Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4036c21a7f01292edd5958f4548e20c9d510bfe72a486a5227ed8346d877e7
+oid sha256:7a061e50b1c06af4217ea1f81e960309b2a1b323e2110b02ae410422aec06916
 size 347665996

tmp-checkpoint-3854/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94980801b22b9ca45cfb65d7c3ad3ebd5a8f313fb90c5a0e93c35c67774739b
+oid sha256:7a061e50b1c06af4217ea1f81e960309b2a1b323e2110b02ae410422aec06916
 size 347665996

tmp-checkpoint-3854/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a0a3a243b9e6b8df312a2ebbf33827e641072aa7c8d57e7047ba64df3f74ae
+oid sha256:a7b7d5cc2193e6c271499d2a48103208ec3fde6473d5d4040419b05738f54a92
 size 695604061

tmp-checkpoint-3854/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8586573850ea10aad2c3b6c907bf797ac34c332d59cd082da972cbb4e65e4a
+oid sha256:60b29fd955076244121e3660fa2d59e8f32d42e330b032192b7da9e853502feb
 size 14244

tmp-checkpoint-3854/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2029738426208496,
+  "best_metric": 0.9808588624000549,
   "best_model_checkpoint": "swinv2-base-patch4-window12-192-22k-ConcreteClassifier-PVT\\checkpoint-1927",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,2351 +11,2351 @@
     {
       "epoch": 0.01,
       "learning_rate": 1.7298045320878742e-06,
-      "loss": 2.1657,
+      "loss": 2.3066,
       "step": 10
     },
     {
       "epoch": 0.01,
       "learning_rate": 3.4596090641757485e-06,
-      "loss": 1.9738,
+      "loss": 2.131,
       "step": 20
     },
     {
       "epoch": 0.02,
       "learning_rate": 5.1894135962636225e-06,
-      "loss": 1.8167,
+      "loss": 2.0104,
       "step": 30
     },
     {
       "epoch": 0.02,
       "learning_rate": 6.919218128351497e-06,
-      "loss": 1.7554,
+      "loss": 1.8938,
       "step": 40
     },
     {
       "epoch": 0.03,
       "learning_rate": 8.649022660439371e-06,
-      "loss": 1.6154,
+      "loss": 1.7743,
       "step": 50
     },
     {
       "epoch": 0.03,
       "learning_rate": 1.0378827192527245e-05,
-      "loss": 1.4087,
+      "loss": 1.73,
       "step": 60
     },
     {
       "epoch": 0.04,
       "learning_rate": 1.2108631724615119e-05,
-      "loss": 1.3473,
+      "loss": 1.6552,
       "step": 70
     },
     {
       "epoch": 0.04,
       "learning_rate": 1.3838436256702994e-05,
-      "loss": 1.2636,
+      "loss": 1.4119,
       "step": 80
     },
     {
       "epoch": 0.05,
       "learning_rate": 1.5568240788790867e-05,
-      "loss": 1.251,
+      "loss": 1.1716,
       "step": 90
     },
     {
       "epoch": 0.05,
       "learning_rate": 1.7298045320878743e-05,
-      "loss": 1.5939,
+      "loss": 1.2431,
       "step": 100
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.9027849852966615e-05,
-      "loss": 1.2923,
+      "loss": 1.1115,
       "step": 110
     },
     {
       "epoch": 0.06,
       "learning_rate": 2.075765438505449e-05,
-      "loss": 0.9352,
+      "loss": 1.0365,
       "step": 120
     },
     {
       "epoch": 0.07,
       "learning_rate": 2.2487458917142365e-05,
-      "loss": 1.3512,
+      "loss": 1.2179,
       "step": 130
     },
     {
       "epoch": 0.07,
       "learning_rate": 2.4217263449230237e-05,
-      "loss": 1.1637,
+      "loss": 1.1192,
       "step": 140
     },
     {
       "epoch": 0.08,
       "learning_rate": 2.5947067981318112e-05,
-      "loss": 0.9679,
+      "loss": 0.8697,
       "step": 150
     },
     {
       "epoch": 0.08,
       "learning_rate": 2.7676872513405988e-05,
-      "loss": 1.0496,
+      "loss": 1.0286,
       "step": 160
     },
     {
       "epoch": 0.09,
       "learning_rate": 2.940667704549386e-05,
-      "loss": 1.2054,
+      "loss": 0.9186,
       "step": 170
     },
     {
       "epoch": 0.09,
       "learning_rate": 3.1136481577581735e-05,
-      "loss": 0.9784,
+      "loss": 1.0909,
       "step": 180
     },
     {
       "epoch": 0.1,
       "learning_rate": 3.286628610966961e-05,
-      "loss": 0.9918,
+      "loss": 1.0519,
       "step": 190
     },
     {
       "epoch": 0.1,
       "learning_rate": 3.4596090641757486e-05,
-      "loss": 1.1241,
+      "loss": 1.1043,
       "step": 200
     },
     {
       "epoch": 0.11,
       "learning_rate": 3.632589517384536e-05,
-      "loss": 0.9452,
+      "loss": 0.8634,
       "step": 210
     },
     {
       "epoch": 0.11,
       "learning_rate": 3.805569970593323e-05,
-      "loss": 0.7674,
+      "loss": 0.86,
       "step": 220
     },
     {
       "epoch": 0.12,
       "learning_rate": 3.97855042380211e-05,
-      "loss": 0.8534,
+      "loss": 0.8325,
       "step": 230
     },
     {
       "epoch": 0.12,
       "learning_rate": 4.151530877010898e-05,
-      "loss": 1.0076,
+      "loss": 1.1083,
       "step": 240
     },
     {
       "epoch": 0.13,
       "learning_rate": 4.324511330219685e-05,
-      "loss": 0.9224,
+      "loss": 1.0759,
       "step": 250
     },
     {
       "epoch": 0.13,
       "learning_rate": 4.497491783428473e-05,
-      "loss": 1.1322,
+      "loss": 0.9178,
       "step": 260
     },
     {
       "epoch": 0.14,
       "learning_rate": 4.67047223663726e-05,
-      "loss": 0.7622,
+      "loss": 1.1132,
       "step": 270
     },
     {
       "epoch": 0.15,
       "learning_rate": 4.8434526898460474e-05,
-      "loss": 0.941,
+      "loss": 1.0484,
       "step": 280
     },
     {
       "epoch": 0.15,
       "learning_rate": 5.0164331430548346e-05,
-      "loss": 0.8296,
+      "loss": 0.8629,
       "step": 290
     },
     {
       "epoch": 0.16,
       "learning_rate": 5.1894135962636225e-05,
-      "loss": 0.9002,
+      "loss": 0.6426,
       "step": 300
     },
     {
       "epoch": 0.16,
       "learning_rate": 5.36239404947241e-05,
-      "loss": 0.9581,
+      "loss": 1.0117,
       "step": 310
     },
     {
       "epoch": 0.17,
       "learning_rate": 5.5353745026811976e-05,
-      "loss": 0.7025,
+      "loss": 0.9769,
       "step": 320
     },
     {
       "epoch": 0.17,
       "learning_rate": 5.708354955889985e-05,
-      "loss": 0.979,
+      "loss": 0.9459,
       "step": 330
     },
     {
       "epoch": 0.18,
       "learning_rate": 5.881335409098772e-05,
-      "loss": 1.0473,
+      "loss": 1.3208,
       "step": 340
     },
     {
       "epoch": 0.18,
       "learning_rate": 6.054315862307559e-05,
-      "loss": 0.9561,
+      "loss": 0.9631,
       "step": 350
     },
     {
       "epoch": 0.19,
       "learning_rate": 6.227296315516347e-05,
-      "loss": 1.0593,
+      "loss": 1.3533,
       "step": 360
     },
     {
       "epoch": 0.19,
       "learning_rate": 6.400276768725135e-05,
-      "loss": 1.0084,
+      "loss": 1.2228,
       "step": 370
     },
     {
       "epoch": 0.2,
       "learning_rate": 6.573257221933921e-05,
-      "loss": 1.1452,
+      "loss": 0.9195,
       "step": 380
     },
     {
       "epoch": 0.2,
       "learning_rate": 6.746237675142709e-05,
-      "loss": 0.9112,
+      "loss": 1.0466,
       "step": 390
     },
     {
       "epoch": 0.21,
       "learning_rate": 6.919218128351497e-05,
-      "loss": 0.8299,
+      "loss": 0.6537,
       "step": 400
     },
     {
       "epoch": 0.21,
       "learning_rate": 7.092198581560285e-05,
-      "loss": 1.014,
+      "loss": 1.0766,
       "step": 410
     },
     {
       "epoch": 0.22,
       "learning_rate": 7.265179034769071e-05,
-      "loss": 0.8594,
+      "loss": 1.3196,
       "step": 420
     },
     {
       "epoch": 0.22,
       "learning_rate": 7.438159487977858e-05,
-      "loss": 0.9563,
+      "loss": 1.1902,
       "step": 430
     },
     {
       "epoch": 0.23,
       "learning_rate": 7.611139941186646e-05,
-      "loss": 0.9631,
+      "loss": 0.8251,
       "step": 440
     },
     {
       "epoch": 0.23,
       "learning_rate": 7.784120394395434e-05,
-      "loss": 0.8729,
+      "loss": 0.6196,
       "step": 450
     },
     {
       "epoch": 0.24,
       "learning_rate": 7.95710084760422e-05,
-      "loss": 1.0304,
+      "loss": 1.1941,
       "step": 460
     },
     {
       "epoch": 0.24,
       "learning_rate": 8.130081300813008e-05,
-      "loss": 0.7785,
+      "loss": 0.9509,
       "step": 470
     },
     {
       "epoch": 0.25,
       "learning_rate": 8.303061754021796e-05,
-      "loss": 0.9516,
+      "loss": 1.0669,
       "step": 480
     },
     {
       "epoch": 0.25,
       "learning_rate": 8.476042207230583e-05,
-      "loss": 0.875,
+      "loss": 0.8493,
       "step": 490
     },
     {
       "epoch": 0.26,
       "learning_rate": 8.64902266043937e-05,
-      "loss": 1.1574,
+      "loss": 1.0381,
       "step": 500
     },
     {
       "epoch": 0.26,
       "learning_rate": 8.822003113648158e-05,
-      "loss": 1.2652,
+      "loss": 0.6853,
       "step": 510
     },
     {
       "epoch": 0.27,
       "learning_rate": 8.994983566856946e-05,
-      "loss": 0.9341,
+      "loss": 1.0025,
       "step": 520
     },
     {
       "epoch": 0.28,
       "learning_rate": 9.167964020065733e-05,
-      "loss": 0.859,
+      "loss": 0.9758,
       "step": 530
     },
     {
       "epoch": 0.28,
       "learning_rate": 9.34094447327452e-05,
-      "loss": 0.738,
+      "loss": 1.2263,
       "step": 540
     },
     {
       "epoch": 0.29,
       "learning_rate": 9.513924926483307e-05,
-      "loss": 1.0468,
+      "loss": 1.0245,
       "step": 550
     },
     {
       "epoch": 0.29,
       "learning_rate": 9.686905379692095e-05,
-      "loss": 1.0018,
+      "loss": 0.9136,
       "step": 560
     },
     {
       "epoch": 0.3,
       "learning_rate": 9.859885832900881e-05,
-      "loss": 0.9798,
+      "loss": 1.0586,
       "step": 570
     },
     {
       "epoch": 0.3,
       "learning_rate": 0.00010032866286109669,
-      "loss": 1.0199,
+      "loss": 1.029,
       "step": 580
     },
     {
       "epoch": 0.31,
       "learning_rate": 0.00010205846739318457,
-      "loss": 0.9069,
+      "loss": 0.9973,
       "step": 590
     },
     {
       "epoch": 0.31,
       "learning_rate": 0.00010378827192527245,
-      "loss": 0.8453,
+      "loss": 0.7652,
       "step": 600
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.00010551807645736032,
-      "loss": 0.9513,
+      "loss": 1.2198,
       "step": 610
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0001072478809894482,
-      "loss": 0.8157,
+      "loss": 1.3727,
       "step": 620
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.00010897768552153607,
-      "loss": 0.9546,
+      "loss": 0.9157,
       "step": 630
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.00011070749005362395,
-      "loss": 1.0515,
+      "loss": 1.4063,
       "step": 640
     },
     {
       "epoch": 0.34,
       "learning_rate": 0.00011243729458571182,
-      "loss": 1.2692,
+      "loss": 0.9697,
       "step": 650
     },
     {
       "epoch": 0.34,
       "learning_rate": 0.0001141670991177997,
-      "loss": 0.8208,
+      "loss": 1.0678,
       "step": 660
     },
     {
       "epoch": 0.35,
       "learning_rate": 0.00011589690364988756,
-      "loss": 0.9837,
+      "loss": 1.1373,
       "step": 670
     },
     {
       "epoch": 0.35,
       "learning_rate": 0.00011762670818197544,
-      "loss": 0.8842,
+      "loss": 1.1127,
       "step": 680
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0001193565127140633,
-      "loss": 1.2168,
+      "loss": 0.8828,
       "step": 690
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.00012108631724615118,
-      "loss": 0.8098,
+      "loss": 1.0497,
       "step": 700
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.00012281612177823906,
-      "loss": 1.1387,
+      "loss": 1.0252,
       "step": 710
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.00012454592631032694,
-      "loss": 1.0108,
+      "loss": 1.0175,
       "step": 720
     },
     {
       "epoch": 0.38,
       "learning_rate": 0.00012627573084241482,
-      "loss": 0.8233,
+      "loss": 1.1303,
       "step": 730
     },
     {
       "epoch": 0.38,
       "learning_rate": 0.0001280055353745027,
-      "loss": 1.0738,
+      "loss": 0.8751,
       "step": 740
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.00012973533990659055,
-      "loss": 1.0947,
+      "loss": 0.9646,
       "step": 750
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.00013146514443867843,
-      "loss": 1.3367,
+      "loss": 1.0412,
       "step": 760
     },
     {
       "epoch": 0.4,
       "learning_rate": 0.0001331949489707663,
-      "loss": 0.9517,
+      "loss": 1.3243,
       "step": 770
     },
     {
       "epoch": 0.4,
       "learning_rate": 0.00013492475350285418,
-      "loss": 1.2106,
+      "loss": 1.0182,
       "step": 780
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.00013665455803494206,
-      "loss": 1.1231,
+      "loss": 1.3814,
       "step": 790
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.00013838436256702994,
-      "loss": 0.9463,
+      "loss": 0.9131,
       "step": 800
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.00014011416709911782,
-      "loss": 0.8069,
+      "loss": 1.0305,
       "step": 810
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.0001418439716312057,
-      "loss": 0.8983,
+      "loss": 0.9296,
       "step": 820
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.00014357377616329355,
-      "loss": 1.2501,
+      "loss": 1.1304,
       "step": 830
     },
     {
       "epoch": 0.44,
       "learning_rate": 0.00014530358069538143,
-      "loss": 1.0822,
+      "loss": 0.964,
       "step": 840
     },
     {
       "epoch": 0.44,
       "learning_rate": 0.0001470333852274693,
-      "loss": 0.9581,
+      "loss": 0.9223,
       "step": 850
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.00014876318975955716,
-      "loss": 1.006,
+      "loss": 0.8419,
       "step": 860
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.00015049299429164504,
-      "loss": 1.2277,
+      "loss": 0.7896,
       "step": 870
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.00015222279882373292,
-      "loss": 0.8975,
+      "loss": 1.2753,
       "step": 880
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.0001539526033558208,
-      "loss": 1.2464,
+      "loss": 1.01,
       "step": 890
     },
     {
       "epoch": 0.47,
       "learning_rate": 0.00015568240788790867,
-      "loss": 0.914,
+      "loss": 0.8729,
       "step": 900
     },
     {
       "epoch": 0.47,
       "learning_rate": 0.00015741221241999653,
-      "loss": 1.1891,
+      "loss": 1.2337,
       "step": 910
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0001591420169520844,
-      "loss": 0.9151,
+      "loss": 1.0598,
       "step": 920
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.00016087182148417228,
-      "loss": 0.8521,
+      "loss": 0.9216,
       "step": 930
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.00016260162601626016,
-      "loss": 1.0762,
+      "loss": 1.2614,
       "step": 940
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.00016433143054834804,
-      "loss": 1.1603,
+      "loss": 0.9602,
       "step": 950
     },
     {
       "epoch": 0.5,
       "learning_rate": 0.00016606123508043592,
-      "loss": 1.1512,
+      "loss": 1.1126,
       "step": 960
     },
     {
       "epoch": 0.5,
       "learning_rate": 0.0001677910396125238,
-      "loss": 1.1018,
+      "loss": 0.7103,
       "step": 970
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.00016952084414461165,
-      "loss": 1.3488,
+      "loss": 1.0462,
       "step": 980
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.00017125064867669953,
-      "loss": 1.0968,
+      "loss": 0.9843,
       "step": 990
     },
     {
       "epoch": 0.52,
       "learning_rate": 0.0001729804532087874,
-      "loss": 1.0725,
+      "loss": 1.2419,
       "step": 1000
     },
     {
       "epoch": 0.52,
       "learning_rate": 0.00017471025774087529,
-      "loss": 1.1117,
+      "loss": 1.3823,
       "step": 1010
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.00017644006227296316,
-      "loss": 0.9088,
+      "loss": 0.9726,
       "step": 1020
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.00017816986680505104,
-      "loss": 0.9328,
+      "loss": 1.1238,
       "step": 1030
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.00017989967133713892,
-      "loss": 1.4789,
+      "loss": 0.934,
       "step": 1040
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0001816294758692268,
-      "loss": 1.0738,
+      "loss": 1.5093,
       "step": 1050
     },
     {
       "epoch": 0.55,
       "learning_rate": 0.00018335928040131465,
-      "loss": 1.2455,
+      "loss": 1.0234,
       "step": 1060
     },
     {
       "epoch": 0.56,
       "learning_rate": 0.00018508908493340253,
-      "loss": 1.1487,
+      "loss": 0.7998,
       "step": 1070
     },
     {
       "epoch": 0.56,
       "learning_rate": 0.0001868188894654904,
-      "loss": 1.0046,
+      "loss": 1.0191,
       "step": 1080
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0001885486939975783,
-      "loss": 1.2662,
+      "loss": 1.1171,
       "step": 1090
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.00019027849852966614,
-      "loss": 1.2935,
+      "loss": 1.1417,
       "step": 1100
     },
     {
       "epoch": 0.58,
       "learning_rate": 0.00019200830306175402,
-      "loss": 1.3252,
+      "loss": 0.9539,
       "step": 1110
     },
     {
       "epoch": 0.58,
       "learning_rate": 0.0001937381075938419,
-      "loss": 1.0672,
+      "loss": 1.0955,
       "step": 1120
     },
     {
       "epoch": 0.59,
       "learning_rate": 0.00019546791212592978,
-      "loss": 1.1187,
+      "loss": 1.3748,
       "step": 1130
     },
     {
       "epoch": 0.59,
       "learning_rate": 0.00019719771665801763,
-      "loss": 1.0334,
+      "loss": 1.1126,
       "step": 1140
     },
     {
       "epoch": 0.6,
       "learning_rate": 0.0001989275211901055,
-      "loss": 1.2401,
+      "loss": 1.0674,
       "step": 1150
     },
     {
       "epoch": 0.6,
       "learning_rate": 0.00020065732572219339,
-      "loss": 1.0143,
+      "loss": 1.1236,
       "step": 1160
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.00020238713025428126,
-      "loss": 1.0219,
+      "loss": 1.0824,
       "step": 1170
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.00020411693478636914,
-      "loss": 0.9133,
+      "loss": 1.1181,
       "step": 1180
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.00020584673931845702,
-      "loss": 0.8646,
+      "loss": 1.0881,
       "step": 1190
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002075765438505449,
-      "loss": 1.0987,
+      "loss": 1.1874,
       "step": 1200
     },
     {
       "epoch": 0.63,
       "learning_rate": 0.00020930634838263278,
-      "loss": 1.1542,
+      "loss": 1.0377,
       "step": 1210
     },
     {
       "epoch": 0.63,
       "learning_rate": 0.00021103615291472063,
-      "loss": 1.1115,
+      "loss": 0.8027,
       "step": 1220
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002127659574468085,
-      "loss": 1.2792,
+      "loss": 0.8027,
       "step": 1230
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002144957619788964,
-      "loss": 1.4426,
+      "loss": 1.2303,
       "step": 1240
     },
     {
       "epoch": 0.65,
       "learning_rate": 0.00021622556651098427,
-      "loss": 1.1541,
+      "loss": 1.2914,
       "step": 1250
     },
     {
       "epoch": 0.65,
       "learning_rate": 0.00021795537104307214,
-      "loss": 1.3394,
+      "loss": 1.2018,
       "step": 1260
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.00021968517557516002,
-      "loss": 1.3261,
+      "loss": 0.994,
       "step": 1270
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002214149801072479,
-      "loss": 1.1333,
+      "loss": 1.1917,
       "step": 1280
     },
     {
       "epoch": 0.67,
       "learning_rate": 0.00022314478463933578,
-      "loss": 1.2157,
+      "loss": 0.9846,
       "step": 1290
     },
     {
       "epoch": 0.67,
       "learning_rate": 0.00022487458917142363,
-      "loss": 1.1464,
+      "loss": 1.1561,
       "step": 1300
     },
     {
       "epoch": 0.68,
       "learning_rate": 0.0002266043937035115,
-      "loss": 1.2047,
+      "loss": 1.3345,
       "step": 1310
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.0002283341982355994,
-      "loss": 0.8407,
+      "loss": 1.1663,
       "step": 1320
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.00023006400276768727,
-      "loss": 1.3505,
+      "loss": 1.0486,
       "step": 1330
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.00023179380729977512,
-      "loss": 1.0958,
+      "loss": 1.2478,
       "step": 1340
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.000233523611831863,
-      "loss": 1.1707,
+      "loss": 1.1334,
       "step": 1350
     },
     {
       "epoch": 0.71,
       "learning_rate": 0.00023525341636395088,
-      "loss": 0.889,
+      "loss": 1.1248,
       "step": 1360
     },
     {
       "epoch": 0.71,
       "learning_rate": 0.00023698322089603876,
-      "loss": 1.0459,
+      "loss": 1.2183,
       "step": 1370
     },
     {
       "epoch": 0.72,
       "learning_rate": 0.0002387130254281266,
-      "loss": 1.2212,
+      "loss": 1.4618,
       "step": 1380
     },
     {
       "epoch": 0.72,
       "learning_rate": 0.00024044282996021449,
-      "loss": 1.0102,
+      "loss": 1.5796,
       "step": 1390
     },
     {
       "epoch": 0.73,
       "learning_rate": 0.00024217263449230237,
-      "loss": 1.0178,
+      "loss": 1.4877,
       "step": 1400
     },
     {
       "epoch": 0.73,
       "learning_rate": 0.00024390243902439024,
-      "loss": 0.9676,
+      "loss": 0.9612,
       "step": 1410
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002456322435564781,
-      "loss": 1.1611,
+      "loss": 1.3634,
       "step": 1420
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.000247362048088566,
-      "loss": 1.2205,
+      "loss": 1.1377,
       "step": 1430
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002490918526206539,
-      "loss": 0.9813,
+      "loss": 1.1365,
       "step": 1440
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.00025082165715274176,
-      "loss": 1.1654,
+      "loss": 1.2433,
       "step": 1450
     },
     {
       "epoch": 0.76,
       "learning_rate": 0.00025255146168482964,
-      "loss": 1.2854,
+      "loss": 1.2164,
       "step": 1460
     },
     {
       "epoch": 0.76,
       "learning_rate": 0.0002542812662169175,
-      "loss": 1.0573,
+      "loss": 1.0668,
       "step": 1470
     },
     {
       "epoch": 0.77,
       "learning_rate": 0.0002560110707490054,
-      "loss": 1.2734,
+      "loss": 1.174,
       "step": 1480
     },
     {
       "epoch": 0.77,
       "learning_rate": 0.0002577408752810932,
-      "loss": 1.2369,
+      "loss": 1.1307,
       "step": 1490
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002594706798131811,
-      "loss": 1.2364,
+      "loss": 1.2406,
       "step": 1500
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.000261200484345269,
-      "loss": 1.1,
+      "loss": 1.2542,
       "step": 1510
     },
     {
       "epoch": 0.79,
       "learning_rate": 0.00026293028887735685,
-      "loss": 0.9999,
+      "loss": 0.9126,
       "step": 1520
     },
     {
       "epoch": 0.79,
       "learning_rate": 0.00026466009340944473,
-      "loss": 1.2802,
+      "loss": 1.1105,
       "step": 1530
     },
     {
       "epoch": 0.8,
       "learning_rate": 0.0002663898979415326,
-      "loss": 1.0885,
+      "loss": 0.8491,
       "step": 1540
     },
     {
       "epoch": 0.8,
       "learning_rate": 0.0002681197024736205,
-      "loss": 1.2307,
+      "loss": 1.4498,
       "step": 1550
     },
     {
       "epoch": 0.81,
       "learning_rate": 0.00026984950700570837,
-      "loss": 1.1289,
+      "loss": 1.3299,
       "step": 1560
     },
     {
       "epoch": 0.81,
       "learning_rate": 0.00027157931153779625,
-      "loss": 1.372,
+      "loss": 1.2222,
       "step": 1570
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002733091160698841,
-      "loss": 1.0389,
+      "loss": 0.9812,
       "step": 1580
     },
     {
       "epoch": 0.83,
       "learning_rate": 0.000275038920601972,
-      "loss": 1.2973,
+      "loss": 1.2824,
       "step": 1590
     },
     {
       "epoch": 0.83,
       "learning_rate": 0.0002767687251340599,
-      "loss": 1.2623,
+      "loss": 1.1105,
       "step": 1600
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.00027849852966614776,
-      "loss": 1.2638,
+      "loss": 1.0978,
       "step": 1610
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.00028022833419823564,
-      "loss": 1.0289,
+      "loss": 1.1159,
       "step": 1620
     },
     {
       "epoch": 0.85,
       "learning_rate": 0.0002819581387303235,
-      "loss": 1.2778,
+      "loss": 1.1441,
       "step": 1630
     },
     {
       "epoch": 0.85,
       "learning_rate": 0.0002836879432624114,
-      "loss": 1.4499,
+      "loss": 1.2566,
       "step": 1640
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002854177477944992,
-      "loss": 1.1778,
+      "loss": 1.1327,
       "step": 1650
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002871475523265871,
-      "loss": 0.9284,
+      "loss": 1.232,
       "step": 1660
     },
     {
       "epoch": 0.87,
       "learning_rate": 0.000288877356858675,
-      "loss": 1.0374,
+      "loss": 1.0974,
       "step": 1670
     },
     {
       "epoch": 0.87,
       "learning_rate": 0.00029060716139076286,
-      "loss": 1.714,
+      "loss": 1.0083,
       "step": 1680
     },
     {
       "epoch": 0.88,
       "learning_rate": 0.00029233696592285074,
-      "loss": 1.3087,
+      "loss": 1.5513,
       "step": 1690
     },
     {
       "epoch": 0.88,
       "learning_rate": 0.0002940667704549386,
-      "loss": 0.9422,
+      "loss": 1.3731,
       "step": 1700
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.00029579657498702644,
-      "loss": 1.2895,
+      "loss": 1.1877,
       "step": 1710
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002975263795191143,
-      "loss": 1.1904,
+      "loss": 1.199,
       "step": 1720
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002992561840512022,
-      "loss": 1.225,
+      "loss": 1.4768,
       "step": 1730
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0003009859885832901,
-      "loss": 1.2768,
+      "loss": 1.7352,
       "step": 1740
     },
     {
       "epoch": 0.91,
       "learning_rate": 0.00030271579311537796,
-      "loss": 1.2937,
+      "loss": 1.3652,
       "step": 1750
     },
     {
       "epoch": 0.91,
       "learning_rate": 0.00030444559764746583,
-      "loss": 1.2911,
+      "loss": 1.1335,
       "step": 1760
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0003061754021795537,
-      "loss": 1.3184,
+      "loss": 1.2259,
       "step": 1770
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0003079052067116416,
-      "loss": 1.375,
+      "loss": 1.3024,
       "step": 1780
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.00030963501124372947,
-      "loss": 1.521,
+      "loss": 1.4433,
       "step": 1790
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.00031136481577581735,
-      "loss": 1.2516,
+      "loss": 1.1668,
       "step": 1800
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0003130946203079052,
-      "loss": 1.4221,
+      "loss": 1.3298,
       "step": 1810
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.00031482442483999305,
-      "loss": 1.4243,
+      "loss": 1.2601,
       "step": 1820
     },
     {
       "epoch": 0.95,
       "learning_rate": 0.00031655422937208093,
-      "loss": 1.0468,
+      "loss": 1.1204,
       "step": 1830
     },
     {
       "epoch": 0.95,
       "learning_rate": 0.0003182840339041688,
-      "loss": 1.1835,
+      "loss": 1.2142,
       "step": 1840
     },
     {
       "epoch": 0.96,
       "learning_rate": 0.0003200138384362567,
-      "loss": 1.0788,
+      "loss": 0.93,
       "step": 1850
     },
     {
       "epoch": 0.97,
       "learning_rate": 0.00032174364296834457,
-      "loss": 0.9704,
+      "loss": 1.4335,
       "step": 1860
     },
     {
       "epoch": 0.97,
       "learning_rate": 0.00032347344750043245,
-      "loss": 1.6059,
+      "loss": 1.3081,
       "step": 1870
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0003252032520325203,
-      "loss": 1.393,
+      "loss": 1.2692,
       "step": 1880
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0003269330565646082,
-      "loss": 1.4794,
+      "loss": 1.2172,
       "step": 1890
     },
     {
       "epoch": 0.99,
       "learning_rate": 0.0003286628610966961,
-      "loss": 1.2421,
+      "loss": 1.2254,
       "step": 1900
     },
     {
       "epoch": 0.99,
       "learning_rate": 0.00033039266562878396,
-      "loss": 1.1183,
+      "loss": 1.1448,
       "step": 1910
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.00033212247016087184,
-      "loss": 1.2477,
+      "loss": 1.2473,
       "step": 1920
     },
     {
       "epoch": 1.0,
       "eval_accuracy": {
-        "accuracy": 0.5325551232166018
+        "accuracy": 0.5909208819714656
       },
       "eval_f1": {
-        "f1": 0.5038817513721507
+        "f1": 0.5910435702573883
       },
-      "eval_loss": 1.2029738426208496,
+      "eval_loss": 0.9808588624000549,
       "eval_precision": {
-        "precision": 0.6627476748491293
+        "precision": 0.6661654194259725
       },
       "eval_recall": {
-        "recall": 0.5484607592874412
+        "recall": 0.6016064778916844
       },
-      "eval_runtime": 214.6494,
-      "eval_samples_per_second": 17.96,
-      "eval_steps_per_second": 8.982,
+      "eval_runtime": 243.6104,
+      "eval_samples_per_second": 15.824,
+      "eval_steps_per_second": 7.914,
       "step": 1927
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0003338522746929597,
-      "loss": 1.2927,
+      "loss": 1.1687,
       "step": 1930
     },
     {
       "epoch": 1.01,
       "learning_rate": 0.0003355820792250476,
-      "loss": 1.4018,
+      "loss": 1.4294,
       "step": 1940
     },
     {
       "epoch": 1.01,
       "learning_rate": 0.0003373118837571355,
-      "loss": 1.2971,
+      "loss": 1.2866,
       "step": 1950
     },
     {
       "epoch": 1.02,
       "learning_rate": 0.0003390416882892233,
-      "loss": 1.2162,
+      "loss": 1.0858,
       "step": 1960
     },
     {
       "epoch": 1.02,
       "learning_rate": 0.0003407714928213112,
-      "loss": 1.1777,
+      "loss": 1.1465,
       "step": 1970
     },
     {
       "epoch": 1.03,
       "learning_rate": 0.00034250129735339906,
-      "loss": 1.4496,
+      "loss": 1.2876,
       "step": 1980
     },
     {
       "epoch": 1.03,
       "learning_rate": 0.00034423110188548694,
-      "loss": 1.2505,
+      "loss": 1.0266,
       "step": 1990
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0003459609064175748,
-      "loss": 1.1245,
+      "loss": 1.1494,
       "step": 2000
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0003476907109496627,
-      "loss": 1.1197,
+      "loss": 1.5705,
       "step": 2010
     },
     {
       "epoch": 1.05,
       "learning_rate": 0.00034942051548175057,
-      "loss": 1.3827,
+      "loss": 0.9916,
       "step": 2020
     },
     {
       "epoch": 1.05,
       "learning_rate": 0.00035115032001383845,
-      "loss": 1.1395,
+      "loss": 1.2183,
       "step": 2030
     },
     {
       "epoch": 1.06,
       "learning_rate": 0.00035288012454592633,
-      "loss": 1.2857,
+      "loss": 1.1186,
       "step": 2040
     },
     {
       "epoch": 1.06,
       "learning_rate": 0.0003546099290780142,
-      "loss": 1.4678,
+      "loss": 1.1386,
       "step": 2050
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0003563397336101021,
-      "loss": 1.2585,
+      "loss": 1.413,
       "step": 2060
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.00035806953814218997,
-      "loss": 0.9441,
+      "loss": 1.4434,
       "step": 2070
     },
     {
       "epoch": 1.08,
       "learning_rate": 0.00035979934267427784,
-      "loss": 1.0969,
+      "loss": 1.3144,
       "step": 2080
     },
     {
       "epoch": 1.08,
       "learning_rate": 0.0003615291472063657,
-      "loss": 1.4104,
+      "loss": 1.4108,
       "step": 2090
     },
     {
       "epoch": 1.09,
       "learning_rate": 0.0003632589517384536,
-      "loss": 1.3551,
+      "loss": 1.2305,
       "step": 2100
     },
     {
       "epoch": 1.09,
       "learning_rate": 0.0003649887562705415,
-      "loss": 1.2055,
+      "loss": 1.2335,
       "step": 2110
     },
     {
       "epoch": 1.1,
       "learning_rate": 0.0003667185608026293,
-      "loss": 1.2156,
+      "loss": 1.3617,
       "step": 2120
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.0003684483653347172,
-      "loss": 0.9952,
+      "loss": 1.1457,
       "step": 2130
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.00037017816986680506,
-      "loss": 1.2264,
+      "loss": 1.0253,
       "step": 2140
     },
     {
       "epoch": 1.12,
       "learning_rate": 0.00037190797439889294,
-      "loss": 1.0521,
+      "loss": 1.1486,
       "step": 2150
     },
     {
       "epoch": 1.12,
       "learning_rate": 0.0003736377789309808,
-      "loss": 1.0916,
+      "loss": 1.2603,
       "step": 2160
     },
     {
       "epoch": 1.13,
       "learning_rate": 0.0003753675834630687,
-      "loss": 1.132,
+      "loss": 1.25,
       "step": 2170
     },
     {
       "epoch": 1.13,
       "learning_rate": 0.0003770973879951566,
-      "loss": 1.4017,
+      "loss": 1.5531,
       "step": 2180
     },
     {
       "epoch": 1.14,
       "learning_rate": 0.0003788271925272444,
-      "loss": 1.1988,
+      "loss": 1.3442,
       "step": 2190
     },
     {
       "epoch": 1.14,
       "learning_rate": 0.0003805569970593323,
-      "loss": 1.4349,
+      "loss": 1.1317,
       "step": 2200
     },
     {
       "epoch": 1.15,
       "learning_rate": 0.00038228680159142016,
-      "loss": 1.2212,
+      "loss": 1.3271,
       "step": 2210
     },
     {
       "epoch": 1.15,
       "learning_rate": 0.00038401660612350804,
-      "loss": 1.1467,
+      "loss": 1.3165,
       "step": 2220
     },
     {
       "epoch": 1.16,
       "learning_rate": 0.0003857464106555959,
-      "loss": 1.5684,
+      "loss": 1.2377,
       "step": 2230
     },
     {
       "epoch": 1.16,
       "learning_rate": 0.0003874762151876838,
-      "loss": 1.3252,
+      "loss": 1.2677,
       "step": 2240
     },
     {
       "epoch": 1.17,
       "learning_rate": 0.0003892060197197717,
-      "loss": 1.3436,
+      "loss": 1.2756,
       "step": 2250
     },
     {
       "epoch": 1.17,
       "learning_rate": 0.00039093582425185955,
-      "loss": 1.4194,
+      "loss": 1.0193,
       "step": 2260
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.00039266562878394743,
-      "loss": 1.3629,
+      "loss": 1.239,
       "step": 2270
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.00039439543331603526,
-      "loss": 1.3456,
+      "loss": 1.6044,
       "step": 2280
     },
     {
       "epoch": 1.19,
       "learning_rate": 0.00039612523784812313,
-      "loss": 1.2017,
+      "loss": 1.2396,
       "step": 2290
     },
     {
       "epoch": 1.19,
       "learning_rate": 0.000397855042380211,
-      "loss": 1.2341,
+      "loss": 1.0345,
       "step": 2300
     },
     {
       "epoch": 1.2,
       "learning_rate": 0.0003995848469122989,
-      "loss": 1.1504,
+      "loss": 1.3125,
       "step": 2310
     },
     {
       "epoch": 1.2,
       "learning_rate": 0.00040131465144438677,
-      "loss": 1.3262,
+      "loss": 1.4382,
       "step": 2320
     },
     {
       "epoch": 1.21,
       "learning_rate": 0.00040304445597647465,
-      "loss": 1.2293,
+      "loss": 1.1232,
       "step": 2330
     },
     {
       "epoch": 1.21,
       "learning_rate": 0.00040477426050856253,
-      "loss": 1.0536,
+      "loss": 1.3415,
       "step": 2340
     },
     {
       "epoch": 1.22,
       "learning_rate": 0.0004065040650406504,
-      "loss": 1.4464,
+      "loss": 1.3517,
       "step": 2350
     },
     {
       "epoch": 1.22,
       "learning_rate": 0.0004082338695727383,
-      "loss": 1.0311,
+      "loss": 1.1871,
       "step": 2360
     },
     {
       "epoch": 1.23,
       "learning_rate": 0.00040996367410482616,
-      "loss": 1.3901,
+      "loss": 1.541,
       "step": 2370
     },
     {
       "epoch": 1.24,
       "learning_rate": 0.00041169347863691404,
-      "loss": 1.0175,
+      "loss": 1.0871,
       "step": 2380
     },
     {
       "epoch": 1.24,
       "learning_rate": 0.0004134232831690019,
-      "loss": 1.5067,
+      "loss": 1.0727,
       "step": 2390
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0004151530877010898,
-      "loss": 1.2357,
+      "loss": 1.2664,
       "step": 2400
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0004168828922331777,
-      "loss": 1.3514,
+      "loss": 0.9518,
       "step": 2410
     },
     {
       "epoch": 1.26,
       "learning_rate": 0.00041861269676526556,
-      "loss": 1.1515,
+      "loss": 1.5851,
       "step": 2420
     },
     {
       "epoch": 1.26,
       "learning_rate": 0.0004203425012973534,
-      "loss": 0.9969,
+      "loss": 1.3433,
       "step": 2430
     },
     {
       "epoch": 1.27,
       "learning_rate": 0.00042207230582944126,
-      "loss": 1.2266,
+      "loss": 1.1357,
       "step": 2440
     },
     {
       "epoch": 1.27,
       "learning_rate": 0.00042380211036152914,
-      "loss": 1.7812,
+      "loss": 1.3124,
       "step": 2450
     },
     {
       "epoch": 1.28,
       "learning_rate": 0.000425531914893617,
-      "loss": 1.0972,
+      "loss": 1.3198,
       "step": 2460
     },
     {
       "epoch": 1.28,
       "learning_rate": 0.0004272617194257049,
-      "loss": 1.3467,
+      "loss": 1.31,
       "step": 2470
     },
     {
       "epoch": 1.29,
       "learning_rate": 0.0004289915239577928,
-      "loss": 1.2125,
+      "loss": 1.2563,
       "step": 2480
     },
     {
       "epoch": 1.29,
       "learning_rate": 0.00043072132848988065,
-      "loss": 1.2568,
+      "loss": 1.2553,
       "step": 2490
     },
     {
       "epoch": 1.3,
       "learning_rate": 0.00043245113302196853,
-      "loss": 0.8703,
+      "loss": 1.3314,
       "step": 2500
     },
     {
       "epoch": 1.3,
       "learning_rate": 0.0004341809375540564,
-      "loss": 1.2506,
+      "loss": 1.8077,
       "step": 2510
     },
     {
       "epoch": 1.31,
       "learning_rate": 0.0004359107420861443,
-      "loss": 1.4445,
+      "loss": 1.7739,
       "step": 2520
     },
     {
       "epoch": 1.31,
       "learning_rate": 0.00043764054661823217,
-      "loss": 1.1034,
+      "loss": 1.3835,
       "step": 2530
     },
     {
       "epoch": 1.32,
       "learning_rate": 0.00043937035115032005,
-      "loss": 1.0994,
+      "loss": 1.3689,
       "step": 2540
     },
     {
       "epoch": 1.32,
       "learning_rate": 0.0004411001556824079,
-      "loss": 1.2385,
+      "loss": 1.4259,
       "step": 2550
     },
     {
       "epoch": 1.33,
       "learning_rate": 0.0004428299602144958,
-      "loss": 1.2876,
+      "loss": 1.0997,
       "step": 2560
     },
     {
       "epoch": 1.33,
       "learning_rate": 0.0004445597647465837,
-      "loss": 1.2809,
+      "loss": 0.944,
       "step": 2570
     },
     {
       "epoch": 1.34,
       "learning_rate": 0.00044628956927867156,
-      "loss": 1.3402,
+      "loss": 1.431,
       "step": 2580
     },
     {
       "epoch": 1.34,
       "learning_rate": 0.0004480193738107594,
-      "loss": 1.3418,
+      "loss": 1.492,
       "step": 2590
     },
     {
       "epoch": 1.35,
       "learning_rate": 0.00044974917834284726,
-      "loss": 1.285,
+      "loss": 1.0205,
       "step": 2600
     },
     {
       "epoch": 1.35,
       "learning_rate": 0.00045147898287493514,
-      "loss": 1.2663,
+      "loss": 1.2334,
       "step": 2610
     },
     {
       "epoch": 1.36,
       "learning_rate": 0.000453208787407023,
-      "loss": 1.3313,
+      "loss": 1.0434,
       "step": 2620
     },
     {
       "epoch": 1.36,
       "learning_rate": 0.0004549385919391109,
-      "loss": 1.5244,
+      "loss": 1.4912,
       "step": 2630
     },
     {
       "epoch": 1.37,
       "learning_rate": 0.0004566683964711988,
-      "loss": 1.2322,
+      "loss": 1.2939,
       "step": 2640
     },
     {
       "epoch": 1.38,
       "learning_rate": 0.00045839820100328666,
-      "loss": 1.3873,
+      "loss": 1.0389,
       "step": 2650
     },
     {
       "epoch": 1.38,
       "learning_rate": 0.00046012800553537454,
-      "loss": 1.257,
+      "loss": 1.1925,
       "step": 2660
     },
     {
       "epoch": 1.39,
       "learning_rate": 0.0004618578100674624,
-      "loss": 1.3883,
+      "loss": 1.5455,
       "step": 2670
     },
     {
       "epoch": 1.39,
       "learning_rate": 0.00046358761459955024,
-      "loss": 1.1631,
+      "loss": 1.2916,
       "step": 2680
     },
     {
       "epoch": 1.4,
       "learning_rate": 0.0004653174191316381,
-      "loss": 1.129,
+      "loss": 1.253,
       "step": 2690
     },
     {
       "epoch": 1.4,
       "learning_rate": 0.000467047223663726,
-      "loss": 1.7315,
+      "loss": 1.377,
       "step": 2700
     },
     {
       "epoch": 1.41,
       "learning_rate": 0.0004687770281958139,
-      "loss": 1.47,
+      "loss": 1.4184,
       "step": 2710
     },
     {
       "epoch": 1.41,
       "learning_rate": 0.00047050683272790175,
-      "loss": 1.3045,
+      "loss": 1.3838,
       "step": 2720
     },
     {
       "epoch": 1.42,
       "learning_rate": 0.00047223663725998963,
-      "loss": 1.2878,
+      "loss": 1.1912,
       "step": 2730
     },
     {
       "epoch": 1.42,
       "learning_rate": 0.0004739664417920775,
-      "loss": 0.9591,
+      "loss": 1.0304,
       "step": 2740
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.00047569624632416534,
-      "loss": 1.3777,
+      "loss": 1.3583,
       "step": 2750
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.0004774260508562532,
-      "loss": 1.3018,
+      "loss": 1.3856,
       "step": 2760
     },
     {
       "epoch": 1.44,
       "learning_rate": 0.0004791558553883411,
-      "loss": 1.0702,
+      "loss": 1.5254,
       "step": 2770
     },
     {
       "epoch": 1.44,
       "learning_rate": 0.00048088565992042897,
-      "loss": 1.0759,
+      "loss": 1.2068,
       "step": 2780
     },
     {
       "epoch": 1.45,
       "learning_rate": 0.00048261546445251685,
-      "loss": 1.3432,
+      "loss": 1.3795,
       "step": 2790
     },
     {
       "epoch": 1.45,
       "learning_rate": 0.00048434526898460473,
-      "loss": 1.2174,
+      "loss": 1.5103,
       "step": 2800
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0004860750735166926,
-      "loss": 1.4213,
+      "loss": 1.6531,
       "step": 2810
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0004878048780487805,
-      "loss": 0.8935,
+      "loss": 1.3675,
       "step": 2820
     },
     {
       "epoch": 1.47,
       "learning_rate": 0.0004895346825808684,
-      "loss": 1.3617,
+      "loss": 1.6244,
       "step": 2830
     },
     {
       "epoch": 1.47,
       "learning_rate": 0.0004912644871129562,
-      "loss": 1.3008,
+      "loss": 1.8395,
       "step": 2840
     },
     {
       "epoch": 1.48,
       "learning_rate": 0.0004929942916450441,
-      "loss": 1.2609,
+      "loss": 1.6552,
       "step": 2850
     },
     {
       "epoch": 1.48,
       "learning_rate": 0.000494724096177132,
-      "loss": 1.2559,
+      "loss": 1.6432,
       "step": 2860
     },
     {
       "epoch": 1.49,
       "learning_rate": 0.0004964539007092199,
-      "loss": 1.3019,
+      "loss": 1.4839,
       "step": 2870
     },
     {
       "epoch": 1.49,
       "learning_rate": 0.0004981837052413078,
-      "loss": 1.1746,
+      "loss": 1.403,
       "step": 2880
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0004999135097733956,
-      "loss": 1.417,
+      "loss": 1.8624,
       "step": 2890
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0005016433143054835,
-      "loss": 1.2709,
+      "loss": 1.4894,
       "step": 2900
     },
     {
       "epoch": 1.51,
       "learning_rate": 0.0005033731188375714,
-      "loss": 1.0585,
+      "loss": 2.1144,
       "step": 2910
     },
     {
       "epoch": 1.52,
       "learning_rate": 0.0005051029233696593,
-      "loss": 1.5526,
+      "loss": 1.7605,
       "step": 2920
     },
     {
       "epoch": 1.52,
       "learning_rate": 0.000506832727901747,
-      "loss": 1.4343,
+      "loss": 1.6352,
       "step": 2930
     },
     {
       "epoch": 1.53,
       "learning_rate": 0.000508562532433835,
-      "loss": 1.5419,
+      "loss": 1.6826,
       "step": 2940
     },
     {
       "epoch": 1.53,
       "learning_rate": 0.0005102923369659228,
-      "loss": 1.6354,
+      "loss": 1.8023,
       "step": 2950
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0005120221414980108,
-      "loss": 1.3269,
+      "loss": 1.6957,
       "step": 2960
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0005137519460300986,
-      "loss": 1.3021,
+      "loss": 2.1667,
       "step": 2970
     },
     {
       "epoch": 1.55,
       "learning_rate": 0.0005154817505621864,
-      "loss": 1.365,
+      "loss": 2.1662,
       "step": 2980
     },
     {
       "epoch": 1.55,
       "learning_rate": 0.0005172115550942743,
-      "loss": 1.1022,
+      "loss": 1.8724,
       "step": 2990
     },
     {
       "epoch": 1.56,
       "learning_rate": 0.0005189413596263622,
-      "loss": 1.1223,
+      "loss": 1.7312,
       "step": 3000
     },
     {
       "epoch": 1.56,
       "learning_rate": 0.0005206711641584501,
-      "loss": 1.1319,
+      "loss": 2.0953,
       "step": 3010
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.000522400968690538,
-      "loss": 1.3323,
+      "loss": 1.8218,
       "step": 3020
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.0005241307732226258,
-      "loss": 1.6277,
+      "loss": 1.9732,
       "step": 3030
     },
     {
       "epoch": 1.58,
       "learning_rate": 0.0005258605777547137,
-      "loss": 1.4376,
+      "loss": 2.229,
       "step": 3040
     },
     {
       "epoch": 1.58,
       "learning_rate": 0.0005275903822868016,
-      "loss": 1.6247,
+      "loss": 1.9946,
       "step": 3050
     },
     {
       "epoch": 1.59,
       "learning_rate": 0.0005293201868188895,
-      "loss": 1.3864,
+      "loss": 2.162,
       "step": 3060
     },
     {
       "epoch": 1.59,
       "learning_rate": 0.0005310499913509773,
-      "loss": 1.4396,
+      "loss": 2.0647,
       "step": 3070
     },
     {
       "epoch": 1.6,
       "learning_rate": 0.0005327797958830652,
-      "loss": 1.3664,
+      "loss": 2.0291,
       "step": 3080
     },
     {
       "epoch": 1.6,
       "learning_rate": 0.0005345096004151531,
-      "loss": 1.2295,
+      "loss": 2.0622,
       "step": 3090
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.000536239404947241,
-      "loss": 1.5317,
+      "loss": 1.9414,
       "step": 3100
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0005379692094793289,
-      "loss": 1.2045,
+      "loss": 2.0906,
       "step": 3110
     },
     {
       "epoch": 1.62,
       "learning_rate": 0.0005396990140114167,
-      "loss": 1.18,
+      "loss": 2.0018,
       "step": 3120
     },
     {
       "epoch": 1.62,
       "learning_rate": 0.0005414288185435046,
-      "loss": 1.2142,
+      "loss": 1.9754,
       "step": 3130
     },
     {
       "epoch": 1.63,
       "learning_rate": 0.0005431586230755925,
-      "loss": 1.1857,
+      "loss": 1.949,
       "step": 3140
     },
     {
       "epoch": 1.63,
       "learning_rate": 0.0005448884276076803,
-      "loss": 1.2765,
+      "loss": 1.918,
       "step": 3150
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0005466182321397683,
-      "loss": 1.2611,
+      "loss": 2.1205,
       "step": 3160
     },
     {
       "epoch": 1.65,
       "learning_rate": 0.000548348036671856,
-      "loss": 1.0898,
+      "loss": 1.8933,
       "step": 3170
     },
     {
       "epoch": 1.65,
       "learning_rate": 0.000550077841203944,
-      "loss": 1.2105,
+      "loss": 1.9666,
       "step": 3180
     },
     {
       "epoch": 1.66,
       "learning_rate": 0.0005518076457360318,
-      "loss": 1.8387,
+      "loss": 1.9286,
       "step": 3190
     },
     {
       "epoch": 1.66,
       "learning_rate": 0.0005535374502681198,
-      "loss": 1.6722,
+      "loss": 1.9417,
       "step": 3200
     },
     {
       "epoch": 1.67,
       "learning_rate": 0.0005552672548002075,
-      "loss": 1.6569,
+      "loss": 1.8296,
       "step": 3210
     },
     {
       "epoch": 1.67,
       "learning_rate": 0.0005569970593322955,
-      "loss": 1.4461,
+      "loss": 1.9005,
       "step": 3220
     },
     {
       "epoch": 1.68,
       "learning_rate": 0.0005587268638643833,
-      "loss": 1.5604,
+      "loss": 1.954,
       "step": 3230
     },
     {
       "epoch": 1.68,
       "learning_rate": 0.0005604566683964713,
-      "loss": 1.5141,
+      "loss": 1.9252,
       "step": 3240
     },
     {
       "epoch": 1.69,
       "learning_rate": 0.000562186472928559,
-      "loss": 1.2892,
+      "loss": 1.9827,
       "step": 3250
     },
     {
       "epoch": 1.69,
       "learning_rate": 0.000563916277460647,
-      "loss": 1.5422,
+      "loss": 1.7931,
       "step": 3260
     },
     {
       "epoch": 1.7,
       "learning_rate": 0.0005656460819927348,
-      "loss": 1.5151,
+      "loss": 1.8842,
       "step": 3270
     },
     {
       "epoch": 1.7,
       "learning_rate": 0.0005673758865248228,
-      "loss": 1.2204,
+      "loss": 1.8838,
       "step": 3280
     },
     {
       "epoch": 1.71,
       "learning_rate": 0.0005691056910569106,
-      "loss": 1.439,
+      "loss": 1.7902,
       "step": 3290
     },
     {
       "epoch": 1.71,
       "learning_rate": 0.0005708354955889984,
-      "loss": 1.4447,
+      "loss": 1.9054,
       "step": 3300
     },
     {
       "epoch": 1.72,
       "learning_rate": 0.0005725653001210863,
-      "loss": 1.1744,
+      "loss": 1.972,
       "step": 3310
     },
     {
       "epoch": 1.72,
       "learning_rate": 0.0005742951046531742,
-      "loss": 1.2408,
+      "loss": 1.999,
       "step": 3320
     },
     {
       "epoch": 1.73,
       "learning_rate": 0.0005760249091852621,
-      "loss": 1.8065,
+      "loss": 1.9566,
       "step": 3330
     },
     {
       "epoch": 1.73,
       "learning_rate": 0.00057775471371735,
-      "loss": 1.3944,
+      "loss": 1.8273,
       "step": 3340
     },
     {
       "epoch": 1.74,
       "learning_rate": 0.0005794845182494378,
-      "loss": 1.1947,
+      "loss": 1.9554,
       "step": 3350
     },
     {
       "epoch": 1.74,
       "learning_rate": 0.0005812143227815257,
-      "loss": 1.3017,
+      "loss": 2.0318,
       "step": 3360
     },
     {
       "epoch": 1.75,
       "learning_rate": 0.0005829441273136136,
-      "loss": 1.4716,
+      "loss": 1.9838,
       "step": 3370
     },
     {
       "epoch": 1.75,
       "learning_rate": 0.0005846739318457015,
-      "loss": 1.2759,
+      "loss": 1.9402,
       "step": 3380
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0005864037363777894,
-      "loss": 1.3031,
+      "loss": 1.9904,
       "step": 3390
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0005881335409098772,
-      "loss": 1.3675,
+      "loss": 1.9198,
       "step": 3400
     },
     {
       "epoch": 1.77,
       "learning_rate": 0.0005898633454419651,
-      "loss": 1.2222,
+      "loss": 1.9405,
       "step": 3410
     },
     {
       "epoch": 1.77,
       "learning_rate": 0.0005915931499740529,
-      "loss": 1.4357,
+      "loss": 1.8445,
       "step": 3420
     },
     {
       "epoch": 1.78,
       "learning_rate": 0.0005933229545061409,
-      "loss": 1.3645,
+      "loss": 1.9201,
       "step": 3430
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0005950527590382286,
-      "loss": 1.2761,
+      "loss": 1.8237,
       "step": 3440
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0005967825635703165,
-      "loss": 1.1856,
+      "loss": 1.7255,
       "step": 3450
     },
     {
       "epoch": 1.8,
       "learning_rate": 0.0005985123681024044,
-      "loss": 1.2648,
+      "loss": 1.844,
       "step": 3460
     },
     {
       "epoch": 1.8,
       "learning_rate": 0.0006002421726344923,
-      "loss": 1.4959,
+      "loss": 2.0433,
       "step": 3470
     },
     {
       "epoch": 1.81,
       "learning_rate": 0.0006019719771665802,
-      "loss": 1.4685,
+      "loss": 1.7753,
       "step": 3480
     },
     {
       "epoch": 1.81,
       "learning_rate": 0.000603701781698668,
-      "loss": 1.3261,
+      "loss": 1.858,
       "step": 3490
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0006054315862307559,
-      "loss": 1.4736,
+      "loss": 1.9348,
       "step": 3500
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0006071613907628438,
-      "loss": 1.1444,
+      "loss": 1.8196,
       "step": 3510
     },
     {
       "epoch": 1.83,
       "learning_rate": 0.0006088911952949317,
-      "loss": 1.2378,
+      "loss": 2.0001,
       "step": 3520
     },
     {
       "epoch": 1.83,
       "learning_rate": 0.0006106209998270195,
-      "loss": 1.223,
+      "loss": 1.806,
       "step": 3530
     },
     {
       "epoch": 1.84,
       "learning_rate": 0.0006123508043591074,
-      "loss": 1.4034,
+      "loss": 1.8369,
       "step": 3540
     },
     {
       "epoch": 1.84,
       "learning_rate": 0.0006140806088911953,
-      "loss": 1.7517,
+      "loss": 1.8824,
       "step": 3550
     },
     {
       "epoch": 1.85,
       "learning_rate": 0.0006158104134232832,
-      "loss": 1.1626,
+      "loss": 1.8376,
       "step": 3560
     },
     {
       "epoch": 1.85,
       "learning_rate": 0.0006175402179553711,
-      "loss": 1.6485,
+      "loss": 1.7554,
       "step": 3570
     },
     {
       "epoch": 1.86,
       "learning_rate": 0.0006192700224874589,
-      "loss": 1.3131,
+      "loss": 1.835,
       "step": 3580
     },
     {
       "epoch": 1.86,
       "learning_rate": 0.0006209998270195468,
-      "loss": 1.9879,
+      "loss": 1.7473,
       "step": 3590
     },
     {
       "epoch": 1.87,
       "learning_rate": 0.0006227296315516347,
-      "loss": 2.2167,
+      "loss": 1.8827,
       "step": 3600
     },
     {
       "epoch": 1.87,
       "learning_rate": 0.0006244594360837226,
-      "loss": 1.7252,
+      "loss": 1.7536,
       "step": 3610
     },
     {
       "epoch": 1.88,
       "learning_rate": 0.0006261892406158103,
-      "loss": 1.4711,
+      "loss": 1.8997,
       "step": 3620
     },
     {
       "epoch": 1.88,
       "learning_rate": 0.0006279190451478983,
-      "loss": 3.0262,
+      "loss": 1.813,
       "step": 3630
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0006296488496799861,
-      "loss": 2.2958,
+      "loss": 1.8474,
       "step": 3640
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0006313786542120741,
-      "loss": 2.0704,
+      "loss": 1.8263,
       "step": 3650
     },
     {
       "epoch": 1.9,
       "learning_rate": 0.0006331084587441619,
-      "loss": 2.2591,
+      "loss": 1.8817,
       "step": 3660
     },
     {
       "epoch": 1.9,
       "learning_rate": 0.0006348382632762499,
-      "loss": 1.97,
+      "loss": 1.9347,
       "step": 3670
     },
     {
       "epoch": 1.91,
       "learning_rate": 0.0006365680678083376,
-      "loss": 2.1573,
+      "loss": 1.786,
       "step": 3680
     },
     {
       "epoch": 1.91,
       "learning_rate": 0.0006382978723404256,
-      "loss": 2.087,
+      "loss": 2.197,
       "step": 3690
     },
     {
       "epoch": 1.92,
       "learning_rate": 0.0006400276768725134,
-      "loss": 2.0663,
+      "loss": 1.9695,
       "step": 3700
     },
     {
       "epoch": 1.93,
       "learning_rate": 0.0006417574814046014,
-      "loss": 2.0064,
+      "loss": 1.8939,
       "step": 3710
     },
     {
       "epoch": 1.93,
       "learning_rate": 0.0006434872859366891,
-      "loss": 2.0182,
+      "loss": 1.8662,
       "step": 3720
     },
     {
       "epoch": 1.94,
       "learning_rate": 0.0006452170904687771,
-      "loss": 1.9402,
+      "loss": 1.8054,
       "step": 3730
     },
     {
       "epoch": 1.94,
       "learning_rate": 0.0006469468950008649,
-      "loss": 1.983,
+      "loss": 1.8351,
       "step": 3740
     },
     {
       "epoch": 1.95,
       "learning_rate": 0.0006486766995329529,
-      "loss": 2.0534,
+      "loss": 1.9102,
       "step": 3750
     },
     {
       "epoch": 1.95,
       "learning_rate": 0.0006504065040650406,
-      "loss": 1.9642,
+      "loss": 1.8462,
       "step": 3760
     },
     {
       "epoch": 1.96,
       "learning_rate": 0.0006521363085971285,
-      "loss": 1.9313,
+      "loss": 1.894,
       "step": 3770
     },
     {
       "epoch": 1.96,
       "learning_rate": 0.0006538661131292164,
-      "loss": 2.0084,
+      "loss": 1.7559,
       "step": 3780
     },
     {
       "epoch": 1.97,
       "learning_rate": 0.0006555959176613043,
-      "loss": 2.0157,
+      "loss": 1.8255,
       "step": 3790
     },
     {
       "epoch": 1.97,
       "learning_rate": 0.0006573257221933922,
-      "loss": 1.9813,
+      "loss": 1.7118,
       "step": 3800
     },
     {
       "epoch": 1.98,
       "learning_rate": 0.00065905552672548,
-      "loss": 1.9853,
+      "loss": 1.8048,
       "step": 3810
     },
     {
       "epoch": 1.98,
       "learning_rate": 0.0006607853312575679,
-      "loss": 1.9809,
+      "loss": 1.7759,
       "step": 3820
     },
     {
       "epoch": 1.99,
       "learning_rate": 0.0006625151357896558,
-      "loss": 2.0094,
+      "loss": 1.7974,
       "step": 3830
     },
     {
       "epoch": 1.99,
       "learning_rate": 0.0006642449403217437,
-      "loss": 1.9417,
+      "loss": 1.7673,
       "step": 3840
     },
     {
       "epoch": 2.0,
       "learning_rate": 0.0006659747448538316,
-      "loss": 2.0076,
+      "loss": 1.7959,
       "step": 3850
     },
     {
       "epoch": 2.0,
       "eval_accuracy": {
-        "accuracy": 0.13955901426718548
+        "accuracy": 0.26848249027237353
       },
       "eval_f1": {
-        "f1": 0.034990732008715164
+        "f1": 0.17635435227079216
       },
-      "eval_loss": 1.934989094734192,
+      "eval_loss": 1.8579649925231934,
       "eval_precision": {
-        "precision": 0.019937002038169355
+        "precision": 0.15600300783137744
       },
       "eval_recall": {
-        "recall": 0.14285714285714285
+        "recall": 0.2748312652287413
       },
-      "eval_runtime": 120.7926,
-      "eval_samples_per_second": 31.914,
-      "eval_steps_per_second": 15.961,
+      "eval_runtime": 115.151,
+      "eval_samples_per_second": 33.478,
+      "eval_steps_per_second": 16.743,
       "step": 3854
     }
   ],

tmp-checkpoint-3854/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7c0f633499ef7b79e3057e99e58bfbfb1c03c08f9b6fa020f2228d0e2537df
+oid sha256:9c4e0514912b5f3d200ad2aec0814727d3064165a4d951379f5c5cc93d9c62d9
 size 4792