Upload 10 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02327efcf7b09ce4e6f4076861caabbc5a9ba706287ac7c9fa1c5d245d41a288
+oid sha256:f057b0846c947bb59d50225087224cb9ccec7e27b7d65bdbc4b57d8f00d8fc54
 size 13779559309

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1843985d65d92cb4cafa4d4d876cf38216612b9052b535a1d4997eb573d80a
+oid sha256:981a73f60e2c53fdc994e2a44ffbd3adaf99e4cd18aa7af9c0a24cd48542713c
 size 6889753481

trainer_state.json

@@ -10,907 +10,907 @@
     {
       "epoch": 0.0,
       "learning_rate": 4.9971428571428576e-05,
-      "loss": 3.1194,
+      "loss": 2.5589,
       "step": 1
     },
     {
       "epoch": 0.02,
       "learning_rate": 4.9e-05,
-      "loss": 3.222,
+      "loss": 4.0188,
       "step": 35
     },
     {
       "epoch": 0.02,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6869668960571289,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 240.1814,
-      "eval_samples_per_second": 12.491,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.5033333333333333,
+      "eval_f1": 0.015852047556142668,
+      "eval_loss": 1.71467924118042,
+      "eval_precision": 0.8571428571428571,
+      "eval_recall": 0.008,
+      "eval_runtime": 245.0349,
+      "eval_samples_per_second": 12.243,
+      "eval_steps_per_second": 1.53,
       "step": 35
     },
     {
       "epoch": 0.04,
       "learning_rate": 4.8e-05,
-      "loss": 1.7052,
+      "loss": 1.1269,
       "step": 70
     },
     {
       "epoch": 0.04,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 2.0989105701446533,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 240.275,
-      "eval_samples_per_second": 12.486,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.5356666666666666,
+      "eval_f1": 0.15932407966203982,
+      "eval_loss": 0.8176602125167847,
+      "eval_precision": 0.8407643312101911,
+      "eval_recall": 0.088,
+      "eval_runtime": 245.0774,
+      "eval_samples_per_second": 12.241,
+      "eval_steps_per_second": 1.53,
       "step": 70
     },
     {
       "epoch": 0.06,
       "learning_rate": 4.7e-05,
-      "loss": 1.4622,
+      "loss": 0.9901,
       "step": 105
     },
     {
       "epoch": 0.06,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.6666666666666666,
-      "eval_loss": 0.706234872341156,
-      "eval_precision": 0.5,
-      "eval_recall": 1.0,
-      "eval_runtime": 240.4103,
-      "eval_samples_per_second": 12.479,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.5946666666666667,
+      "eval_f1": 0.36401673640167365,
+      "eval_loss": 1.4929765462875366,
+      "eval_precision": 0.8446601941747572,
+      "eval_recall": 0.232,
+      "eval_runtime": 244.7538,
+      "eval_samples_per_second": 12.257,
+      "eval_steps_per_second": 1.532,
       "step": 105
     },
     {
       "epoch": 0.08,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 0.9345,
+      "loss": 1.2113,
       "step": 140
     },
     {
       "epoch": 0.08,
-      "eval_accuracy": 0.514,
-      "eval_f1": 0.6729475100942127,
-      "eval_loss": 0.7361006140708923,
-      "eval_precision": 0.5070993914807302,
-      "eval_recall": 1.0,
-      "eval_runtime": 240.3366,
-      "eval_samples_per_second": 12.482,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.619,
+      "eval_f1": 0.7197842608482471,
+      "eval_loss": 0.744438648223877,
+      "eval_precision": 0.5692128732066692,
+      "eval_recall": 0.9786666666666667,
+      "eval_runtime": 244.6225,
+      "eval_samples_per_second": 12.264,
+      "eval_steps_per_second": 1.533,
       "step": 140
     },
     {
       "epoch": 0.1,
       "learning_rate": 4.5e-05,
-      "loss": 1.3471,
+      "loss": 0.7836,
       "step": 175
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.5063333333333333,
-      "eval_f1": 0.6693458361241348,
-      "eval_loss": 0.7378450632095337,
-      "eval_precision": 0.5031889895938234,
-      "eval_recall": 0.9993333333333333,
-      "eval_runtime": 240.3903,
-      "eval_samples_per_second": 12.48,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.689,
+      "eval_f1": 0.5959289735816371,
+      "eval_loss": 0.6166332364082336,
+      "eval_precision": 0.8504326328800988,
+      "eval_recall": 0.45866666666666667,
+      "eval_runtime": 244.7744,
+      "eval_samples_per_second": 12.256,
+      "eval_steps_per_second": 1.532,
       "step": 175
     },
     {
       "epoch": 0.12,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 1.0776,
+      "loss": 0.7519,
       "step": 210
     },
     {
       "epoch": 0.12,
-      "eval_accuracy": 0.502,
-      "eval_f1": 0.6675567423230975,
-      "eval_loss": 1.2094249725341797,
-      "eval_precision": 0.501002004008016,
-      "eval_recall": 1.0,
-      "eval_runtime": 241.2524,
-      "eval_samples_per_second": 12.435,
-      "eval_steps_per_second": 1.554,
+      "eval_accuracy": 0.775,
+      "eval_f1": 0.7330960854092525,
+      "eval_loss": 0.6699690818786621,
+      "eval_precision": 0.9008746355685131,
+      "eval_recall": 0.618,
+      "eval_runtime": 245.4062,
+      "eval_samples_per_second": 12.225,
+      "eval_steps_per_second": 1.528,
       "step": 210
     },
     {
       "epoch": 0.14,
       "learning_rate": 4.3e-05,
-      "loss": 0.7897,
+      "loss": 1.0327,
       "step": 245
     },
     {
       "epoch": 0.14,
-      "eval_accuracy": 0.818,
-      "eval_f1": 0.8189655172413793,
-      "eval_loss": 0.42468851804733276,
-      "eval_precision": 0.8146437994722955,
-      "eval_recall": 0.8233333333333334,
-      "eval_runtime": 240.4771,
-      "eval_samples_per_second": 12.475,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_f1": 0.5988078862906923,
+      "eval_loss": 0.5815353393554688,
+      "eval_precision": 0.9588839941262849,
+      "eval_recall": 0.43533333333333335,
+      "eval_runtime": 245.1736,
+      "eval_samples_per_second": 12.236,
+      "eval_steps_per_second": 1.53,
       "step": 245
     },
     {
       "epoch": 0.16,
       "learning_rate": 4.2e-05,
-      "loss": 0.8229,
+      "loss": 0.7039,
       "step": 280
     },
     {
       "epoch": 0.16,
-      "eval_accuracy": 0.6603333333333333,
-      "eval_f1": 0.7405143875732112,
-      "eval_loss": 0.7496446967124939,
-      "eval_precision": 0.5990935311083643,
-      "eval_recall": 0.9693333333333334,
-      "eval_runtime": 241.2847,
-      "eval_samples_per_second": 12.433,
-      "eval_steps_per_second": 1.554,
+      "eval_accuracy": 0.7043333333333334,
+      "eval_f1": 0.5891616489115331,
+      "eval_loss": 1.3649965524673462,
+      "eval_precision": 0.9650986342943855,
+      "eval_recall": 0.424,
+      "eval_runtime": 247.043,
+      "eval_samples_per_second": 12.144,
+      "eval_steps_per_second": 1.518,
       "step": 280
     },
     {
       "epoch": 0.18,
       "learning_rate": 4.1e-05,
-      "loss": 0.8056,
+      "loss": 1.26,
       "step": 315
     },
     {
       "epoch": 0.18,
-      "eval_accuracy": 0.653,
-      "eval_f1": 0.7400749063670412,
-      "eval_loss": 0.7388193607330322,
-      "eval_precision": 0.5916167664670658,
-      "eval_recall": 0.988,
-      "eval_runtime": 240.4851,
-      "eval_samples_per_second": 12.475,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.7916666666666666,
+      "eval_f1": 0.7464503042596349,
+      "eval_loss": 0.6255013942718506,
+      "eval_precision": 0.9533678756476683,
+      "eval_recall": 0.6133333333333333,
+      "eval_runtime": 245.1858,
+      "eval_samples_per_second": 12.236,
+      "eval_steps_per_second": 1.529,
       "step": 315
     },
     {
       "epoch": 0.2,
       "learning_rate": 4e-05,
-      "loss": 0.831,
+      "loss": 0.5196,
       "step": 350
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.7976666666666666,
-      "eval_f1": 0.7876880027981812,
-      "eval_loss": 0.45541757345199585,
-      "eval_precision": 0.8285504047093452,
-      "eval_recall": 0.7506666666666667,
-      "eval_runtime": 240.8878,
-      "eval_samples_per_second": 12.454,
-      "eval_steps_per_second": 1.557,
+      "eval_accuracy": 0.855,
+      "eval_f1": 0.8476357267950964,
+      "eval_loss": 0.4524073004722595,
+      "eval_precision": 0.8929889298892989,
+      "eval_recall": 0.8066666666666666,
+      "eval_runtime": 244.8477,
+      "eval_samples_per_second": 12.253,
+      "eval_steps_per_second": 1.532,
       "step": 350
     },
     {
       "epoch": 0.22,
       "learning_rate": 3.9000000000000006e-05,
-      "loss": 0.3693,
+      "loss": 0.7179,
       "step": 385
     },
     {
       "epoch": 0.22,
-      "eval_accuracy": 0.764,
-      "eval_f1": 0.7972508591065293,
-      "eval_loss": 0.567838191986084,
-      "eval_precision": 0.6987951807228916,
-      "eval_recall": 0.928,
-      "eval_runtime": 240.8981,
-      "eval_samples_per_second": 12.453,
-      "eval_steps_per_second": 1.557,
+      "eval_accuracy": 0.795,
+      "eval_f1": 0.76409666283084,
+      "eval_loss": 0.6408818960189819,
+      "eval_precision": 0.8997289972899729,
+      "eval_recall": 0.664,
+      "eval_runtime": 244.8569,
+      "eval_samples_per_second": 12.252,
+      "eval_steps_per_second": 1.532,
       "step": 385
     },
     {
       "epoch": 0.24,
       "learning_rate": 3.8e-05,
-      "loss": 0.7178,
+      "loss": 0.7823,
       "step": 420
     },
     {
       "epoch": 0.24,
-      "eval_accuracy": 0.8273333333333334,
-      "eval_f1": 0.832579185520362,
-      "eval_loss": 0.4122844934463501,
-      "eval_precision": 0.8080301129234629,
-      "eval_recall": 0.8586666666666667,
-      "eval_runtime": 240.7253,
-      "eval_samples_per_second": 12.462,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.821,
+      "eval_f1": 0.7869892899643,
+      "eval_loss": 0.4732283651828766,
+      "eval_precision": 0.9715964740450539,
+      "eval_recall": 0.6613333333333333,
+      "eval_runtime": 244.9263,
+      "eval_samples_per_second": 12.249,
+      "eval_steps_per_second": 1.531,
       "step": 420
     },
     {
       "epoch": 0.26,
       "learning_rate": 3.7e-05,
-      "loss": 0.5769,
+      "loss": 0.2816,
       "step": 455
     },
     {
       "epoch": 0.26,
-      "eval_accuracy": 0.8406666666666667,
-      "eval_f1": 0.8505315822388994,
-      "eval_loss": 0.3792554438114166,
-      "eval_precision": 0.800942285041225,
-      "eval_recall": 0.9066666666666666,
-      "eval_runtime": 240.7257,
-      "eval_samples_per_second": 12.462,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.89,
+      "eval_f1": 0.8825622775800712,
+      "eval_loss": 0.5548559427261353,
+      "eval_precision": 0.9465648854961832,
+      "eval_recall": 0.8266666666666667,
+      "eval_runtime": 245.0027,
+      "eval_samples_per_second": 12.245,
+      "eval_steps_per_second": 1.531,
       "step": 455
     },
     {
       "epoch": 0.28,
       "learning_rate": 3.6e-05,
-      "loss": 0.5896,
+      "loss": 0.3043,
       "step": 490
     },
     {
       "epoch": 0.28,
-      "eval_accuracy": 0.6713333333333333,
-      "eval_f1": 0.7512613521695257,
-      "eval_loss": 0.8622921705245972,
-      "eval_precision": 0.604301948051948,
-      "eval_recall": 0.9926666666666667,
-      "eval_runtime": 240.7579,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.8976666666666666,
+      "eval_f1": 0.8971524288107202,
+      "eval_loss": 0.48737743496894836,
+      "eval_precision": 0.9016835016835016,
+      "eval_recall": 0.8926666666666667,
+      "eval_runtime": 245.4898,
+      "eval_samples_per_second": 12.22,
+      "eval_steps_per_second": 1.528,
       "step": 490
     },
     {
       "epoch": 0.3,
       "learning_rate": 3.5e-05,
-      "loss": 0.4586,
+      "loss": 0.8005,
       "step": 525
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.8066666666666666,
-      "eval_f1": 0.791816223977028,
-      "eval_loss": 0.5524763464927673,
-      "eval_precision": 0.8576982892690513,
-      "eval_recall": 0.7353333333333333,
-      "eval_runtime": 241.0103,
-      "eval_samples_per_second": 12.448,
-      "eval_steps_per_second": 1.556,
+      "eval_accuracy": 0.8443333333333334,
+      "eval_f1": 0.8613831997625407,
+      "eval_loss": 0.899199366569519,
+      "eval_precision": 0.7763509898341359,
+      "eval_recall": 0.9673333333333334,
+      "eval_runtime": 245.655,
+      "eval_samples_per_second": 12.212,
+      "eval_steps_per_second": 1.527,
       "step": 525
     },
     {
       "epoch": 0.32,
       "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.5359,
+      "loss": 0.5206,
       "step": 560
     },
     {
       "epoch": 0.32,
-      "eval_accuracy": 0.5066666666666667,
-      "eval_f1": 0.6696428571428572,
-      "eval_loss": 2.7870869636535645,
-      "eval_precision": 0.5033557046979866,
-      "eval_recall": 1.0,
-      "eval_runtime": 240.5172,
-      "eval_samples_per_second": 12.473,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.881,
+      "eval_f1": 0.8879824286162535,
+      "eval_loss": 0.5689557194709778,
+      "eval_precision": 0.8387670420865442,
+      "eval_recall": 0.9433333333333334,
+      "eval_runtime": 245.8808,
+      "eval_samples_per_second": 12.201,
+      "eval_steps_per_second": 1.525,
       "step": 560
     },
     {
       "epoch": 0.34,
       "learning_rate": 3.3e-05,
-      "loss": 0.4746,
+      "loss": 0.2982,
       "step": 595
     },
     {
       "epoch": 0.34,
-      "eval_accuracy": 0.728,
-      "eval_f1": 0.7827476038338658,
-      "eval_loss": 0.8008346557617188,
-      "eval_precision": 0.651595744680851,
-      "eval_recall": 0.98,
-      "eval_runtime": 241.3279,
-      "eval_samples_per_second": 12.431,
-      "eval_steps_per_second": 1.554,
+      "eval_accuracy": 0.8383333333333334,
+      "eval_f1": 0.8556977090151742,
+      "eval_loss": 1.3064663410186768,
+      "eval_precision": 0.7727028479312198,
+      "eval_recall": 0.9586666666666667,
+      "eval_runtime": 244.8259,
+      "eval_samples_per_second": 12.254,
+      "eval_steps_per_second": 1.532,
       "step": 595
     },
     {
       "epoch": 0.36,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 0.4525,
+      "loss": 1.159,
       "step": 630
     },
     {
       "epoch": 0.36,
-      "eval_accuracy": 0.819,
-      "eval_f1": 0.831104199066874,
-      "eval_loss": 0.4293590486049652,
-      "eval_precision": 0.7790087463556852,
-      "eval_recall": 0.8906666666666667,
-      "eval_runtime": 240.4794,
-      "eval_samples_per_second": 12.475,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.8866666666666667,
+      "eval_f1": 0.8924731182795699,
+      "eval_loss": 0.6431537866592407,
+      "eval_precision": 0.8489771359807461,
+      "eval_recall": 0.9406666666666667,
+      "eval_runtime": 244.8113,
+      "eval_samples_per_second": 12.254,
+      "eval_steps_per_second": 1.532,
       "step": 630
     },
     {
       "epoch": 0.38,
       "learning_rate": 3.1e-05,
-      "loss": 0.5492,
+      "loss": 0.4328,
       "step": 665
     },
     {
       "epoch": 0.38,
-      "eval_accuracy": 0.8193333333333334,
-      "eval_f1": 0.7991104521868051,
-      "eval_loss": 0.6366798281669617,
-      "eval_precision": 0.8998330550918197,
-      "eval_recall": 0.7186666666666667,
-      "eval_runtime": 240.7182,
-      "eval_samples_per_second": 12.463,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.8996666666666666,
+      "eval_f1": 0.9056130448416432,
+      "eval_loss": 0.4550739824771881,
+      "eval_precision": 0.8549437537004144,
+      "eval_recall": 0.9626666666666667,
+      "eval_runtime": 250.1284,
+      "eval_samples_per_second": 11.994,
+      "eval_steps_per_second": 1.499,
       "step": 665
     },
     {
       "epoch": 0.4,
       "learning_rate": 3e-05,
-      "loss": 0.3315,
+      "loss": 0.4249,
       "step": 700
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.8446666666666667,
-      "eval_f1": 0.8411724608043626,
-      "eval_loss": 0.44469600915908813,
-      "eval_precision": 0.8605299860529986,
-      "eval_recall": 0.8226666666666667,
-      "eval_runtime": 240.3073,
-      "eval_samples_per_second": 12.484,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.8913333333333333,
+      "eval_f1": 0.8823953823953824,
+      "eval_loss": 0.40748831629753113,
+      "eval_precision": 0.9614779874213837,
+      "eval_recall": 0.8153333333333334,
+      "eval_runtime": 244.9069,
+      "eval_samples_per_second": 12.25,
+      "eval_steps_per_second": 1.531,
       "step": 700
     },
     {
       "epoch": 0.42,
       "learning_rate": 2.9e-05,
-      "loss": 0.5122,
+      "loss": 0.435,
       "step": 735
     },
     {
       "epoch": 0.42,
-      "eval_accuracy": 0.723,
-      "eval_f1": 0.7735077677841373,
-      "eval_loss": 0.7516367435455322,
-      "eval_precision": 0.6542185338865837,
-      "eval_recall": 0.946,
-      "eval_runtime": 240.4309,
-      "eval_samples_per_second": 12.478,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.9173333333333333,
+      "eval_f1": 0.9194805194805196,
+      "eval_loss": 0.28212666511535645,
+      "eval_precision": 0.8962025316455696,
+      "eval_recall": 0.944,
+      "eval_runtime": 247.2532,
+      "eval_samples_per_second": 12.133,
+      "eval_steps_per_second": 1.517,
       "step": 735
     },
     {
       "epoch": 0.44,
       "learning_rate": 2.8000000000000003e-05,
-      "loss": 0.4712,
+      "loss": 0.2909,
       "step": 770
     },
     {
       "epoch": 0.44,
-      "eval_accuracy": 0.7073333333333334,
-      "eval_f1": 0.7701570680628271,
-      "eval_loss": 0.7024486660957336,
-      "eval_precision": 0.634051724137931,
-      "eval_recall": 0.9806666666666667,
-      "eval_runtime": 240.5793,
-      "eval_samples_per_second": 12.47,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9186666666666666,
+      "eval_f1": 0.9155124653739612,
+      "eval_loss": 0.2652963101863861,
+      "eval_precision": 0.952449567723343,
+      "eval_recall": 0.8813333333333333,
+      "eval_runtime": 244.8465,
+      "eval_samples_per_second": 12.253,
+      "eval_steps_per_second": 1.532,
       "step": 770
     },
     {
       "epoch": 0.46,
       "learning_rate": 2.7000000000000002e-05,
-      "loss": 0.5167,
+      "loss": 0.2164,
       "step": 805
     },
     {
       "epoch": 0.46,
-      "eval_accuracy": 0.637,
-      "eval_f1": 0.7323666748586877,
-      "eval_loss": 1.0258432626724243,
-      "eval_precision": 0.5799922148695991,
-      "eval_recall": 0.9933333333333333,
-      "eval_runtime": 240.5552,
-      "eval_samples_per_second": 12.471,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.908,
+      "eval_f1": 0.911651728553137,
+      "eval_loss": 0.41052377223968506,
+      "eval_precision": 0.8768472906403941,
+      "eval_recall": 0.9493333333333334,
+      "eval_runtime": 244.9871,
+      "eval_samples_per_second": 12.246,
+      "eval_steps_per_second": 1.531,
       "step": 805
     },
     {
       "epoch": 0.48,
       "learning_rate": 2.6000000000000002e-05,
-      "loss": 0.3025,
+      "loss": 0.2741,
       "step": 840
     },
     {
       "epoch": 0.48,
-      "eval_accuracy": 0.7826666666666666,
-      "eval_f1": 0.8170594837261503,
-      "eval_loss": 0.5468646883964539,
-      "eval_precision": 0.7054263565891473,
-      "eval_recall": 0.9706666666666667,
-      "eval_runtime": 240.9803,
-      "eval_samples_per_second": 12.449,
-      "eval_steps_per_second": 1.556,
+      "eval_accuracy": 0.9086666666666666,
+      "eval_f1": 0.9023521026372059,
+      "eval_loss": 0.35454556345939636,
+      "eval_precision": 0.9693721286370597,
+      "eval_recall": 0.844,
+      "eval_runtime": 245.5305,
+      "eval_samples_per_second": 12.218,
+      "eval_steps_per_second": 1.527,
       "step": 840
     },
     {
       "epoch": 0.5,
       "learning_rate": 2.5e-05,
-      "loss": 0.3937,
+      "loss": 0.3406,
       "step": 875
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.7956666666666666,
-      "eval_f1": 0.8233938346297897,
-      "eval_loss": 0.5975732207298279,
-      "eval_precision": 0.7250126839167935,
-      "eval_recall": 0.9526666666666667,
-      "eval_runtime": 240.6768,
-      "eval_samples_per_second": 12.465,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.9306666666666666,
+      "eval_f1": 0.9311258278145697,
+      "eval_loss": 0.2322322428226471,
+      "eval_precision": 0.925,
+      "eval_recall": 0.9373333333333334,
+      "eval_runtime": 244.978,
+      "eval_samples_per_second": 12.246,
+      "eval_steps_per_second": 1.531,
       "step": 875
     },
     {
       "epoch": 0.52,
       "learning_rate": 2.4e-05,
-      "loss": 0.3635,
+      "loss": 0.2471,
       "step": 910
     },
     {
       "epoch": 0.52,
-      "eval_accuracy": 0.7516666666666667,
-      "eval_f1": 0.7974993204675184,
-      "eval_loss": 0.681395411491394,
-      "eval_precision": 0.6732446076181735,
-      "eval_recall": 0.978,
-      "eval_runtime": 243.1168,
-      "eval_samples_per_second": 12.34,
-      "eval_steps_per_second": 1.542,
+      "eval_accuracy": 0.9176666666666666,
+      "eval_f1": 0.9146804835924007,
+      "eval_loss": 0.3999188542366028,
+      "eval_precision": 0.9491039426523298,
+      "eval_recall": 0.8826666666666667,
+      "eval_runtime": 246.19,
+      "eval_samples_per_second": 12.186,
+      "eval_steps_per_second": 1.523,
       "step": 910
     },
     {
       "epoch": 0.54,
       "learning_rate": 2.3000000000000003e-05,
-      "loss": 0.3354,
+      "loss": 0.4955,
       "step": 945
     },
     {
       "epoch": 0.54,
-      "eval_accuracy": 0.6006666666666667,
-      "eval_f1": 0.7139446036294174,
-      "eval_loss": 1.097399115562439,
-      "eval_precision": 0.5561755952380952,
-      "eval_recall": 0.9966666666666667,
-      "eval_runtime": 240.1778,
-      "eval_samples_per_second": 12.491,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.8633333333333333,
+      "eval_f1": 0.844106463878327,
+      "eval_loss": 0.5945030450820923,
+      "eval_precision": 0.9823008849557522,
+      "eval_recall": 0.74,
+      "eval_runtime": 245.9264,
+      "eval_samples_per_second": 12.199,
+      "eval_steps_per_second": 1.525,
       "step": 945
     },
     {
       "epoch": 0.56,
       "learning_rate": 2.2000000000000003e-05,
-      "loss": 0.2047,
+      "loss": 0.3085,
       "step": 980
     },
     {
       "epoch": 0.56,
-      "eval_accuracy": 0.5143333333333333,
-      "eval_f1": 0.6729517396184064,
-      "eval_loss": 1.91347074508667,
-      "eval_precision": 0.5072758037225042,
-      "eval_recall": 0.9993333333333333,
-      "eval_runtime": 240.5169,
-      "eval_samples_per_second": 12.473,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9136666666666666,
+      "eval_f1": 0.908641975308642,
+      "eval_loss": 0.39902010560035706,
+      "eval_precision": 0.9647940074906367,
+      "eval_recall": 0.8586666666666667,
+      "eval_runtime": 245.3453,
+      "eval_samples_per_second": 12.228,
+      "eval_steps_per_second": 1.528,
       "step": 980
     },
     {
       "epoch": 0.58,
       "learning_rate": 2.1e-05,
-      "loss": 0.4875,
+      "loss": 0.513,
       "step": 1015
     },
     {
       "epoch": 0.58,
-      "eval_accuracy": 0.8083333333333333,
-      "eval_f1": 0.833574529667149,
-      "eval_loss": 0.5008577704429626,
-      "eval_precision": 0.7365728900255755,
-      "eval_recall": 0.96,
-      "eval_runtime": 240.1154,
-      "eval_samples_per_second": 12.494,
-      "eval_steps_per_second": 1.562,
+      "eval_accuracy": 0.9236666666666666,
+      "eval_f1": 0.9236921026324558,
+      "eval_loss": 0.21340703964233398,
+      "eval_precision": 0.9233844103930713,
+      "eval_recall": 0.924,
+      "eval_runtime": 244.8648,
+      "eval_samples_per_second": 12.252,
+      "eval_steps_per_second": 1.531,
       "step": 1015
     },
     {
       "epoch": 0.6,
       "learning_rate": 2e-05,
-      "loss": 0.2811,
+      "loss": 0.2576,
       "step": 1050
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.8413333333333334,
-      "eval_f1": 0.8487928843710293,
-      "eval_loss": 0.3812311887741089,
-      "eval_precision": 0.8106796116504854,
-      "eval_recall": 0.8906666666666667,
-      "eval_runtime": 240.4478,
-      "eval_samples_per_second": 12.477,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.9283333333333333,
+      "eval_f1": 0.9271926854046733,
+      "eval_loss": 0.30752047896385193,
+      "eval_precision": 0.9421885753613214,
+      "eval_recall": 0.9126666666666666,
+      "eval_runtime": 319.7381,
+      "eval_samples_per_second": 9.383,
+      "eval_steps_per_second": 1.173,
       "step": 1050
     },
     {
       "epoch": 0.62,
       "learning_rate": 1.9e-05,
-      "loss": 0.2227,
+      "loss": 0.3558,
       "step": 1085
     },
     {
       "epoch": 0.62,
-      "eval_accuracy": 0.8606666666666667,
-      "eval_f1": 0.862137203166227,
-      "eval_loss": 0.36810368299484253,
-      "eval_precision": 0.8531331592689295,
-      "eval_recall": 0.8713333333333333,
-      "eval_runtime": 240.5301,
-      "eval_samples_per_second": 12.472,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9276666666666666,
+      "eval_f1": 0.9297961824652217,
+      "eval_loss": 0.24874693155288696,
+      "eval_precision": 0.9032055311125079,
+      "eval_recall": 0.958,
+      "eval_runtime": 245.9624,
+      "eval_samples_per_second": 12.197,
+      "eval_steps_per_second": 1.525,
       "step": 1085
     },
     {
       "epoch": 0.64,
       "learning_rate": 1.8e-05,
-      "loss": 0.3917,
+      "loss": 0.2618,
       "step": 1120
     },
     {
       "epoch": 0.64,
-      "eval_accuracy": 0.8543333333333333,
-      "eval_f1": 0.8612257859637981,
-      "eval_loss": 0.4265972375869751,
-      "eval_precision": 0.8223165554881746,
-      "eval_recall": 0.904,
-      "eval_runtime": 241.0329,
-      "eval_samples_per_second": 12.446,
-      "eval_steps_per_second": 1.556,
+      "eval_accuracy": 0.9396666666666667,
+      "eval_f1": 0.9407528641571195,
+      "eval_loss": 0.3159142732620239,
+      "eval_precision": 0.9241157556270096,
+      "eval_recall": 0.958,
+      "eval_runtime": 245.9065,
+      "eval_samples_per_second": 12.2,
+      "eval_steps_per_second": 1.525,
       "step": 1120
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.7000000000000003e-05,
-      "loss": 0.3635,
+      "loss": 0.2992,
       "step": 1155
     },
     {
       "epoch": 0.66,
-      "eval_accuracy": 0.6436666666666667,
-      "eval_f1": 0.736374845869297,
-      "eval_loss": 1.1040711402893066,
-      "eval_precision": 0.5843444227005871,
-      "eval_recall": 0.9953333333333333,
-      "eval_runtime": 240.5878,
-      "eval_samples_per_second": 12.469,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9313333333333333,
+      "eval_f1": 0.9339320076972418,
+      "eval_loss": 0.33460330963134766,
+      "eval_precision": 0.899876390605686,
+      "eval_recall": 0.9706666666666667,
+      "eval_runtime": 245.128,
+      "eval_samples_per_second": 12.239,
+      "eval_steps_per_second": 1.53,
       "step": 1155
     },
     {
       "epoch": 0.68,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.4145,
+      "loss": 0.2474,
       "step": 1190
     },
     {
       "epoch": 0.68,
-      "eval_accuracy": 0.8136666666666666,
-      "eval_f1": 0.8390440541318746,
-      "eval_loss": 0.5226981043815613,
-      "eval_precision": 0.7384693360364927,
-      "eval_recall": 0.9713333333333334,
-      "eval_runtime": 240.5513,
-      "eval_samples_per_second": 12.471,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9346666666666666,
+      "eval_f1": 0.9332879509870661,
+      "eval_loss": 0.265165776014328,
+      "eval_precision": 0.9534075104311543,
+      "eval_recall": 0.914,
+      "eval_runtime": 245.8947,
+      "eval_samples_per_second": 12.2,
+      "eval_steps_per_second": 1.525,
       "step": 1190
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.5e-05,
-      "loss": 0.4154,
+      "loss": 0.3008,
       "step": 1225
     },
     {
       "epoch": 0.7,
-      "eval_accuracy": 0.6573333333333333,
-      "eval_f1": 0.7438963627304432,
-      "eval_loss": 0.8615061640739441,
-      "eval_precision": 0.5938743038981702,
-      "eval_recall": 0.9953333333333333,
-      "eval_runtime": 241.311,
-      "eval_samples_per_second": 12.432,
-      "eval_steps_per_second": 1.554,
+      "eval_accuracy": 0.9423333333333334,
+      "eval_f1": 0.9421211107393778,
+      "eval_loss": 0.22882609069347382,
+      "eval_precision": 0.9456010745466756,
+      "eval_recall": 0.9386666666666666,
+      "eval_runtime": 245.6581,
+      "eval_samples_per_second": 12.212,
+      "eval_steps_per_second": 1.527,
       "step": 1225
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.4000000000000001e-05,
-      "loss": 0.2322,
+      "loss": 0.2605,
       "step": 1260
     },
     {
       "epoch": 0.72,
-      "eval_accuracy": 0.627,
-      "eval_f1": 0.7275383491599707,
-      "eval_loss": 1.0941112041473389,
-      "eval_precision": 0.57307249712313,
-      "eval_recall": 0.996,
-      "eval_runtime": 240.2621,
-      "eval_samples_per_second": 12.486,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.9256666666666666,
+      "eval_f1": 0.9292288162488098,
+      "eval_loss": 0.3908889591693878,
+      "eval_precision": 0.8867353119321624,
+      "eval_recall": 0.976,
+      "eval_runtime": 246.273,
+      "eval_samples_per_second": 12.182,
+      "eval_steps_per_second": 1.523,
       "step": 1260
     },
     {
       "epoch": 0.74,
       "learning_rate": 1.3000000000000001e-05,
-      "loss": 0.3221,
+      "loss": 0.2565,
       "step": 1295
     },
     {
       "epoch": 0.74,
-      "eval_accuracy": 0.722,
-      "eval_f1": 0.7807570977917981,
-      "eval_loss": 0.7642508149147034,
-      "eval_precision": 0.64453125,
-      "eval_recall": 0.99,
-      "eval_runtime": 240.1026,
-      "eval_samples_per_second": 12.495,
-      "eval_steps_per_second": 1.562,
+      "eval_accuracy": 0.9313333333333333,
+      "eval_f1": 0.9340588988476314,
+      "eval_loss": 0.39725252985954285,
+      "eval_precision": 0.8983990147783252,
+      "eval_recall": 0.9726666666666667,
+      "eval_runtime": 245.9637,
+      "eval_samples_per_second": 12.197,
+      "eval_steps_per_second": 1.525,
       "step": 1295
     },
     {
       "epoch": 0.76,
       "learning_rate": 1.2e-05,
-      "loss": 0.2182,
+      "loss": 0.3269,
       "step": 1330
     },
     {
       "epoch": 0.76,
-      "eval_accuracy": 0.8256666666666667,
-      "eval_f1": 0.847477398658501,
-      "eval_loss": 0.4936087727546692,
-      "eval_precision": 0.7532400207361327,
-      "eval_recall": 0.9686666666666667,
-      "eval_runtime": 240.5209,
-      "eval_samples_per_second": 12.473,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9373333333333334,
+      "eval_f1": 0.936141304347826,
+      "eval_loss": 0.2685074806213379,
+      "eval_precision": 0.9542936288088643,
+      "eval_recall": 0.9186666666666666,
+      "eval_runtime": 245.6322,
+      "eval_samples_per_second": 12.213,
+      "eval_steps_per_second": 1.527,
       "step": 1330
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.1000000000000001e-05,
-      "loss": 0.2608,
+      "loss": 0.2149,
       "step": 1365
     },
     {
       "epoch": 0.78,
-      "eval_accuracy": 0.7696666666666667,
-      "eval_f1": 0.8104252400548698,
-      "eval_loss": 0.6222155690193176,
-      "eval_precision": 0.6885780885780886,
-      "eval_recall": 0.9846666666666667,
-      "eval_runtime": 242.2988,
-      "eval_samples_per_second": 12.381,
-      "eval_steps_per_second": 1.548,
+      "eval_accuracy": 0.934,
+      "eval_f1": 0.931582584657913,
+      "eval_loss": 0.26127538084983826,
+      "eval_precision": 0.9670014347202296,
+      "eval_recall": 0.8986666666666666,
+      "eval_runtime": 244.9705,
+      "eval_samples_per_second": 12.246,
+      "eval_steps_per_second": 1.531,
       "step": 1365
     },
     {
       "epoch": 0.8,
       "learning_rate": 1e-05,
-      "loss": 0.3251,
+      "loss": 0.204,
       "step": 1400
     },
     {
       "epoch": 0.8,
-      "eval_accuracy": 0.8256666666666667,
-      "eval_f1": 0.8467623791385878,
-      "eval_loss": 0.4772394299507141,
-      "eval_precision": 0.7553580763199164,
-      "eval_recall": 0.9633333333333334,
-      "eval_runtime": 240.46,
-      "eval_samples_per_second": 12.476,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.944,
+      "eval_f1": 0.9432048681541583,
+      "eval_loss": 0.22753384709358215,
+      "eval_precision": 0.9567901234567902,
+      "eval_recall": 0.93,
+      "eval_runtime": 246.146,
+      "eval_samples_per_second": 12.188,
+      "eval_steps_per_second": 1.523,
       "step": 1400
     },
     {
       "epoch": 0.82,
       "learning_rate": 9e-06,
-      "loss": 0.1763,
+      "loss": 0.165,
       "step": 1435
     },
     {
       "epoch": 0.82,
-      "eval_accuracy": 0.7433333333333333,
-      "eval_f1": 0.7941176470588235,
-      "eval_loss": 0.6803577542304993,
-      "eval_precision": 0.6629464285714286,
-      "eval_recall": 0.99,
-      "eval_runtime": 240.563,
-      "eval_samples_per_second": 12.471,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9433333333333334,
+      "eval_f1": 0.9422946367956553,
+      "eval_loss": 0.22660386562347412,
+      "eval_precision": 0.9598893499308437,
+      "eval_recall": 0.9253333333333333,
+      "eval_runtime": 244.7679,
+      "eval_samples_per_second": 12.257,
+      "eval_steps_per_second": 1.532,
       "step": 1435
     },
     {
       "epoch": 0.84,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.2904,
+      "loss": 0.2662,
       "step": 1470
     },
     {
       "epoch": 0.84,
-      "eval_accuracy": 0.7246666666666667,
-      "eval_f1": 0.7827459231983166,
-      "eval_loss": 0.727342426776886,
-      "eval_precision": 0.6463944396177237,
-      "eval_recall": 0.992,
-      "eval_runtime": 241.4946,
-      "eval_samples_per_second": 12.423,
-      "eval_steps_per_second": 1.553,
+      "eval_accuracy": 0.938,
+      "eval_f1": 0.9363449691991785,
+      "eval_loss": 0.2438994199037552,
+      "eval_precision": 0.9620253164556962,
+      "eval_recall": 0.912,
+      "eval_runtime": 246.2921,
+      "eval_samples_per_second": 12.181,
+      "eval_steps_per_second": 1.523,
       "step": 1470
     },
     {
       "epoch": 0.86,
       "learning_rate": 7.000000000000001e-06,
-      "loss": 0.2758,
+      "loss": 0.1704,
       "step": 1505
     },
     {
       "epoch": 0.86,
-      "eval_accuracy": 0.689,
-      "eval_f1": 0.7615640173779707,
-      "eval_loss": 0.8572436571121216,
-      "eval_precision": 0.6174886033982594,
-      "eval_recall": 0.9933333333333333,
-      "eval_runtime": 240.6981,
-      "eval_samples_per_second": 12.464,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.9446666666666667,
+      "eval_f1": 0.9449966865473823,
+      "eval_loss": 0.24109722673892975,
+      "eval_precision": 0.9393939393939394,
+      "eval_recall": 0.9506666666666667,
+      "eval_runtime": 244.6596,
+      "eval_samples_per_second": 12.262,
+      "eval_steps_per_second": 1.533,
       "step": 1505
     },
     {
       "epoch": 0.88,
       "learning_rate": 6e-06,
-      "loss": 0.3054,
+      "loss": 0.1694,
       "step": 1540
     },
     {
       "epoch": 0.88,
-      "eval_accuracy": 0.6446666666666667,
-      "eval_f1": 0.7369200394866732,
-      "eval_loss": 0.9957032799720764,
-      "eval_precision": 0.5850313479623824,
-      "eval_recall": 0.9953333333333333,
-      "eval_runtime": 240.6892,
-      "eval_samples_per_second": 12.464,
-      "eval_steps_per_second": 1.558,
+      "eval_accuracy": 0.9423333333333334,
+      "eval_f1": 0.9411364409663151,
+      "eval_loss": 0.24637927114963531,
+      "eval_precision": 0.9610840861709521,
+      "eval_recall": 0.922,
+      "eval_runtime": 246.6002,
+      "eval_samples_per_second": 12.165,
+      "eval_steps_per_second": 1.521,
       "step": 1540
     },
     {
       "epoch": 0.9,
       "learning_rate": 5e-06,
-      "loss": 0.2433,
+      "loss": 0.2994,
       "step": 1575
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.7466666666666667,
-      "eval_f1": 0.7960279119699409,
-      "eval_loss": 0.6531896591186523,
-      "eval_precision": 0.6662174303683738,
-      "eval_recall": 0.9886666666666667,
-      "eval_runtime": 242.6474,
-      "eval_samples_per_second": 12.364,
-      "eval_steps_per_second": 1.545,
+      "eval_accuracy": 0.947,
+      "eval_f1": 0.9469469469469469,
+      "eval_loss": 0.22698351740837097,
+      "eval_precision": 0.9478957915831663,
+      "eval_recall": 0.946,
+      "eval_runtime": 244.8716,
+      "eval_samples_per_second": 12.251,
+      "eval_steps_per_second": 1.531,
       "step": 1575
     },
     {
       "epoch": 0.92,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.2869,
+      "loss": 0.1833,
       "step": 1610
     },
     {
       "epoch": 0.92,
-      "eval_accuracy": 0.816,
-      "eval_f1": 0.8410138248847926,
-      "eval_loss": 0.45964765548706055,
-      "eval_precision": 0.7403651115618661,
-      "eval_recall": 0.9733333333333334,
-      "eval_runtime": 240.842,
-      "eval_samples_per_second": 12.456,
-      "eval_steps_per_second": 1.557,
+      "eval_accuracy": 0.9443333333333334,
+      "eval_f1": 0.9438655462184874,
+      "eval_loss": 0.23095431923866272,
+      "eval_precision": 0.951864406779661,
+      "eval_recall": 0.936,
+      "eval_runtime": 245.8383,
+      "eval_samples_per_second": 12.203,
+      "eval_steps_per_second": 1.525,
       "step": 1610
     },
     {
       "epoch": 0.94,
       "learning_rate": 3e-06,
-      "loss": 0.119,
+      "loss": 0.2646,
       "step": 1645
     },
     {
       "epoch": 0.94,
-      "eval_accuracy": 0.727,
-      "eval_f1": 0.7838479809976248,
-      "eval_loss": 0.7068488001823425,
-      "eval_precision": 0.6487549148099607,
-      "eval_recall": 0.99,
-      "eval_runtime": 240.4825,
-      "eval_samples_per_second": 12.475,
-      "eval_steps_per_second": 1.559,
+      "eval_accuracy": 0.9476666666666667,
+      "eval_f1": 0.9484400656814449,
+      "eval_loss": 0.27593639492988586,
+      "eval_precision": 0.9346278317152104,
+      "eval_recall": 0.9626666666666667,
+      "eval_runtime": 244.6822,
+      "eval_samples_per_second": 12.261,
+      "eval_steps_per_second": 1.533,
       "step": 1645
     },
     {
       "epoch": 0.96,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.2153,
+      "loss": 0.1927,
       "step": 1680
     },
     {
       "epoch": 0.96,
-      "eval_accuracy": 0.7513333333333333,
-      "eval_f1": 0.7988133764832793,
-      "eval_loss": 0.6478840112686157,
-      "eval_precision": 0.6707427536231884,
-      "eval_recall": 0.9873333333333333,
-      "eval_runtime": 240.4615,
-      "eval_samples_per_second": 12.476,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.949,
+      "eval_f1": 0.9487437185929648,
+      "eval_loss": 0.2200535088777542,
+      "eval_precision": 0.9535353535353536,
+      "eval_recall": 0.944,
+      "eval_runtime": 245.0433,
+      "eval_samples_per_second": 12.243,
+      "eval_steps_per_second": 1.53,
       "step": 1680
     },
     {
       "epoch": 0.98,
       "learning_rate": 1.0000000000000002e-06,
-      "loss": 0.2594,
+      "loss": 0.2153,
       "step": 1715
     },
     {
       "epoch": 0.98,
-      "eval_accuracy": 0.7313333333333333,
-      "eval_f1": 0.7866596082583377,
-      "eval_loss": 0.6965696811676025,
-      "eval_precision": 0.6523266022827041,
-      "eval_recall": 0.9906666666666667,
-      "eval_runtime": 240.2996,
-      "eval_samples_per_second": 12.484,
-      "eval_steps_per_second": 1.561,
+      "eval_accuracy": 0.948,
+      "eval_f1": 0.9477911646586344,
+      "eval_loss": 0.2146720141172409,
+      "eval_precision": 0.9516129032258065,
+      "eval_recall": 0.944,
+      "eval_runtime": 246.1882,
+      "eval_samples_per_second": 12.186,
+      "eval_steps_per_second": 1.523,
       "step": 1715
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0,
-      "loss": 0.2108,
+      "loss": 0.1213,
       "step": 1750
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7433333333333333,
-      "eval_f1": 0.7938972162740899,
-      "eval_loss": 0.6547001004219055,
-      "eval_precision": 0.6632379248658319,
-      "eval_recall": 0.9886666666666667,
-      "eval_runtime": 240.3896,
-      "eval_samples_per_second": 12.48,
-      "eval_steps_per_second": 1.56,
+      "eval_accuracy": 0.948,
+      "eval_f1": 0.9478957915831663,
+      "eval_loss": 0.21715900301933289,
+      "eval_precision": 0.9497991967871486,
+      "eval_recall": 0.946,
+      "eval_runtime": 245.0021,
+      "eval_samples_per_second": 12.245,
+      "eval_steps_per_second": 1.531,
       "step": 1750
     }
   ],