step": 2600
     },
     {
       "epoch": 2.34,
       "learning_rate": 2.3429084380610415e-05,
-      "loss": 0.3619,
+      "loss": 0.3406,
       "step": 2610
     },
     {
       "epoch": 2.35,
       "learning_rate": 2.3518850987432676e-05,
-      "loss": 0.3428,
+      "loss": 0.3433,
       "step": 2620
     },
     {
       "epoch": 2.36,
       "learning_rate": 2.360861759425494e-05,
-      "loss": 0.3425,
+      "loss": 0.3169,
       "step": 2630
     },
     {
       "epoch": 2.37,
       "learning_rate": 2.3698384201077202e-05,
-      "loss": 0.3027,
+      "loss": 0.3855,
       "step": 2640
     },
     {
       "epoch": 2.38,
       "learning_rate": 2.3788150807899463e-05,
-      "loss": 0.3723,
+      "loss": 0.3036,
       "step": 2650
     },
     {
       "epoch": 2.39,
       "learning_rate": 2.3877917414721724e-05,
-      "loss": 0.3813,
+      "loss": 0.3076,
       "step": 2660
     },
     {
       "epoch": 2.4,
       "learning_rate": 2.396768402154399e-05,
-      "loss": 0.3423,
+      "loss": 0.3052,
       "step": 2670
     },
     {
       "epoch": 2.4,
       "learning_rate": 2.405745062836625e-05,
-      "loss": 0.355,
+      "loss": 0.3253,
       "step": 2680
     },
     {
       "epoch": 2.41,
       "learning_rate": 2.414721723518851e-05,
-      "loss": 0.3047,
+      "loss": 0.3235,
       "step": 2690
     },
     {
       "epoch": 2.42,
       "learning_rate": 2.4236983842010776e-05,
-      "loss": 0.3049,
+      "loss": 0.2835,
       "step": 2700
     },
     {
       "epoch": 2.43,
       "learning_rate": 2.4326750448833037e-05,
-      "loss": 0.2876,
+      "loss": 0.2824,
       "step": 2710
     },
     {
       "epoch": 2.44,
       "learning_rate": 2.4416517055655298e-05,
-      "loss": 0.3166,
+      "loss": 0.3183,
       "step": 2720
     },
     {
       "epoch": 2.45,
       "learning_rate": 2.450628366247756e-05,
-      "loss": 0.3468,
+      "loss": 0.3281,
       "step": 2730
     },
     {
       "epoch": 2.46,
       "learning_rate": 2.4596050269299824e-05,
-      "loss": 0.3173,
+      "loss": 0.2939,
       "step": 2740
     },
     {
       "epoch": 2.47,
       "learning_rate": 2.4685816876122085e-05,
-      "loss": 0.3189,
+      "loss": 0.3679,
       "step": 2750
     },
     {
       "epoch": 2.48,
       "learning_rate": 2.4775583482944346e-05,
-      "loss": 0.3321,
+      "loss": 0.3165,
       "step": 2760
     },
     {
       "epoch": 2.48,
       "learning_rate": 2.4865350089766608e-05,
-      "loss": 0.3314,
+      "loss": 0.3146,
       "step": 2770
     },
     {
       "epoch": 2.49,
       "learning_rate": 2.495511669658887e-05,
-      "loss": 0.3338,
+      "loss": 0.2981,
       "step": 2780
     },
     {
       "epoch": 2.5,
       "learning_rate": 2.5044883303411134e-05,
-      "loss": 0.3212,
+      "loss": 0.3099,
       "step": 2790
     },
     {
       "epoch": 2.51,
       "learning_rate": 2.5134649910233395e-05,
-      "loss": 0.3814,
+      "loss": 0.267,
       "step": 2800
     },
     {
       "epoch": 2.52,
       "learning_rate": 2.5224416517055656e-05,
-      "loss": 0.3548,
+      "loss": 0.3317,
       "step": 2810
     },
     {
       "epoch": 2.53,
       "learning_rate": 2.5314183123877917e-05,
-      "loss": 0.3111,
+      "loss": 0.3241,
       "step": 2820
     },
     {
       "epoch": 2.54,
       "learning_rate": 2.5403949730700182e-05,
-      "loss": 0.2813,
+      "loss": 0.371,
       "step": 2830
     },
     {
       "epoch": 2.55,
       "learning_rate": 2.5493716337522443e-05,
-      "loss": 0.2877,
+      "loss": 0.3431,
       "step": 2840
     },
     {
       "epoch": 2.56,
       "learning_rate": 2.5583482944344704e-05,
-      "loss": 0.3169,
+      "loss": 0.3218,
       "step": 2850
     },
     {
       "epoch": 2.57,
       "learning_rate": 2.5673249551166965e-05,
-      "loss": 0.2842,
+      "loss": 0.3222,
       "step": 2860
     },
     {
       "epoch": 2.57,
       "learning_rate": 2.5763016157989227e-05,
-      "loss": 0.3174,
+      "loss": 0.3176,
       "step": 2870
     },
     {
       "epoch": 2.58,
       "learning_rate": 2.585278276481149e-05,
-      "loss": 0.3094,
+      "loss": 0.3256,
       "step": 2880
     },
     {
       "epoch": 2.59,
       "learning_rate": 2.5942549371633752e-05,
-      "loss": 0.3405,
+      "loss": 0.2971,
       "step": 2890
     },
     {
       "epoch": 2.6,
       "learning_rate": 2.6032315978456017e-05,
-      "loss": 0.3013,
+      "loss": 0.253,
       "step": 2900
     },
     {
       "epoch": 2.61,
       "learning_rate": 2.6122082585278278e-05,
-      "loss": 0.322,
+      "loss": 0.3261,
       "step": 2910
     },
     {
       "epoch": 2.62,
       "learning_rate": 2.621184919210054e-05,
-      "loss": 0.2959,
+      "loss": 0.3325,
       "step": 2920
     },
     {
       "epoch": 2.63,
       "learning_rate": 2.63016157989228e-05,
-      "loss": 0.3343,
+      "loss": 0.3005,
       "step": 2930
     },
     {
       "epoch": 2.64,
       "learning_rate": 2.6391382405745062e-05,
-      "loss": 0.3079,
+      "loss": 0.2897,
       "step": 2940
     },
     {
       "epoch": 2.65,
       "learning_rate": 2.6481149012567323e-05,
-      "loss": 0.2994,
+      "loss": 0.3249,
       "step": 2950
     },
     {
       "epoch": 2.66,
       "learning_rate": 2.6570915619389584e-05,
-      "loss": 0.3091,
+      "loss": 0.3647,
       "step": 2960
     },
     {
       "epoch": 2.66,
       "learning_rate": 2.6660682226211852e-05,
-      "loss": 0.3317,
+      "loss": 0.3034,
       "step": 2970
     },
     {
       "epoch": 2.67,
       "learning_rate": 2.6750448833034114e-05,
-      "loss": 0.2687,
+      "loss": 0.2735,
       "step": 2980
     },
     {
       "epoch": 2.68,
       "learning_rate": 2.6840215439856375e-05,
-      "loss": 0.2859,
+      "loss": 0.3122,
       "step": 2990
     },
     {
       "epoch": 2.69,
       "learning_rate": 2.6929982046678636e-05,
-      "loss": 0.2997,
+      "loss": 0.2622,
       "step": 3000
     },
     {
       "epoch": 2.7,
       "learning_rate": 2.7019748653500897e-05,
-      "loss": 0.2603,
+      "loss": 0.322,
       "step": 3010
     },
     {
       "epoch": 2.71,
       "learning_rate": 2.710951526032316e-05,
-      "loss": 0.3452,
+      "loss": 0.2671,
       "step": 3020
     },
     {
       "epoch": 2.72,
       "learning_rate": 2.719928186714542e-05,
-      "loss": 0.3475,
+      "loss": 0.3392,
       "step": 3030
     },
     {
       "epoch": 2.73,
       "learning_rate": 2.7289048473967688e-05,
-      "loss": 0.317,
+      "loss": 0.2507,
       "step": 3040
     },
     {
       "epoch": 2.74,
       "learning_rate": 2.737881508078995e-05,
-      "loss": 0.3266,
+      "loss": 0.294,
       "step": 3050
     },
     {
       "epoch": 2.75,
       "learning_rate": 2.746858168761221e-05,
-      "loss": 0.291,
+      "loss": 0.3119,
       "step": 3060
     },
     {
       "epoch": 2.75,
       "learning_rate": 2.755834829443447e-05,
-      "loss": 0.3323,
+      "loss": 0.2956,
       "step": 3070
     },
     {
       "epoch": 2.76,
       "learning_rate": 2.7648114901256732e-05,
-      "loss": 0.32,
+      "loss": 0.2744,
       "step": 3080
     },
     {
       "epoch": 2.77,
       "learning_rate": 2.7737881508078994e-05,
-      "loss": 0.2792,
+      "loss": 0.279,
       "step": 3090
     },
     {
       "epoch": 2.78,
       "learning_rate": 2.7827648114901255e-05,
-      "loss": 0.2858,
+      "loss": 0.379,
       "step": 3100
     },
     {
       "epoch": 2.79,
       "learning_rate": 2.7917414721723523e-05,
-      "loss": 0.2447,
+      "loss": 0.2667,
       "step": 3110
     },
     {
       "epoch": 2.8,
       "learning_rate": 2.8007181328545784e-05,
-      "loss": 0.3039,
+      "loss": 0.2732,
       "step": 3120
     },
     {
       "epoch": 2.81,
       "learning_rate": 2.8096947935368045e-05,
-      "loss": 0.323,
+      "loss": 0.311,
       "step": 3130
     },
     {
       "epoch": 2.82,
       "learning_rate": 2.8186714542190307e-05,
-      "loss": 0.3041,
+      "loss": 0.3404,
       "step": 3140
     },
     {
       "epoch": 2.83,
       "learning_rate": 2.8276481149012568e-05,
-      "loss": 0.2496,
+      "loss": 0.2479,
       "step": 3150
     },
     {
       "epoch": 2.83,
       "learning_rate": 2.836624775583483e-05,
-      "loss": 0.3205,
+      "loss": 0.3057,
       "step": 3160
     },
     {
       "epoch": 2.84,
       "learning_rate": 2.845601436265709e-05,
-      "loss": 0.3079,
+      "loss": 0.3075,
       "step": 3170
     },
     {
       "epoch": 2.85,
       "learning_rate": 2.8545780969479358e-05,
-      "loss": 0.3112,
+      "loss": 0.3008,
       "step": 3180
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.863554757630162e-05,
-      "loss": 0.2674,
+      "loss": 0.2372,
       "step": 3190
     },
     {
       "epoch": 2.87,
       "learning_rate": 2.872531418312388e-05,
-      "loss": 0.3094,
+      "loss": 0.2617,
       "step": 3200
     },
     {
       "epoch": 2.88,
       "learning_rate": 2.8815080789946142e-05,
-      "loss": 0.2895,
+      "loss": 0.3,
       "step": 3210
     },
     {
       "epoch": 2.89,
       "learning_rate": 2.8904847396768403e-05,
-      "loss": 0.3456,
+      "loss": 0.2749,
       "step": 3220
     },
     {
       "epoch": 2.9,
       "learning_rate": 2.8994614003590664e-05,
-      "loss": 0.2602,
+      "loss": 0.2742,
       "step": 3230
     },
     {
       "epoch": 2.91,
       "learning_rate": 2.9084380610412926e-05,
-      "loss": 0.3198,
+      "loss": 0.2844,
       "step": 3240
     },
     {
       "epoch": 2.92,
       "learning_rate": 2.9174147217235194e-05,
-      "loss": 0.3463,
+      "loss": 0.2909,
       "step": 3250
     },
     {
       "epoch": 2.92,
       "learning_rate": 2.9263913824057455e-05,
-      "loss": 0.3456,
+      "loss": 0.3045,
       "step": 3260
     },
     {
       "epoch": 2.93,
       "learning_rate": 2.9353680430879716e-05,
-      "loss": 0.2803,
+      "loss": 0.2875,
       "step": 3270
     },
     {
       "epoch": 2.94,
       "learning_rate": 2.9443447037701977e-05,
-      "loss": 0.302,
+      "loss": 0.2963,
       "step": 3280
     },
     {
       "epoch": 2.95,
       "learning_rate": 2.953321364452424e-05,
-      "loss": 0.2851,
+      "loss": 0.314,
       "step": 3290
     },
     {
       "epoch": 2.96,
       "learning_rate": 2.96229802513465e-05,
-      "loss": 0.2752,
+      "loss": 0.3005,
       "step": 3300
     },
     {
       "epoch": 2.97,
       "learning_rate": 2.971274685816876e-05,
-      "loss": 0.2655,
+      "loss": 0.3127,
       "step": 3310
     },
     {
       "epoch": 2.98,
       "learning_rate": 2.9802513464991022e-05,
-      "loss": 0.2716,
+      "loss": 0.3113,
       "step": 3320
     },
     {
       "epoch": 2.99,
       "learning_rate": 2.989228007181329e-05,
-      "loss": 0.2591,
+      "loss": 0.2886,
       "step": 3330
     },
     {
       "epoch": 3.0,
       "learning_rate": 2.998204667863555e-05,
-      "loss": 0.2794,
+      "loss": 0.321,
       "step": 3340
     },
     {
       "epoch": 3.0,
       "eval_accuracy": {
-        "accuracy": 0.9377663153173357
+        "accuracy": 0.9410742318905584
       },
       "eval_f1": {
-        "f1": 0.9340905709341878
+        "f1": 0.9378351696354423
       },
-      "eval_loss": 0.18664708733558655,
+      "eval_loss": 0.18490658700466156,
       "eval_precision": {
-        "precision": 0.9374045110718889
+        "precision": 0.9376663800198108
       },
       "eval_recall": {
-        "recall": 0.9314497447723507
+        "recall": 0.9381803360170522
       },
-      "eval_runtime": 164.7744,
-      "eval_samples_per_second": 108.245,
-      "eval_steps_per_second": 6.767,
+      "eval_runtime": 165.2584,
+      "eval_samples_per_second": 107.928,
+      "eval_steps_per_second": 6.747,
       "step": 3344
     }
   ],

tmp-checkpoint-3344/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3394b871720811033add862f1e1383ca3790e6ab55972b19ed900a5d6b59c978
+oid sha256:5c55fb57ba4dc2c9b2c813516c4846a21f1047b19b6cf48a97b9224ced523b9b
 size 4792