Upload folder using huggingface_hub

checkpoint-225/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-225/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9517f2f487cc511e8eec491053c2954cf4e038fb8e2229f02b808b95c9d3da4
+oid sha256:5a710df18036887c45209248f8cb4504febfca55fea06798168e68cb8296b09d
 size 80792096

checkpoint-225/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9dde7c6f487941d81830bd899369e9a94c4ba059061f8dde8f70f0e57c29e39
+oid sha256:7e0a126e2b5994ed22c9bec9cc85ffe67ba8a110a6ae34c1a007b466a5872181
 size 161816187

checkpoint-225/trainer_state.json

@@ -46,1542 +46,1542 @@
     },
     {
       "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
     },
     {
       "epoch": 0.6989010989010989,
-      "grad_norm": 0.35568344593048096,
+      "grad_norm": 0.35129332542419434,
       "learning_rate": 0.00015565410199556542,
-      "loss": 0.4304,
+      "loss": 0.4308,
       "step": 106
     },
     {
       "epoch": 0.7054945054945055,
-      "grad_norm": 0.3308112621307373,
+      "grad_norm": 0.33428147435188293,
       "learning_rate": 0.00015521064301552106,
-      "loss": 0.4929,
+      "loss": 0.4936,
       "step": 107
     },
     {
       "epoch": 0.7120879120879121,
-      "grad_norm": 0.38374829292297363,
+      "grad_norm": 0.3858307898044586,
       "learning_rate": 0.0001547671840354767,
-      "loss": 0.5403,
+      "loss": 0.5394,
       "step": 108
     },
     {
       "epoch": 0.7186813186813187,
-      "grad_norm": 0.3858916163444519,
+      "grad_norm": 0.38559332489967346,
       "learning_rate": 0.00015432372505543238,
-      "loss": 0.5486,
+      "loss": 0.5491,
       "step": 109
     },
     {
       "epoch": 0.7252747252747253,
-      "grad_norm": 0.33181118965148926,
+      "grad_norm": 0.3332304358482361,
       "learning_rate": 0.00015388026607538802,
-      "loss": 0.429,
+      "loss": 0.4284,
       "step": 110
     },
     {
       "epoch": 0.7318681318681318,
-      "grad_norm": 0.3062156140804291,
+      "grad_norm": 0.3078184723854065,
       "learning_rate": 0.0001534368070953437,
-      "loss": 0.4611,
+      "loss": 0.4619,
       "step": 111
     },
     {
       "epoch": 0.7384615384615385,
-      "grad_norm": 0.29854118824005127,
+      "grad_norm": 0.30087363719940186,
       "learning_rate": 0.00015299334811529934,
-      "loss": 0.5785,
+      "loss": 0.578,
       "step": 112
     },
     {
       "epoch": 0.7450549450549451,
-      "grad_norm": 0.36773180961608887,
+      "grad_norm": 0.36946234107017517,
       "learning_rate": 0.00015254988913525498,
-      "loss": 0.6849,
+      "loss": 0.685,
       "step": 113
     },
     {
       "epoch": 0.7516483516483516,
-      "grad_norm": 0.3187403976917267,
+      "grad_norm": 0.31981852650642395,
       "learning_rate": 0.00015210643015521066,
-      "loss": 0.4572,
+      "loss": 0.4574,
       "step": 114
     },
     {
       "epoch": 0.7582417582417582,
-      "grad_norm": 0.41137224435806274,
+      "grad_norm": 0.4113558232784271,
       "learning_rate": 0.0001516629711751663,
-      "loss": 0.5473,
+      "loss": 0.5476,
       "step": 115
     },
     {
       "epoch": 0.7648351648351648,
-      "grad_norm": 0.2698902487754822,
+      "grad_norm": 0.2684549391269684,
       "learning_rate": 0.00015121951219512197,
-      "loss": 0.5083,
+      "loss": 0.5091,
       "step": 116
     },
     {
       "epoch": 0.7714285714285715,
-      "grad_norm": 0.4021186828613281,
+      "grad_norm": 0.39670345187187195,
       "learning_rate": 0.00015077605321507762,
-      "loss": 0.536,
+      "loss": 0.5356,
       "step": 117
     },
     {
       "epoch": 0.778021978021978,
-      "grad_norm": 0.31166961789131165,
+      "grad_norm": 0.3148877024650574,
       "learning_rate": 0.0001503325942350333,
-      "loss": 0.5479,
+      "loss": 0.5495,
       "step": 118
     },
     {
       "epoch": 0.7846153846153846,
-      "grad_norm": 0.4277777373790741,
+      "grad_norm": 0.43104320764541626,
       "learning_rate": 0.0001498891352549889,
-      "loss": 0.519,
+      "loss": 0.5205,
       "step": 119
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.3523145020008087,
+      "grad_norm": 0.35208654403686523,
       "learning_rate": 0.00014944567627494458,
-      "loss": 0.6647,
+      "loss": 0.6632,
       "step": 120
     },
     {
       "epoch": 0.7978021978021979,
-      "grad_norm": 0.37467220425605774,
+      "grad_norm": 0.3757804036140442,
       "learning_rate": 0.00014900221729490022,
-      "loss": 0.4162,
+      "loss": 0.4175,
       "step": 121
     },
     {
       "epoch": 0.8043956043956044,
-      "grad_norm": 0.3397470712661743,
+      "grad_norm": 0.33744513988494873,
       "learning_rate": 0.0001485587583148559,
-      "loss": 0.4727,
+      "loss": 0.4729,
       "step": 122
     },
     {
       "epoch": 0.810989010989011,
-      "grad_norm": 0.26907649636268616,
+      "grad_norm": 0.2748795747756958,
       "learning_rate": 0.00014811529933481154,
-      "loss": 0.5576,
+      "loss": 0.5578,
       "step": 123
     },
     {
       "epoch": 0.8175824175824176,
-      "grad_norm": 0.3066836893558502,
+      "grad_norm": 0.3063929080963135,
       "learning_rate": 0.0001476718403547672,
-      "loss": 0.6146,
+      "loss": 0.615,
       "step": 124
     },
     {
       "epoch": 0.8241758241758241,
-      "grad_norm": 0.3007436692714691,
+      "grad_norm": 0.3011712431907654,
       "learning_rate": 0.00014722838137472282,
-      "loss": 0.5554,
+      "loss": 0.5569,
       "step": 125
     },
     {
       "epoch": 0.8307692307692308,
-      "grad_norm": 0.3789789080619812,
+      "grad_norm": 0.3757825195789337,
       "learning_rate": 0.0001467849223946785,
-      "loss": 0.5418,
+      "loss": 0.539,
       "step": 126
     },
     {
       "epoch": 0.8373626373626374,
-      "grad_norm": 0.3495182394981384,
+      "grad_norm": 0.3501187562942505,
       "learning_rate": 0.00014634146341463414,
-      "loss": 0.4498,
+      "loss": 0.4512,
       "step": 127
     },
     {
       "epoch": 0.843956043956044,
-      "grad_norm": 0.296125203371048,
+      "grad_norm": 0.2940189242362976,
       "learning_rate": 0.0001458980044345898,
-      "loss": 0.3671,
+      "loss": 0.3654,
       "step": 128
     },
     {
       "epoch": 0.8505494505494505,
-      "grad_norm": 0.3562738299369812,
+      "grad_norm": 0.35613664984703064,
       "learning_rate": 0.00014545454545454546,
-      "loss": 0.4513,
+      "loss": 0.4493,
       "step": 129
     },
     {
       "epoch": 0.8571428571428571,
-      "grad_norm": 0.33697131276130676,
+      "grad_norm": 0.33651602268218994,
       "learning_rate": 0.00014501108647450113,
-      "loss": 0.578,
+      "loss": 0.5778,
       "step": 130
     },
     {
       "epoch": 0.8637362637362638,
-      "grad_norm": 0.37678807973861694,
+      "grad_norm": 0.3811281621456146,
       "learning_rate": 0.00014456762749445675,
-      "loss": 0.5955,
+      "loss": 0.5954,
       "step": 131
     },
     {
       "epoch": 0.8703296703296703,
-      "grad_norm": 0.3169262707233429,
+      "grad_norm": 0.3208426833152771,
       "learning_rate": 0.00014412416851441242,
-      "loss": 0.5925,
+      "loss": 0.594,
       "step": 132
     },
     {
       "epoch": 0.8769230769230769,
-      "grad_norm": 0.40469977259635925,
+      "grad_norm": 0.40951108932495117,
       "learning_rate": 0.00014368070953436806,
-      "loss": 0.6089,
+      "loss": 0.6094,
       "step": 133
     },
     {
       "epoch": 0.8835164835164835,
-      "grad_norm": 0.41255781054496765,
+      "grad_norm": 0.40604957938194275,
       "learning_rate": 0.00014323725055432373,
-      "loss": 0.5271,
+      "loss": 0.5255,
       "step": 134
     },
     {
       "epoch": 0.8901098901098901,
-      "grad_norm": 0.35277947783470154,
+      "grad_norm": 0.35446712374687195,
       "learning_rate": 0.00014279379157427938,
-      "loss": 0.4963,
+      "loss": 0.4968,
       "step": 135
     },
     {
       "epoch": 0.8967032967032967,
-      "grad_norm": 0.38576146960258484,
+      "grad_norm": 0.38552945852279663,
       "learning_rate": 0.00014235033259423505,
-      "loss": 0.5281,
+      "loss": 0.5275,
       "step": 136
     },
     {
       "epoch": 0.9032967032967033,
-      "grad_norm": 0.38165539503097534,
+      "grad_norm": 0.38577142357826233,
       "learning_rate": 0.0001419068736141907,
-      "loss": 0.5149,
+      "loss": 0.5163,
       "step": 137
     },
     {
       "epoch": 0.9098901098901099,
-      "grad_norm": 0.3021070659160614,
+      "grad_norm": 0.30422845482826233,
       "learning_rate": 0.00014146341463414634,
-      "loss": 0.5546,
+      "loss": 0.554,
       "step": 138
     },
     {
       "epoch": 0.9164835164835164,
-      "grad_norm": 0.33052921295166016,
+      "grad_norm": 0.33201268315315247,
       "learning_rate": 0.000141019955654102,
-      "loss": 0.6413,
+      "loss": 0.6399,
       "step": 139
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.4279260039329529,
+      "grad_norm": 0.42985525727272034,
       "learning_rate": 0.00014057649667405765,
-      "loss": 0.524,
+      "loss": 0.5237,
       "step": 140
     },
     {
       "epoch": 0.9296703296703297,
-      "grad_norm": 0.3015099763870239,
+      "grad_norm": 0.29981592297554016,
       "learning_rate": 0.00014013303769401332,
-      "loss": 0.5545,
+      "loss": 0.5546,
       "step": 141
     },
     {
       "epoch": 0.9362637362637363,
-      "grad_norm": 0.27604034543037415,
+      "grad_norm": 0.2759975790977478,
       "learning_rate": 0.00013968957871396897,
-      "loss": 0.5117,
+      "loss": 0.5112,
       "step": 142
     },
     {
       "epoch": 0.9428571428571428,
-      "grad_norm": 0.2875494658946991,
+      "grad_norm": 0.28473037481307983,
       "learning_rate": 0.00013924611973392464,
-      "loss": 0.3677,
+      "loss": 0.3682,
       "step": 143
     },
     {
       "epoch": 0.9494505494505494,
-      "grad_norm": 0.2923910319805145,
+      "grad_norm": 0.2925246059894562,
       "learning_rate": 0.00013880266075388026,
-      "loss": 0.4148,
+      "loss": 0.4146,
       "step": 144
     },
     {
       "epoch": 0.9560439560439561,
-      "grad_norm": 0.35929375886917114,
+      "grad_norm": 0.3603278398513794,
       "learning_rate": 0.00013835920177383593,
-      "loss": 0.5216,
+      "loss": 0.5228,
       "step": 145
     },
     {
       "epoch": 0.9626373626373627,
-      "grad_norm": 0.37820327281951904,
+      "grad_norm": 0.377169132232666,
       "learning_rate": 0.00013791574279379157,
-      "loss": 0.5282,
+      "loss": 0.5283,
       "step": 146
     },
     {
       "epoch": 0.9692307692307692,
-      "grad_norm": 0.31699371337890625,
+      "grad_norm": 0.3173151910305023,
       "learning_rate": 0.00013747228381374724,
-      "loss": 0.6546,
+      "loss": 0.6543,
       "step": 147
     },
     {
       "epoch": 0.9758241758241758,
-      "grad_norm": 0.33894863724708557,
+      "grad_norm": 0.33789265155792236,
       "learning_rate": 0.0001370288248337029,
-      "loss": 0.524,
+      "loss": 0.5227,
       "step": 148
     },
     {
       "epoch": 0.9824175824175824,
-      "grad_norm": 0.32184189558029175,
+      "grad_norm": 0.3221614956855774,
       "learning_rate": 0.00013658536585365856,
-      "loss": 0.535,
+      "loss": 0.5334,
       "step": 149
     },
     {
       "epoch": 0.989010989010989,
-      "grad_norm": 0.3463665246963501,
+      "grad_norm": 0.34865596890449524,
       "learning_rate": 0.00013614190687361418,
-      "loss": 0.4861,
+      "loss": 0.4883,
       "step": 150
     },
     {
       "epoch": 0.9956043956043956,
-      "grad_norm": 0.4191942512989044,
+      "grad_norm": 0.4125325381755829,
       "learning_rate": 0.00013569844789356985,
-      "loss": 0.6246,
+      "loss": 0.6229,
       "step": 151
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.6371860504150391,
+      "grad_norm": 0.6319997906684875,
       "learning_rate": 0.0001352549889135255,
-      "loss": 0.5405,
+      "loss": 0.54,
       "step": 152
     },
     {
       "epoch": 1.0065934065934066,
-      "grad_norm": 0.366366982460022,
+      "grad_norm": 0.3639872968196869,
       "learning_rate": 0.00013481152993348116,
-      "loss": 0.4963,
+      "loss": 0.4948,
       "step": 153
     },
     {
       "epoch": 1.0131868131868131,
-      "grad_norm": 0.27636903524398804,
+      "grad_norm": 0.2758268117904663,
       "learning_rate": 0.0001343680709534368,
-      "loss": 0.6119,
+      "loss": 0.614,
       "step": 154
     },
     {
       "epoch": 1.0197802197802197,
-      "grad_norm": 0.31429532170295715,
+      "grad_norm": 0.31727808713912964,
       "learning_rate": 0.00013392461197339248,
-      "loss": 0.448,
+      "loss": 0.4463,
       "step": 155
     },
     {
       "epoch": 1.0263736263736263,
-      "grad_norm": 0.3276287019252777,
+      "grad_norm": 0.3282637894153595,
       "learning_rate": 0.00013348115299334812,
       "loss": 0.5902,
       "step": 156
     },
     {
       "epoch": 1.032967032967033,
-      "grad_norm": 0.28313398361206055,
+      "grad_norm": 0.28062060475349426,
       "learning_rate": 0.00013303769401330377,
-      "loss": 0.511,
+      "loss": 0.5102,
       "step": 157
     },
     {
       "epoch": 1.0395604395604396,
-      "grad_norm": 0.3366428017616272,
+      "grad_norm": 0.3372250497341156,
       "learning_rate": 0.00013259423503325944,
-      "loss": 0.4171,
+      "loss": 0.4166,
       "step": 158
     },
     {
       "epoch": 1.0461538461538462,
-      "grad_norm": 0.35323694348335266,
+      "grad_norm": 0.35462722182273865,
       "learning_rate": 0.00013215077605321509,
-      "loss": 0.459,
+      "loss": 0.4608,
       "step": 159
     },
     {
       "epoch": 1.0527472527472528,
-      "grad_norm": 0.4649209976196289,
+      "grad_norm": 0.46279245615005493,
       "learning_rate": 0.00013170731707317076,
-      "loss": 0.6039,
+      "loss": 0.6045,
       "step": 160
     },
     {
       "epoch": 1.0593406593406594,
-      "grad_norm": 0.3635141849517822,
+      "grad_norm": 0.35800057649612427,
       "learning_rate": 0.0001312638580931264,
-      "loss": 0.4078,
+      "loss": 0.406,
       "step": 161
     },
     {
       "epoch": 1.065934065934066,
-      "grad_norm": 0.33368000388145447,
+      "grad_norm": 0.3310445547103882,
       "learning_rate": 0.00013082039911308205,
-      "loss": 0.4182,
+      "loss": 0.4186,
       "step": 162
     },
     {
       "epoch": 1.0725274725274725,
-      "grad_norm": 0.32055410742759705,
+      "grad_norm": 0.31068041920661926,
       "learning_rate": 0.0001303769401330377,
-      "loss": 0.2769,
+      "loss": 0.2765,
       "step": 163
     },
     {
       "epoch": 1.079120879120879,
-      "grad_norm": 0.40329527854919434,
+      "grad_norm": 0.40664976835250854,
       "learning_rate": 0.00012993348115299336,
-      "loss": 0.4545,
+      "loss": 0.4562,
       "step": 164
     },
     {
       "epoch": 1.0857142857142856,
-      "grad_norm": 0.5172844529151917,
+      "grad_norm": 0.512418270111084,
       "learning_rate": 0.000129490022172949,
-      "loss": 0.5064,
+      "loss": 0.5065,
       "step": 165
     },
     {
       "epoch": 1.0923076923076924,
-      "grad_norm": 0.32881635427474976,
+      "grad_norm": 0.3328132629394531,
       "learning_rate": 0.00012904656319290468,
-      "loss": 0.4023,
+      "loss": 0.4016,
       "step": 166
     },
     {
       "epoch": 1.098901098901099,
-      "grad_norm": 0.3940103352069855,
+      "grad_norm": 0.3887135684490204,
       "learning_rate": 0.00012860310421286032,
-      "loss": 0.4526,
+      "loss": 0.4514,
       "step": 167
     },
     {
       "epoch": 1.1054945054945056,
-      "grad_norm": 0.4381999969482422,
+      "grad_norm": 0.43707022070884705,
       "learning_rate": 0.00012815964523281597,
-      "loss": 0.441,
+      "loss": 0.4417,
       "step": 168
     },
     {
       "epoch": 1.1120879120879121,
-      "grad_norm": 0.40614739060401917,
+      "grad_norm": 0.39931192994117737,
       "learning_rate": 0.0001277161862527716,
-      "loss": 0.4061,
+      "loss": 0.4031,
       "step": 169
     },
     {
       "epoch": 1.1186813186813187,
-      "grad_norm": 0.37779855728149414,
+      "grad_norm": 0.38393622636795044,
       "learning_rate": 0.00012727272727272728,
-      "loss": 0.4281,
+      "loss": 0.4296,
       "step": 170
     },
     {
       "epoch": 1.1252747252747253,
-      "grad_norm": 0.4330942630767822,
+      "grad_norm": 0.44032469391822815,
       "learning_rate": 0.00012682926829268293,
-      "loss": 0.4949,
+      "loss": 0.4956,
       "step": 171
     },
     {
       "epoch": 1.1318681318681318,
-      "grad_norm": 0.4749648869037628,
+      "grad_norm": 0.4821639955043793,
       "learning_rate": 0.0001263858093126386,
-      "loss": 0.542,
+      "loss": 0.545,
       "step": 172
     },
     {
       "epoch": 1.1384615384615384,
-      "grad_norm": 0.3527723252773285,
+      "grad_norm": 0.35123512148857117,
       "learning_rate": 0.00012594235033259424,
-      "loss": 0.3557,
+      "loss": 0.3524,
       "step": 173
     },
     {
       "epoch": 1.145054945054945,
-      "grad_norm": 0.29305532574653625,
+      "grad_norm": 0.29495614767074585,
       "learning_rate": 0.00012549889135254989,
-      "loss": 0.4416,
+      "loss": 0.441,
       "step": 174
     },
     {
       "epoch": 1.1516483516483516,
-      "grad_norm": 0.33726340532302856,
+      "grad_norm": 0.33546820282936096,
       "learning_rate": 0.00012505543237250553,
-      "loss": 0.4623,
+      "loss": 0.4615,
       "step": 175
     },
     {
       "epoch": 1.1582417582417581,
-      "grad_norm": 0.3799065947532654,
+      "grad_norm": 0.38181272149086,
       "learning_rate": 0.0001246119733924612,
-      "loss": 0.4791,
+      "loss": 0.4789,
       "step": 176
     },
     {
       "epoch": 1.164835164835165,
-      "grad_norm": 0.3472652733325958,
+      "grad_norm": 0.3501313328742981,
       "learning_rate": 0.00012416851441241685,
-      "loss": 0.4403,
+      "loss": 0.4415,
       "step": 177
     },
     {
       "epoch": 1.1714285714285715,
-      "grad_norm": 0.39185139536857605,
+      "grad_norm": 0.3939834535121918,
       "learning_rate": 0.00012372505543237252,
-      "loss": 0.4296,
+      "loss": 0.43,
       "step": 178
     },
     {
       "epoch": 1.178021978021978,
-      "grad_norm": 0.4938018023967743,
+      "grad_norm": 0.4963679909706116,
       "learning_rate": 0.00012328159645232816,
-      "loss": 0.4334,
+      "loss": 0.4333,
       "step": 179
     },
     {
       "epoch": 1.1846153846153846,
-      "grad_norm": 0.5348626375198364,
+      "grad_norm": 0.5315191745758057,
       "learning_rate": 0.0001228381374722838,
-      "loss": 0.4294,
+      "loss": 0.4297,
       "step": 180
     },
     {
       "epoch": 1.1912087912087912,
-      "grad_norm": 0.33656343817710876,
+      "grad_norm": 0.33417269587516785,
       "learning_rate": 0.00012239467849223948,
-      "loss": 0.3643,
+      "loss": 0.3628,
       "step": 181
     },
     {
       "epoch": 1.1978021978021978,
-      "grad_norm": 0.3550446033477783,
+      "grad_norm": 0.35668453574180603,
       "learning_rate": 0.00012195121951219512,
-      "loss": 0.404,
+      "loss": 0.4051,
       "step": 182
     },
     {
       "epoch": 1.2043956043956043,
-      "grad_norm": 0.37620025873184204,
+      "grad_norm": 0.3780662715435028,
       "learning_rate": 0.00012150776053215078,
-      "loss": 0.4504,
+      "loss": 0.4502,
       "step": 183
     },
     {
       "epoch": 1.210989010989011,
-      "grad_norm": 0.4174230992794037,
+      "grad_norm": 0.4298599660396576,
       "learning_rate": 0.00012106430155210644,
-      "loss": 0.4507,
+      "loss": 0.4524,
       "step": 184
     },
     {
       "epoch": 1.2175824175824177,
-      "grad_norm": 0.4068443179130554,
+      "grad_norm": 0.4104001224040985,
       "learning_rate": 0.0001206208425720621,
-      "loss": 0.4322,
+      "loss": 0.4335,
       "step": 185
     },
     {
       "epoch": 1.2241758241758243,
-      "grad_norm": 0.4173579514026642,
+      "grad_norm": 0.4124521315097809,
       "learning_rate": 0.00012017738359201774,
-      "loss": 0.4127,
+      "loss": 0.4122,
       "step": 186
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 0.37026944756507874,
+      "grad_norm": 0.36973732709884644,
       "learning_rate": 0.0001197339246119734,
-      "loss": 0.3955,
+      "loss": 0.395,
       "step": 187
     },
     {
       "epoch": 1.2373626373626374,
-      "grad_norm": 0.4721613824367523,
+      "grad_norm": 0.47219377756118774,
       "learning_rate": 0.00011929046563192906,
-      "loss": 0.454,
+      "loss": 0.4539,
       "step": 188
     },
     {
       "epoch": 1.243956043956044,
-      "grad_norm": 0.46989724040031433,
+      "grad_norm": 0.4713725745677948,
       "learning_rate": 0.00011884700665188471,
-      "loss": 0.4357,
+      "loss": 0.4359,
       "step": 189
     },
     {
       "epoch": 1.2505494505494505,
-      "grad_norm": 0.40494221448898315,
+      "grad_norm": 0.4039464294910431,
       "learning_rate": 0.00011840354767184036,
       "loss": 0.4296,
       "step": 190
     },
     {
       "epoch": 1.2571428571428571,
-      "grad_norm": 0.4352794289588928,
+      "grad_norm": 0.4269494414329529,
       "learning_rate": 0.00011796008869179602,
-      "loss": 0.4343,
+      "loss": 0.4321,
       "step": 191
     },
     {
       "epoch": 1.2637362637362637,
-      "grad_norm": 0.442832887172699,
+      "grad_norm": 0.442822128534317,
       "learning_rate": 0.00011751662971175166,
-      "loss": 0.3926,
+      "loss": 0.393,
       "step": 192
     },
     {
       "epoch": 1.2703296703296703,
-      "grad_norm": 0.5452187061309814,
+      "grad_norm": 0.5490491390228271,
       "learning_rate": 0.00011707317073170732,
-      "loss": 0.4587,
+      "loss": 0.4583,
       "step": 193
     },
     {
       "epoch": 1.2769230769230768,
-      "grad_norm": 0.501698911190033,
+      "grad_norm": 0.4975128769874573,
       "learning_rate": 0.00011662971175166298,
-      "loss": 0.4135,
+      "loss": 0.412,
       "step": 194
     },
     {
       "epoch": 1.2835164835164834,
-      "grad_norm": 0.586365282535553,
+      "grad_norm": 0.5764912366867065,
       "learning_rate": 0.00011618625277161863,
-      "loss": 0.3953,
+      "loss": 0.3959,
       "step": 195
     },
     {
       "epoch": 1.2901098901098902,
-      "grad_norm": 0.609646201133728,
+      "grad_norm": 0.6070420145988464,
       "learning_rate": 0.00011574279379157429,
-      "loss": 0.4386,
+      "loss": 0.4373,
       "step": 196
     },
     {
       "epoch": 1.2967032967032968,
-      "grad_norm": 0.4692327380180359,
+      "grad_norm": 0.47154393792152405,
       "learning_rate": 0.00011529933481152995,
-      "loss": 0.4099,
+      "loss": 0.4102,
       "step": 197
     },
     {
       "epoch": 1.3032967032967033,
-      "grad_norm": 0.49465101957321167,
+      "grad_norm": 0.4946073591709137,
       "learning_rate": 0.00011485587583148558,
-      "loss": 0.5054,
+      "loss": 0.5053,
       "step": 198
     },
     {
       "epoch": 1.30989010989011,
-      "grad_norm": 0.49324506521224976,
+      "grad_norm": 0.49047937989234924,
       "learning_rate": 0.00011441241685144124,
-      "loss": 0.4617,
+      "loss": 0.4618,
       "step": 199
     },
     {
       "epoch": 1.3164835164835165,
-      "grad_norm": 0.47912997007369995,
+      "grad_norm": 0.4761285185813904,
       "learning_rate": 0.0001139689578713969,
-      "loss": 0.4179,
+      "loss": 0.4168,
       "step": 200
     },
     {
       "epoch": 1.323076923076923,
-      "grad_norm": 0.4326474666595459,
+      "grad_norm": 0.43215903639793396,
       "learning_rate": 0.00011352549889135255,
-      "loss": 0.5625,
+      "loss": 0.5628,
       "step": 201
     },
     {
       "epoch": 1.3296703296703296,
-      "grad_norm": 0.4624297320842743,
+      "grad_norm": 0.4638778567314148,
       "learning_rate": 0.00011308203991130821,
-      "loss": 0.3578,
+      "loss": 0.3562,
       "step": 202
     },
     {
       "epoch": 1.3362637362637364,
-      "grad_norm": 0.4258561134338379,
+      "grad_norm": 0.4210982024669647,
       "learning_rate": 0.00011263858093126387,
-      "loss": 0.3842,
+      "loss": 0.3832,
       "step": 203
     },
     {
       "epoch": 1.342857142857143,
-      "grad_norm": 0.463854044675827,
+      "grad_norm": 0.4595351219177246,
       "learning_rate": 0.00011219512195121953,
-      "loss": 0.4307,
+      "loss": 0.4305,
       "step": 204
     },
     {
       "epoch": 1.3494505494505495,
-      "grad_norm": 0.5509984493255615,
+      "grad_norm": 0.5463175773620605,
       "learning_rate": 0.00011175166297117516,
-      "loss": 0.4541,
+      "loss": 0.4532,
       "step": 205
     },
     {
       "epoch": 1.3560439560439561,
-      "grad_norm": 0.45098432898521423,
+      "grad_norm": 0.4275128245353699,
       "learning_rate": 0.00011130820399113082,
-      "loss": 0.4116,
+      "loss": 0.4104,
       "step": 206
     },
     {
       "epoch": 1.3626373626373627,
-      "grad_norm": 0.4335211217403412,
+      "grad_norm": 0.43406739830970764,
       "learning_rate": 0.00011086474501108647,
-      "loss": 0.3698,
+      "loss": 0.3707,
       "step": 207
     },
     {
       "epoch": 1.3692307692307693,
-      "grad_norm": 0.490063339471817,
+      "grad_norm": 0.49074482917785645,
       "learning_rate": 0.00011042128603104213,
       "loss": 0.4733,
       "step": 208
     },
     {
       "epoch": 1.3758241758241758,
-      "grad_norm": 0.5077163577079773,
+      "grad_norm": 0.5087794065475464,
       "learning_rate": 0.00010997782705099779,
-      "loss": 0.5421,
+      "loss": 0.5424,
       "step": 209
     },
     {
       "epoch": 1.3824175824175824,
-      "grad_norm": 0.4260414242744446,
+      "grad_norm": 0.42750105261802673,
       "learning_rate": 0.00010953436807095345,
-      "loss": 0.3797,
+      "loss": 0.379,
       "step": 210
     },
     {
       "epoch": 1.389010989010989,
-      "grad_norm": 0.4791169762611389,
+      "grad_norm": 0.48225167393684387,
       "learning_rate": 0.00010909090909090909,
-      "loss": 0.4795,
+      "loss": 0.4807,
       "step": 211
     },
     {
       "epoch": 1.3956043956043955,
-      "grad_norm": 0.5247262120246887,
+      "grad_norm": 0.5264402627944946,
       "learning_rate": 0.00010864745011086475,
-      "loss": 0.5034,
+      "loss": 0.5044,
       "step": 212
     },
     {
       "epoch": 1.402197802197802,
-      "grad_norm": 0.5030892491340637,
+      "grad_norm": 0.5037549734115601,
       "learning_rate": 0.00010820399113082041,
-      "loss": 0.3187,
+      "loss": 0.3193,
       "step": 213
     },
     {
       "epoch": 1.4087912087912087,
-      "grad_norm": 0.49852412939071655,
+      "grad_norm": 0.4975391626358032,
       "learning_rate": 0.00010776053215077607,
-      "loss": 0.4606,
+      "loss": 0.46,
       "step": 214
     },
     {
       "epoch": 1.4153846153846155,
-      "grad_norm": 0.4788177013397217,
+      "grad_norm": 0.47859132289886475,
       "learning_rate": 0.00010731707317073172,
-      "loss": 0.3939,
+      "loss": 0.3936,
       "step": 215
     },
     {
       "epoch": 1.421978021978022,
-      "grad_norm": 0.556289553642273,
+      "grad_norm": 0.5597440600395203,
       "learning_rate": 0.00010687361419068738,
-      "loss": 0.3672,
+      "loss": 0.369,
       "step": 216
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.522782027721405,
+      "grad_norm": 0.527248740196228,
       "learning_rate": 0.00010643015521064301,
-      "loss": 0.3746,
+      "loss": 0.3762,
       "step": 217
     },
     {
       "epoch": 1.4351648351648352,
-      "grad_norm": 0.49437379837036133,
+      "grad_norm": 0.49342048168182373,
       "learning_rate": 0.00010598669623059867,
-      "loss": 0.3698,
+      "loss": 0.3724,
       "step": 218
     },
     {
       "epoch": 1.4417582417582417,
-      "grad_norm": 0.5110532641410828,
+      "grad_norm": 0.507117748260498,
       "learning_rate": 0.00010554323725055433,
-      "loss": 0.4712,
+      "loss": 0.4706,
       "step": 219
     },
     {
       "epoch": 1.4483516483516483,
-      "grad_norm": 0.5341584086418152,
+      "grad_norm": 0.5301528573036194,
       "learning_rate": 0.00010509977827050999,
-      "loss": 0.3484,
+      "loss": 0.3483,
       "step": 220
     },
     {
       "epoch": 1.4549450549450549,
-      "grad_norm": 0.4161616265773773,
+      "grad_norm": 0.41132017970085144,
       "learning_rate": 0.00010465631929046564,
-      "loss": 0.3062,
+      "loss": 0.3065,
       "step": 221
     },
     {
       "epoch": 1.4615384615384617,
-      "grad_norm": 0.5076987147331238,
+      "grad_norm": 0.514223575592041,
       "learning_rate": 0.0001042128603104213,
-      "loss": 0.3501,
+      "loss": 0.3523,
       "step": 222
     },
     {
       "epoch": 1.4681318681318682,
-      "grad_norm": 0.48905038833618164,
+      "grad_norm": 0.49537795782089233,
       "learning_rate": 0.00010376940133037693,
-      "loss": 0.3401,
+      "loss": 0.3407,
       "step": 223
     },
     {
       "epoch": 1.4747252747252748,
-      "grad_norm": 0.5411365032196045,
+      "grad_norm": 0.543089747428894,
       "learning_rate": 0.00010332594235033259,
-      "loss": 0.4791,
+      "loss": 0.4795,
       "step": 224
     },
     {
       "epoch": 1.4813186813186814,
-      "grad_norm": 0.5800930261611938,
+      "grad_norm": 0.5868189930915833,
       "learning_rate": 0.00010288248337028825,
-      "loss": 0.5287,
+      "loss": 0.5282,
       "step": 225
     }
   ],

checkpoint-225/training_args.bin

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