Training in progress, step 466, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec54759a05472ae7a29a21fdf6126f1d45b726b646072c21020ad09361d3328
+oid sha256:9950900927a23fbd1b057f1ed69b550d4d273f0934840d83f894c02eebcfc265
 size 791869518

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29760e0d43434a73d45aa9ad569d3c685b638d1b0d6e03deb084b9431cffcba
+oid sha256:18064bdb794c779bde41993ce05e33f03aa1951793cd63343a1b068033ddfd01
 size 2375752250

last-checkpoint/trainer_state.json

@@ -10,653 +10,653 @@
   "log_history": [
     {
       "epoch": 0.010718831647350439,
-      "grad_norm": 211.25,
+      "grad_norm": 252.125,
       "learning_rate": 1.0638297872340427e-06,
-      "loss": 153.567,
+      "loss": 155.9409,
       "step": 5
     },
     {
       "epoch": 0.021437663294700877,
-      "grad_norm": 158.625,
+      "grad_norm": 173.875,
       "learning_rate": 2.1276595744680853e-06,
-      "loss": 140.0117,
+      "loss": 138.2581,
       "step": 10
     },
     {
       "epoch": 0.03215649494205132,
-      "grad_norm": 133.375,
+      "grad_norm": 162.125,
       "learning_rate": 3.191489361702128e-06,
-      "loss": 129.8682,
+      "loss": 125.8547,
       "step": 15
     },
     {
       "epoch": 0.042875326589401755,
-      "grad_norm": 144.875,
+      "grad_norm": 179.75,
       "learning_rate": 4.255319148936171e-06,
-      "loss": 126.0052,
+      "loss": 119.6304,
       "step": 20
     },
     {
       "epoch": 0.0535941582367522,
-      "grad_norm": 129.625,
+      "grad_norm": 152.25,
       "learning_rate": 5.319148936170213e-06,
-      "loss": 119.8439,
+      "loss": 115.1023,
       "step": 25
     },
     {
       "epoch": 0.06431298988410264,
-      "grad_norm": 137.0,
+      "grad_norm": 152.25,
       "learning_rate": 6.382978723404256e-06,
-      "loss": 116.4664,
+      "loss": 109.8922,
       "step": 30
     },
     {
       "epoch": 0.07503182153145307,
-      "grad_norm": 129.875,
+      "grad_norm": 172.25,
       "learning_rate": 7.446808510638298e-06,
-      "loss": 113.5729,
+      "loss": 106.5941,
       "step": 35
     },
     {
       "epoch": 0.08575065317880351,
-      "grad_norm": 137.25,
+      "grad_norm": 144.875,
       "learning_rate": 8.510638297872341e-06,
-      "loss": 110.4895,
+      "loss": 104.125,
       "step": 40
     },
     {
       "epoch": 0.09646948482615395,
-      "grad_norm": 148.625,
+      "grad_norm": 167.25,
       "learning_rate": 9.574468085106385e-06,
-      "loss": 108.5547,
+      "loss": 101.1203,
       "step": 45
     },
     {
       "epoch": 0.1071883164735044,
-      "grad_norm": 146.75,
+      "grad_norm": 129.75,
       "learning_rate": 9.928400954653938e-06,
-      "loss": 106.053,
+      "loss": 100.9157,
       "step": 50
     },
     {
       "epoch": 0.11790714812085483,
-      "grad_norm": 141.75,
+      "grad_norm": 139.75,
       "learning_rate": 9.809069212410502e-06,
-      "loss": 104.916,
+      "loss": 98.701,
       "step": 55
     },
     {
       "epoch": 0.12862597976820528,
-      "grad_norm": 124.4375,
+      "grad_norm": 136.125,
       "learning_rate": 9.689737470167065e-06,
-      "loss": 103.8926,
+      "loss": 97.0131,
       "step": 60
     },
     {
       "epoch": 0.1393448114155557,
-      "grad_norm": 114.4375,
+      "grad_norm": 139.375,
       "learning_rate": 9.570405727923628e-06,
-      "loss": 102.8004,
+      "loss": 96.8509,
       "step": 65
     },
     {
       "epoch": 0.15006364306290615,
-      "grad_norm": 139.375,
+      "grad_norm": 137.125,
       "learning_rate": 9.451073985680192e-06,
-      "loss": 100.971,
+      "loss": 95.0264,
       "step": 70
     },
     {
       "epoch": 0.16078247471025658,
-      "grad_norm": 126.0,
+      "grad_norm": 129.625,
       "learning_rate": 9.331742243436755e-06,
-      "loss": 101.7109,
+      "loss": 95.4573,
       "step": 75
     },
     {
       "epoch": 0.17150130635760702,
-      "grad_norm": 127.4375,
+      "grad_norm": 139.875,
       "learning_rate": 9.212410501193319e-06,
-      "loss": 98.4631,
+      "loss": 92.0226,
       "step": 80
     },
     {
       "epoch": 0.18222013800495745,
-      "grad_norm": 110.5625,
+      "grad_norm": 122.625,
       "learning_rate": 9.093078758949882e-06,
-      "loss": 99.3711,
+      "loss": 92.689,
       "step": 85
     },
     {
       "epoch": 0.1929389696523079,
-      "grad_norm": 116.75,
+      "grad_norm": 127.3125,
       "learning_rate": 8.973747016706445e-06,
-      "loss": 95.8763,
+      "loss": 91.2317,
       "step": 90
     },
     {
       "epoch": 0.20365780129965833,
-      "grad_norm": 120.875,
+      "grad_norm": 117.875,
       "learning_rate": 8.854415274463007e-06,
-      "loss": 96.4408,
+      "loss": 91.711,
       "step": 95
     },
     {
       "epoch": 0.2143766329470088,
-      "grad_norm": 115.0,
+      "grad_norm": 121.0,
       "learning_rate": 8.735083532219572e-06,
-      "loss": 96.3821,
+      "loss": 90.7297,
       "step": 100
     },
     {
       "epoch": 0.22509546459435922,
-      "grad_norm": 112.0,
+      "grad_norm": 127.0,
       "learning_rate": 8.615751789976134e-06,
-      "loss": 94.4185,
+      "loss": 89.1753,
       "step": 105
     },
     {
       "epoch": 0.23581429624170966,
-      "grad_norm": 113.8125,
+      "grad_norm": 120.125,
       "learning_rate": 8.496420047732697e-06,
-      "loss": 92.697,
+      "loss": 88.5173,
       "step": 110
     },
     {
       "epoch": 0.2465331278890601,
-      "grad_norm": 117.0,
+      "grad_norm": 119.5,
       "learning_rate": 8.37708830548926e-06,
-      "loss": 93.9249,
+      "loss": 88.5147,
       "step": 115
     },
     {
       "epoch": 0.25725195953641056,
-      "grad_norm": 129.625,
+      "grad_norm": 118.75,
       "learning_rate": 8.257756563245824e-06,
-      "loss": 93.7763,
+      "loss": 88.3917,
       "step": 120
     },
     {
       "epoch": 0.267970791183761,
-      "grad_norm": 105.3125,
+      "grad_norm": 110.875,
       "learning_rate": 8.138424821002387e-06,
-      "loss": 92.1832,
+      "loss": 86.6302,
       "step": 125
     },
     {
       "epoch": 0.2786896228311114,
-      "grad_norm": 111.0625,
+      "grad_norm": 120.375,
       "learning_rate": 8.01909307875895e-06,
-      "loss": 91.3985,
+      "loss": 85.9245,
       "step": 130
     },
     {
       "epoch": 0.28940845447846186,
-      "grad_norm": 116.8125,
+      "grad_norm": 117.5625,
       "learning_rate": 7.899761336515514e-06,
-      "loss": 91.9044,
+      "loss": 85.8226,
       "step": 135
     },
     {
       "epoch": 0.3001272861258123,
-      "grad_norm": 108.125,
+      "grad_norm": 125.0625,
       "learning_rate": 7.780429594272077e-06,
-      "loss": 90.6969,
+      "loss": 84.2932,
       "step": 140
     },
     {
       "epoch": 0.31084611777316273,
-      "grad_norm": 102.6875,
+      "grad_norm": 125.75,
       "learning_rate": 7.661097852028641e-06,
-      "loss": 89.3236,
+      "loss": 84.1921,
       "step": 145
     },
     {
       "epoch": 0.32156494942051317,
-      "grad_norm": 110.875,
+      "grad_norm": 136.625,
       "learning_rate": 7.541766109785204e-06,
-      "loss": 89.5013,
+      "loss": 82.9208,
       "step": 150
     },
     {
       "epoch": 0.3322837810678636,
-      "grad_norm": 114.0,
+      "grad_norm": 116.9375,
       "learning_rate": 7.422434367541767e-06,
-      "loss": 90.3805,
+      "loss": 84.027,
       "step": 155
     },
     {
       "epoch": 0.34300261271521404,
-      "grad_norm": 107.4375,
+      "grad_norm": 117.4375,
       "learning_rate": 7.303102625298329e-06,
-      "loss": 89.5262,
+      "loss": 83.1317,
       "step": 160
     },
     {
       "epoch": 0.3537214443625645,
-      "grad_norm": 108.75,
+      "grad_norm": 107.4375,
       "learning_rate": 7.183770883054894e-06,
-      "loss": 89.764,
+      "loss": 83.4804,
       "step": 165
     },
     {
       "epoch": 0.3644402760099149,
-      "grad_norm": 114.0625,
+      "grad_norm": 105.6875,
       "learning_rate": 7.0644391408114565e-06,
-      "loss": 88.8421,
+      "loss": 83.8133,
       "step": 170
     },
     {
       "epoch": 0.37515910765726534,
-      "grad_norm": 129.125,
+      "grad_norm": 118.1875,
       "learning_rate": 6.945107398568019e-06,
-      "loss": 88.3883,
+      "loss": 82.0148,
       "step": 175
     },
     {
       "epoch": 0.3858779393046158,
-      "grad_norm": 109.125,
+      "grad_norm": 123.9375,
       "learning_rate": 6.825775656324583e-06,
-      "loss": 86.4718,
+      "loss": 81.4826,
       "step": 180
     },
     {
       "epoch": 0.3965967709519662,
-      "grad_norm": 105.625,
+      "grad_norm": 108.125,
       "learning_rate": 6.706443914081146e-06,
-      "loss": 86.6102,
+      "loss": 80.8058,
       "step": 185
     },
     {
       "epoch": 0.40731560259931665,
-      "grad_norm": 99.4375,
+      "grad_norm": 117.1875,
       "learning_rate": 6.58711217183771e-06,
-      "loss": 87.2404,
+      "loss": 81.278,
       "step": 190
     },
     {
       "epoch": 0.4180344342466671,
-      "grad_norm": 122.5625,
+      "grad_norm": 110.25,
       "learning_rate": 6.467780429594273e-06,
-      "loss": 86.983,
+      "loss": 81.0989,
       "step": 195
     },
     {
       "epoch": 0.4287532658940176,
-      "grad_norm": 107.375,
+      "grad_norm": 117.25,
       "learning_rate": 6.348448687350835e-06,
-      "loss": 85.9044,
+      "loss": 79.6685,
       "step": 200
     },
     {
       "epoch": 0.439472097541368,
-      "grad_norm": 105.25,
+      "grad_norm": 111.75,
       "learning_rate": 6.2291169451074e-06,
-      "loss": 85.5443,
+      "loss": 79.1052,
       "step": 205
     },
     {
       "epoch": 0.45019092918871845,
-      "grad_norm": 98.0625,
+      "grad_norm": 108.0625,
       "learning_rate": 6.109785202863962e-06,
-      "loss": 84.8833,
+      "loss": 79.6372,
       "step": 210
     },
     {
       "epoch": 0.4609097608360689,
-      "grad_norm": 103.375,
+      "grad_norm": 111.5625,
       "learning_rate": 5.990453460620526e-06,
-      "loss": 83.3222,
+      "loss": 77.5653,
       "step": 215
     },
     {
       "epoch": 0.4716285924834193,
-      "grad_norm": 106.6875,
+      "grad_norm": 107.6875,
       "learning_rate": 5.871121718377089e-06,
-      "loss": 83.0749,
+      "loss": 77.3766,
       "step": 220
     },
     {
       "epoch": 0.48234742413076975,
-      "grad_norm": 110.0,
+      "grad_norm": 108.75,
       "learning_rate": 5.751789976133651e-06,
-      "loss": 83.5757,
+      "loss": 77.9029,
       "step": 225
     },
     {
       "epoch": 0.4930662557781202,
-      "grad_norm": 111.875,
+      "grad_norm": 110.4375,
       "learning_rate": 5.632458233890216e-06,
-      "loss": 84.4967,
+      "loss": 77.637,
       "step": 230
     },
     {
       "epoch": 0.5037850874254707,
-      "grad_norm": 100.6875,
+      "grad_norm": 105.4375,
       "learning_rate": 5.5131264916467785e-06,
-      "loss": 83.1593,
+      "loss": 77.9697,
       "step": 235
     },
     {
       "epoch": 0.5145039190728211,
-      "grad_norm": 110.0,
+      "grad_norm": 106.5,
       "learning_rate": 5.393794749403341e-06,
-      "loss": 82.6202,
+      "loss": 76.8029,
       "step": 240
     },
     {
       "epoch": 0.5252227507201715,
-      "grad_norm": 105.0,
+      "grad_norm": 100.1875,
       "learning_rate": 5.274463007159905e-06,
-      "loss": 83.1495,
+      "loss": 76.3629,
       "step": 245
     },
     {
       "epoch": 0.535941582367522,
-      "grad_norm": 104.1875,
+      "grad_norm": 111.8125,
       "learning_rate": 5.155131264916468e-06,
-      "loss": 81.8701,
+      "loss": 76.2163,
       "step": 250
     },
     {
       "epoch": 0.5466604140148724,
-      "grad_norm": 106.375,
+      "grad_norm": 96.875,
       "learning_rate": 5.035799522673032e-06,
-      "loss": 83.2251,
+      "loss": 77.568,
       "step": 255
     },
     {
       "epoch": 0.5573792456622229,
-      "grad_norm": 99.0,
+      "grad_norm": 102.75,
       "learning_rate": 4.916467780429595e-06,
-      "loss": 81.6166,
+      "loss": 75.3195,
       "step": 260
     },
     {
       "epoch": 0.5680980773095733,
-      "grad_norm": 103.5625,
+      "grad_norm": 99.5,
       "learning_rate": 4.797136038186158e-06,
-      "loss": 81.3204,
+      "loss": 75.8809,
       "step": 265
     },
     {
       "epoch": 0.5788169089569237,
-      "grad_norm": 94.875,
+      "grad_norm": 99.8125,
       "learning_rate": 4.677804295942721e-06,
-      "loss": 81.0188,
+      "loss": 74.9826,
       "step": 270
     },
     {
       "epoch": 0.5895357406042742,
-      "grad_norm": 108.25,
+      "grad_norm": 97.75,
       "learning_rate": 4.5584725536992845e-06,
-      "loss": 80.7994,
+      "loss": 75.0475,
       "step": 275
     },
     {
       "epoch": 0.6002545722516246,
-      "grad_norm": 102.5,
+      "grad_norm": 107.6875,
       "learning_rate": 4.439140811455848e-06,
-      "loss": 81.4588,
+      "loss": 75.2888,
       "step": 280
     },
     {
       "epoch": 0.610973403898975,
-      "grad_norm": 100.25,
+      "grad_norm": 100.8125,
       "learning_rate": 4.319809069212411e-06,
-      "loss": 79.9005,
+      "loss": 73.6369,
       "step": 285
     },
     {
       "epoch": 0.6216922355463255,
-      "grad_norm": 99.875,
+      "grad_norm": 95.8125,
       "learning_rate": 4.200477326968974e-06,
-      "loss": 80.4906,
+      "loss": 74.4059,
       "step": 290
     },
     {
       "epoch": 0.6324110671936759,
-      "grad_norm": 102.4375,
+      "grad_norm": 106.75,
       "learning_rate": 4.081145584725537e-06,
-      "loss": 80.2348,
+      "loss": 74.0677,
       "step": 295
     },
     {
       "epoch": 0.6431298988410263,
-      "grad_norm": 97.8125,
+      "grad_norm": 101.125,
       "learning_rate": 3.961813842482101e-06,
-      "loss": 79.5465,
+      "loss": 74.2879,
       "step": 300
     },
     {
       "epoch": 0.6538487304883768,
-      "grad_norm": 107.375,
+      "grad_norm": 105.625,
       "learning_rate": 3.842482100238663e-06,
-      "loss": 79.8271,
+      "loss": 73.0384,
       "step": 305
     },
     {
       "epoch": 0.6645675621357272,
-      "grad_norm": 98.125,
+      "grad_norm": 102.5625,
       "learning_rate": 3.7231503579952273e-06,
-      "loss": 79.2237,
+      "loss": 73.1361,
       "step": 310
     },
     {
       "epoch": 0.6752863937830776,
-      "grad_norm": 92.0625,
+      "grad_norm": 93.875,
       "learning_rate": 3.60381861575179e-06,
-      "loss": 77.8435,
+      "loss": 71.0992,
       "step": 315
     },
     {
       "epoch": 0.6860052254304281,
-      "grad_norm": 94.5625,
+      "grad_norm": 93.8125,
       "learning_rate": 3.4844868735083536e-06,
-      "loss": 78.0483,
+      "loss": 71.7427,
       "step": 320
     },
     {
       "epoch": 0.6967240570777785,
-      "grad_norm": 96.875,
+      "grad_norm": 103.8125,
       "learning_rate": 3.3651551312649167e-06,
-      "loss": 79.3898,
+      "loss": 72.686,
       "step": 325
     },
     {
       "epoch": 0.707442888725129,
-      "grad_norm": 101.3125,
+      "grad_norm": 107.3125,
       "learning_rate": 3.2458233890214803e-06,
-      "loss": 77.8723,
+      "loss": 71.6971,
       "step": 330
     },
     {
       "epoch": 0.7181617203724794,
-      "grad_norm": 95.0625,
+      "grad_norm": 101.125,
       "learning_rate": 3.126491646778043e-06,
-      "loss": 78.3611,
+      "loss": 71.9173,
       "step": 335
     },
     {
       "epoch": 0.7288805520198298,
-      "grad_norm": 94.375,
+      "grad_norm": 107.0625,
       "learning_rate": 3.0071599045346066e-06,
-      "loss": 77.2158,
+      "loss": 70.1084,
       "step": 340
     },
     {
       "epoch": 0.7395993836671803,
-      "grad_norm": 97.75,
+      "grad_norm": 100.3125,
       "learning_rate": 2.8878281622911697e-06,
-      "loss": 77.1143,
+      "loss": 70.9213,
       "step": 345
     },
     {
       "epoch": 0.7503182153145307,
-      "grad_norm": 96.0,
+      "grad_norm": 98.1875,
       "learning_rate": 2.768496420047733e-06,
-      "loss": 76.7089,
+      "loss": 70.0351,
       "step": 350
     },
     {
       "epoch": 0.7610370469618811,
-      "grad_norm": 99.9375,
+      "grad_norm": 94.75,
       "learning_rate": 2.6491646778042964e-06,
-      "loss": 76.2333,
+      "loss": 71.2901,
       "step": 355
     },
     {
       "epoch": 0.7717558786092316,
-      "grad_norm": 95.9375,
+      "grad_norm": 94.875,
       "learning_rate": 2.529832935560859e-06,
-      "loss": 76.3484,
+      "loss": 70.3854,
       "step": 360
     },
     {
       "epoch": 0.782474710256582,
-      "grad_norm": 99.375,
+      "grad_norm": 95.3125,
       "learning_rate": 2.4105011933174227e-06,
-      "loss": 76.2618,
+      "loss": 69.4661,
       "step": 365
     },
     {
       "epoch": 0.7931935419039324,
-      "grad_norm": 92.5625,
+      "grad_norm": 94.75,
       "learning_rate": 2.291169451073986e-06,
-      "loss": 75.671,
+      "loss": 69.8691,
       "step": 370
     },
     {
       "epoch": 0.8039123735512829,
-      "grad_norm": 93.0625,
+      "grad_norm": 95.5,
       "learning_rate": 2.1718377088305494e-06,
-      "loss": 76.9299,
+      "loss": 71.2865,
       "step": 375
     },
     {
       "epoch": 0.8146312051986333,
-      "grad_norm": 89.625,
+      "grad_norm": 94.25,
       "learning_rate": 2.052505966587112e-06,
-      "loss": 76.8329,
+      "loss": 70.158,
       "step": 380
     },
     {
       "epoch": 0.8253500368459837,
-      "grad_norm": 90.6875,
+      "grad_norm": 93.75,
       "learning_rate": 1.9331742243436756e-06,
-      "loss": 76.2561,
+      "loss": 69.3283,
       "step": 385
     },
     {
       "epoch": 0.8360688684933342,
       "grad_norm": 93.4375,
       "learning_rate": 1.8138424821002388e-06,
-      "loss": 76.3544,
+      "loss": 69.9503,
       "step": 390
     },
     {
       "epoch": 0.8467877001406847,
-      "grad_norm": 95.9375,
+      "grad_norm": 94.9375,
       "learning_rate": 1.694510739856802e-06,
-      "loss": 75.7927,
+      "loss": 68.9377,
       "step": 395
     },
     {
       "epoch": 0.8575065317880352,
-      "grad_norm": 94.1875,
+      "grad_norm": 95.25,
       "learning_rate": 1.5751789976133653e-06,
-      "loss": 74.7918,
+      "loss": 68.6082,
       "step": 400
     },
     {
       "epoch": 0.8682253634353856,
-      "grad_norm": 89.9375,
+      "grad_norm": 90.125,
       "learning_rate": 1.4558472553699284e-06,
-      "loss": 75.3931,
+      "loss": 68.844,
       "step": 405
     },
     {
       "epoch": 0.878944195082736,
-      "grad_norm": 89.0625,
+      "grad_norm": 94.8125,
       "learning_rate": 1.3365155131264918e-06,
-      "loss": 73.8404,
+      "loss": 67.8577,
       "step": 410
     },
     {
       "epoch": 0.8896630267300865,
-      "grad_norm": 92.625,
+      "grad_norm": 91.1875,
       "learning_rate": 1.217183770883055e-06,
-      "loss": 74.9777,
+      "loss": 68.8943,
       "step": 415
     },
     {
       "epoch": 0.9003818583774369,
-      "grad_norm": 92.25,
+      "grad_norm": 93.5,
       "learning_rate": 1.0978520286396182e-06,
-      "loss": 75.7055,
+      "loss": 69.4524,
       "step": 420
     },
     {
       "epoch": 0.9111006900247873,
-      "grad_norm": 90.8125,
+      "grad_norm": 93.0625,
       "learning_rate": 9.785202863961816e-07,
-      "loss": 74.1974,
+      "loss": 68.2064,
       "step": 425
     },
     {
       "epoch": 0.9218195216721378,
-      "grad_norm": 95.5625,
+      "grad_norm": 89.6875,
       "learning_rate": 8.591885441527446e-07,
-      "loss": 73.9709,
+      "loss": 67.2536,
       "step": 430
     },
     {
       "epoch": 0.9325383533194882,
-      "grad_norm": 90.4375,
+      "grad_norm": 91.5625,
       "learning_rate": 7.398568019093079e-07,
-      "loss": 73.6577,
+      "loss": 68.1469,
       "step": 435
     },
     {
       "epoch": 0.9432571849668386,
-      "grad_norm": 87.5,
+      "grad_norm": 88.5,
       "learning_rate": 6.205250596658711e-07,
-      "loss": 73.7618,
+      "loss": 68.1032,
       "step": 440
     },
     {
       "epoch": 0.9539760166141891,
-      "grad_norm": 85.3125,
+      "grad_norm": 91.0,
       "learning_rate": 5.011933174224344e-07,
-      "loss": 73.906,
+      "loss": 68.6026,
       "step": 445
     },
     {
       "epoch": 0.9646948482615395,
-      "grad_norm": 89.5,
+      "grad_norm": 84.5625,
       "learning_rate": 3.8186157517899765e-07,
-      "loss": 73.9408,
+      "loss": 68.6085,
       "step": 450
     },
     {
       "epoch": 0.9754136799088899,
-      "grad_norm": 85.5625,
+      "grad_norm": 85.75,
       "learning_rate": 2.625298329355609e-07,
-      "loss": 75.0269,
+      "loss": 68.5711,
       "step": 455
     },
     {
       "epoch": 0.9861325115562404,
-      "grad_norm": 88.875,
+      "grad_norm": 88.0625,
       "learning_rate": 1.431980906921241e-07,
-      "loss": 73.8874,
+      "loss": 66.8683,
       "step": 460
     },
     {
       "epoch": 0.9968513432035908,
-      "grad_norm": 87.875,
+      "grad_norm": 90.3125,
       "learning_rate": 2.3866348448687353e-08,
-      "loss": 73.0409,
+      "loss": 67.1773,
       "step": 465
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8553050a9b54098589a5ae3ae31ca1f1d96324b6497e3365485d197a9e8d5e71
+oid sha256:362a2dcbab555f7393868e7ecbc85fab889229eb10dc422f6bb212221b59f85a
 size 5752