Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8967e449012f7c944184f3ce6349fd31aa445ea5aa57e3ed9c3ebe1b72e9154e
+oid sha256:1c27310485a9b79a035ce96eefa30c3f05ca41b3dbc0a791f8358ec7a4cade6b
 size 343263964

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1e1a549d597eaafe6ed33bbfaef5b45c6b665601d3306f11a2c94af7c827b5
+oid sha256:dcd11d58bd2ec412b20b27e86c8f5848d6add1200c349b431a5cd60b5225319b
 size 686648762

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e639b2ecb2aadfd272d6a9f35fa08de5eb4f8889c32310c3292be755c67c29
+oid sha256:fd5a7979006addc7da940500294cb37f12b9720d1946ac787792f8aae8227211
 size 1064

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.16356664896011353,
+  "best_metric": 0.16896109282970428,
   "best_model_checkpoint": "./vit-indian-food/checkpoint-500",
   "epoch": 2.6178010471204187,
   "eval_steps": 50,
@@ -10,819 +10,819 @@
   "log_history": [
     {
       "epoch": 0.03,
-      "grad_norm": 6.967112064361572,
-      "learning_rate": 0.00019895287958115185,
-      "loss": 2.3423,
+      "grad_norm": 7.558130264282227,
+      "learning_rate": 0.00019947643979057592,
+      "loss": 2.4369,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 6.768218517303467,
-      "learning_rate": 0.00019790575916230367,
-      "loss": 1.5082,
+      "grad_norm": 6.5493950843811035,
+      "learning_rate": 0.00019895287958115185,
+      "loss": 1.6214,
       "step": 10
     },
     {
       "epoch": 0.08,
-      "grad_norm": 6.283707141876221,
-      "learning_rate": 0.0001968586387434555,
-      "loss": 1.1555,
+      "grad_norm": 6.205695629119873,
+      "learning_rate": 0.00019842931937172776,
+      "loss": 1.197,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 4.167559623718262,
-      "learning_rate": 0.00019581151832460733,
-      "loss": 0.7045,
+      "grad_norm": 3.8880319595336914,
+      "learning_rate": 0.00019790575916230367,
+      "loss": 0.7391,
       "step": 20
     },
     {
       "epoch": 0.13,
-      "grad_norm": 6.519095420837402,
-      "learning_rate": 0.00019476439790575917,
-      "loss": 0.5942,
+      "grad_norm": 6.315922260284424,
+      "learning_rate": 0.0001973821989528796,
+      "loss": 0.6288,
       "step": 25
     },
     {
       "epoch": 0.16,
-      "grad_norm": 4.0483479499816895,
-      "learning_rate": 0.000193717277486911,
-      "loss": 0.45,
+      "grad_norm": 4.008142471313477,
+      "learning_rate": 0.0001968586387434555,
+      "loss": 0.3582,
       "step": 30
     },
     {
       "epoch": 0.18,
-      "grad_norm": 4.359745025634766,
-      "learning_rate": 0.00019267015706806283,
-      "loss": 0.3833,
+      "grad_norm": 4.005300998687744,
+      "learning_rate": 0.00019633507853403142,
+      "loss": 0.3882,
       "step": 35
     },
     {
       "epoch": 0.21,
-      "grad_norm": 5.201784610748291,
-      "learning_rate": 0.00019162303664921465,
-      "loss": 0.3702,
+      "grad_norm": 3.9506969451904297,
+      "learning_rate": 0.00019581151832460733,
+      "loss": 0.39,
       "step": 40
     },
     {
       "epoch": 0.24,
-      "grad_norm": 4.259886741638184,
-      "learning_rate": 0.0001905759162303665,
-      "loss": 0.3227,
+      "grad_norm": 4.074863910675049,
+      "learning_rate": 0.00019528795811518326,
+      "loss": 0.3413,
       "step": 45
     },
     {
       "epoch": 0.26,
-      "grad_norm": 4.89500617980957,
-      "learning_rate": 0.00018952879581151833,
-      "loss": 0.2368,
+      "grad_norm": 4.617203712463379,
+      "learning_rate": 0.00019476439790575917,
+      "loss": 0.358,
       "step": 50
     },
     {
       "epoch": 0.26,
-      "eval_accuracy": 0.9002624671916011,
-      "eval_loss": 0.33144867420196533,
-      "eval_precision": 0.9131344269428404,
-      "eval_recall": 0.9002624671916011,
-      "eval_runtime": 17.436,
-      "eval_samples_per_second": 43.703,
-      "eval_steps_per_second": 2.753,
+      "eval_accuracy": 0.9081364829396326,
+      "eval_loss": 0.32936015725135803,
+      "eval_precision": 0.9220515144455581,
+      "eval_recall": 0.9081364829396326,
+      "eval_runtime": 17.5763,
+      "eval_samples_per_second": 43.354,
+      "eval_steps_per_second": 2.731,
       "step": 50
     },
     {
       "epoch": 0.29,
-      "grad_norm": 4.650336265563965,
-      "learning_rate": 0.00018848167539267018,
-      "loss": 0.4139,
+      "grad_norm": 4.685304641723633,
+      "learning_rate": 0.0001942408376963351,
+      "loss": 0.3669,
       "step": 55
     },
     {
       "epoch": 0.31,
-      "grad_norm": 4.881960391998291,
-      "learning_rate": 0.00018743455497382202,
-      "loss": 0.2109,
+      "grad_norm": 3.119244337081909,
+      "learning_rate": 0.000193717277486911,
+      "loss": 0.1722,
       "step": 60
     },
     {
       "epoch": 0.34,
-      "grad_norm": 5.3574066162109375,
-      "learning_rate": 0.00018638743455497384,
-      "loss": 0.3076,
+      "grad_norm": 6.17639684677124,
+      "learning_rate": 0.00019319371727748692,
+      "loss": 0.405,
       "step": 65
     },
     {
       "epoch": 0.37,
-      "grad_norm": 5.008607864379883,
-      "learning_rate": 0.00018534031413612568,
-      "loss": 0.2632,
+      "grad_norm": 4.263852119445801,
+      "learning_rate": 0.00019267015706806283,
+      "loss": 0.5013,
       "step": 70
     },
     {
       "epoch": 0.39,
-      "grad_norm": 4.561398506164551,
-      "learning_rate": 0.0001842931937172775,
-      "loss": 0.2062,
+      "grad_norm": 2.03020977973938,
+      "learning_rate": 0.00019214659685863877,
+      "loss": 0.2251,
       "step": 75
     },
     {
       "epoch": 0.42,
-      "grad_norm": 5.034663677215576,
-      "learning_rate": 0.00018324607329842934,
-      "loss": 0.4752,
+      "grad_norm": 5.0216193199157715,
+      "learning_rate": 0.00019162303664921465,
+      "loss": 0.3329,
       "step": 80
     },
     {
       "epoch": 0.45,
-      "grad_norm": 8.143318176269531,
-      "learning_rate": 0.00018219895287958115,
-      "loss": 0.3963,
+      "grad_norm": 7.692380428314209,
+      "learning_rate": 0.00019109947643979058,
+      "loss": 0.2191,
       "step": 85
     },
     {
       "epoch": 0.47,
-      "grad_norm": 6.556373119354248,
-      "learning_rate": 0.000181151832460733,
-      "loss": 0.5088,
+      "grad_norm": 5.645913600921631,
+      "learning_rate": 0.0001905759162303665,
+      "loss": 0.3437,
       "step": 90
     },
     {
       "epoch": 0.5,
-      "grad_norm": 4.414945125579834,
-      "learning_rate": 0.0001801047120418848,
-      "loss": 0.2903,
+      "grad_norm": 5.066718578338623,
+      "learning_rate": 0.00019005235602094243,
+      "loss": 0.4461,
       "step": 95
     },
     {
       "epoch": 0.52,
-      "grad_norm": 2.464193820953369,
-      "learning_rate": 0.00017905759162303666,
-      "loss": 0.2801,
+      "grad_norm": 4.659124851226807,
+      "learning_rate": 0.00018952879581151833,
+      "loss": 0.5051,
       "step": 100
     },
     {
       "epoch": 0.52,
-      "eval_accuracy": 0.9422572178477691,
-      "eval_loss": 0.18048594892024994,
-      "eval_precision": 0.9466471604125616,
-      "eval_recall": 0.9422572178477691,
-      "eval_runtime": 17.2463,
-      "eval_samples_per_second": 44.183,
-      "eval_steps_per_second": 2.783,
+      "eval_accuracy": 0.9291338582677166,
+      "eval_loss": 0.22470374405384064,
+      "eval_precision": 0.9372539303361345,
+      "eval_recall": 0.9291338582677166,
+      "eval_runtime": 17.4785,
+      "eval_samples_per_second": 43.597,
+      "eval_steps_per_second": 2.746,
       "step": 100
     },
     {
       "epoch": 0.55,
-      "grad_norm": 5.096113681793213,
-      "learning_rate": 0.0001780104712041885,
-      "loss": 0.213,
+      "grad_norm": 4.5200324058532715,
+      "learning_rate": 0.00018900523560209424,
+      "loss": 0.2615,
       "step": 105
     },
     {
       "epoch": 0.58,
-      "grad_norm": 1.4251294136047363,
-      "learning_rate": 0.00017696335078534032,
-      "loss": 0.1831,
+      "grad_norm": 1.2165738344192505,
+      "learning_rate": 0.00018848167539267018,
+      "loss": 0.2415,
       "step": 110
     },
     {
       "epoch": 0.6,
-      "grad_norm": 3.766965627670288,
-      "learning_rate": 0.00017591623036649216,
-      "loss": 0.1636,
+      "grad_norm": 6.801146030426025,
+      "learning_rate": 0.00018795811518324608,
+      "loss": 0.3234,
       "step": 115
     },
     {
       "epoch": 0.63,
-      "grad_norm": 3.66446852684021,
-      "learning_rate": 0.00017486910994764398,
-      "loss": 0.3075,
+      "grad_norm": 0.8039401173591614,
+      "learning_rate": 0.00018743455497382202,
+      "loss": 0.1962,
       "step": 120
     },
     {
       "epoch": 0.65,
-      "grad_norm": 4.702181339263916,
-      "learning_rate": 0.00017382198952879582,
-      "loss": 0.2472,
+      "grad_norm": 4.639632701873779,
+      "learning_rate": 0.0001869109947643979,
+      "loss": 0.2755,
       "step": 125
     },
     {
       "epoch": 0.68,
-      "grad_norm": 8.463685035705566,
-      "learning_rate": 0.00017277486910994763,
-      "loss": 0.4341,
+      "grad_norm": 3.4670636653900146,
+      "learning_rate": 0.00018638743455497384,
+      "loss": 0.3463,
       "step": 130
     },
     {
       "epoch": 0.71,
-      "grad_norm": 5.947971343994141,
-      "learning_rate": 0.00017172774869109948,
-      "loss": 0.2291,
+      "grad_norm": 6.07156229019165,
+      "learning_rate": 0.00018586387434554974,
+      "loss": 0.3047,
       "step": 135
     },
     {
       "epoch": 0.73,
-      "grad_norm": 5.682934761047363,
-      "learning_rate": 0.00017068062827225132,
-      "loss": 0.1632,
+      "grad_norm": 6.347087860107422,
+      "learning_rate": 0.00018534031413612568,
+      "loss": 0.2364,
       "step": 140
     },
     {
       "epoch": 0.76,
-      "grad_norm": 9.100614547729492,
-      "learning_rate": 0.00016963350785340316,
-      "loss": 0.307,
+      "grad_norm": 5.963706970214844,
+      "learning_rate": 0.00018481675392670156,
+      "loss": 0.4148,
       "step": 145
     },
     {
       "epoch": 0.79,
-      "grad_norm": 4.207605361938477,
-      "learning_rate": 0.00016858638743455498,
-      "loss": 0.2362,
+      "grad_norm": 4.037764072418213,
+      "learning_rate": 0.0001842931937172775,
+      "loss": 0.1361,
       "step": 150
     },
     {
       "epoch": 0.79,
-      "eval_accuracy": 0.9186351706036745,
-      "eval_loss": 0.29145774245262146,
-      "eval_precision": 0.9273784378254858,
-      "eval_recall": 0.9186351706036745,
-      "eval_runtime": 17.4226,
-      "eval_samples_per_second": 43.736,
-      "eval_steps_per_second": 2.755,
+      "eval_accuracy": 0.9409448818897638,
+      "eval_loss": 0.21655863523483276,
+      "eval_precision": 0.9454930944052194,
+      "eval_recall": 0.9409448818897638,
+      "eval_runtime": 17.4607,
+      "eval_samples_per_second": 43.641,
+      "eval_steps_per_second": 2.749,
       "step": 150
     },
     {
       "epoch": 0.81,
-      "grad_norm": 3.4303929805755615,
-      "learning_rate": 0.00016753926701570682,
-      "loss": 0.074,
+      "grad_norm": 4.717739582061768,
+      "learning_rate": 0.0001837696335078534,
+      "loss": 0.1183,
       "step": 155
     },
     {
       "epoch": 0.84,
-      "grad_norm": 4.852244853973389,
-      "learning_rate": 0.00016649214659685867,
-      "loss": 0.2731,
+      "grad_norm": 3.9427084922790527,
+      "learning_rate": 0.00018324607329842934,
+      "loss": 0.1138,
       "step": 160
     },
     {
       "epoch": 0.86,
-      "grad_norm": 0.3142894506454468,
-      "learning_rate": 0.00016544502617801048,
-      "loss": 0.1295,
+      "grad_norm": 4.915616989135742,
+      "learning_rate": 0.00018272251308900525,
+      "loss": 0.2988,
       "step": 165
     },
     {
       "epoch": 0.89,
-      "grad_norm": 3.892892360687256,
-      "learning_rate": 0.00016439790575916233,
-      "loss": 0.225,
+      "grad_norm": 6.3770432472229,
+      "learning_rate": 0.00018219895287958115,
+      "loss": 0.1744,
       "step": 170
     },
     {
       "epoch": 0.92,
-      "grad_norm": 4.833043575286865,
-      "learning_rate": 0.00016335078534031414,
-      "loss": 0.2674,
+      "grad_norm": 0.7859281301498413,
+      "learning_rate": 0.00018167539267015706,
+      "loss": 0.2486,
       "step": 175
     },
     {
       "epoch": 0.94,
-      "grad_norm": 5.150189399719238,
-      "learning_rate": 0.00016230366492146599,
-      "loss": 0.241,
+      "grad_norm": 3.75736141204834,
+      "learning_rate": 0.000181151832460733,
+      "loss": 0.2637,
       "step": 180
     },
     {
       "epoch": 0.97,
-      "grad_norm": 5.426727771759033,
-      "learning_rate": 0.0001612565445026178,
-      "loss": 0.2049,
+      "grad_norm": 6.771958351135254,
+      "learning_rate": 0.0001806282722513089,
+      "loss": 0.2305,
       "step": 185
     },
     {
       "epoch": 0.99,
-      "grad_norm": 5.2064738273620605,
-      "learning_rate": 0.00016020942408376964,
-      "loss": 0.1756,
+      "grad_norm": 4.951119899749756,
+      "learning_rate": 0.0001801047120418848,
+      "loss": 0.1108,
       "step": 190
     },
     {
       "epoch": 1.02,
-      "grad_norm": 2.034318685531616,
-      "learning_rate": 0.00015916230366492146,
-      "loss": 0.0499,
+      "grad_norm": 3.362152576446533,
+      "learning_rate": 0.00017958115183246075,
+      "loss": 0.133,
       "step": 195
     },
     {
       "epoch": 1.05,
-      "grad_norm": 4.4703145027160645,
-      "learning_rate": 0.0001581151832460733,
-      "loss": 0.042,
+      "grad_norm": 0.8346299529075623,
+      "learning_rate": 0.00017905759162303666,
+      "loss": 0.0611,
       "step": 200
     },
     {
       "epoch": 1.05,
-      "eval_accuracy": 0.9461942257217848,
-      "eval_loss": 0.16130226850509644,
-      "eval_precision": 0.9511635531837818,
-      "eval_recall": 0.9461942257217848,
-      "eval_runtime": 17.3623,
-      "eval_samples_per_second": 43.888,
-      "eval_steps_per_second": 2.765,
+      "eval_accuracy": 0.9488188976377953,
+      "eval_loss": 0.18689152598381042,
+      "eval_precision": 0.9533647964651322,
+      "eval_recall": 0.9488188976377953,
+      "eval_runtime": 17.6111,
+      "eval_samples_per_second": 43.268,
+      "eval_steps_per_second": 2.726,
       "step": 200
     },
     {
       "epoch": 1.07,
-      "grad_norm": 0.06716866791248322,
-      "learning_rate": 0.00015706806282722515,
-      "loss": 0.0643,
+      "grad_norm": 0.5746695399284363,
+      "learning_rate": 0.0001785340314136126,
+      "loss": 0.0241,
       "step": 205
     },
     {
       "epoch": 1.1,
-      "grad_norm": 7.002842903137207,
-      "learning_rate": 0.00015602094240837696,
-      "loss": 0.1028,
+      "grad_norm": 2.0743372440338135,
+      "learning_rate": 0.0001780104712041885,
+      "loss": 0.0662,
       "step": 210
     },
     {
       "epoch": 1.13,
-      "grad_norm": 0.013943655416369438,
-      "learning_rate": 0.0001549738219895288,
-      "loss": 0.0941,
+      "grad_norm": 1.6814557313919067,
+      "learning_rate": 0.0001774869109947644,
+      "loss": 0.0635,
       "step": 215
     },
     {
       "epoch": 1.15,
-      "grad_norm": 0.42214348912239075,
-      "learning_rate": 0.00015392670157068062,
-      "loss": 0.0273,
+      "grad_norm": 2.118739128112793,
+      "learning_rate": 0.00017696335078534032,
+      "loss": 0.1024,
       "step": 220
     },
     {
       "epoch": 1.18,
-      "grad_norm": 8.428805351257324,
-      "learning_rate": 0.00015287958115183247,
-      "loss": 0.0589,
+      "grad_norm": 3.4306182861328125,
+      "learning_rate": 0.00017643979057591625,
+      "loss": 0.0201,
       "step": 225
     },
     {
       "epoch": 1.2,
-      "grad_norm": 2.468398094177246,
-      "learning_rate": 0.00015183246073298428,
-      "loss": 0.0321,
+      "grad_norm": 0.28945377469062805,
+      "learning_rate": 0.00017591623036649216,
+      "loss": 0.1151,
       "step": 230
     },
     {
       "epoch": 1.23,
-      "grad_norm": 0.8661732077598572,
-      "learning_rate": 0.00015078534031413612,
-      "loss": 0.0856,
+      "grad_norm": 4.6208648681640625,
+      "learning_rate": 0.00017539267015706807,
+      "loss": 0.2324,
       "step": 235
     },
     {
       "epoch": 1.26,
-      "grad_norm": 0.4541776478290558,
-      "learning_rate": 0.00014973821989528797,
-      "loss": 0.0136,
+      "grad_norm": 1.6085395812988281,
+      "learning_rate": 0.00017486910994764398,
+      "loss": 0.0429,
       "step": 240
     },
     {
       "epoch": 1.28,
-      "grad_norm": 4.832011699676514,
-      "learning_rate": 0.0001486910994764398,
-      "loss": 0.1087,
+      "grad_norm": 5.860565185546875,
+      "learning_rate": 0.0001743455497382199,
+      "loss": 0.0567,
       "step": 245
     },
     {
       "epoch": 1.31,
-      "grad_norm": 4.744746685028076,
-      "learning_rate": 0.00014764397905759163,
-      "loss": 0.0477,
+      "grad_norm": 5.421276092529297,
+      "learning_rate": 0.00017382198952879582,
+      "loss": 0.1037,
       "step": 250
     },
     {
       "epoch": 1.31,
-      "eval_accuracy": 0.9514435695538058,
-      "eval_loss": 0.14496225118637085,
-      "eval_precision": 0.9534067355318784,
-      "eval_recall": 0.9514435695538058,
-      "eval_runtime": 17.4463,
-      "eval_samples_per_second": 43.677,
-      "eval_steps_per_second": 2.751,
+      "eval_accuracy": 0.968503937007874,
+      "eval_loss": 0.11793948709964752,
+      "eval_precision": 0.9693355319509627,
+      "eval_recall": 0.968503937007874,
+      "eval_runtime": 17.5701,
+      "eval_samples_per_second": 43.369,
+      "eval_steps_per_second": 2.732,
       "step": 250
     },
     {
       "epoch": 1.34,
-      "grad_norm": 0.053365129977464676,
-      "learning_rate": 0.00014659685863874347,
-      "loss": 0.0171,
+      "grad_norm": 3.9477956295013428,
+      "learning_rate": 0.00017329842931937175,
+      "loss": 0.0285,
       "step": 255
     },
     {
       "epoch": 1.36,
-      "grad_norm": 0.41375842690467834,
-      "learning_rate": 0.00014554973821989531,
-      "loss": 0.1189,
+      "grad_norm": 7.515362739562988,
+      "learning_rate": 0.00017277486910994763,
+      "loss": 0.2195,
       "step": 260
     },
     {
       "epoch": 1.39,
-      "grad_norm": 0.05034720525145531,
-      "learning_rate": 0.00014450261780104713,
-      "loss": 0.0377,
+      "grad_norm": 0.1676739752292633,
+      "learning_rate": 0.00017225130890052357,
+      "loss": 0.0172,
       "step": 265
     },
     {
       "epoch": 1.41,
-      "grad_norm": 2.498413324356079,
-      "learning_rate": 0.00014345549738219897,
-      "loss": 0.0334,
+      "grad_norm": 8.235359191894531,
+      "learning_rate": 0.00017172774869109948,
+      "loss": 0.1756,
       "step": 270
     },
     {
       "epoch": 1.44,
-      "grad_norm": 0.06190189719200134,
-      "learning_rate": 0.0001424083769633508,
-      "loss": 0.0158,
+      "grad_norm": 7.9198832511901855,
+      "learning_rate": 0.0001712041884816754,
+      "loss": 0.0663,
       "step": 275
     },
     {
       "epoch": 1.47,
-      "grad_norm": 1.9862781763076782,
-      "learning_rate": 0.00014136125654450263,
-      "loss": 0.0186,
+      "grad_norm": 6.388627529144287,
+      "learning_rate": 0.00017068062827225132,
+      "loss": 0.1467,
       "step": 280
     },
     {
       "epoch": 1.49,
-      "grad_norm": 0.047805577516555786,
-      "learning_rate": 0.00014031413612565445,
-      "loss": 0.0705,
+      "grad_norm": 0.09213338047266006,
+      "learning_rate": 0.00017015706806282723,
+      "loss": 0.0684,
       "step": 285
     },
     {
       "epoch": 1.52,
-      "grad_norm": 0.03765374794602394,
-      "learning_rate": 0.0001392670157068063,
-      "loss": 0.1822,
+      "grad_norm": 1.0691012144088745,
+      "learning_rate": 0.00016963350785340316,
+      "loss": 0.0954,
       "step": 290
     },
     {
       "epoch": 1.54,
-      "grad_norm": 5.020593643188477,
-      "learning_rate": 0.0001382198952879581,
-      "loss": 0.0375,
+      "grad_norm": 6.120029449462891,
+      "learning_rate": 0.00016910994764397907,
+      "loss": 0.0587,
       "step": 295
     },
     {
       "epoch": 1.57,
-      "grad_norm": 1.0980048179626465,
-      "learning_rate": 0.00013717277486910995,
-      "loss": 0.1297,
+      "grad_norm": 0.0928138718008995,
+      "learning_rate": 0.00016858638743455498,
+      "loss": 0.0294,
       "step": 300
     },
     {
       "epoch": 1.57,
-      "eval_accuracy": 0.937007874015748,
-      "eval_loss": 0.24536970257759094,
-      "eval_precision": 0.9442846541005356,
-      "eval_recall": 0.937007874015748,
-      "eval_runtime": 17.5121,
-      "eval_samples_per_second": 43.513,
-      "eval_steps_per_second": 2.741,
+      "eval_accuracy": 0.963254593175853,
+      "eval_loss": 0.11820019036531448,
+      "eval_precision": 0.9645155573207865,
+      "eval_recall": 0.963254593175853,
+      "eval_runtime": 17.5014,
+      "eval_samples_per_second": 43.539,
+      "eval_steps_per_second": 2.743,
       "step": 300
     },
     {
       "epoch": 1.6,
-      "grad_norm": 3.535846471786499,
-      "learning_rate": 0.0001361256544502618,
-      "loss": 0.1071,
+      "grad_norm": 0.3131069242954254,
+      "learning_rate": 0.0001680628272251309,
+      "loss": 0.1184,
       "step": 305
     },
     {
       "epoch": 1.62,
-      "grad_norm": 4.182868957519531,
-      "learning_rate": 0.0001350785340314136,
-      "loss": 0.0249,
+      "grad_norm": 0.417850524187088,
+      "learning_rate": 0.00016753926701570682,
+      "loss": 0.0053,
       "step": 310
     },
     {
       "epoch": 1.65,
-      "grad_norm": 0.36884206533432007,
-      "learning_rate": 0.00013403141361256545,
-      "loss": 0.0762,
+      "grad_norm": 5.371811389923096,
+      "learning_rate": 0.00016701570680628273,
+      "loss": 0.1099,
       "step": 315
     },
     {
       "epoch": 1.68,
-      "grad_norm": 5.14253044128418,
-      "learning_rate": 0.00013298429319371727,
-      "loss": 0.0766,
+      "grad_norm": 4.09129524230957,
+      "learning_rate": 0.00016649214659685867,
+      "loss": 0.2501,
       "step": 320
     },
     {
       "epoch": 1.7,
-      "grad_norm": 1.2552727460861206,
-      "learning_rate": 0.0001319371727748691,
-      "loss": 0.0093,
+      "grad_norm": 0.6515682935714722,
+      "learning_rate": 0.00016596858638743455,
+      "loss": 0.0528,
       "step": 325
     },
     {
       "epoch": 1.73,
-      "grad_norm": 3.767280101776123,
-      "learning_rate": 0.00013089005235602096,
-      "loss": 0.2232,
+      "grad_norm": 0.5656059384346008,
+      "learning_rate": 0.00016544502617801048,
+      "loss": 0.1378,
       "step": 330
     },
     {
       "epoch": 1.75,
-      "grad_norm": 0.010386645793914795,
-      "learning_rate": 0.00012984293193717277,
-      "loss": 0.0026,
+      "grad_norm": 0.10378353297710419,
+      "learning_rate": 0.0001649214659685864,
+      "loss": 0.0329,
       "step": 335
     },
     {
       "epoch": 1.78,
-      "grad_norm": 4.292264461517334,
-      "learning_rate": 0.00012879581151832462,
-      "loss": 0.2457,
+      "grad_norm": 2.387305736541748,
+      "learning_rate": 0.00016439790575916233,
+      "loss": 0.0353,
       "step": 340
     },
     {
       "epoch": 1.81,
-      "grad_norm": 0.024649567902088165,
-      "learning_rate": 0.00012774869109947646,
-      "loss": 0.0306,
+      "grad_norm": 0.05628238245844841,
+      "learning_rate": 0.0001638743455497382,
+      "loss": 0.0138,
       "step": 345
     },
     {
       "epoch": 1.83,
-      "grad_norm": 5.098654270172119,
-      "learning_rate": 0.00012670157068062827,
-      "loss": 0.1156,
+      "grad_norm": 0.04053734615445137,
+      "learning_rate": 0.00016335078534031414,
+      "loss": 0.0082,
       "step": 350
     },
     {
       "epoch": 1.83,
-      "eval_accuracy": 0.9501312335958005,
-      "eval_loss": 0.17998863756656647,
-      "eval_precision": 0.9531660720469141,
-      "eval_recall": 0.9501312335958005,
-      "eval_runtime": 17.4136,
-      "eval_samples_per_second": 43.759,
-      "eval_steps_per_second": 2.756,
+      "eval_accuracy": 0.963254593175853,
+      "eval_loss": 0.11838709563016891,
+      "eval_precision": 0.9654537871036863,
+      "eval_recall": 0.963254593175853,
+      "eval_runtime": 17.4034,
+      "eval_samples_per_second": 43.785,
+      "eval_steps_per_second": 2.758,
       "step": 350
     },
     {
       "epoch": 1.86,
-      "grad_norm": 0.9651967287063599,
-      "learning_rate": 0.00012565445026178012,
-      "loss": 0.0618,
+      "grad_norm": 2.287546396255493,
+      "learning_rate": 0.00016282722513089005,
+      "loss": 0.02,
       "step": 355
     },
     {
       "epoch": 1.88,
-      "grad_norm": 2.727735996246338,
-      "learning_rate": 0.00012460732984293196,
-      "loss": 0.0705,
+      "grad_norm": 4.561453342437744,
+      "learning_rate": 0.00016230366492146599,
+      "loss": 0.203,
       "step": 360
     },
     {
       "epoch": 1.91,
-      "grad_norm": 4.953824043273926,
-      "learning_rate": 0.00012356020942408378,
-      "loss": 0.2112,
+      "grad_norm": 4.0477294921875,
+      "learning_rate": 0.0001617801047120419,
+      "loss": 0.0646,
       "step": 365
     },
     {
       "epoch": 1.94,
-      "grad_norm": 0.08269181102514267,
-      "learning_rate": 0.00012251308900523562,
-      "loss": 0.071,
+      "grad_norm": 1.0380969047546387,
+      "learning_rate": 0.0001612565445026178,
+      "loss": 0.0848,
       "step": 370
     },
     {
       "epoch": 1.96,
-      "grad_norm": 0.06396706402301788,
-      "learning_rate": 0.00012146596858638744,
-      "loss": 0.1069,
+      "grad_norm": 4.385131359100342,
+      "learning_rate": 0.0001607329842931937,
+      "loss": 0.166,
       "step": 375
     },
     {
       "epoch": 1.99,
-      "grad_norm": 0.28295230865478516,
-      "learning_rate": 0.00012041884816753928,
-      "loss": 0.0759,
+      "grad_norm": 0.036621347069740295,
+      "learning_rate": 0.00016020942408376964,
+      "loss": 0.0871,
       "step": 380
     },
     {
       "epoch": 2.02,
-      "grad_norm": 1.5805819034576416,
-      "learning_rate": 0.0001193717277486911,
-      "loss": 0.0622,
+      "grad_norm": 0.5929269194602966,
+      "learning_rate": 0.00015968586387434555,
+      "loss": 0.1271,
       "step": 385
     },
     {
       "epoch": 2.04,
-      "grad_norm": 2.3917598724365234,
-      "learning_rate": 0.00011832460732984294,
-      "loss": 0.0512,
+      "grad_norm": 0.26594266295433044,
+      "learning_rate": 0.00015916230366492146,
+      "loss": 0.0114,
       "step": 390
     },
     {
       "epoch": 2.07,
-      "grad_norm": 0.03971586003899574,
-      "learning_rate": 0.00011727748691099475,
-      "loss": 0.0163,
+      "grad_norm": 0.020196596160531044,
+      "learning_rate": 0.0001586387434554974,
+      "loss": 0.0081,
       "step": 395
     },
     {
       "epoch": 2.09,
-      "grad_norm": 0.024471383541822433,
-      "learning_rate": 0.0001162303664921466,
-      "loss": 0.0188,
+      "grad_norm": 0.6509531140327454,
+      "learning_rate": 0.0001581151832460733,
+      "loss": 0.0206,
       "step": 400
     },
     {
       "epoch": 2.09,
-      "eval_accuracy": 0.9593175853018373,
-      "eval_loss": 0.14536795020103455,
-      "eval_precision": 0.9601421810596481,
-      "eval_recall": 0.9593175853018373,
-      "eval_runtime": 17.4,
-      "eval_samples_per_second": 43.793,
-      "eval_steps_per_second": 2.759,
+      "eval_accuracy": 0.963254593175853,
+      "eval_loss": 0.130891352891922,
+      "eval_precision": 0.964741369994443,
+      "eval_recall": 0.963254593175853,
+      "eval_runtime": 17.4584,
+      "eval_samples_per_second": 43.647,
+      "eval_steps_per_second": 2.749,
       "step": 400
     },
     {
       "epoch": 2.12,
-      "grad_norm": 0.0705149918794632,
-      "learning_rate": 0.00011518324607329844,
-      "loss": 0.0062,
+      "grad_norm": 0.04883525148034096,
+      "learning_rate": 0.00015759162303664924,
+      "loss": 0.047,
       "step": 405
     },
     {
       "epoch": 2.15,
-      "grad_norm": 0.013097544200718403,
-      "learning_rate": 0.00011413612565445027,
-      "loss": 0.0191,
+      "grad_norm": 1.4584039449691772,
+      "learning_rate": 0.00015706806282722515,
+      "loss": 0.0393,
       "step": 410
     },
     {
       "epoch": 2.17,
-      "grad_norm": 0.5236541628837585,
-      "learning_rate": 0.00011308900523560211,
-      "loss": 0.0403,
+      "grad_norm": 0.3986053466796875,
+      "learning_rate": 0.00015654450261780105,
+      "loss": 0.0606,
       "step": 415
     },
     {
       "epoch": 2.2,
-      "grad_norm": 0.01967461034655571,
-      "learning_rate": 0.00011204188481675393,
-      "loss": 0.0032,
+      "grad_norm": 0.11985136568546295,
+      "learning_rate": 0.00015602094240837696,
+      "loss": 0.0379,
       "step": 420
     },
     {
       "epoch": 2.23,
-      "grad_norm": 0.02198900654911995,
-      "learning_rate": 0.00011099476439790577,
-      "loss": 0.0019,
+      "grad_norm": 0.07443628460168839,
+      "learning_rate": 0.0001554973821989529,
+      "loss": 0.0157,
       "step": 425
     },
     {
       "epoch": 2.25,
-      "grad_norm": 0.14719614386558533,
-      "learning_rate": 0.00010994764397905759,
-      "loss": 0.0052,
+      "grad_norm": 0.03219376876950264,
+      "learning_rate": 0.0001549738219895288,
+      "loss": 0.01,
       "step": 430
     },
     {
       "epoch": 2.28,
-      "grad_norm": 0.021793629974126816,
-      "learning_rate": 0.00010890052356020943,
-      "loss": 0.0105,
+      "grad_norm": 0.17020490765571594,
+      "learning_rate": 0.00015445026178010471,
+      "loss": 0.0093,
       "step": 435
     },
     {
       "epoch": 2.3,
-      "grad_norm": 0.02368028089404106,
-      "learning_rate": 0.00010785340314136125,
-      "loss": 0.001,
+      "grad_norm": 2.6877171993255615,
+      "learning_rate": 0.00015392670157068062,
+      "loss": 0.021,
       "step": 440
     },
     {
       "epoch": 2.33,
-      "grad_norm": 0.010441082529723644,
-      "learning_rate": 0.00010680628272251309,
-      "loss": 0.0019,
+      "grad_norm": 0.010094034485518932,
+      "learning_rate": 0.00015340314136125656,
+      "loss": 0.0083,
       "step": 445
     },
     {
       "epoch": 2.36,
-      "grad_norm": 0.015402965247631073,
-      "learning_rate": 0.00010575916230366492,
-      "loss": 0.0049,
+      "grad_norm": 0.0077184755355119705,
+      "learning_rate": 0.00015287958115183247,
+      "loss": 0.0246,
       "step": 450
     },
     {
       "epoch": 2.36,
-      "eval_accuracy": 0.9711286089238845,
-      "eval_loss": 0.1082761362195015,
-      "eval_precision": 0.9714506772867647,
-      "eval_recall": 0.9711286089238845,
-      "eval_runtime": 17.6808,
-      "eval_samples_per_second": 43.098,
-      "eval_steps_per_second": 2.715,
+      "eval_accuracy": 0.9553805774278216,
+      "eval_loss": 0.17534801363945007,
+      "eval_precision": 0.9586171915743325,
+      "eval_recall": 0.9553805774278216,
+      "eval_runtime": 17.505,
+      "eval_samples_per_second": 43.53,
+      "eval_steps_per_second": 2.742,
       "step": 450
     },
     {
       "epoch": 2.38,
-      "grad_norm": 0.07379986345767975,
-      "learning_rate": 0.00010471204188481676,
-      "loss": 0.0047,
+      "grad_norm": 5.202419757843018,
+      "learning_rate": 0.0001523560209424084,
+      "loss": 0.032,
       "step": 455
     },
     {
       "epoch": 2.41,
-      "grad_norm": 5.459177494049072,
-      "learning_rate": 0.0001036649214659686,
-      "loss": 0.0192,
+      "grad_norm": 0.018663793802261353,
+      "learning_rate": 0.00015183246073298428,
+      "loss": 0.0221,
       "step": 460
     },
     {
       "epoch": 2.43,
-      "grad_norm": 0.004949438851326704,
-      "learning_rate": 0.00010261780104712042,
-      "loss": 0.0148,
+      "grad_norm": 1.0761280059814453,
+      "learning_rate": 0.00015130890052356022,
+      "loss": 0.0055,
       "step": 465
     },
     {
       "epoch": 2.46,
-      "grad_norm": 0.17624743282794952,
-      "learning_rate": 0.00010157068062827227,
-      "loss": 0.0087,
+      "grad_norm": 0.8688761591911316,
+      "learning_rate": 0.00015078534031413612,
+      "loss": 0.0852,
       "step": 470
     },
     {
       "epoch": 2.49,
-      "grad_norm": 0.010408706963062286,
-      "learning_rate": 0.00010052356020942408,
-      "loss": 0.0018,
+      "grad_norm": 0.06378360092639923,
+      "learning_rate": 0.00015026178010471206,
+      "loss": 0.0031,
       "step": 475
     },
     {
       "epoch": 2.51,
-      "grad_norm": 0.007278731558471918,
-      "learning_rate": 9.947643979057593e-05,
-      "loss": 0.0029,
+      "grad_norm": 7.236721992492676,
+      "learning_rate": 0.00014973821989528797,
+      "loss": 0.0106,
       "step": 480
     },
     {
       "epoch": 2.54,
-      "grad_norm": 0.01558419968932867,
-      "learning_rate": 9.842931937172776e-05,
-      "loss": 0.0549,
+      "grad_norm": 0.013875219039618969,
+      "learning_rate": 0.00014921465968586388,
+      "loss": 0.0032,
       "step": 485
     },
     {
       "epoch": 2.57,
-      "grad_norm": 0.005123753100633621,
-      "learning_rate": 9.738219895287959e-05,
-      "loss": 0.0006,
+      "grad_norm": 0.031233886256814003,
+      "learning_rate": 0.0001486910994764398,
+      "loss": 0.0047,
       "step": 490
     },
     {
       "epoch": 2.59,
-      "grad_norm": 0.011126354336738586,
-      "learning_rate": 9.633507853403142e-05,
-      "loss": 0.003,
+      "grad_norm": 0.2528940439224243,
+      "learning_rate": 0.00014816753926701572,
+      "loss": 0.0081,
       "step": 495
     },
     {
       "epoch": 2.62,
-      "grad_norm": 0.02012033388018608,
-      "learning_rate": 9.528795811518324e-05,
-      "loss": 0.0139,
+      "grad_norm": 0.02138712629675865,
+      "learning_rate": 0.00014764397905759163,
+      "loss": 0.0161,
       "step": 500
     },
     {
       "epoch": 2.62,
-      "eval_accuracy": 0.963254593175853,
-      "eval_loss": 0.16356664896011353,
-      "eval_precision": 0.9644146563432678,
-      "eval_recall": 0.963254593175853,
-      "eval_runtime": 17.6855,
-      "eval_samples_per_second": 43.086,
-      "eval_steps_per_second": 2.714,
+      "eval_accuracy": 0.9514435695538058,
+      "eval_loss": 0.16896109282970428,
+      "eval_precision": 0.9537490891546931,
+      "eval_recall": 0.9514435695538058,
+      "eval_runtime": 17.5851,
+      "eval_samples_per_second": 43.332,
+      "eval_steps_per_second": 2.73,
       "step": 500
     }
   ],
   "logging_steps": 5,
-  "max_steps": 955,
+  "max_steps": 1910,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "total_flos": 6.186131303461724e+17,
   "train_batch_size": 16,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9351bf119f7d6bd8f47397285059fe8f281c9320b7267ccda968417cdf32d2fa
+oid sha256:20978be5af09aa5e062dc23ab1ae5cd2911d62519dbe8c26b70e5d2de0491f9b
 size 4856