Upload folder using huggingface_hub

checkpoint-105/adapter_config.json

@@ -34,11 +34,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
+    "q_proj",
     "gate_proj",
     "up_proj"
   ],

checkpoint-105/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b569e972a86d6829e78f0b3b2f82887532346fcbc5d95bee095bc82deb1d217
+oid sha256:dc5cdba83f568df3c108ca3af2835134bafde41909e7c6f1dae4a1ca05037743
 size 80792096

checkpoint-105/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3149f049f163343f6033f5769d9b307ba8bb6315316d6dda0904a701685ecb
+oid sha256:2c4803d420353619833e64f8e79262aae498b4c43730a1e0bdd1bf9f1d0d30bd
 size 161816187

checkpoint-105/trainer_state.json

@@ -46,702 +46,702 @@
     },
     {
       "epoch": 0.03956043956043956,
-      "grad_norm": 1.4210177659988403,
+      "grad_norm": 1.4210093021392822,
       "learning_rate": 0.0002,
       "loss": 2.0834,
       "step": 6
     },
     {
       "epoch": 0.046153846153846156,
-      "grad_norm": 2.1953322887420654,
+      "grad_norm": 2.191202163696289,
       "learning_rate": 0.00019955654101995565,
-      "loss": 2.3527,
+      "loss": 2.356,
       "step": 7
     },
     {
       "epoch": 0.05274725274725275,
-      "grad_norm": 1.3501241207122803,
+      "grad_norm": 1.3515082597732544,
       "learning_rate": 0.00019911308203991133,
-      "loss": 1.6168,
+      "loss": 1.6185,
       "step": 8
     },
     {
       "epoch": 0.05934065934065934,
-      "grad_norm": 1.0528779029846191,
+      "grad_norm": 1.0511066913604736,
       "learning_rate": 0.00019866962305986697,
-      "loss": 1.2372,
+      "loss": 1.2398,
       "step": 9
     },
     {
       "epoch": 0.06593406593406594,
-      "grad_norm": 1.0986005067825317,
+      "grad_norm": 1.1089080572128296,
       "learning_rate": 0.00019822616407982261,
-      "loss": 1.0832,
+      "loss": 1.0841,
       "step": 10
     },
     {
       "epoch": 0.07252747252747253,
-      "grad_norm": 0.7291749119758606,
+      "grad_norm": 0.7258754372596741,
       "learning_rate": 0.00019778270509977829,
-      "loss": 0.8899,
+      "loss": 0.891,
       "step": 11
     },
     {
       "epoch": 0.07912087912087912,
-      "grad_norm": 0.7171648740768433,
+      "grad_norm": 0.7209516763687134,
       "learning_rate": 0.00019733924611973393,
-      "loss": 0.901,
+      "loss": 0.9001,
       "step": 12
     },
     {
       "epoch": 0.08571428571428572,
-      "grad_norm": 0.769551694393158,
+      "grad_norm": 0.7664763927459717,
       "learning_rate": 0.0001968957871396896,
-      "loss": 0.774,
+      "loss": 0.7743,
       "step": 13
     },
     {
       "epoch": 0.09230769230769231,
-      "grad_norm": 0.8533819317817688,
+      "grad_norm": 0.8576359748840332,
       "learning_rate": 0.00019645232815964525,
-      "loss": 0.8341,
+      "loss": 0.8357,
       "step": 14
     },
     {
       "epoch": 0.0989010989010989,
-      "grad_norm": 0.5951386094093323,
+      "grad_norm": 0.595888614654541,
       "learning_rate": 0.00019600886917960092,
-      "loss": 0.7088,
+      "loss": 0.7084,
       "step": 15
     },
     {
       "epoch": 0.1054945054945055,
-      "grad_norm": 0.5491686463356018,
+      "grad_norm": 0.5491059422492981,
       "learning_rate": 0.00019556541019955653,
-      "loss": 0.7881,
+      "loss": 0.7878,
       "step": 16
     },
     {
       "epoch": 0.11208791208791209,
-      "grad_norm": 0.4747234582901001,
+      "grad_norm": 0.4769267141819,
       "learning_rate": 0.0001951219512195122,
-      "loss": 0.8774,
+      "loss": 0.8773,
       "step": 17
     },
     {
       "epoch": 0.11868131868131868,
-      "grad_norm": 0.4941480755805969,
+      "grad_norm": 0.49563226103782654,
       "learning_rate": 0.00019467849223946785,
-      "loss": 0.5531,
+      "loss": 0.5533,
       "step": 18
     },
     {
       "epoch": 0.12527472527472527,
-      "grad_norm": 0.3821296691894531,
+      "grad_norm": 0.38295453786849976,
       "learning_rate": 0.00019423503325942352,
-      "loss": 0.6682,
+      "loss": 0.6684,
       "step": 19
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 0.44070833921432495,
+      "grad_norm": 0.440352201461792,
       "learning_rate": 0.00019379157427937917,
-      "loss": 0.6901,
+      "loss": 0.6908,
       "step": 20
     },
     {
       "epoch": 0.13846153846153847,
-      "grad_norm": 0.6101831197738647,
+      "grad_norm": 0.6130449175834656,
       "learning_rate": 0.00019334811529933484,
-      "loss": 0.7096,
+      "loss": 0.7121,
       "step": 21
     },
     {
       "epoch": 0.14505494505494507,
-      "grad_norm": 0.4495581388473511,
+      "grad_norm": 0.4496903419494629,
       "learning_rate": 0.00019290465631929045,
-      "loss": 0.5936,
+      "loss": 0.5951,
       "step": 22
     },
     {
       "epoch": 0.15164835164835164,
-      "grad_norm": 0.4235256612300873,
+      "grad_norm": 0.4229985177516937,
       "learning_rate": 0.00019246119733924613,
-      "loss": 0.807,
+      "loss": 0.8088,
       "step": 23
     },
     {
       "epoch": 0.15824175824175823,
-      "grad_norm": 0.3769803047180176,
+      "grad_norm": 0.3770928382873535,
       "learning_rate": 0.00019201773835920177,
-      "loss": 0.4834,
+      "loss": 0.483,
       "step": 24
     },
     {
       "epoch": 0.16483516483516483,
-      "grad_norm": 0.39769601821899414,
+      "grad_norm": 0.3968537747859955,
       "learning_rate": 0.00019157427937915744,
-      "loss": 0.7437,
+      "loss": 0.7432,
       "step": 25
     },
     {
       "epoch": 0.17142857142857143,
-      "grad_norm": 0.3540402948856354,
+      "grad_norm": 0.35443034768104553,
       "learning_rate": 0.00019113082039911309,
-      "loss": 0.7367,
+      "loss": 0.7378,
       "step": 26
     },
     {
       "epoch": 0.17802197802197803,
-      "grad_norm": 0.3442913591861725,
+      "grad_norm": 0.3410908281803131,
       "learning_rate": 0.00019068736141906876,
-      "loss": 0.6653,
+      "loss": 0.6648,
       "step": 27
     },
     {
       "epoch": 0.18461538461538463,
-      "grad_norm": 0.3774307668209076,
+      "grad_norm": 0.3770894706249237,
       "learning_rate": 0.0001902439024390244,
-      "loss": 0.5388,
+      "loss": 0.5379,
       "step": 28
     },
     {
       "epoch": 0.1912087912087912,
-      "grad_norm": 0.425573468208313,
+      "grad_norm": 0.4255348742008209,
       "learning_rate": 0.00018980044345898005,
-      "loss": 0.6212,
+      "loss": 0.6209,
       "step": 29
     },
     {
       "epoch": 0.1978021978021978,
-      "grad_norm": 0.36889106035232544,
+      "grad_norm": 0.36734604835510254,
       "learning_rate": 0.00018935698447893572,
-      "loss": 0.5505,
+      "loss": 0.5492,
       "step": 30
     },
     {
       "epoch": 0.2043956043956044,
-      "grad_norm": 0.41763660311698914,
+      "grad_norm": 0.4194317162036896,
       "learning_rate": 0.00018891352549889136,
-      "loss": 0.6563,
+      "loss": 0.6574,
       "step": 31
     },
     {
       "epoch": 0.210989010989011,
-      "grad_norm": 0.4044314920902252,
+      "grad_norm": 0.40617868304252625,
       "learning_rate": 0.00018847006651884703,
-      "loss": 0.7254,
+      "loss": 0.7256,
       "step": 32
     },
     {
       "epoch": 0.2175824175824176,
-      "grad_norm": 0.4232475161552429,
+      "grad_norm": 0.4234406352043152,
       "learning_rate": 0.00018802660753880268,
-      "loss": 0.5845,
+      "loss": 0.5833,
       "step": 33
     },
     {
       "epoch": 0.22417582417582418,
-      "grad_norm": 0.4286547005176544,
+      "grad_norm": 0.42862963676452637,
       "learning_rate": 0.00018758314855875832,
-      "loss": 0.6785,
+      "loss": 0.679,
       "step": 34
     },
     {
       "epoch": 0.23076923076923078,
-      "grad_norm": 0.31076809763908386,
+      "grad_norm": 0.30872148275375366,
       "learning_rate": 0.00018713968957871397,
-      "loss": 0.499,
+      "loss": 0.4977,
       "step": 35
     },
     {
       "epoch": 0.23736263736263735,
-      "grad_norm": 0.36596956849098206,
+      "grad_norm": 0.3625873625278473,
       "learning_rate": 0.00018669623059866964,
-      "loss": 0.5066,
+      "loss": 0.5081,
       "step": 36
     },
     {
       "epoch": 0.24395604395604395,
-      "grad_norm": 0.538699746131897,
+      "grad_norm": 0.5377358794212341,
       "learning_rate": 0.00018625277161862528,
-      "loss": 0.6999,
+      "loss": 0.699,
       "step": 37
     },
     {
       "epoch": 0.25054945054945055,
-      "grad_norm": 0.40492090582847595,
+      "grad_norm": 0.4084674119949341,
       "learning_rate": 0.00018580931263858095,
-      "loss": 0.6028,
+      "loss": 0.6026,
       "step": 38
     },
     {
       "epoch": 0.2571428571428571,
-      "grad_norm": 0.40941327810287476,
+      "grad_norm": 0.408764511346817,
       "learning_rate": 0.0001853658536585366,
-      "loss": 0.5741,
+      "loss": 0.573,
       "step": 39
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.49566400051116943,
+      "grad_norm": 0.49357256293296814,
       "learning_rate": 0.00018492239467849224,
       "loss": 0.5661,
       "step": 40
     },
     {
       "epoch": 0.2703296703296703,
-      "grad_norm": 0.43741264939308167,
+      "grad_norm": 0.4367434084415436,
       "learning_rate": 0.0001844789356984479,
-      "loss": 0.546,
+      "loss": 0.5467,
       "step": 41
     },
     {
       "epoch": 0.27692307692307694,
-      "grad_norm": 0.438276082277298,
+      "grad_norm": 0.43745237588882446,
       "learning_rate": 0.00018403547671840356,
-      "loss": 0.4637,
+      "loss": 0.4629,
       "step": 42
     },
     {
       "epoch": 0.2835164835164835,
-      "grad_norm": 0.4048697054386139,
+      "grad_norm": 0.40380334854125977,
       "learning_rate": 0.0001835920177383592,
-      "loss": 0.639,
+      "loss": 0.6396,
       "step": 43
     },
     {
       "epoch": 0.29010989010989013,
-      "grad_norm": 0.4107864499092102,
+      "grad_norm": 0.40799689292907715,
       "learning_rate": 0.00018314855875831487,
-      "loss": 0.6006,
+      "loss": 0.599,
       "step": 44
     },
     {
       "epoch": 0.2967032967032967,
-      "grad_norm": 0.28709277510643005,
+      "grad_norm": 0.28567400574684143,
       "learning_rate": 0.00018270509977827052,
-      "loss": 0.4367,
+      "loss": 0.4377,
       "step": 45
     },
     {
       "epoch": 0.3032967032967033,
-      "grad_norm": 0.452434241771698,
+      "grad_norm": 0.4526217579841614,
       "learning_rate": 0.00018226164079822616,
-      "loss": 0.7652,
+      "loss": 0.7656,
       "step": 46
     },
     {
       "epoch": 0.3098901098901099,
-      "grad_norm": 0.31990426778793335,
+      "grad_norm": 0.3180352449417114,
       "learning_rate": 0.00018181818181818183,
-      "loss": 0.5955,
+      "loss": 0.5954,
       "step": 47
     },
     {
       "epoch": 0.31648351648351647,
-      "grad_norm": 0.35008805990219116,
+      "grad_norm": 0.3497668206691742,
       "learning_rate": 0.00018137472283813748,
-      "loss": 0.6933,
+      "loss": 0.6921,
       "step": 48
     },
     {
       "epoch": 0.3230769230769231,
-      "grad_norm": 0.29008418321609497,
+      "grad_norm": 0.29014813899993896,
       "learning_rate": 0.00018093126385809312,
-      "loss": 0.5714,
+      "loss": 0.5719,
       "step": 49
     },
     {
       "epoch": 0.32967032967032966,
-      "grad_norm": 0.35922980308532715,
+      "grad_norm": 0.3539118766784668,
       "learning_rate": 0.0001804878048780488,
-      "loss": 0.5607,
+      "loss": 0.5592,
       "step": 50
     },
     {
       "epoch": 0.3362637362637363,
-      "grad_norm": 0.3305734694004059,
+      "grad_norm": 0.329170823097229,
       "learning_rate": 0.00018004434589800444,
-      "loss": 0.5821,
+      "loss": 0.5826,
       "step": 51
     },
     {
       "epoch": 0.34285714285714286,
-      "grad_norm": 0.3513537347316742,
+      "grad_norm": 0.35174617171287537,
       "learning_rate": 0.00017960088691796008,
-      "loss": 0.5481,
+      "loss": 0.5477,
       "step": 52
     },
     {
       "epoch": 0.34945054945054943,
-      "grad_norm": 0.3159414827823639,
+      "grad_norm": 0.3147708773612976,
       "learning_rate": 0.00017915742793791575,
-      "loss": 0.5447,
+      "loss": 0.5454,
       "step": 53
     },
     {
       "epoch": 0.35604395604395606,
-      "grad_norm": 0.2907983958721161,
+      "grad_norm": 0.29042673110961914,
       "learning_rate": 0.0001787139689578714,
-      "loss": 0.5342,
+      "loss": 0.5355,
       "step": 54
     },
     {
       "epoch": 0.3626373626373626,
-      "grad_norm": 0.3384917974472046,
+      "grad_norm": 0.3362969160079956,
       "learning_rate": 0.00017827050997782707,
-      "loss": 0.4418,
+      "loss": 0.4426,
       "step": 55
     },
     {
       "epoch": 0.36923076923076925,
-      "grad_norm": 0.4053548276424408,
+      "grad_norm": 0.40394821763038635,
       "learning_rate": 0.00017782705099778271,
-      "loss": 0.5753,
+      "loss": 0.5756,
       "step": 56
     },
     {
       "epoch": 0.3758241758241758,
-      "grad_norm": 0.4862969219684601,
+      "grad_norm": 0.4828003942966461,
       "learning_rate": 0.00017738359201773839,
-      "loss": 0.5427,
+      "loss": 0.5425,
       "step": 57
     },
     {
       "epoch": 0.3824175824175824,
-      "grad_norm": 0.4132358729839325,
+      "grad_norm": 0.41234296560287476,
       "learning_rate": 0.000176940133037694,
-      "loss": 0.5032,
+      "loss": 0.5034,
       "step": 58
     },
     {
       "epoch": 0.389010989010989,
-      "grad_norm": 0.3131895661354065,
+      "grad_norm": 0.3114299774169922,
       "learning_rate": 0.00017649667405764967,
-      "loss": 0.5134,
+      "loss": 0.5133,
       "step": 59
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.41834479570388794,
+      "grad_norm": 0.4113824665546417,
       "learning_rate": 0.00017605321507760532,
-      "loss": 0.4807,
+      "loss": 0.4794,
       "step": 60
     },
     {
       "epoch": 0.4021978021978022,
-      "grad_norm": 0.39823901653289795,
+      "grad_norm": 0.39749574661254883,
       "learning_rate": 0.000175609756097561,
-      "loss": 0.5923,
+      "loss": 0.5918,
       "step": 61
     },
     {
       "epoch": 0.4087912087912088,
-      "grad_norm": 0.3001629710197449,
+      "grad_norm": 0.2998730540275574,
       "learning_rate": 0.00017516629711751663,
-      "loss": 0.4608,
+      "loss": 0.4609,
       "step": 62
     },
     {
       "epoch": 0.4153846153846154,
-      "grad_norm": 0.33100757002830505,
+      "grad_norm": 0.33303892612457275,
       "learning_rate": 0.0001747228381374723,
-      "loss": 0.5746,
+      "loss": 0.5749,
       "step": 63
     },
     {
       "epoch": 0.421978021978022,
-      "grad_norm": 0.38101696968078613,
+      "grad_norm": 0.3806542158126831,
       "learning_rate": 0.00017427937915742792,
-      "loss": 0.6248,
+      "loss": 0.6255,
       "step": 64
     },
     {
       "epoch": 0.42857142857142855,
-      "grad_norm": 0.3749473989009857,
+      "grad_norm": 0.37488535046577454,
       "learning_rate": 0.0001738359201773836,
-      "loss": 0.5436,
+      "loss": 0.5428,
       "step": 65
     },
     {
       "epoch": 0.4351648351648352,
-      "grad_norm": 0.3627394139766693,
+      "grad_norm": 0.3625684082508087,
       "learning_rate": 0.00017339246119733924,
-      "loss": 0.4833,
+      "loss": 0.4832,
       "step": 66
     },
     {
       "epoch": 0.44175824175824174,
-      "grad_norm": 0.32703840732574463,
+      "grad_norm": 0.3280394673347473,
       "learning_rate": 0.0001729490022172949,
-      "loss": 0.5082,
+      "loss": 0.5081,
       "step": 67
     },
     {
       "epoch": 0.44835164835164837,
-      "grad_norm": 0.3377853333950043,
+      "grad_norm": 0.33734264969825745,
       "learning_rate": 0.00017250554323725056,
-      "loss": 0.5851,
+      "loss": 0.5846,
       "step": 68
     },
     {
       "epoch": 0.45494505494505494,
-      "grad_norm": 0.2636179029941559,
+      "grad_norm": 0.26452669501304626,
       "learning_rate": 0.00017206208425720623,
-      "loss": 0.6152,
+      "loss": 0.6158,
       "step": 69
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 0.32934603095054626,
+      "grad_norm": 0.3296058475971222,
       "learning_rate": 0.00017161862527716187,
-      "loss": 0.5501,
+      "loss": 0.5506,
       "step": 70
     },
     {
       "epoch": 0.46813186813186813,
-      "grad_norm": 0.3468154966831207,
+      "grad_norm": 0.34564757347106934,
       "learning_rate": 0.00017117516629711752,
-      "loss": 0.5,
+      "loss": 0.501,
       "step": 71
     },
     {
       "epoch": 0.4747252747252747,
-      "grad_norm": 0.3443688750267029,
+      "grad_norm": 0.34410351514816284,
       "learning_rate": 0.0001707317073170732,
-      "loss": 0.6958,
+      "loss": 0.6951,
       "step": 72
     },
     {
       "epoch": 0.48131868131868133,
-      "grad_norm": 0.31319597363471985,
+      "grad_norm": 0.31216946244239807,
       "learning_rate": 0.00017028824833702883,
-      "loss": 0.5448,
+      "loss": 0.5436,
       "step": 73
     },
     {
       "epoch": 0.4879120879120879,
-      "grad_norm": 0.4158133864402771,
+      "grad_norm": 0.41745084524154663,
       "learning_rate": 0.0001698447893569845,
-      "loss": 0.5519,
+      "loss": 0.5543,
       "step": 74
     },
     {
       "epoch": 0.4945054945054945,
-      "grad_norm": 0.3488521873950958,
+      "grad_norm": 0.34854283928871155,
       "learning_rate": 0.00016940133037694015,
       "loss": 0.4548,
       "step": 75
     },
     {
       "epoch": 0.5010989010989011,
-      "grad_norm": 0.34698039293289185,
+      "grad_norm": 0.34482014179229736,
       "learning_rate": 0.00016895787139689582,
-      "loss": 0.5589,
+      "loss": 0.5569,
       "step": 76
     },
     {
       "epoch": 0.5076923076923077,
-      "grad_norm": 0.3786613941192627,
+      "grad_norm": 0.3797132670879364,
       "learning_rate": 0.00016851441241685144,
-      "loss": 0.6392,
+      "loss": 0.6374,
       "step": 77
     },
     {
       "epoch": 0.5142857142857142,
-      "grad_norm": 0.4199986159801483,
+      "grad_norm": 0.42068514227867126,
       "learning_rate": 0.0001680709534368071,
-      "loss": 0.7377,
+      "loss": 0.7371,
       "step": 78
     },
     {
       "epoch": 0.5208791208791209,
-      "grad_norm": 0.38042977452278137,
+      "grad_norm": 0.38008517026901245,
       "learning_rate": 0.00016762749445676275,
-      "loss": 0.5973,
+      "loss": 0.5977,
       "step": 79
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.31035611033439636,
+      "grad_norm": 0.31223198771476746,
       "learning_rate": 0.00016718403547671842,
-      "loss": 0.5988,
+      "loss": 0.6004,
       "step": 80
     },
     {
       "epoch": 0.5340659340659341,
-      "grad_norm": 0.34894973039627075,
+      "grad_norm": 0.34468576312065125,
       "learning_rate": 0.00016674057649667407,
-      "loss": 0.4984,
+      "loss": 0.4985,
       "step": 81
     },
     {
       "epoch": 0.5406593406593406,
-      "grad_norm": 0.3106113374233246,
+      "grad_norm": 0.3130583167076111,
       "learning_rate": 0.00016629711751662974,
-      "loss": 0.3352,
+      "loss": 0.3374,
       "step": 82
     },
     {
       "epoch": 0.5472527472527473,
-      "grad_norm": 0.40006911754608154,
+      "grad_norm": 0.4015103280544281,
       "learning_rate": 0.00016585365853658536,
       "loss": 0.5788,
       "step": 83
     },
     {
       "epoch": 0.5538461538461539,
-      "grad_norm": 0.34596022963523865,
+      "grad_norm": 0.34522417187690735,
       "learning_rate": 0.00016541019955654103,
-      "loss": 0.6014,
+      "loss": 0.6012,
       "step": 84
     },
     {
       "epoch": 0.5604395604395604,
-      "grad_norm": 0.35695880651474,
+      "grad_norm": 0.358808308839798,
       "learning_rate": 0.00016496674057649667,
-      "loss": 0.4872,
+      "loss": 0.4878,
       "step": 85
     },
     {
       "epoch": 0.567032967032967,
-      "grad_norm": 0.33931764960289,
+      "grad_norm": 0.34078314900398254,
       "learning_rate": 0.00016452328159645234,
-      "loss": 0.6237,
+      "loss": 0.6232,
       "step": 86
     },
     {
       "epoch": 0.5736263736263736,
-      "grad_norm": 0.3436149060726166,
+      "grad_norm": 0.34465718269348145,
       "learning_rate": 0.000164079822616408,
-      "loss": 0.6567,
+      "loss": 0.6572,
       "step": 87
     },
     {
       "epoch": 0.5802197802197803,
-      "grad_norm": 0.31438586115837097,
+      "grad_norm": 0.3138117492198944,
       "learning_rate": 0.00016363636363636366,
-      "loss": 0.4692,
+      "loss": 0.4689,
       "step": 88
     },
     {
       "epoch": 0.5868131868131868,
-      "grad_norm": 0.37511250376701355,
+      "grad_norm": 0.3753935396671295,
       "learning_rate": 0.0001631929046563193,
-      "loss": 0.7077,
+      "loss": 0.7078,
       "step": 89
     },
     {
       "epoch": 0.5934065934065934,
-      "grad_norm": 0.3482561409473419,
+      "grad_norm": 0.3477277457714081,
       "learning_rate": 0.00016274944567627495,
-      "loss": 0.5538,
+      "loss": 0.5523,
       "step": 90
     },
     {
       "epoch": 0.6,
-      "grad_norm": 0.37848830223083496,
+      "grad_norm": 0.3810032904148102,
       "learning_rate": 0.0001623059866962306,
       "loss": 0.6114,
       "step": 91
     },
     {
       "epoch": 0.6065934065934065,
-      "grad_norm": 0.3630884885787964,
+      "grad_norm": 0.35794568061828613,
       "learning_rate": 0.00016186252771618626,
-      "loss": 0.5914,
+      "loss": 0.5901,
       "step": 92
     },
     {
       "epoch": 0.6131868131868132,
-      "grad_norm": 0.3143329620361328,
+      "grad_norm": 0.31707000732421875,
       "learning_rate": 0.0001614190687361419,
-      "loss": 0.3932,
+      "loss": 0.3925,
       "step": 93
     },
     {
       "epoch": 0.6197802197802198,
-      "grad_norm": 0.48530277609825134,
+      "grad_norm": 0.48514524102211,
       "learning_rate": 0.00016097560975609758,
-      "loss": 0.6057,
+      "loss": 0.6058,
       "step": 94
     },
     {
       "epoch": 0.6263736263736264,
-      "grad_norm": 0.36521366238594055,
+      "grad_norm": 0.36429929733276367,
       "learning_rate": 0.00016053215077605322,
-      "loss": 0.547,
+      "loss": 0.5482,
       "step": 95
     },
     {
       "epoch": 0.6329670329670329,
-      "grad_norm": 0.3816615641117096,
+      "grad_norm": 0.3820970058441162,
       "learning_rate": 0.00016008869179600887,
-      "loss": 0.6192,
+      "loss": 0.619,
       "step": 96
     },
     {
       "epoch": 0.6395604395604395,
-      "grad_norm": 0.3620418906211853,
+      "grad_norm": 0.3634980022907257,
       "learning_rate": 0.00015964523281596454,
-      "loss": 0.5911,
+      "loss": 0.5914,
       "step": 97
     },
     {
       "epoch": 0.6461538461538462,
-      "grad_norm": 0.3318828046321869,
+      "grad_norm": 0.3295753300189972,
       "learning_rate": 0.00015920177383592018,
-      "loss": 0.7183,
+      "loss": 0.7175,
       "step": 98
     },
     {
       "epoch": 0.6527472527472528,
-      "grad_norm": 0.45500969886779785,
+      "grad_norm": 0.4538663625717163,
       "learning_rate": 0.00015875831485587586,
-      "loss": 0.6887,
+      "loss": 0.6873,
       "step": 99
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.33934152126312256,
+      "grad_norm": 0.3351002633571625,
       "learning_rate": 0.0001583148558758315,
-      "loss": 0.5101,
+      "loss": 0.5097,
       "step": 100
     },
     {
       "epoch": 0.6659340659340659,
-      "grad_norm": 0.34676507115364075,
+      "grad_norm": 0.34361809492111206,
       "learning_rate": 0.00015787139689578714,
       "loss": 0.4697,
       "step": 101
     },
     {
       "epoch": 0.6725274725274726,
-      "grad_norm": 0.30761954188346863,
+      "grad_norm": 0.3062559962272644,
       "learning_rate": 0.0001574279379157428,
-      "loss": 0.4226,
+      "loss": 0.4207,
       "step": 102
     },
     {
       "epoch": 0.6791208791208792,
-      "grad_norm": 0.42817234992980957,
+      "grad_norm": 0.42917492985725403,
       "learning_rate": 0.00015698447893569846,
-      "loss": 0.6624,
+      "loss": 0.6632,
       "step": 103
     },
     {
       "epoch": 0.6857142857142857,
-      "grad_norm": 0.3944794833660126,
+      "grad_norm": 0.3931623101234436,
       "learning_rate": 0.0001565410199556541,
-      "loss": 0.5922,
+      "loss": 0.5934,
       "step": 104
     },
     {
       "epoch": 0.6923076923076923,
-      "grad_norm": 0.3339543640613556,
+      "grad_norm": 0.33303365111351013,
       "learning_rate": 0.00015609756097560978,
-      "loss": 0.7868,
+      "loss": 0.7856,
       "step": 105
     }
   ],

checkpoint-105/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74a0b78df55a9ae148a95ee8f9638c53af5131c315495799af1ef7c5ddad212
+oid sha256:ae2f0e5bc705bbb6948e189fec5cfc4daf0e80a723aaeef1f31cef9d9d490a75
 size 6417