Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cac443dc31ef4fa509e8a533d609447e9408e9fcc6a4c34574adc713af26700
-size 1450506320
+oid sha256:5880c72cd9dc9381c1a7280d33283e6d327e90a452e4259d67dd59af7eeeabe4
+size 1452607848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1881d8684e4da3b4d7efe825ccff51224f8ed8c542abc8b927dbc46478c012
-size 2901190266
+oid sha256:e34e673333434978f89f9428bc14a37c916b36288eda14ce222667dc75063e47
+size 2905395322

last-checkpoint/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 493,
-  "best_metric": 0.4431517720222473,
+  "best_metric": 0.3493718206882477,
   "best_model_checkpoint": "./VulnSentry/checkpoint-493",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,700 +11,700 @@
   "log_history": [
     {
       "epoch": 0.01015916017609211,
-      "grad_norm": 124.9168472290039,
+      "grad_norm": 14.128280639648438,
       "learning_rate": 1.0810810810810812e-06,
-      "loss": 0.7082,
+      "loss": 0.6978,
       "step": 5
     },
     {
       "epoch": 0.02031832035218422,
-      "grad_norm": 216.048095703125,
+      "grad_norm": 11.447400093078613,
       "learning_rate": 2.432432432432433e-06,
-      "loss": 0.6676,
+      "loss": 0.6352,
       "step": 10
     },
     {
       "epoch": 0.03047748052827633,
-      "grad_norm": 129.1244354248047,
+      "grad_norm": 7.649522304534912,
       "learning_rate": 3.7837837837837844e-06,
-      "loss": 0.6235,
+      "loss": 0.4539,
       "step": 15
     },
     {
       "epoch": 0.04063664070436844,
-      "grad_norm": 99.75704956054688,
+      "grad_norm": 6.1048126220703125,
       "learning_rate": 5.135135135135135e-06,
-      "loss": 0.6237,
+      "loss": 0.4387,
       "step": 20
     },
     {
       "epoch": 0.05079580088046055,
-      "grad_norm": 99.64442443847656,
+      "grad_norm": 4.185236930847168,
       "learning_rate": 6.486486486486487e-06,
-      "loss": 0.507,
+      "loss": 0.2257,
       "step": 25
     },
     {
       "epoch": 0.06095496105655266,
-      "grad_norm": 130.50547790527344,
+      "grad_norm": 8.491202354431152,
       "learning_rate": 7.837837837837838e-06,
-      "loss": 0.4867,
+      "loss": 0.363,
       "step": 30
     },
     {
       "epoch": 0.07111412123264477,
-      "grad_norm": 480.7685241699219,
+      "grad_norm": 11.918909072875977,
       "learning_rate": 9.189189189189191e-06,
-      "loss": 0.4644,
+      "loss": 0.3753,
       "step": 35
     },
     {
       "epoch": 0.08127328140873688,
-      "grad_norm": 499.7054748535156,
+      "grad_norm": 9.919339179992676,
       "learning_rate": 1.0540540540540541e-05,
-      "loss": 0.5031,
+      "loss": 0.4218,
       "step": 40
     },
     {
       "epoch": 0.091432441584829,
-      "grad_norm": 152.89173889160156,
+      "grad_norm": 5.582858085632324,
       "learning_rate": 1.1891891891891894e-05,
-      "loss": 0.4018,
+      "loss": 0.3665,
       "step": 45
     },
     {
       "epoch": 0.1015916017609211,
-      "grad_norm": 134.70472717285156,
+      "grad_norm": 3.795450210571289,
       "learning_rate": 1.3243243243243244e-05,
-      "loss": 0.3914,
+      "loss": 0.3243,
       "step": 50
     },
     {
       "epoch": 0.11175076193701321,
-      "grad_norm": 124.81039428710938,
+      "grad_norm": 4.975071430206299,
       "learning_rate": 1.4594594594594596e-05,
-      "loss": 0.4259,
+      "loss": 0.4053,
       "step": 55
     },
     {
       "epoch": 0.12190992211310532,
-      "grad_norm": 417.4250793457031,
+      "grad_norm": 4.534969806671143,
       "learning_rate": 1.5945945945945947e-05,
-      "loss": 0.4314,
+      "loss": 0.3801,
       "step": 60
     },
     {
       "epoch": 0.13206908228919742,
-      "grad_norm": 111.6860580444336,
+      "grad_norm": 6.309267997741699,
       "learning_rate": 1.72972972972973e-05,
-      "loss": 0.3708,
+      "loss": 0.3039,
       "step": 65
     },
     {
       "epoch": 0.14222824246528953,
-      "grad_norm": 57.337913513183594,
+      "grad_norm": 4.233974933624268,
       "learning_rate": 1.864864864864865e-05,
-      "loss": 0.3717,
+      "loss": 0.3271,
       "step": 70
     },
     {
       "epoch": 0.15238740264138165,
-      "grad_norm": 82.06193542480469,
+      "grad_norm": 8.308606147766113,
       "learning_rate": 2e-05,
-      "loss": 0.4444,
+      "loss": 0.3606,
       "step": 75
     },
     {
       "epoch": 0.16254656281747376,
-      "grad_norm": 62.36454772949219,
+      "grad_norm": 6.605645656585693,
       "learning_rate": 1.999978329580869e-05,
-      "loss": 0.4449,
+      "loss": 0.4022,
       "step": 80
     },
     {
       "epoch": 0.17270572299356587,
-      "grad_norm": 51.05297088623047,
+      "grad_norm": 4.964644432067871,
       "learning_rate": 1.9999133192626893e-05,
-      "loss": 0.4272,
+      "loss": 0.3618,
       "step": 85
     },
     {
       "epoch": 0.182864883169658,
-      "grad_norm": 40.76633834838867,
+      "grad_norm": 3.2400362491607666,
       "learning_rate": 1.999804971863063e-05,
-      "loss": 0.3714,
+      "loss": 0.359,
       "step": 90
     },
     {
       "epoch": 0.19302404334575007,
-      "grad_norm": 56.4720344543457,
+      "grad_norm": 3.639561891555786,
       "learning_rate": 1.999653292077857e-05,
-      "loss": 0.4217,
+      "loss": 0.4124,
       "step": 95
     },
     {
       "epoch": 0.2031832035218422,
-      "grad_norm": 59.50137710571289,
+      "grad_norm": 5.324073314666748,
       "learning_rate": 1.9994582864810008e-05,
-      "loss": 0.4571,
+      "loss": 0.4223,
       "step": 100
     },
     {
       "epoch": 0.2133423636979343,
-      "grad_norm": 35.567649841308594,
+      "grad_norm": 5.942139148712158,
       "learning_rate": 1.9992199635241997e-05,
-      "loss": 0.3531,
+      "loss": 0.3179,
       "step": 105
     },
     {
       "epoch": 0.22350152387402641,
-      "grad_norm": 46.55067825317383,
+      "grad_norm": 4.13494348526001,
       "learning_rate": 1.9989383335365713e-05,
-      "loss": 0.4312,
+      "loss": 0.3899,
       "step": 110
     },
     {
       "epoch": 0.23366068405011853,
-      "grad_norm": 36.95201110839844,
+      "grad_norm": 4.3291144371032715,
       "learning_rate": 1.998613408724195e-05,
-      "loss": 0.4454,
+      "loss": 0.3629,
       "step": 115
     },
     {
       "epoch": 0.24381984422621064,
-      "grad_norm": 37.9529914855957,
+      "grad_norm": 4.0282487869262695,
       "learning_rate": 1.9982452031695837e-05,
-      "loss": 0.4221,
+      "loss": 0.3643,
       "step": 120
     },
     {
       "epoch": 0.25397900440230275,
-      "grad_norm": 27.23141860961914,
+      "grad_norm": 4.823352336883545,
       "learning_rate": 1.997833732831076e-05,
-      "loss": 0.5048,
+      "loss": 0.4598,
       "step": 125
     },
     {
       "epoch": 0.26413816457839484,
-      "grad_norm": 28.440961837768555,
+      "grad_norm": 4.248661041259766,
       "learning_rate": 1.9973790155421406e-05,
-      "loss": 0.3467,
+      "loss": 0.3078,
       "step": 130
     },
     {
       "epoch": 0.274297324754487,
-      "grad_norm": 25.352418899536133,
+      "grad_norm": 3.6865596771240234,
       "learning_rate": 1.9968810710106065e-05,
-      "loss": 0.4385,
+      "loss": 0.4342,
       "step": 135
     },
     {
       "epoch": 0.28445648493057907,
-      "grad_norm": 23.881067276000977,
+      "grad_norm": 4.331181049346924,
       "learning_rate": 1.9963399208178066e-05,
-      "loss": 0.4138,
+      "loss": 0.3653,
       "step": 140
     },
     {
       "epoch": 0.2946156451066712,
-      "grad_norm": 10.770444869995117,
+      "grad_norm": 2.6197454929351807,
       "learning_rate": 1.995755588417644e-05,
-      "loss": 0.3605,
+      "loss": 0.3168,
       "step": 145
     },
     {
       "epoch": 0.3047748052827633,
-      "grad_norm": 10.67106819152832,
+      "grad_norm": 2.402017116546631,
       "learning_rate": 1.995128099135575e-05,
-      "loss": 0.3031,
+      "loss": 0.3011,
       "step": 150
     },
     {
       "epoch": 0.3149339654588554,
-      "grad_norm": 12.032747268676758,
+      "grad_norm": 2.0846991539001465,
       "learning_rate": 1.9944574801675106e-05,
-      "loss": 0.4027,
+      "loss": 0.3704,
       "step": 155
     },
     {
       "epoch": 0.3250931256349475,
-      "grad_norm": 13.55962085723877,
+      "grad_norm": 3.2597687244415283,
       "learning_rate": 1.9937437605786395e-05,
-      "loss": 0.4205,
+      "loss": 0.3465,
       "step": 160
     },
     {
       "epoch": 0.3352522858110396,
-      "grad_norm": 10.579209327697754,
+      "grad_norm": 3.3900413513183594,
       "learning_rate": 1.9929869713021668e-05,
-      "loss": 0.4578,
+      "loss": 0.3905,
       "step": 165
     },
     {
       "epoch": 0.34541144598713175,
-      "grad_norm": 9.225481033325195,
+      "grad_norm": 2.0387165546417236,
       "learning_rate": 1.992187145137974e-05,
-      "loss": 0.3515,
+      "loss": 0.3366,
       "step": 170
     },
     {
       "epoch": 0.35557060616322383,
-      "grad_norm": 11.829900741577148,
+      "grad_norm": 3.4242238998413086,
       "learning_rate": 1.991344316751198e-05,
-      "loss": 0.4827,
+      "loss": 0.6067,
       "step": 175
     },
     {
       "epoch": 0.365729766339316,
-      "grad_norm": 8.982975006103516,
+      "grad_norm": 1.9061392545700073,
       "learning_rate": 1.990458522670727e-05,
-      "loss": 0.3654,
+      "loss": 0.3279,
       "step": 180
     },
     {
       "epoch": 0.37588892651540806,
-      "grad_norm": 13.60408878326416,
+      "grad_norm": 2.485625743865967,
       "learning_rate": 1.9895298012876192e-05,
-      "loss": 0.4196,
+      "loss": 0.3374,
       "step": 185
     },
     {
       "epoch": 0.38604808669150015,
-      "grad_norm": 15.972042083740234,
+      "grad_norm": 4.814594268798828,
       "learning_rate": 1.988558192853438e-05,
-      "loss": 0.4916,
+      "loss": 0.4168,
       "step": 190
     },
     {
       "epoch": 0.3962072468675923,
-      "grad_norm": 13.422971725463867,
+      "grad_norm": 2.605052947998047,
       "learning_rate": 1.987543739478507e-05,
-      "loss": 0.4736,
+      "loss": 0.3989,
       "step": 195
     },
     {
       "epoch": 0.4063664070436844,
-      "grad_norm": 7.696578502655029,
+      "grad_norm": 2.1149821281433105,
       "learning_rate": 1.9864864851300863e-05,
-      "loss": 0.3668,
+      "loss": 0.3135,
       "step": 200
     },
     {
       "epoch": 0.4165255672197765,
-      "grad_norm": 10.70732593536377,
+      "grad_norm": 2.4672765731811523,
       "learning_rate": 1.9853864756304654e-05,
-      "loss": 0.3385,
+      "loss": 0.3369,
       "step": 205
     },
     {
       "epoch": 0.4266847273958686,
-      "grad_norm": 11.150247573852539,
+      "grad_norm": 3.507082223892212,
       "learning_rate": 1.9842437586549783e-05,
-      "loss": 0.4407,
+      "loss": 0.4491,
       "step": 210
     },
     {
       "epoch": 0.43684388757196074,
-      "grad_norm": 9.345061302185059,
+      "grad_norm": 2.400405168533325,
       "learning_rate": 1.9830583837299363e-05,
-      "loss": 0.363,
+      "loss": 0.261,
       "step": 215
     },
     {
       "epoch": 0.44700304774805283,
-      "grad_norm": 10.30116081237793,
+      "grad_norm": 2.11639142036438,
       "learning_rate": 1.9818304022304824e-05,
-      "loss": 0.3223,
+      "loss": 0.2729,
       "step": 220
     },
     {
       "epoch": 0.4571622079241449,
-      "grad_norm": 11.17568588256836,
+      "grad_norm": 2.694459915161133,
       "learning_rate": 1.9805598673783644e-05,
-      "loss": 0.4883,
+      "loss": 0.3632,
       "step": 225
     },
     {
       "epoch": 0.46732136810023706,
-      "grad_norm": 7.653155326843262,
+      "grad_norm": 3.1920552253723145,
       "learning_rate": 1.9792468342396277e-05,
-      "loss": 0.3687,
+      "loss": 0.3526,
       "step": 230
     },
     {
       "epoch": 0.47748052827632914,
-      "grad_norm": 8.249720573425293,
+      "grad_norm": 3.2202322483062744,
       "learning_rate": 1.977891359722229e-05,
-      "loss": 0.3696,
+      "loss": 0.379,
       "step": 235
     },
     {
       "epoch": 0.4876396884524213,
-      "grad_norm": 6.872019290924072,
+      "grad_norm": 2.3833398818969727,
       "learning_rate": 1.9764935025735704e-05,
-      "loss": 0.2978,
+      "loss": 0.2775,
       "step": 240
     },
     {
       "epoch": 0.49779884862851337,
-      "grad_norm": 8.779520034790039,
+      "grad_norm": 2.6584055423736572,
       "learning_rate": 1.975053323377952e-05,
-      "loss": 0.4099,
+      "loss": 0.3379,
       "step": 245
     },
     {
       "epoch": 0.5079580088046055,
-      "grad_norm": 6.471978664398193,
+      "grad_norm": 2.2189712524414062,
       "learning_rate": 1.9735708845539486e-05,
-      "loss": 0.3345,
+      "loss": 0.322,
       "step": 250
     },
     {
       "epoch": 0.5181171689806976,
-      "grad_norm": 7.227390766143799,
+      "grad_norm": 2.330989122390747,
       "learning_rate": 1.9720462503517e-05,
-      "loss": 0.4044,
+      "loss": 0.3427,
       "step": 255
     },
     {
       "epoch": 0.5282763291567897,
-      "grad_norm": 10.536629676818848,
+      "grad_norm": 3.947791576385498,
       "learning_rate": 1.9704794868501314e-05,
-      "loss": 0.3444,
+      "loss": 0.3343,
       "step": 260
     },
     {
       "epoch": 0.5384354893328818,
-      "grad_norm": 5.935635566711426,
+      "grad_norm": 2.047577142715454,
       "learning_rate": 1.9688706619540863e-05,
-      "loss": 0.4022,
+      "loss": 0.358,
       "step": 265
     },
     {
       "epoch": 0.548594649508974,
-      "grad_norm": 10.507606506347656,
+      "grad_norm": 4.56735372543335,
       "learning_rate": 1.967219845391384e-05,
-      "loss": 0.453,
+      "loss": 0.4109,
       "step": 270
     },
     {
       "epoch": 0.558753809685066,
-      "grad_norm": 9.127860069274902,
+      "grad_norm": 3.7139999866485596,
       "learning_rate": 1.965527108709798e-05,
-      "loss": 0.3919,
+      "loss": 0.2783,
       "step": 275
     },
     {
       "epoch": 0.5689129698611581,
-      "grad_norm": 8.938516616821289,
+      "grad_norm": 2.7121667861938477,
       "learning_rate": 1.963792525273956e-05,
-      "loss": 0.4063,
+      "loss": 0.3055,
       "step": 280
     },
     {
       "epoch": 0.5790721300372502,
-      "grad_norm": 5.574091911315918,
+      "grad_norm": 2.758436441421509,
       "learning_rate": 1.962016170262157e-05,
-      "loss": 0.3903,
+      "loss": 0.3774,
       "step": 285
     },
     {
       "epoch": 0.5892312902133424,
-      "grad_norm": 8.818571090698242,
+      "grad_norm": 1.9737869501113892,
       "learning_rate": 1.960198120663117e-05,
-      "loss": 0.3645,
+      "loss": 0.2895,
       "step": 290
     },
     {
       "epoch": 0.5993904503894345,
-      "grad_norm": 10.282978057861328,
+      "grad_norm": 2.611140012741089,
       "learning_rate": 1.9583384552726294e-05,
-      "loss": 0.4503,
+      "loss": 0.3837,
       "step": 295
     },
     {
       "epoch": 0.6095496105655266,
-      "grad_norm": 11.942185401916504,
+      "grad_norm": 2.4054672718048096,
       "learning_rate": 1.9564372546901512e-05,
-      "loss": 0.3296,
+      "loss": 0.2958,
       "step": 300
     },
     {
       "epoch": 0.6197087707416187,
-      "grad_norm": 15.513096809387207,
+      "grad_norm": 4.541679859161377,
       "learning_rate": 1.9544946013153093e-05,
-      "loss": 0.4272,
+      "loss": 0.4041,
       "step": 305
     },
     {
       "epoch": 0.6298679309177108,
-      "grad_norm": 13.280257225036621,
+      "grad_norm": 2.5539488792419434,
       "learning_rate": 1.9525105793443288e-05,
-      "loss": 0.4149,
+      "loss": 0.3,
       "step": 310
     },
     {
       "epoch": 0.640027091093803,
-      "grad_norm": 14.556711196899414,
+      "grad_norm": 2.7427711486816406,
       "learning_rate": 1.9504852747663862e-05,
-      "loss": 0.371,
+      "loss": 0.3478,
       "step": 315
     },
     {
       "epoch": 0.650186251269895,
-      "grad_norm": 11.565403938293457,
+      "grad_norm": 2.7473108768463135,
       "learning_rate": 1.948418775359879e-05,
-      "loss": 0.3603,
+      "loss": 0.3385,
       "step": 320
     },
     {
       "epoch": 0.6603454114459871,
-      "grad_norm": 7.955371379852295,
+      "grad_norm": 1.8745321035385132,
       "learning_rate": 1.9463111706886234e-05,
-      "loss": 0.4072,
+      "loss": 0.3085,
       "step": 325
     },
     {
       "epoch": 0.6705045716220792,
-      "grad_norm": 10.183494567871094,
+      "grad_norm": 4.0707902908325195,
       "learning_rate": 1.9441625520979736e-05,
-      "loss": 0.4365,
+      "loss": 0.4277,
       "step": 330
     },
     {
       "epoch": 0.6806637317981713,
-      "grad_norm": 7.960467338562012,
+      "grad_norm": 3.7354769706726074,
       "learning_rate": 1.941973012710859e-05,
-      "loss": 0.4313,
+      "loss": 0.3845,
       "step": 335
     },
     {
       "epoch": 0.6908228919742635,
-      "grad_norm": 7.371551990509033,
+      "grad_norm": 2.520270824432373,
       "learning_rate": 1.9397426474237538e-05,
-      "loss": 0.4297,
+      "loss": 0.3038,
       "step": 340
     },
     {
       "epoch": 0.7009820521503556,
-      "grad_norm": 7.921060562133789,
+      "grad_norm": 3.105069637298584,
       "learning_rate": 1.9374715529025575e-05,
-      "loss": 0.3439,
+      "loss": 0.3525,
       "step": 345
     },
     {
       "epoch": 0.7111412123264477,
-      "grad_norm": 7.862534999847412,
+      "grad_norm": 3.4266366958618164,
       "learning_rate": 1.9351598275784116e-05,
-      "loss": 0.3239,
+      "loss": 0.255,
       "step": 350
     },
     {
       "epoch": 0.7213003725025398,
-      "grad_norm": 7.013054847717285,
+      "grad_norm": 2.866426467895508,
       "learning_rate": 1.9328075716434287e-05,
-      "loss": 0.3831,
+      "loss": 0.384,
       "step": 355
     },
     {
       "epoch": 0.731459532678632,
-      "grad_norm": 8.324191093444824,
+      "grad_norm": 2.250730276107788,
       "learning_rate": 1.9304148870463534e-05,
-      "loss": 0.4026,
+      "loss": 0.3071,
       "step": 360
     },
     {
       "epoch": 0.741618692854724,
-      "grad_norm": 6.676064491271973,
+      "grad_norm": 1.4349896907806396,
       "learning_rate": 1.9279818774881418e-05,
-      "loss": 0.3658,
+      "loss": 0.2613,
       "step": 365
     },
     {
       "epoch": 0.7517778530308161,
-      "grad_norm": 9.717394828796387,
+      "grad_norm": 2.4176418781280518,
       "learning_rate": 1.925508648417467e-05,
-      "loss": 0.4352,
+      "loss": 0.4177,
       "step": 370
     },
     {
       "epoch": 0.7619370132069082,
-      "grad_norm": 11.164401054382324,
+      "grad_norm": 2.631744623184204,
       "learning_rate": 1.922995307026151e-05,
-      "loss": 0.3615,
+      "loss": 0.3349,
       "step": 375
     },
     {
       "epoch": 0.7720961733830003,
-      "grad_norm": 11.754335403442383,
+      "grad_norm": 2.8593008518218994,
       "learning_rate": 1.9204419622445157e-05,
-      "loss": 0.418,
+      "loss": 0.3561,
       "step": 380
     },
     {
       "epoch": 0.7822553335590925,
-      "grad_norm": 12.489151000976562,
+      "grad_norm": 2.936988353729248,
       "learning_rate": 1.9178487247366652e-05,
-      "loss": 0.4442,
+      "loss": 0.3504,
       "step": 385
     },
     {
       "epoch": 0.7924144937351846,
-      "grad_norm": 9.152201652526855,
+      "grad_norm": 2.569715976715088,
       "learning_rate": 1.9152157068956863e-05,
-      "loss": 0.433,
+      "loss": 0.3347,
       "step": 390
     },
     {
       "epoch": 0.8025736539112767,
-      "grad_norm": 11.61486530303955,
+      "grad_norm": 2.0628387928009033,
       "learning_rate": 1.9125430228387794e-05,
-      "loss": 0.3619,
+      "loss": 0.338,
       "step": 395
     },
     {
       "epoch": 0.8127328140873687,
-      "grad_norm": 11.761738777160645,
+      "grad_norm": 2.280639171600342,
       "learning_rate": 1.9098307884023122e-05,
-      "loss": 0.4475,
+      "loss": 0.3312,
       "step": 400
     },
     {
       "epoch": 0.8228919742634608,
-      "grad_norm": 13.330485343933105,
+      "grad_norm": 3.135791063308716,
       "learning_rate": 1.9070791211367984e-05,
-      "loss": 0.4375,
+      "loss": 0.3486,
       "step": 405
     },
     {
       "epoch": 0.833051134439553,
-      "grad_norm": 11.111174583435059,
+      "grad_norm": 2.3634705543518066,
       "learning_rate": 1.9042881403018044e-05,
-      "loss": 0.4828,
+      "loss": 0.3452,
       "step": 410
     },
     {
       "epoch": 0.8432102946156451,
-      "grad_norm": 9.631218910217285,
+      "grad_norm": 2.907541036605835,
       "learning_rate": 1.901457966860779e-05,
-      "loss": 0.3723,
+      "loss": 0.3432,
       "step": 415
     },
     {
       "epoch": 0.8533694547917372,
-      "grad_norm": 9.732425689697266,
+      "grad_norm": 3.2630741596221924,
       "learning_rate": 1.898588723475811e-05,
-      "loss": 0.4157,
+      "loss": 0.2978,
       "step": 420
     },
     {
       "epoch": 0.8635286149678293,
-      "grad_norm": 7.526575565338135,
+      "grad_norm": 6.598920822143555,
       "learning_rate": 1.8956805345023145e-05,
-      "loss": 0.3623,
+      "loss": 0.2262,
       "step": 425
     },
     {
       "epoch": 0.8736877751439215,
-      "grad_norm": 2.7879254817962646,
+      "grad_norm": 1.824955940246582,
       "learning_rate": 1.8927335259836376e-05,
-      "loss": 0.3487,
+      "loss": 0.3078,
       "step": 430
     },
     {
       "epoch": 0.8838469353200136,
-      "grad_norm": 7.137866497039795,
+      "grad_norm": 3.684520721435547,
       "learning_rate": 1.889747825645599e-05,
-      "loss": 0.5294,
+      "loss": 0.5071,
       "step": 435
     },
     {
       "epoch": 0.8940060954961057,
-      "grad_norm": 9.2273588180542,
+      "grad_norm": 4.583770275115967,
       "learning_rate": 1.8867235628909553e-05,
-      "loss": 0.4501,
+      "loss": 0.3513,
       "step": 440
     },
     {
       "epoch": 0.9041652556721977,
-      "grad_norm": 5.851348876953125,
+      "grad_norm": 2.5512242317199707,
       "learning_rate": 1.8836608687937883e-05,
-      "loss": 0.3622,
+      "loss": 0.33,
       "step": 445
     },
     {
       "epoch": 0.9143244158482898,
-      "grad_norm": 5.815377712249756,
+      "grad_norm": 2.3241894245147705,
       "learning_rate": 1.8805598760938282e-05,
-      "loss": 0.3976,
+      "loss": 0.2769,
       "step": 450
     },
     {
       "epoch": 0.924483576024382,
-      "grad_norm": 5.44211483001709,
+      "grad_norm": 2.3357667922973633,
       "learning_rate": 1.8774207191906976e-05,
-      "loss": 0.385,
+      "loss": 0.2971,
       "step": 455
     },
     {
       "epoch": 0.9346427362004741,
-      "grad_norm": 4.0405049324035645,
+      "grad_norm": 2.1042768955230713,
       "learning_rate": 1.874243534138089e-05,
-      "loss": 0.3863,
+      "loss": 0.3591,
       "step": 460
     },
     {
       "epoch": 0.9448018963765662,
-      "grad_norm": 5.252662658691406,
+      "grad_norm": 2.9413928985595703,
       "learning_rate": 1.8710284586378645e-05,
-      "loss": 0.3869,
+      "loss": 0.3325,
       "step": 465
     },
     {
       "epoch": 0.9549610565526583,
-      "grad_norm": 5.840423583984375,
+      "grad_norm": 5.109018325805664,
       "learning_rate": 1.8677756320340927e-05,
-      "loss": 0.4685,
+      "loss": 0.3563,
       "step": 470
     },
     {
       "epoch": 0.9651202167287504,
-      "grad_norm": 10.367392539978027,
+      "grad_norm": 2.7905688285827637,
       "learning_rate": 1.8644851953070045e-05,
-      "loss": 0.4045,
+      "loss": 0.3286,
       "step": 475
     },
     {
       "epoch": 0.9752793769048426,
-      "grad_norm": 6.398050785064697,
+      "grad_norm": 1.115858793258667,
       "learning_rate": 1.8611572910668866e-05,
-      "loss": 0.2973,
+      "loss": 0.3017,
       "step": 480
     },
     {
       "epoch": 0.9854385370809347,
-      "grad_norm": 11.543962478637695,
+      "grad_norm": 3.1876089572906494,
       "learning_rate": 1.8577920635478976e-05,
-      "loss": 0.3855,
+      "loss": 0.327,
       "step": 485
     },
     {
       "epoch": 0.9955976972570267,
-      "grad_norm": 12.093887329101562,
+      "grad_norm": 3.669804334640503,
       "learning_rate": 1.85438965860182e-05,
-      "loss": 0.3772,
+      "loss": 0.3641,
       "step": 490
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9081264108352144,
-      "eval_f1": 0.0,
-      "eval_loss": 0.4431517720222473,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 242.2358,
-      "eval_samples_per_second": 18.288,
-      "eval_steps_per_second": 4.574,
+      "eval_accuracy": 0.9139954853273138,
+      "eval_f1": 0.1771058315334773,
+      "eval_loss": 0.3493718206882477,
+      "eval_precision": 0.7321428571428571,
+      "eval_recall": 0.10073710073710074,
+      "eval_runtime": 241.1239,
+      "eval_samples_per_second": 18.372,
+      "eval_steps_per_second": 4.595,
       "step": 493
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9165fd87d622bef9592d08dfe6f3ba05ef5d0823e7e8902cf48a842306247f27
+oid sha256:f5a040469cbc12515aa68e8f12e3b297144262ee28cc7ace4e1afedab7e3815b
 size 5304