Upload folder using huggingface_hub

checkpoint-300/adapter_config.json

@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj"
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-300/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472aac703a8325a576e561dcb48b35df734929def93d058cbf63812ece57e43d
+oid sha256:58b3bcc79204b33cc95598bebe9605378174c72b29e072defca0c197ddb8a451
 size 59933632

checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ef3faa8996e340f410fc042c56180c02237b9ef1229ab89beec2be8c61deb1
+oid sha256:b254a047a008aea6ed46e2515dfa4f037289c12ecbcc428c02aeea164048eafa
 size 120166091

checkpoint-300/trainer_state.json

@@ -46,2067 +46,2067 @@
     },
     {
       "epoch": 0.03956043956043956,
-      "grad_norm": 1.9752649068832397,
+      "grad_norm": 1.97528076171875,
       "learning_rate": 0.0002,
       "loss": 1.7334,
       "step": 6
     },
     {
       "epoch": 0.046153846153846156,
-      "grad_norm": 2.564279317855835,
+      "grad_norm": 2.583857297897339,
       "learning_rate": 0.00019955654101995565,
-      "loss": 1.8931,
+      "loss": 1.8924,
       "step": 7
     },
     {
       "epoch": 0.05274725274725275,
-      "grad_norm": 1.9491405487060547,
+      "grad_norm": 1.9402282238006592,
       "learning_rate": 0.00019911308203991133,
-      "loss": 1.2738,
+      "loss": 1.273,
       "step": 8
     },
     {
       "epoch": 0.05934065934065934,
-      "grad_norm": 1.026367425918579,
+      "grad_norm": 1.030725359916687,
       "learning_rate": 0.00019866962305986697,
-      "loss": 1.33,
+      "loss": 1.3303,
       "step": 9
     },
     {
       "epoch": 0.06593406593406594,
-      "grad_norm": 1.3561840057373047,
+      "grad_norm": 1.3545081615447998,
       "learning_rate": 0.00019822616407982261,
-      "loss": 1.3474,
+      "loss": 1.3464,
       "step": 10
     },
     {
       "epoch": 0.07252747252747253,
-      "grad_norm": 0.9841963648796082,
+      "grad_norm": 0.9670407176017761,
       "learning_rate": 0.00019778270509977829,
-      "loss": 1.26,
+      "loss": 1.2525,
       "step": 11
     },
     {
       "epoch": 0.07912087912087912,
-      "grad_norm": 0.7599233984947205,
+      "grad_norm": 0.7464919090270996,
       "learning_rate": 0.00019733924611973393,
-      "loss": 1.1589,
+      "loss": 1.1564,
       "step": 12
     },
     {
       "epoch": 0.08571428571428572,
-      "grad_norm": 0.5863561630249023,
+      "grad_norm": 0.5867994427680969,
       "learning_rate": 0.0001968957871396896,
-      "loss": 1.0918,
+      "loss": 1.0917,
       "step": 13
     },
     {
       "epoch": 0.09230769230769231,
-      "grad_norm": 0.614296019077301,
+      "grad_norm": 0.6113730669021606,
       "learning_rate": 0.00019645232815964525,
-      "loss": 1.1588,
+      "loss": 1.1594,
       "step": 14
     },
     {
       "epoch": 0.0989010989010989,
-      "grad_norm": 0.46234244108200073,
+      "grad_norm": 0.4500170052051544,
       "learning_rate": 0.00019600886917960092,
-      "loss": 1.0832,
+      "loss": 1.0796,
       "step": 15
     },
     {
       "epoch": 0.1054945054945055,
-      "grad_norm": 0.5534088015556335,
+      "grad_norm": 0.5538170337677002,
       "learning_rate": 0.00019556541019955653,
-      "loss": 1.1643,
+      "loss": 1.1618,
       "step": 16
     },
     {
       "epoch": 0.11208791208791209,
-      "grad_norm": 0.45435506105422974,
+      "grad_norm": 0.45620211958885193,
       "learning_rate": 0.0001951219512195122,
-      "loss": 1.1515,
+      "loss": 1.1508,
       "step": 17
     },
     {
       "epoch": 0.11868131868131868,
-      "grad_norm": 0.4777897894382477,
+      "grad_norm": 0.4772197902202606,
       "learning_rate": 0.00019467849223946785,
-      "loss": 1.062,
+      "loss": 1.061,
       "step": 18
     },
     {
       "epoch": 0.12527472527472527,
-      "grad_norm": 0.525127649307251,
+      "grad_norm": 0.533805787563324,
       "learning_rate": 0.00019423503325942352,
-      "loss": 1.1474,
+      "loss": 1.1468,
       "step": 19
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 0.413349986076355,
+      "grad_norm": 0.4162095785140991,
       "learning_rate": 0.00019379157427937917,
-      "loss": 0.9223,
+      "loss": 0.9207,
       "step": 20
     },
     {
       "epoch": 0.13846153846153847,
-      "grad_norm": 0.30619320273399353,
+      "grad_norm": 0.30745798349380493,
       "learning_rate": 0.00019334811529933484,
-      "loss": 0.8226,
+      "loss": 0.8223,
       "step": 21
     },
     {
       "epoch": 0.14505494505494507,
-      "grad_norm": 0.30665796995162964,
+      "grad_norm": 0.29989153146743774,
       "learning_rate": 0.00019290465631929045,
-      "loss": 1.063,
+      "loss": 1.0635,
       "step": 22
     },
     {
       "epoch": 0.15164835164835164,
-      "grad_norm": 0.4375471770763397,
+      "grad_norm": 0.4353378415107727,
       "learning_rate": 0.00019246119733924613,
-      "loss": 1.1137,
+      "loss": 1.1136,
       "step": 23
     },
     {
       "epoch": 0.15824175824175823,
-      "grad_norm": 0.3059830069541931,
+      "grad_norm": 0.30720826983451843,
       "learning_rate": 0.00019201773835920177,
-      "loss": 1.0795,
+      "loss": 1.0796,
       "step": 24
     },
     {
       "epoch": 0.16483516483516483,
-      "grad_norm": 0.303276389837265,
+      "grad_norm": 0.30275797843933105,
       "learning_rate": 0.00019157427937915744,
-      "loss": 0.9357,
+      "loss": 0.9368,
       "step": 25
     },
     {
       "epoch": 0.17142857142857143,
-      "grad_norm": 0.30064496397972107,
+      "grad_norm": 0.3034687042236328,
       "learning_rate": 0.00019113082039911309,
-      "loss": 0.9608,
+      "loss": 0.9616,
       "step": 26
     },
     {
       "epoch": 0.17802197802197803,
-      "grad_norm": 0.3118164539337158,
+      "grad_norm": 0.3129018545150757,
       "learning_rate": 0.00019068736141906876,
-      "loss": 0.976,
+      "loss": 0.9762,
       "step": 27
     },
     {
       "epoch": 0.18461538461538463,
-      "grad_norm": 0.32316967844963074,
+      "grad_norm": 0.32465481758117676,
       "learning_rate": 0.0001902439024390244,
-      "loss": 1.0248,
+      "loss": 1.025,
       "step": 28
     },
     {
       "epoch": 0.1912087912087912,
-      "grad_norm": 0.38039305806159973,
+      "grad_norm": 0.3805822730064392,
       "learning_rate": 0.00018980044345898005,
-      "loss": 1.0935,
+      "loss": 1.0966,
       "step": 29
     },
     {
       "epoch": 0.1978021978021978,
-      "grad_norm": 0.3035508692264557,
+      "grad_norm": 0.30361831188201904,
       "learning_rate": 0.00018935698447893572,
-      "loss": 1.1209,
+      "loss": 1.1199,
       "step": 30
     },
     {
       "epoch": 0.2043956043956044,
-      "grad_norm": 0.3552742600440979,
+      "grad_norm": 0.3538556694984436,
       "learning_rate": 0.00018891352549889136,
-      "loss": 0.8599,
+      "loss": 0.8606,
       "step": 31
     },
     {
       "epoch": 0.210989010989011,
-      "grad_norm": 0.4854717254638672,
+      "grad_norm": 0.4855636954307556,
       "learning_rate": 0.00018847006651884703,
-      "loss": 1.2983,
+      "loss": 1.3002,
       "step": 32
     },
     {
       "epoch": 0.2175824175824176,
-      "grad_norm": 0.3681517541408539,
+      "grad_norm": 0.36801108717918396,
       "learning_rate": 0.00018802660753880268,
       "loss": 1.1441,
       "step": 33
     },
     {
       "epoch": 0.22417582417582418,
-      "grad_norm": 0.303026407957077,
+      "grad_norm": 0.3000083565711975,
       "learning_rate": 0.00018758314855875832,
-      "loss": 1.0872,
+      "loss": 1.0868,
       "step": 34
     },
     {
       "epoch": 0.23076923076923078,
-      "grad_norm": 0.3582163155078888,
+      "grad_norm": 0.35833317041397095,
       "learning_rate": 0.00018713968957871397,
-      "loss": 0.981,
+      "loss": 0.9805,
       "step": 35
     },
     {
       "epoch": 0.23736263736263735,
-      "grad_norm": 0.27061930298805237,
+      "grad_norm": 0.26648440957069397,
       "learning_rate": 0.00018669623059866964,
-      "loss": 0.9192,
+      "loss": 0.9186,
       "step": 36
     },
     {
       "epoch": 0.24395604395604395,
-      "grad_norm": 0.29702866077423096,
+      "grad_norm": 0.29637497663497925,
       "learning_rate": 0.00018625277161862528,
       "loss": 1.0078,
       "step": 37
     },
     {
       "epoch": 0.25054945054945055,
-      "grad_norm": 0.37023022770881653,
+      "grad_norm": 0.3601683974266052,
       "learning_rate": 0.00018580931263858095,
-      "loss": 1.0047,
+      "loss": 1.0045,
       "step": 38
     },
     {
       "epoch": 0.2571428571428571,
-      "grad_norm": 0.3519829511642456,
+      "grad_norm": 0.3521329462528229,
       "learning_rate": 0.0001853658536585366,
-      "loss": 0.999,
+      "loss": 1.0004,
       "step": 39
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.2641372084617615,
+      "grad_norm": 0.2667492628097534,
       "learning_rate": 0.00018492239467849224,
-      "loss": 0.9269,
+      "loss": 0.9271,
       "step": 40
     },
     {
       "epoch": 0.2703296703296703,
-      "grad_norm": 0.3424227833747864,
+      "grad_norm": 0.33176255226135254,
       "learning_rate": 0.0001844789356984479,
-      "loss": 1.0748,
+      "loss": 1.0735,
       "step": 41
     },
     {
       "epoch": 0.27692307692307694,
-      "grad_norm": 0.3919481039047241,
+      "grad_norm": 0.3940621018409729,
       "learning_rate": 0.00018403547671840356,
-      "loss": 1.1445,
+      "loss": 1.1447,
       "step": 42
     },
     {
       "epoch": 0.2835164835164835,
-      "grad_norm": 0.3040602207183838,
+      "grad_norm": 0.3026503324508667,
       "learning_rate": 0.0001835920177383592,
-      "loss": 0.8869,
+      "loss": 0.8857,
       "step": 43
     },
     {
       "epoch": 0.29010989010989013,
-      "grad_norm": 0.2948625683784485,
+      "grad_norm": 0.2967509627342224,
       "learning_rate": 0.00018314855875831487,
-      "loss": 1.0821,
+      "loss": 1.0834,
       "step": 44
     },
     {
       "epoch": 0.2967032967032967,
-      "grad_norm": 0.2821897566318512,
+      "grad_norm": 0.2822628319263458,
       "learning_rate": 0.00018270509977827052,
-      "loss": 0.9714,
+      "loss": 0.9712,
       "step": 45
     },
     {
       "epoch": 0.3032967032967033,
-      "grad_norm": 0.3602289855480194,
+      "grad_norm": 0.36211535334587097,
       "learning_rate": 0.00018226164079822616,
-      "loss": 1.0296,
+      "loss": 1.0312,
       "step": 46
     },
     {
       "epoch": 0.3098901098901099,
-      "grad_norm": 0.3210930824279785,
+      "grad_norm": 0.3197602331638336,
       "learning_rate": 0.00018181818181818183,
-      "loss": 0.9409,
+      "loss": 0.9411,
       "step": 47
     },
     {
       "epoch": 0.31648351648351647,
-      "grad_norm": 0.3485034704208374,
+      "grad_norm": 0.34601065516471863,
       "learning_rate": 0.00018137472283813748,
-      "loss": 0.9463,
+      "loss": 0.9466,
       "step": 48
     },
     {
       "epoch": 0.3230769230769231,
-      "grad_norm": 0.30606183409690857,
+      "grad_norm": 0.3059934973716736,
       "learning_rate": 0.00018093126385809312,
-      "loss": 0.8539,
+      "loss": 0.8534,
       "step": 49
     },
     {
       "epoch": 0.32967032967032966,
-      "grad_norm": 0.30226030945777893,
+      "grad_norm": 0.3049042820930481,
       "learning_rate": 0.0001804878048780488,
-      "loss": 0.9588,
+      "loss": 0.9564,
       "step": 50
     },
     {
       "epoch": 0.3362637362637363,
-      "grad_norm": 0.3496457040309906,
+      "grad_norm": 0.3513273298740387,
       "learning_rate": 0.00018004434589800444,
-      "loss": 1.0444,
+      "loss": 1.0429,
       "step": 51
     },
     {
       "epoch": 0.34285714285714286,
-      "grad_norm": 0.33469706773757935,
+      "grad_norm": 0.33669522404670715,
       "learning_rate": 0.00017960088691796008,
-      "loss": 0.9727,
+      "loss": 0.9706,
       "step": 52
     },
     {
       "epoch": 0.34945054945054943,
-      "grad_norm": 0.3913564383983612,
+      "grad_norm": 0.3956065773963928,
       "learning_rate": 0.00017915742793791575,
-      "loss": 1.0487,
+      "loss": 1.0505,
       "step": 53
     },
     {
       "epoch": 0.35604395604395606,
-      "grad_norm": 0.31554681062698364,
+      "grad_norm": 0.31517383456230164,
       "learning_rate": 0.0001787139689578714,
-      "loss": 1.0484,
+      "loss": 1.0469,
       "step": 54
     },
     {
       "epoch": 0.3626373626373626,
-      "grad_norm": 0.3576411306858063,
+      "grad_norm": 0.36682212352752686,
       "learning_rate": 0.00017827050997782707,
       "loss": 0.9408,
       "step": 55
     },
     {
       "epoch": 0.36923076923076925,
-      "grad_norm": 0.38003620505332947,
+      "grad_norm": 0.38366109132766724,
       "learning_rate": 0.00017782705099778271,
-      "loss": 1.1853,
+      "loss": 1.1865,
       "step": 56
     },
     {
       "epoch": 0.3758241758241758,
-      "grad_norm": 0.2947905659675598,
+      "grad_norm": 0.30710846185684204,
       "learning_rate": 0.00017738359201773839,
-      "loss": 1.0223,
+      "loss": 1.0216,
       "step": 57
     },
     {
       "epoch": 0.3824175824175824,
-      "grad_norm": 0.2967394292354584,
+      "grad_norm": 0.29654064774513245,
       "learning_rate": 0.000176940133037694,
-      "loss": 0.9359,
+      "loss": 0.9368,
       "step": 58
     },
     {
       "epoch": 0.389010989010989,
-      "grad_norm": 0.43115320801734924,
+      "grad_norm": 0.43266645073890686,
       "learning_rate": 0.00017649667405764967,
-      "loss": 0.9404,
+      "loss": 0.9399,
       "step": 59
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.33834582567214966,
+      "grad_norm": 0.3399896025657654,
       "learning_rate": 0.00017605321507760532,
-      "loss": 1.2252,
+      "loss": 1.2272,
       "step": 60
     },
     {
       "epoch": 0.4021978021978022,
-      "grad_norm": 0.35457855463027954,
+      "grad_norm": 0.35805898904800415,
       "learning_rate": 0.000175609756097561,
-      "loss": 1.1279,
+      "loss": 1.1291,
       "step": 61
     },
     {
       "epoch": 0.4087912087912088,
-      "grad_norm": 0.3393542170524597,
+      "grad_norm": 0.3398084044456482,
       "learning_rate": 0.00017516629711751663,
-      "loss": 1.0621,
+      "loss": 1.062,
       "step": 62
     },
     {
       "epoch": 0.4153846153846154,
-      "grad_norm": 0.29777970910072327,
+      "grad_norm": 0.3010111451148987,
       "learning_rate": 0.0001747228381374723,
-      "loss": 0.9896,
+      "loss": 0.9908,
       "step": 63
     },
     {
       "epoch": 0.421978021978022,
-      "grad_norm": 0.3347181975841522,
+      "grad_norm": 0.3359769284725189,
       "learning_rate": 0.00017427937915742792,
-      "loss": 1.0941,
+      "loss": 1.094,
       "step": 64
     },
     {
       "epoch": 0.42857142857142855,
-      "grad_norm": 0.35212668776512146,
+      "grad_norm": 0.35044530034065247,
       "learning_rate": 0.0001738359201773836,
-      "loss": 0.9955,
+      "loss": 0.9933,
       "step": 65
     },
     {
       "epoch": 0.4351648351648352,
-      "grad_norm": 0.4496903717517853,
+      "grad_norm": 0.4499974548816681,
       "learning_rate": 0.00017339246119733924,
-      "loss": 1.099,
+      "loss": 1.0979,
       "step": 66
     },
     {
       "epoch": 0.44175824175824174,
-      "grad_norm": 0.23707008361816406,
+      "grad_norm": 0.2390085607767105,
       "learning_rate": 0.0001729490022172949,
-      "loss": 0.7456,
+      "loss": 0.7452,
       "step": 67
     },
     {
       "epoch": 0.44835164835164837,
-      "grad_norm": 0.2926875650882721,
+      "grad_norm": 0.2939722239971161,
       "learning_rate": 0.00017250554323725056,
-      "loss": 1.1481,
+      "loss": 1.1464,
       "step": 68
     },
     {
       "epoch": 0.45494505494505494,
-      "grad_norm": 0.42252832651138306,
+      "grad_norm": 0.4215264916419983,
       "learning_rate": 0.00017206208425720623,
-      "loss": 1.0156,
+      "loss": 1.0169,
       "step": 69
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 0.2438354790210724,
+      "grad_norm": 0.24245759844779968,
       "learning_rate": 0.00017161862527716187,
       "loss": 0.7183,
       "step": 70
     },
     {
       "epoch": 0.46813186813186813,
-      "grad_norm": 0.33233973383903503,
+      "grad_norm": 0.33143526315689087,
       "learning_rate": 0.00017117516629711752,
-      "loss": 1.1451,
+      "loss": 1.1435,
       "step": 71
     },
     {
       "epoch": 0.4747252747252747,
-      "grad_norm": 0.30313268303871155,
+      "grad_norm": 0.3057692348957062,
       "learning_rate": 0.0001707317073170732,
-      "loss": 0.7117,
+      "loss": 0.7141,
       "step": 72
     },
     {
       "epoch": 0.48131868131868133,
-      "grad_norm": 0.31673258543014526,
+      "grad_norm": 0.3185351490974426,
       "learning_rate": 0.00017028824833702883,
-      "loss": 0.9695,
+      "loss": 0.9677,
       "step": 73
     },
     {
       "epoch": 0.4879120879120879,
-      "grad_norm": 0.31357434391975403,
+      "grad_norm": 0.3105548322200775,
       "learning_rate": 0.0001698447893569845,
-      "loss": 1.0329,
+      "loss": 1.0319,
       "step": 74
     },
     {
       "epoch": 0.4945054945054945,
-      "grad_norm": 0.26894521713256836,
+      "grad_norm": 0.27544498443603516,
       "learning_rate": 0.00016940133037694015,
-      "loss": 0.8497,
+      "loss": 0.8509,
       "step": 75
     },
     {
       "epoch": 0.5010989010989011,
-      "grad_norm": 0.24665911495685577,
+      "grad_norm": 0.24930939078330994,
       "learning_rate": 0.00016895787139689582,
-      "loss": 0.9803,
+      "loss": 0.9795,
       "step": 76
     },
     {
       "epoch": 0.5076923076923077,
-      "grad_norm": 0.3271327614784241,
+      "grad_norm": 0.326751172542572,
       "learning_rate": 0.00016851441241685144,
-      "loss": 1.0342,
+      "loss": 1.0334,
       "step": 77
     },
     {
       "epoch": 0.5142857142857142,
-      "grad_norm": 0.27658379077911377,
+      "grad_norm": 0.2782577574253082,
       "learning_rate": 0.0001680709534368071,
-      "loss": 0.9028,
+      "loss": 0.9029,
       "step": 78
     },
     {
       "epoch": 0.5208791208791209,
-      "grad_norm": 0.28840765357017517,
+      "grad_norm": 0.29126885533332825,
       "learning_rate": 0.00016762749445676275,
-      "loss": 0.9316,
+      "loss": 0.9306,
       "step": 79
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.25261417031288147,
+      "grad_norm": 0.25332754850387573,
       "learning_rate": 0.00016718403547671842,
-      "loss": 0.9062,
+      "loss": 0.9057,
       "step": 80
     },
     {
       "epoch": 0.5340659340659341,
-      "grad_norm": 0.33007004857063293,
+      "grad_norm": 0.3294142782688141,
       "learning_rate": 0.00016674057649667407,
-      "loss": 0.7618,
+      "loss": 0.7615,
       "step": 81
     },
     {
       "epoch": 0.5406593406593406,
-      "grad_norm": 0.37919148802757263,
+      "grad_norm": 0.39348527789115906,
       "learning_rate": 0.00016629711751662974,
-      "loss": 0.8487,
+      "loss": 0.8525,
       "step": 82
     },
     {
       "epoch": 0.5472527472527473,
-      "grad_norm": 0.3373790979385376,
+      "grad_norm": 0.3311331868171692,
       "learning_rate": 0.00016585365853658536,
-      "loss": 1.0527,
+      "loss": 1.0504,
       "step": 83
     },
     {
       "epoch": 0.5538461538461539,
-      "grad_norm": 0.3170938491821289,
+      "grad_norm": 0.32208502292633057,
       "learning_rate": 0.00016541019955654103,
-      "loss": 1.0429,
+      "loss": 1.043,
       "step": 84
     },
     {
       "epoch": 0.5604395604395604,
-      "grad_norm": 0.3070983290672302,
+      "grad_norm": 0.3057066798210144,
       "learning_rate": 0.00016496674057649667,
-      "loss": 0.917,
+      "loss": 0.9153,
       "step": 85
     },
     {
       "epoch": 0.567032967032967,
-      "grad_norm": 0.3040669560432434,
+      "grad_norm": 0.3061386048793793,
       "learning_rate": 0.00016452328159645234,
-      "loss": 0.8483,
+      "loss": 0.8475,
       "step": 86
     },
     {
       "epoch": 0.5736263736263736,
-      "grad_norm": 0.3397156596183777,
+      "grad_norm": 0.34367796778678894,
       "learning_rate": 0.000164079822616408,
-      "loss": 1.1383,
+      "loss": 1.1397,
       "step": 87
     },
     {
       "epoch": 0.5802197802197803,
-      "grad_norm": 0.3420846164226532,
+      "grad_norm": 0.3496788442134857,
       "learning_rate": 0.00016363636363636366,
-      "loss": 0.9135,
+      "loss": 0.9111,
       "step": 88
     },
     {
       "epoch": 0.5868131868131868,
-      "grad_norm": 0.33865463733673096,
+      "grad_norm": 0.34243008494377136,
       "learning_rate": 0.0001631929046563193,
-      "loss": 0.9746,
+      "loss": 0.9765,
       "step": 89
     },
     {
       "epoch": 0.5934065934065934,
-      "grad_norm": 0.40767139196395874,
+      "grad_norm": 0.4083498418331146,
       "learning_rate": 0.00016274944567627495,
-      "loss": 1.0905,
+      "loss": 1.09,
       "step": 90
     },
     {
       "epoch": 0.6,
-      "grad_norm": 0.32135534286499023,
+      "grad_norm": 0.32501041889190674,
       "learning_rate": 0.0001623059866962306,
-      "loss": 0.9839,
+      "loss": 0.983,
       "step": 91
     },
     {
       "epoch": 0.6065934065934065,
-      "grad_norm": 0.29726099967956543,
+      "grad_norm": 0.2962501645088196,
       "learning_rate": 0.00016186252771618626,
-      "loss": 0.8087,
+      "loss": 0.8079,
       "step": 92
     },
     {
       "epoch": 0.6131868131868132,
-      "grad_norm": 0.3343488574028015,
+      "grad_norm": 0.339017778635025,
       "learning_rate": 0.0001614190687361419,
-      "loss": 1.062,
+      "loss": 1.0645,
       "step": 93
     },
     {
       "epoch": 0.6197802197802198,
-      "grad_norm": 0.3392772972583771,
+      "grad_norm": 0.33595070242881775,
       "learning_rate": 0.00016097560975609758,
-      "loss": 0.9496,
+      "loss": 0.9504,
       "step": 94
     },
     {
       "epoch": 0.6263736263736264,
-      "grad_norm": 0.38109564781188965,
+      "grad_norm": 0.3844953179359436,
       "learning_rate": 0.00016053215077605322,
-      "loss": 0.8332,
+      "loss": 0.8361,
       "step": 95
     },
     {
       "epoch": 0.6329670329670329,
-      "grad_norm": 0.4026820659637451,
+      "grad_norm": 0.4032916724681854,
       "learning_rate": 0.00016008869179600887,
-      "loss": 1.0506,
+      "loss": 1.0501,
       "step": 96
     },
     {
       "epoch": 0.6395604395604395,
-      "grad_norm": 0.32605379819869995,
+      "grad_norm": 0.3297523856163025,
       "learning_rate": 0.00015964523281596454,
-      "loss": 0.9707,
+      "loss": 0.9706,
       "step": 97
     },
     {
       "epoch": 0.6461538461538462,
-      "grad_norm": 0.32885733246803284,
+      "grad_norm": 0.3284400403499603,
       "learning_rate": 0.00015920177383592018,
-      "loss": 0.95,
+      "loss": 0.9507,
       "step": 98
     },
     {
       "epoch": 0.6527472527472528,
-      "grad_norm": 0.2949531078338623,
+      "grad_norm": 0.3026384115219116,
       "learning_rate": 0.00015875831485587586,
-      "loss": 0.9197,
+      "loss": 0.9194,
       "step": 99
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.34610554575920105,
+      "grad_norm": 0.3462526500225067,
       "learning_rate": 0.0001583148558758315,
-      "loss": 0.9544,
+      "loss": 0.9535,
       "step": 100
     },
     {
       "epoch": 0.6659340659340659,
-      "grad_norm": 0.2914392650127411,
+      "grad_norm": 0.2929343283176422,
       "learning_rate": 0.00015787139689578714,
-      "loss": 1.0428,
+      "loss": 1.0426,
       "step": 101
     },
     {
       "epoch": 0.6725274725274726,
-      "grad_norm": 0.33224692940711975,
+      "grad_norm": 0.33232760429382324,
       "learning_rate": 0.0001574279379157428,
-      "loss": 0.9962,
+      "loss": 0.9976,
       "step": 102
     },
     {
       "epoch": 0.6791208791208792,
-      "grad_norm": 0.3527650833129883,
+      "grad_norm": 0.3566662073135376,
       "learning_rate": 0.00015698447893569846,
-      "loss": 0.8515,
+      "loss": 0.8533,
       "step": 103
     },
     {
       "epoch": 0.6857142857142857,
-      "grad_norm": 0.3555796444416046,
+      "grad_norm": 0.3751154839992523,
       "learning_rate": 0.0001565410199556541,
-      "loss": 0.957,
+      "loss": 0.9584,
       "step": 104
     },
     {
       "epoch": 0.6923076923076923,
-      "grad_norm": 0.33348530530929565,
+      "grad_norm": 0.3387792408466339,
       "learning_rate": 0.00015609756097560978,
-      "loss": 0.9111,
+      "loss": 0.9135,
       "step": 105
     },
     {
       "epoch": 0.6989010989010989,
-      "grad_norm": 0.29242005944252014,
+      "grad_norm": 0.2936052978038788,
       "learning_rate": 0.00015565410199556542,
-      "loss": 0.7325,
+      "loss": 0.7321,
       "step": 106
     },
     {
       "epoch": 0.7054945054945055,
-      "grad_norm": 0.3308833837509155,
+      "grad_norm": 0.3313789963722229,
       "learning_rate": 0.00015521064301552106,
-      "loss": 0.9916,
+      "loss": 0.9921,
       "step": 107
     },
     {
       "epoch": 0.7120879120879121,
-      "grad_norm": 0.38151150941848755,
+      "grad_norm": 0.3824083209037781,
       "learning_rate": 0.0001547671840354767,
-      "loss": 0.867,
+      "loss": 0.8662,
       "step": 108
     },
     {
       "epoch": 0.7186813186813187,
-      "grad_norm": 0.2719651758670807,
+      "grad_norm": 0.271816611289978,
       "learning_rate": 0.00015432372505543238,
-      "loss": 0.7214,
+      "loss": 0.7216,
       "step": 109
     },
     {
       "epoch": 0.7252747252747253,
-      "grad_norm": 0.3571125566959381,
+      "grad_norm": 0.3538140654563904,
       "learning_rate": 0.00015388026607538802,
-      "loss": 0.8555,
+      "loss": 0.8546,
       "step": 110
     },
     {
       "epoch": 0.7318681318681318,
-      "grad_norm": 0.3709869980812073,
+      "grad_norm": 0.3695511817932129,
       "learning_rate": 0.0001534368070953437,
-      "loss": 0.9381,
+      "loss": 0.9383,
       "step": 111
     },
     {
       "epoch": 0.7384615384615385,
-      "grad_norm": 0.34119173884391785,
+      "grad_norm": 0.3450765311717987,
       "learning_rate": 0.00015299334811529934,
-      "loss": 1.0286,
+      "loss": 1.0277,
       "step": 112
     },
     {
       "epoch": 0.7450549450549451,
-      "grad_norm": 0.35051465034484863,
+      "grad_norm": 0.3513217270374298,
       "learning_rate": 0.00015254988913525498,
-      "loss": 0.8688,
+      "loss": 0.8685,
       "step": 113
     },
     {
       "epoch": 0.7516483516483516,
-      "grad_norm": 0.3159275949001312,
+      "grad_norm": 0.31267625093460083,
       "learning_rate": 0.00015210643015521066,
-      "loss": 0.9751,
+      "loss": 0.9752,
       "step": 114
     },
     {
       "epoch": 0.7582417582417582,
-      "grad_norm": 0.27043935656547546,
+      "grad_norm": 0.2716124653816223,
       "learning_rate": 0.0001516629711751663,
-      "loss": 0.7634,
+      "loss": 0.7638,
       "step": 115
     },
     {
       "epoch": 0.7648351648351648,
-      "grad_norm": 0.37761369347572327,
+      "grad_norm": 0.3737407922744751,
       "learning_rate": 0.00015121951219512197,
-      "loss": 0.9724,
+      "loss": 0.9719,
       "step": 116
     },
     {
       "epoch": 0.7714285714285715,
-      "grad_norm": 0.3172036111354828,
+      "grad_norm": 0.3199615776538849,
       "learning_rate": 0.00015077605321507762,
-      "loss": 0.8525,
+      "loss": 0.8535,
       "step": 117
     },
     {
       "epoch": 0.778021978021978,
-      "grad_norm": 0.28983673453330994,
+      "grad_norm": 0.29326456785202026,
       "learning_rate": 0.0001503325942350333,
-      "loss": 0.9894,
+      "loss": 0.991,
       "step": 118
     },
     {
       "epoch": 0.7846153846153846,
-      "grad_norm": 0.3155057430267334,
+      "grad_norm": 0.3158397674560547,
       "learning_rate": 0.0001498891352549889,
-      "loss": 0.9778,
+      "loss": 0.9742,
       "step": 119
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.33516910672187805,
+      "grad_norm": 0.340801477432251,
       "learning_rate": 0.00014944567627494458,
-      "loss": 1.0043,
+      "loss": 1.006,
       "step": 120
     },
     {
       "epoch": 0.7978021978021979,
-      "grad_norm": 0.41567182540893555,
+      "grad_norm": 0.4258521795272827,
       "learning_rate": 0.00014900221729490022,
-      "loss": 1.023,
+      "loss": 1.0222,
       "step": 121
     },
     {
       "epoch": 0.8043956043956044,
-      "grad_norm": 0.40814825892448425,
+      "grad_norm": 0.40230363607406616,
       "learning_rate": 0.0001485587583148559,
-      "loss": 1.0267,
+      "loss": 1.0283,
       "step": 122
     },
     {
       "epoch": 0.810989010989011,
-      "grad_norm": 0.297061949968338,
+      "grad_norm": 0.298953652381897,
       "learning_rate": 0.00014811529933481154,
-      "loss": 0.8668,
+      "loss": 0.8674,
       "step": 123
     },
     {
       "epoch": 0.8175824175824176,
-      "grad_norm": 0.3487430512905121,
+      "grad_norm": 0.34640374779701233,
       "learning_rate": 0.0001476718403547672,
-      "loss": 0.9448,
+      "loss": 0.9418,
       "step": 124
     },
     {
       "epoch": 0.8241758241758241,
-      "grad_norm": 0.2947084307670593,
+      "grad_norm": 0.2947790026664734,
       "learning_rate": 0.00014722838137472282,
-      "loss": 0.8624,
+      "loss": 0.8632,
       "step": 125
     },
     {
       "epoch": 0.8307692307692308,
-      "grad_norm": 0.4176642894744873,
+      "grad_norm": 0.42390382289886475,
       "learning_rate": 0.0001467849223946785,
-      "loss": 0.9898,
+      "loss": 0.992,
       "step": 126
     },
     {
       "epoch": 0.8373626373626374,
-      "grad_norm": 0.3396783173084259,
+      "grad_norm": 0.33880630135536194,
       "learning_rate": 0.00014634146341463414,
-      "loss": 0.8457,
+      "loss": 0.8464,
       "step": 127
     },
     {
       "epoch": 0.843956043956044,
-      "grad_norm": 0.30610787868499756,
+      "grad_norm": 0.305600106716156,
       "learning_rate": 0.0001458980044345898,
-      "loss": 0.7489,
+      "loss": 0.7496,
       "step": 128
     },
     {
       "epoch": 0.8505494505494505,
-      "grad_norm": 0.411915123462677,
+      "grad_norm": 0.4102969765663147,
       "learning_rate": 0.00014545454545454546,
-      "loss": 1.0267,
+      "loss": 1.027,
       "step": 129
     },
     {
       "epoch": 0.8571428571428571,
-      "grad_norm": 0.2569451332092285,
+      "grad_norm": 0.25675109028816223,
       "learning_rate": 0.00014501108647450113,
-      "loss": 0.8711,
+      "loss": 0.8703,
       "step": 130
     },
     {
       "epoch": 0.8637362637362638,
-      "grad_norm": 0.3669357895851135,
+      "grad_norm": 0.37069281935691833,
       "learning_rate": 0.00014456762749445675,
-      "loss": 0.978,
+      "loss": 0.9777,
       "step": 131
     },
     {
       "epoch": 0.8703296703296703,
-      "grad_norm": 0.4036771357059479,
+      "grad_norm": 0.4089072644710541,
       "learning_rate": 0.00014412416851441242,
-      "loss": 0.8404,
+      "loss": 0.8419,
       "step": 132
     },
     {
       "epoch": 0.8769230769230769,
-      "grad_norm": 0.30679866671562195,
+      "grad_norm": 0.31191402673721313,
       "learning_rate": 0.00014368070953436806,
-      "loss": 0.9304,
+      "loss": 0.9311,
       "step": 133
     },
     {
       "epoch": 0.8835164835164835,
-      "grad_norm": 0.4402814507484436,
+      "grad_norm": 0.4401726722717285,
       "learning_rate": 0.00014323725055432373,
-      "loss": 0.9296,
+      "loss": 0.9287,
       "step": 134
     },
     {
       "epoch": 0.8901098901098901,
-      "grad_norm": 0.31870439648628235,
+      "grad_norm": 0.3216991424560547,
       "learning_rate": 0.00014279379157427938,
-      "loss": 0.9951,
+      "loss": 0.9944,
       "step": 135
     },
     {
       "epoch": 0.8967032967032967,
-      "grad_norm": 0.36312800645828247,
+      "grad_norm": 0.3641892075538635,
       "learning_rate": 0.00014235033259423505,
-      "loss": 1.0001,
+      "loss": 1.0015,
       "step": 136
     },
     {
       "epoch": 0.9032967032967033,
-      "grad_norm": 0.3176593780517578,
+      "grad_norm": 0.31928136944770813,
       "learning_rate": 0.0001419068736141907,
-      "loss": 0.8874,
+      "loss": 0.888,
       "step": 137
     },
     {
       "epoch": 0.9098901098901099,
-      "grad_norm": 0.34519079327583313,
+      "grad_norm": 0.34381303191185,
       "learning_rate": 0.00014146341463414634,
-      "loss": 0.918,
+      "loss": 0.9181,
       "step": 138
     },
     {
       "epoch": 0.9164835164835164,
-      "grad_norm": 0.34109336137771606,
+      "grad_norm": 0.34465450048446655,
       "learning_rate": 0.000141019955654102,
-      "loss": 0.9881,
+      "loss": 0.9856,
       "step": 139
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.33588215708732605,
+      "grad_norm": 0.34267473220825195,
       "learning_rate": 0.00014057649667405765,
-      "loss": 1.0556,
+      "loss": 1.0567,
       "step": 140
     },
     {
       "epoch": 0.9296703296703297,
-      "grad_norm": 0.3143637180328369,
+      "grad_norm": 0.31306982040405273,
       "learning_rate": 0.00014013303769401332,
-      "loss": 0.8042,
+      "loss": 0.8032,
       "step": 141
     },
     {
       "epoch": 0.9362637362637363,
-      "grad_norm": 0.34192153811454773,
+      "grad_norm": 0.3434275984764099,
       "learning_rate": 0.00013968957871396897,
-      "loss": 0.9389,
+      "loss": 0.9398,
       "step": 142
     },
     {
       "epoch": 0.9428571428571428,
-      "grad_norm": 0.33687394857406616,
+      "grad_norm": 0.33172014355659485,
       "learning_rate": 0.00013924611973392464,
-      "loss": 0.9696,
+      "loss": 0.97,
       "step": 143
     },
     {
       "epoch": 0.9494505494505494,
-      "grad_norm": 0.32633718848228455,
+      "grad_norm": 0.3282938599586487,
       "learning_rate": 0.00013880266075388026,
-      "loss": 0.9389,
+      "loss": 0.9407,
       "step": 144
     },
     {
       "epoch": 0.9560439560439561,
-      "grad_norm": 0.33426982164382935,
+      "grad_norm": 0.332861065864563,
       "learning_rate": 0.00013835920177383593,
-      "loss": 1.0901,
+      "loss": 1.0917,
       "step": 145
     },
     {
       "epoch": 0.9626373626373627,
-      "grad_norm": 0.3398204743862152,
+      "grad_norm": 0.336420476436615,
       "learning_rate": 0.00013791574279379157,
-      "loss": 1.0035,
+      "loss": 1.003,
       "step": 146
     },
     {
       "epoch": 0.9692307692307692,
-      "grad_norm": 0.3482389450073242,
+      "grad_norm": 0.34626010060310364,
       "learning_rate": 0.00013747228381374724,
-      "loss": 1.0233,
+      "loss": 1.0213,
       "step": 147
     },
     {
       "epoch": 0.9758241758241758,
-      "grad_norm": 0.27446088194847107,
+      "grad_norm": 0.2741713225841522,
       "learning_rate": 0.0001370288248337029,
-      "loss": 0.8593,
+      "loss": 0.8592,
       "step": 148
     },
     {
       "epoch": 0.9824175824175824,
-      "grad_norm": 0.3116665184497833,
+      "grad_norm": 0.3122574985027313,
       "learning_rate": 0.00013658536585365856,
-      "loss": 0.9122,
+      "loss": 0.9123,
       "step": 149
     },
     {
       "epoch": 0.989010989010989,
-      "grad_norm": 0.32924315333366394,
+      "grad_norm": 0.32611116766929626,
       "learning_rate": 0.00013614190687361418,
-      "loss": 0.8465,
+      "loss": 0.8468,
       "step": 150
     },
     {
       "epoch": 0.9956043956043956,
-      "grad_norm": 0.3131709396839142,
+      "grad_norm": 0.31028270721435547,
       "learning_rate": 0.00013569844789356985,
-      "loss": 1.1115,
+      "loss": 1.1108,
       "step": 151
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.5639778971672058,
+      "grad_norm": 0.5587679147720337,
       "learning_rate": 0.0001352549889135255,
-      "loss": 1.0023,
+      "loss": 1.0044,
       "step": 152
     },
     {
       "epoch": 1.0065934065934066,
-      "grad_norm": 0.3395214080810547,
+      "grad_norm": 0.34237536787986755,
       "learning_rate": 0.00013481152993348116,
-      "loss": 0.7579,
+      "loss": 0.7587,
       "step": 153
     },
     {
       "epoch": 1.0131868131868131,
-      "grad_norm": 0.4451121985912323,
+      "grad_norm": 0.4465104639530182,
       "learning_rate": 0.0001343680709534368,
-      "loss": 0.9046,
+      "loss": 0.904,
       "step": 154
     },
     {
       "epoch": 1.0197802197802197,
-      "grad_norm": 0.30658870935440063,
+      "grad_norm": 0.30461183190345764,
       "learning_rate": 0.00013392461197339248,
-      "loss": 0.7993,
+      "loss": 0.7978,
       "step": 155
     },
     {
       "epoch": 1.0263736263736263,
-      "grad_norm": 0.3359564542770386,
+      "grad_norm": 0.33155784010887146,
       "learning_rate": 0.00013348115299334812,
-      "loss": 0.9043,
+      "loss": 0.9028,
       "step": 156
     },
     {
       "epoch": 1.032967032967033,
-      "grad_norm": 0.3504899740219116,
+      "grad_norm": 0.3484174311161041,
       "learning_rate": 0.00013303769401330377,
-      "loss": 0.7881,
+      "loss": 0.7883,
       "step": 157
     },
     {
       "epoch": 1.0395604395604396,
-      "grad_norm": 0.3386143445968628,
+      "grad_norm": 0.3378135561943054,
       "learning_rate": 0.00013259423503325944,
-      "loss": 0.9221,
+      "loss": 0.9246,
       "step": 158
     },
     {
       "epoch": 1.0461538461538462,
-      "grad_norm": 0.28975123167037964,
+      "grad_norm": 0.2909366190433502,
       "learning_rate": 0.00013215077605321509,
-      "loss": 0.7426,
+      "loss": 0.7427,
       "step": 159
     },
     {
       "epoch": 1.0527472527472528,
-      "grad_norm": 0.3702305853366852,
+      "grad_norm": 0.370918869972229,
       "learning_rate": 0.00013170731707317076,
-      "loss": 0.7627,
+      "loss": 0.762,
       "step": 160
     },
     {
       "epoch": 1.0593406593406594,
-      "grad_norm": 0.394538551568985,
+      "grad_norm": 0.3959696888923645,
       "learning_rate": 0.0001312638580931264,
-      "loss": 0.9105,
+      "loss": 0.9099,
       "step": 161
     },
     {
       "epoch": 1.065934065934066,
-      "grad_norm": 0.3724621832370758,
+      "grad_norm": 0.36984387040138245,
       "learning_rate": 0.00013082039911308205,
-      "loss": 0.9514,
+      "loss": 0.9537,
       "step": 162
     },
     {
       "epoch": 1.0725274725274725,
-      "grad_norm": 0.3351310193538666,
+      "grad_norm": 0.33510100841522217,
       "learning_rate": 0.0001303769401330377,
-      "loss": 0.863,
+      "loss": 0.8638,
       "step": 163
     },
     {
       "epoch": 1.079120879120879,
-      "grad_norm": 0.3554590344429016,
+      "grad_norm": 0.35161909461021423,
       "learning_rate": 0.00012993348115299336,
-      "loss": 0.9837,
+      "loss": 0.9841,
       "step": 164
     },
     {
       "epoch": 1.0857142857142856,
-      "grad_norm": 0.3050754964351654,
+      "grad_norm": 0.3048061728477478,
       "learning_rate": 0.000129490022172949,
       "loss": 0.7628,
       "step": 165
     },
     {
       "epoch": 1.0923076923076924,
-      "grad_norm": 0.35037916898727417,
+      "grad_norm": 0.35248255729675293,
       "learning_rate": 0.00012904656319290468,
-      "loss": 0.8715,
+      "loss": 0.8721,
       "step": 166
     },
     {
       "epoch": 1.098901098901099,
-      "grad_norm": 0.4356972873210907,
+      "grad_norm": 0.43364354968070984,
       "learning_rate": 0.00012860310421286032,
       "loss": 0.8514,
       "step": 167
     },
     {
       "epoch": 1.1054945054945056,
-      "grad_norm": 0.44227975606918335,
+      "grad_norm": 0.4386586546897888,
       "learning_rate": 0.00012815964523281597,
-      "loss": 0.8368,
+      "loss": 0.8363,
       "step": 168
     },
     {
       "epoch": 1.1120879120879121,
-      "grad_norm": 0.41575899720191956,
+      "grad_norm": 0.4130457639694214,
       "learning_rate": 0.0001277161862527716,
-      "loss": 0.9083,
+      "loss": 0.9079,
       "step": 169
     },
     {
       "epoch": 1.1186813186813187,
-      "grad_norm": 0.32656052708625793,
+      "grad_norm": 0.32351064682006836,
       "learning_rate": 0.00012727272727272728,
-      "loss": 0.7544,
+      "loss": 0.7551,
       "step": 170
     },
     {
       "epoch": 1.1252747252747253,
-      "grad_norm": 0.4732937812805176,
+      "grad_norm": 0.47145897150039673,
       "learning_rate": 0.00012682926829268293,
-      "loss": 1.0187,
+      "loss": 1.0163,
       "step": 171
     },
     {
       "epoch": 1.1318681318681318,
-      "grad_norm": 0.3214307427406311,
+      "grad_norm": 0.31925448775291443,
       "learning_rate": 0.0001263858093126386,
-      "loss": 0.8781,
+      "loss": 0.877,
       "step": 172
     },
     {
       "epoch": 1.1384615384615384,
-      "grad_norm": 0.4291451573371887,
+      "grad_norm": 0.42638224363327026,
       "learning_rate": 0.00012594235033259424,
-      "loss": 0.869,
+      "loss": 0.867,
       "step": 173
     },
     {
       "epoch": 1.145054945054945,
-      "grad_norm": 0.4516123831272125,
+      "grad_norm": 0.4519364535808563,
       "learning_rate": 0.00012549889135254989,
-      "loss": 0.9012,
+      "loss": 0.8992,
       "step": 174
     },
     {
       "epoch": 1.1516483516483516,
-      "grad_norm": 0.39512842893600464,
+      "grad_norm": 0.39410778880119324,
       "learning_rate": 0.00012505543237250553,
-      "loss": 0.897,
+      "loss": 0.8946,
       "step": 175
     },
     {
       "epoch": 1.1582417582417581,
-      "grad_norm": 0.32635363936424255,
+      "grad_norm": 0.32669949531555176,
       "learning_rate": 0.0001246119733924612,
-      "loss": 0.7872,
+      "loss": 0.7879,
       "step": 176
     },
     {
       "epoch": 1.164835164835165,
-      "grad_norm": 0.34062984585762024,
+      "grad_norm": 0.3455027639865875,
       "learning_rate": 0.00012416851441241685,
-      "loss": 0.7698,
+      "loss": 0.7705,
       "step": 177
     },
     {
       "epoch": 1.1714285714285715,
-      "grad_norm": 0.4236986041069031,
+      "grad_norm": 0.42715129256248474,
       "learning_rate": 0.00012372505543237252,
-      "loss": 0.8203,
+      "loss": 0.8197,
       "step": 178
     },
     {
       "epoch": 1.178021978021978,
-      "grad_norm": 0.3937680721282959,
+      "grad_norm": 0.3946492671966553,
       "learning_rate": 0.00012328159645232816,
       "loss": 0.6399,
       "step": 179
     },
     {
       "epoch": 1.1846153846153846,
-      "grad_norm": 0.45519042015075684,
+      "grad_norm": 0.45343202352523804,
       "learning_rate": 0.0001228381374722838,
-      "loss": 0.9213,
+      "loss": 0.925,
       "step": 180
     },
     {
       "epoch": 1.1912087912087912,
-      "grad_norm": 0.44973817467689514,
+      "grad_norm": 0.44791096448898315,
       "learning_rate": 0.00012239467849223948,
-      "loss": 0.9743,
+      "loss": 0.9734,
       "step": 181
     },
     {
       "epoch": 1.1978021978021978,
-      "grad_norm": 0.42643284797668457,
+      "grad_norm": 0.4247220456600189,
       "learning_rate": 0.00012195121951219512,
-      "loss": 0.9751,
+      "loss": 0.9757,
       "step": 182
     },
     {
       "epoch": 1.2043956043956043,
-      "grad_norm": 0.41849836707115173,
+      "grad_norm": 0.4177721440792084,
       "learning_rate": 0.00012150776053215078,
-      "loss": 0.8524,
+      "loss": 0.8537,
       "step": 183
     },
     {
       "epoch": 1.210989010989011,
-      "grad_norm": 0.48973095417022705,
+      "grad_norm": 0.47911062836647034,
       "learning_rate": 0.00012106430155210644,
-      "loss": 0.722,
+      "loss": 0.7214,
       "step": 184
     },
     {
       "epoch": 1.2175824175824177,
-      "grad_norm": 0.4730561077594757,
+      "grad_norm": 0.470956951379776,
       "learning_rate": 0.0001206208425720621,
-      "loss": 0.8323,
+      "loss": 0.8312,
       "step": 185
     },
     {
       "epoch": 1.2241758241758243,
-      "grad_norm": 0.43756726384162903,
+      "grad_norm": 0.4381925165653229,
       "learning_rate": 0.00012017738359201774,
-      "loss": 0.8261,
+      "loss": 0.8253,
       "step": 186
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 0.34324491024017334,
+      "grad_norm": 0.3466181457042694,
       "learning_rate": 0.0001197339246119734,
-      "loss": 0.7222,
+      "loss": 0.7228,
       "step": 187
     },
     {
       "epoch": 1.2373626373626374,
-      "grad_norm": 0.4662308990955353,
+      "grad_norm": 0.47227564454078674,
       "learning_rate": 0.00011929046563192906,
-      "loss": 0.9886,
+      "loss": 0.9872,
       "step": 188
     },
     {
       "epoch": 1.243956043956044,
-      "grad_norm": 0.39682698249816895,
+      "grad_norm": 0.3967965543270111,
       "learning_rate": 0.00011884700665188471,
-      "loss": 0.8586,
+      "loss": 0.8568,
       "step": 189
     },
     {
       "epoch": 1.2505494505494505,
-      "grad_norm": 0.4866606891155243,
+      "grad_norm": 0.4912855923175812,
       "learning_rate": 0.00011840354767184036,
-      "loss": 0.9655,
+      "loss": 0.9629,
       "step": 190
     },
     {
       "epoch": 1.2571428571428571,
-      "grad_norm": 0.43162989616394043,
+      "grad_norm": 0.4317874312400818,
       "learning_rate": 0.00011796008869179602,
-      "loss": 0.8334,
+      "loss": 0.8323,
       "step": 191
     },
     {
       "epoch": 1.2637362637362637,
-      "grad_norm": 0.4115634560585022,
+      "grad_norm": 0.4118874967098236,
       "learning_rate": 0.00011751662971175166,
-      "loss": 0.9202,
+      "loss": 0.9194,
       "step": 192
     },
     {
       "epoch": 1.2703296703296703,
-      "grad_norm": 0.45951539278030396,
+      "grad_norm": 0.4587341547012329,
       "learning_rate": 0.00011707317073170732,
-      "loss": 0.903,
+      "loss": 0.9024,
       "step": 193
     },
     {
       "epoch": 1.2769230769230768,
-      "grad_norm": 0.4265710413455963,
+      "grad_norm": 0.4255760908126831,
       "learning_rate": 0.00011662971175166298,
-      "loss": 0.7974,
+      "loss": 0.7961,
       "step": 194
     },
     {
       "epoch": 1.2835164835164834,
-      "grad_norm": 0.4018781781196594,
+      "grad_norm": 0.39803823828697205,
       "learning_rate": 0.00011618625277161863,
-      "loss": 0.7937,
+      "loss": 0.793,
       "step": 195
     },
     {
       "epoch": 1.2901098901098902,
-      "grad_norm": 0.33751317858695984,
+      "grad_norm": 0.33639976382255554,
       "learning_rate": 0.00011574279379157429,
-      "loss": 0.958,
+      "loss": 0.9582,
       "step": 196
     },
     {
       "epoch": 1.2967032967032968,
-      "grad_norm": 0.5202163457870483,
+      "grad_norm": 0.5177255868911743,
       "learning_rate": 0.00011529933481152995,
-      "loss": 0.8871,
+      "loss": 0.8881,
       "step": 197
     },
     {
       "epoch": 1.3032967032967033,
-      "grad_norm": 0.5462297797203064,
+      "grad_norm": 0.5451109409332275,
       "learning_rate": 0.00011485587583148558,
-      "loss": 0.8778,
+      "loss": 0.8771,
       "step": 198
     },
     {
       "epoch": 1.30989010989011,
-      "grad_norm": 0.5294543504714966,
+      "grad_norm": 0.5325527787208557,
       "learning_rate": 0.00011441241685144124,
-      "loss": 0.8053,
+      "loss": 0.8054,
       "step": 199
     },
     {
       "epoch": 1.3164835164835165,
-      "grad_norm": 0.508984386920929,
+      "grad_norm": 0.5048739910125732,
       "learning_rate": 0.0001139689578713969,
-      "loss": 0.9449,
+      "loss": 0.9425,
       "step": 200
     },
     {
       "epoch": 1.323076923076923,
-      "grad_norm": 0.4766629934310913,
+      "grad_norm": 0.477891206741333,
       "learning_rate": 0.00011352549889135255,
-      "loss": 0.9975,
+      "loss": 0.9965,
       "step": 201
     },
     {
       "epoch": 1.3296703296703296,
-      "grad_norm": 0.4836457073688507,
+      "grad_norm": 0.4765445291996002,
       "learning_rate": 0.00011308203991130821,
-      "loss": 1.0674,
+      "loss": 1.0682,
       "step": 202
     },
     {
       "epoch": 1.3362637362637364,
-      "grad_norm": 0.4459066689014435,
+      "grad_norm": 0.44138312339782715,
       "learning_rate": 0.00011263858093126387,
-      "loss": 0.9403,
+      "loss": 0.9393,
       "step": 203
     },
     {
       "epoch": 1.342857142857143,
-      "grad_norm": 0.49527183175086975,
+      "grad_norm": 0.49631035327911377,
       "learning_rate": 0.00011219512195121953,
-      "loss": 1.0174,
+      "loss": 1.018,
       "step": 204
     },
     {
       "epoch": 1.3494505494505495,
-      "grad_norm": 0.4496254026889801,
+      "grad_norm": 0.4567028284072876,
       "learning_rate": 0.00011175166297117516,
-      "loss": 0.8753,
+      "loss": 0.8774,
       "step": 205
     },
     {
       "epoch": 1.3560439560439561,
-      "grad_norm": 0.5478966236114502,
+      "grad_norm": 0.55516117811203,
       "learning_rate": 0.00011130820399113082,
-      "loss": 1.0999,
+      "loss": 1.1016,
       "step": 206
     },
     {
       "epoch": 1.3626373626373627,
-      "grad_norm": 0.4426548182964325,
+      "grad_norm": 0.4408508539199829,
       "learning_rate": 0.00011086474501108647,
-      "loss": 0.7285,
+      "loss": 0.7284,
       "step": 207
     },
     {
       "epoch": 1.3692307692307693,
-      "grad_norm": 0.5293945670127869,
+      "grad_norm": 0.5260791778564453,
       "learning_rate": 0.00011042128603104213,
-      "loss": 0.9999,
+      "loss": 0.9981,
       "step": 208
     },
     {
       "epoch": 1.3758241758241758,
-      "grad_norm": 0.47293853759765625,
+      "grad_norm": 0.47149479389190674,
       "learning_rate": 0.00010997782705099779,
-      "loss": 0.7832,
+      "loss": 0.782,
       "step": 209
     },
     {
       "epoch": 1.3824175824175824,
-      "grad_norm": 0.47598668932914734,
+      "grad_norm": 0.4713144600391388,
       "learning_rate": 0.00010953436807095345,
-      "loss": 0.8358,
+      "loss": 0.8344,
       "step": 210
     },
     {
       "epoch": 1.389010989010989,
-      "grad_norm": 0.426973432302475,
+      "grad_norm": 0.4286600351333618,
       "learning_rate": 0.00010909090909090909,
-      "loss": 0.7659,
+      "loss": 0.7674,
       "step": 211
     },
     {
       "epoch": 1.3956043956043955,
-      "grad_norm": 0.4742601215839386,
+      "grad_norm": 0.47824904322624207,
       "learning_rate": 0.00010864745011086475,
-      "loss": 0.8223,
+      "loss": 0.8219,
       "step": 212
     },
     {
       "epoch": 1.402197802197802,
-      "grad_norm": 0.5977970957756042,
+      "grad_norm": 0.5984587073326111,
       "learning_rate": 0.00010820399113082041,
-      "loss": 0.8722,
+      "loss": 0.8736,
       "step": 213
     },
     {
       "epoch": 1.4087912087912087,
-      "grad_norm": 0.4443981647491455,
+      "grad_norm": 0.4488672912120819,
       "learning_rate": 0.00010776053215077607,
-      "loss": 0.842,
+      "loss": 0.8427,
       "step": 214
     },
     {
       "epoch": 1.4153846153846155,
-      "grad_norm": 0.5637273788452148,
+      "grad_norm": 0.562637448310852,
       "learning_rate": 0.00010731707317073172,
-      "loss": 0.9229,
+      "loss": 0.9239,
       "step": 215
     },
     {
       "epoch": 1.421978021978022,
-      "grad_norm": 0.4368816018104553,
+      "grad_norm": 0.43384426832199097,
       "learning_rate": 0.00010687361419068738,
-      "loss": 0.8706,
+      "loss": 0.8691,
       "step": 216
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.47785332798957825,
+      "grad_norm": 0.47463458776474,
       "learning_rate": 0.00010643015521064301,
-      "loss": 0.8216,
+      "loss": 0.8234,
       "step": 217
     },
     {
       "epoch": 1.4351648351648352,
-      "grad_norm": 0.5267130136489868,
+      "grad_norm": 0.5394907593727112,
       "learning_rate": 0.00010598669623059867,
-      "loss": 0.8562,
+      "loss": 0.8585,
       "step": 218
     },
     {
       "epoch": 1.4417582417582417,
-      "grad_norm": 0.4472438097000122,
+      "grad_norm": 0.4483904242515564,
       "learning_rate": 0.00010554323725055433,
-      "loss": 0.6763,
+      "loss": 0.6775,
       "step": 219
     },
     {
       "epoch": 1.4483516483516483,
-      "grad_norm": 0.5247462391853333,
+      "grad_norm": 0.5243779420852661,
       "learning_rate": 0.00010509977827050999,
-      "loss": 0.9322,
+      "loss": 0.934,
       "step": 220
     },
     {
       "epoch": 1.4549450549450549,
-      "grad_norm": 0.5785446763038635,
+      "grad_norm": 0.5830507278442383,
       "learning_rate": 0.00010465631929046564,
-      "loss": 0.8836,
+      "loss": 0.8841,
       "step": 221
     },
     {
       "epoch": 1.4615384615384617,
-      "grad_norm": 0.5753875970840454,
+      "grad_norm": 0.587237536907196,
       "learning_rate": 0.0001042128603104213,
-      "loss": 0.9538,
+      "loss": 0.9594,
       "step": 222
     },
     {
       "epoch": 1.4681318681318682,
-      "grad_norm": 0.4653920829296112,
+      "grad_norm": 0.46859410405158997,
       "learning_rate": 0.00010376940133037693,
-      "loss": 0.8921,
+      "loss": 0.8952,
       "step": 223
     },
     {
       "epoch": 1.4747252747252748,
-      "grad_norm": 0.6153593063354492,
+      "grad_norm": 0.619542121887207,
       "learning_rate": 0.00010332594235033259,
-      "loss": 0.9249,
+      "loss": 0.9253,
       "step": 224
     },
     {
       "epoch": 1.4813186813186814,
-      "grad_norm": 0.41231054067611694,
+      "grad_norm": 0.41206881403923035,
       "learning_rate": 0.00010288248337028825,
-      "loss": 0.7862,
+      "loss": 0.7864,
       "step": 225
     },
     {
       "epoch": 1.487912087912088,
-      "grad_norm": 0.42926061153411865,
+      "grad_norm": 0.42798635363578796,
       "learning_rate": 0.0001024390243902439,
-      "loss": 0.6944,
+      "loss": 0.6949,
       "step": 226
     },
     {
       "epoch": 1.4945054945054945,
-      "grad_norm": 0.5749198198318481,
+      "grad_norm": 0.5727190971374512,
       "learning_rate": 0.00010199556541019956,
-      "loss": 0.8639,
+      "loss": 0.8635,
       "step": 227
     },
     {
       "epoch": 1.501098901098901,
-      "grad_norm": 0.5089406967163086,
+      "grad_norm": 0.5052634477615356,
       "learning_rate": 0.00010155210643015522,
-      "loss": 0.848,
+      "loss": 0.8481,
       "step": 228
     },
     {
       "epoch": 1.5076923076923077,
-      "grad_norm": 0.47087109088897705,
+      "grad_norm": 0.4678313732147217,
       "learning_rate": 0.00010110864745011087,
-      "loss": 0.7546,
+      "loss": 0.7565,
       "step": 229
     },
     {
       "epoch": 1.5142857142857142,
-      "grad_norm": 0.48008468747138977,
+      "grad_norm": 0.4803018867969513,
       "learning_rate": 0.00010066518847006652,
-      "loss": 0.7108,
+      "loss": 0.7101,
       "step": 230
     },
     {
       "epoch": 1.5208791208791208,
-      "grad_norm": 0.5517432689666748,
+      "grad_norm": 0.5546374917030334,
       "learning_rate": 0.00010022172949002218,
-      "loss": 0.7404,
+      "loss": 0.7391,
       "step": 231
     },
     {
       "epoch": 1.5274725274725274,
-      "grad_norm": 0.5300886631011963,
+      "grad_norm": 0.5278930068016052,
       "learning_rate": 9.977827050997783e-05,
-      "loss": 0.764,
+      "loss": 0.7634,
       "step": 232
     },
     {
       "epoch": 1.534065934065934,
-      "grad_norm": 0.5006000995635986,
+      "grad_norm": 0.5004315972328186,
       "learning_rate": 9.933481152993348e-05,
-      "loss": 0.7367,
+      "loss": 0.7371,
       "step": 233
     },
     {
       "epoch": 1.5406593406593405,
-      "grad_norm": 0.49519893527030945,
+      "grad_norm": 0.4936966598033905,
       "learning_rate": 9.889135254988914e-05,
-      "loss": 0.9038,
+      "loss": 0.901,
       "step": 234
     },
     {
       "epoch": 1.5472527472527473,
-      "grad_norm": 0.5353063344955444,
+      "grad_norm": 0.5347455739974976,
       "learning_rate": 9.84478935698448e-05,
-      "loss": 0.9174,
+      "loss": 0.9187,
       "step": 235
     },
     {
       "epoch": 1.5538461538461539,
-      "grad_norm": 0.4727020859718323,
+      "grad_norm": 0.4705422818660736,
       "learning_rate": 9.800443458980046e-05,
-      "loss": 0.859,
+      "loss": 0.8574,
       "step": 236
     },
     {
       "epoch": 1.5604395604395604,
-      "grad_norm": 0.4980611801147461,
+      "grad_norm": 0.4970325827598572,
       "learning_rate": 9.75609756097561e-05,
-      "loss": 1.0518,
+      "loss": 1.0511,
       "step": 237
     },
     {
       "epoch": 1.567032967032967,
-      "grad_norm": 0.4948464632034302,
+      "grad_norm": 0.49616602063179016,
       "learning_rate": 9.711751662971176e-05,
-      "loss": 0.8243,
+      "loss": 0.8263,
       "step": 238
     },
     {
       "epoch": 1.5736263736263736,
-      "grad_norm": 0.5270423889160156,
+      "grad_norm": 0.5309842228889465,
       "learning_rate": 9.667405764966742e-05,
-      "loss": 0.9291,
+      "loss": 0.9275,
       "step": 239
     },
     {
       "epoch": 1.5802197802197804,
-      "grad_norm": 0.5233663320541382,
+      "grad_norm": 0.5249683856964111,
       "learning_rate": 9.623059866962306e-05,
-      "loss": 1.0248,
+      "loss": 1.0206,
       "step": 240
     },
     {
       "epoch": 1.586813186813187,
-      "grad_norm": 0.590831458568573,
+      "grad_norm": 0.5909983515739441,
       "learning_rate": 9.578713968957872e-05,
-      "loss": 1.119,
+      "loss": 1.1204,
       "step": 241
     },
     {
       "epoch": 1.5934065934065935,
-      "grad_norm": 0.5016458034515381,
+      "grad_norm": 0.4994933605194092,
       "learning_rate": 9.534368070953438e-05,
-      "loss": 0.9389,
+      "loss": 0.9374,
       "step": 242
     },
     {
       "epoch": 1.6,
-      "grad_norm": 0.5507176518440247,
+      "grad_norm": 0.5519099235534668,
       "learning_rate": 9.490022172949002e-05,
-      "loss": 0.7676,
+      "loss": 0.7673,
       "step": 243
     },
     {
       "epoch": 1.6065934065934067,
-      "grad_norm": 0.49372318387031555,
+      "grad_norm": 0.49864885210990906,
       "learning_rate": 9.445676274944568e-05,
-      "loss": 0.8448,
+      "loss": 0.8424,
       "step": 244
     },
     {
       "epoch": 1.6131868131868132,
-      "grad_norm": 0.5039417147636414,
+      "grad_norm": 0.5097473859786987,
       "learning_rate": 9.401330376940134e-05,
-      "loss": 0.8028,
+      "loss": 0.803,
       "step": 245
     },
     {
       "epoch": 1.6197802197802198,
-      "grad_norm": 0.5067917704582214,
+      "grad_norm": 0.512746274471283,
       "learning_rate": 9.356984478935698e-05,
-      "loss": 0.8708,
+      "loss": 0.8722,
       "step": 246
     },
     {
       "epoch": 1.6263736263736264,
-      "grad_norm": 0.517314076423645,
+      "grad_norm": 0.5191940069198608,
       "learning_rate": 9.312638580931264e-05,
-      "loss": 0.748,
+      "loss": 0.7468,
       "step": 247
     },
     {
       "epoch": 1.632967032967033,
-      "grad_norm": 0.5289116501808167,
+      "grad_norm": 0.532005786895752,
       "learning_rate": 9.26829268292683e-05,
-      "loss": 0.9131,
+      "loss": 0.914,
       "step": 248
     },
     {
       "epoch": 1.6395604395604395,
-      "grad_norm": 0.515396773815155,
+      "grad_norm": 0.5155553221702576,
       "learning_rate": 9.223946784922394e-05,
-      "loss": 0.6893,
+      "loss": 0.6895,
       "step": 249
     },
     {
       "epoch": 1.646153846153846,
-      "grad_norm": 0.4606779217720032,
+      "grad_norm": 0.4564570486545563,
       "learning_rate": 9.17960088691796e-05,
-      "loss": 0.6963,
+      "loss": 0.6956,
       "step": 250
     },
     {
       "epoch": 1.6527472527472526,
-      "grad_norm": 0.626171350479126,
+      "grad_norm": 0.6313489079475403,
       "learning_rate": 9.135254988913526e-05,
-      "loss": 0.8437,
+      "loss": 0.8443,
       "step": 251
     },
     {
       "epoch": 1.6593406593406592,
-      "grad_norm": 0.5930360555648804,
+      "grad_norm": 0.5917752981185913,
       "learning_rate": 9.090909090909092e-05,
-      "loss": 0.818,
+      "loss": 0.8156,
       "step": 252
     },
     {
       "epoch": 1.6659340659340658,
-      "grad_norm": 0.5804259181022644,
+      "grad_norm": 0.5950708985328674,
       "learning_rate": 9.046563192904656e-05,
-      "loss": 0.9461,
+      "loss": 0.9472,
       "step": 253
     },
     {
       "epoch": 1.6725274725274726,
-      "grad_norm": 0.5499175190925598,
+      "grad_norm": 0.5504249930381775,
       "learning_rate": 9.002217294900222e-05,
-      "loss": 0.8106,
+      "loss": 0.8124,
       "step": 254
     },
     {
       "epoch": 1.6791208791208792,
-      "grad_norm": 0.3868570625782013,
+      "grad_norm": 0.3866679072380066,
       "learning_rate": 8.957871396895788e-05,
-      "loss": 0.6983,
+      "loss": 0.6982,
       "step": 255
     },
     {
       "epoch": 1.6857142857142857,
-      "grad_norm": 0.572151243686676,
+      "grad_norm": 0.5705950856208801,
       "learning_rate": 8.913525498891354e-05,
-      "loss": 0.7609,
+      "loss": 0.7596,
       "step": 256
     },
     {
       "epoch": 1.6923076923076923,
-      "grad_norm": 0.5721766948699951,
+      "grad_norm": 0.5793991088867188,
       "learning_rate": 8.869179600886919e-05,
-      "loss": 0.8263,
+      "loss": 0.8257,
       "step": 257
     },
     {
       "epoch": 1.6989010989010989,
-      "grad_norm": 0.5553361773490906,
+      "grad_norm": 0.5562020540237427,
       "learning_rate": 8.824833702882484e-05,
-      "loss": 0.9169,
+      "loss": 0.9161,
       "step": 258
     },
     {
       "epoch": 1.7054945054945057,
-      "grad_norm": 0.5333415865898132,
+      "grad_norm": 0.5355163812637329,
       "learning_rate": 8.78048780487805e-05,
-      "loss": 1.0914,
+      "loss": 1.0931,
       "step": 259
     },
     {
       "epoch": 1.7120879120879122,
-      "grad_norm": 0.44406670331954956,
+      "grad_norm": 0.4376404285430908,
       "learning_rate": 8.736141906873615e-05,
-      "loss": 0.7741,
+      "loss": 0.7723,
       "step": 260
     },
     {
       "epoch": 1.7186813186813188,
-      "grad_norm": 0.5063455700874329,
+      "grad_norm": 0.5053808093070984,
       "learning_rate": 8.69179600886918e-05,
-      "loss": 0.9668,
+      "loss": 0.9649,
       "step": 261
     },
     {
       "epoch": 1.7252747252747254,
-      "grad_norm": 0.5529189705848694,
+      "grad_norm": 0.5418540835380554,
       "learning_rate": 8.647450110864746e-05,
-      "loss": 0.9054,
+      "loss": 0.9049,
       "step": 262
     },
     {
       "epoch": 1.731868131868132,
-      "grad_norm": 0.5595840215682983,
+      "grad_norm": 0.557334303855896,
       "learning_rate": 8.603104212860311e-05,
-      "loss": 0.816,
+      "loss": 0.8178,
       "step": 263
     },
     {
       "epoch": 1.7384615384615385,
-      "grad_norm": 0.5390612483024597,
+      "grad_norm": 0.5328534245491028,
       "learning_rate": 8.558758314855876e-05,
-      "loss": 0.7387,
+      "loss": 0.7365,
       "step": 264
     },
     {
       "epoch": 1.745054945054945,
-      "grad_norm": 0.5740283727645874,
+      "grad_norm": 0.5694268941879272,
       "learning_rate": 8.514412416851442e-05,
-      "loss": 0.9647,
+      "loss": 0.962,
       "step": 265
     },
     {
       "epoch": 1.7516483516483516,
-      "grad_norm": 0.6255824565887451,
+      "grad_norm": 0.615943431854248,
       "learning_rate": 8.470066518847007e-05,
-      "loss": 1.01,
+      "loss": 1.0112,
       "step": 266
     },
     {
       "epoch": 1.7582417582417582,
-      "grad_norm": 0.5318125486373901,
+      "grad_norm": 0.5294637680053711,
       "learning_rate": 8.425720620842572e-05,
-      "loss": 0.8678,
+      "loss": 0.8686,
       "step": 267
     },
     {
       "epoch": 1.7648351648351648,
-      "grad_norm": 0.4187081754207611,
+      "grad_norm": 0.41722503304481506,
       "learning_rate": 8.381374722838138e-05,
-      "loss": 0.859,
+      "loss": 0.8581,
       "step": 268
     },
     {
       "epoch": 1.7714285714285714,
-      "grad_norm": 0.5770336985588074,
+      "grad_norm": 0.5750018954277039,
       "learning_rate": 8.337028824833703e-05,
-      "loss": 0.8747,
+      "loss": 0.8743,
       "step": 269
     },
     {
       "epoch": 1.778021978021978,
-      "grad_norm": 0.4633336067199707,
+      "grad_norm": 0.46019288897514343,
       "learning_rate": 8.292682926829268e-05,
-      "loss": 0.9147,
+      "loss": 0.9135,
       "step": 270
     },
     {
       "epoch": 1.7846153846153845,
-      "grad_norm": 0.4776274859905243,
+      "grad_norm": 0.47639933228492737,
       "learning_rate": 8.248337028824834e-05,
-      "loss": 0.9318,
+      "loss": 0.9316,
       "step": 271
     },
     {
       "epoch": 1.791208791208791,
-      "grad_norm": 0.7317682504653931,
+      "grad_norm": 0.7167646884918213,
       "learning_rate": 8.2039911308204e-05,
-      "loss": 0.9723,
+      "loss": 0.9709,
       "step": 272
     },
     {
       "epoch": 1.7978021978021979,
-      "grad_norm": 0.5217792987823486,
+      "grad_norm": 0.5192975401878357,
       "learning_rate": 8.159645232815965e-05,
-      "loss": 0.9407,
+      "loss": 0.9414,
       "step": 273
     },
     {
       "epoch": 1.8043956043956044,
-      "grad_norm": 0.5275446772575378,
+      "grad_norm": 0.5262181162834167,
       "learning_rate": 8.11529933481153e-05,
-      "loss": 0.8643,
+      "loss": 0.8627,
       "step": 274
     },
     {
       "epoch": 1.810989010989011,
-      "grad_norm": 0.669671356678009,
+      "grad_norm": 0.6696521043777466,
       "learning_rate": 8.070953436807095e-05,
-      "loss": 0.8596,
+      "loss": 0.8618,
       "step": 275
     },
     {
       "epoch": 1.8175824175824176,
-      "grad_norm": 0.5502275824546814,
+      "grad_norm": 0.5426575541496277,
       "learning_rate": 8.026607538802661e-05,
-      "loss": 0.8945,
+      "loss": 0.8942,
       "step": 276
     },
     {
       "epoch": 1.8241758241758241,
-      "grad_norm": 0.5572497248649597,
+      "grad_norm": 0.5545498132705688,
       "learning_rate": 7.982261640798227e-05,
-      "loss": 0.9932,
+      "loss": 0.9942,
       "step": 277
     },
     {
       "epoch": 1.830769230769231,
-      "grad_norm": 0.42105263471603394,
+      "grad_norm": 0.42044493556022644,
       "learning_rate": 7.937915742793793e-05,
-      "loss": 0.7142,
+      "loss": 0.7124,
       "step": 278
     },
     {
       "epoch": 1.8373626373626375,
-      "grad_norm": 0.5113288164138794,
+      "grad_norm": 0.5082975625991821,
       "learning_rate": 7.893569844789357e-05,
-      "loss": 0.7668,
+      "loss": 0.7645,
       "step": 279
     },
     {
       "epoch": 1.843956043956044,
-      "grad_norm": 0.4879838824272156,
+      "grad_norm": 0.489961713552475,
       "learning_rate": 7.849223946784923e-05,
-      "loss": 0.8119,
+      "loss": 0.812,
       "step": 280
     },
     {
       "epoch": 1.8505494505494506,
-      "grad_norm": 0.5138363242149353,
+      "grad_norm": 0.5158363580703735,
       "learning_rate": 7.804878048780489e-05,
-      "loss": 0.86,
+      "loss": 0.8612,
       "step": 281
     },
     {
       "epoch": 1.8571428571428572,
-      "grad_norm": 0.42918461561203003,
+      "grad_norm": 0.43079808354377747,
       "learning_rate": 7.760532150776053e-05,
-      "loss": 0.7694,
+      "loss": 0.7685,
       "step": 282
     },
     {
       "epoch": 1.8637362637362638,
-      "grad_norm": 0.5903877019882202,
+      "grad_norm": 0.5886262655258179,
       "learning_rate": 7.716186252771619e-05,
-      "loss": 0.8804,
+      "loss": 0.8799,
       "step": 283
     },
     {
       "epoch": 1.8703296703296703,
-      "grad_norm": 0.5936295986175537,
+      "grad_norm": 0.5958455801010132,
       "learning_rate": 7.671840354767185e-05,
-      "loss": 0.7532,
+      "loss": 0.7535,
       "step": 284
     },
     {
       "epoch": 1.876923076923077,
-      "grad_norm": 0.5549003481864929,
+      "grad_norm": 0.5544354319572449,
       "learning_rate": 7.627494456762749e-05,
-      "loss": 0.8225,
+      "loss": 0.8202,
       "step": 285
     },
     {
       "epoch": 1.8835164835164835,
-      "grad_norm": 0.45071983337402344,
+      "grad_norm": 0.4507337510585785,
       "learning_rate": 7.583148558758315e-05,
-      "loss": 0.9675,
+      "loss": 0.9666,
       "step": 286
     },
     {
       "epoch": 1.89010989010989,
-      "grad_norm": 0.5381602644920349,
+      "grad_norm": 0.537993311882019,
       "learning_rate": 7.538802660753881e-05,
-      "loss": 0.8273,
+      "loss": 0.8264,
       "step": 287
     },
     {
       "epoch": 1.8967032967032966,
-      "grad_norm": 0.5621278882026672,
+      "grad_norm": 0.5618338584899902,
       "learning_rate": 7.494456762749445e-05,
-      "loss": 0.8176,
+      "loss": 0.8165,
       "step": 288
     },
     {
       "epoch": 1.9032967032967032,
-      "grad_norm": 0.5810724496841431,
+      "grad_norm": 0.5855028629302979,
       "learning_rate": 7.450110864745011e-05,
-      "loss": 0.7506,
+      "loss": 0.7508,
       "step": 289
     },
     {
       "epoch": 1.9098901098901098,
-      "grad_norm": 0.5444163084030151,
+      "grad_norm": 0.5481427311897278,
       "learning_rate": 7.405764966740577e-05,
-      "loss": 0.7305,
+      "loss": 0.73,
       "step": 290
     },
     {
       "epoch": 1.9164835164835163,
-      "grad_norm": 0.5373480319976807,
+      "grad_norm": 0.5455793142318726,
       "learning_rate": 7.361419068736141e-05,
-      "loss": 0.8135,
+      "loss": 0.8251,
       "step": 291
     },
     {
       "epoch": 1.9230769230769231,
-      "grad_norm": 0.5446553230285645,
+      "grad_norm": 0.5479074716567993,
       "learning_rate": 7.317073170731707e-05,
-      "loss": 0.8316,
+      "loss": 0.8328,
       "step": 292
     },
     {
       "epoch": 1.9296703296703297,
-      "grad_norm": 0.5608210563659668,
+      "grad_norm": 0.558845579624176,
       "learning_rate": 7.272727272727273e-05,
-      "loss": 0.8076,
+      "loss": 0.8069,
       "step": 293
     },
     {
       "epoch": 1.9362637362637363,
-      "grad_norm": 0.5300861597061157,
+      "grad_norm": 0.5320450663566589,
       "learning_rate": 7.228381374722837e-05,
-      "loss": 0.8772,
+      "loss": 0.8758,
       "step": 294
     },
     {
       "epoch": 1.9428571428571428,
-      "grad_norm": 0.5608508586883545,
+      "grad_norm": 0.56231689453125,
       "learning_rate": 7.184035476718403e-05,
-      "loss": 0.7926,
+      "loss": 0.7928,
       "step": 295
     },
     {
       "epoch": 1.9494505494505494,
-      "grad_norm": 0.6337592601776123,
+      "grad_norm": 0.6288520097732544,
       "learning_rate": 7.139689578713969e-05,
-      "loss": 0.9388,
+      "loss": 0.9385,
       "step": 296
     },
     {
       "epoch": 1.9560439560439562,
-      "grad_norm": 0.6125892996788025,
+      "grad_norm": 0.614974856376648,
       "learning_rate": 7.095343680709535e-05,
-      "loss": 0.9204,
+      "loss": 0.9189,
       "step": 297
     },
     {
       "epoch": 1.9626373626373628,
-      "grad_norm": 0.5068105459213257,
+      "grad_norm": 0.5072554349899292,
       "learning_rate": 7.0509977827051e-05,
-      "loss": 0.8169,
+      "loss": 0.818,
       "step": 298
     },
     {
       "epoch": 1.9692307692307693,
-      "grad_norm": 0.6008275151252747,
+      "grad_norm": 0.6028959155082703,
       "learning_rate": 7.006651884700666e-05,
-      "loss": 0.803,
+      "loss": 0.8039,
       "step": 299
     },
     {
       "epoch": 1.975824175824176,
-      "grad_norm": 0.5600306987762451,
+      "grad_norm": 0.561110258102417,
       "learning_rate": 6.962305986696232e-05,
-      "loss": 0.6676,
+      "loss": 0.667,
       "step": 300
     }
   ],

checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07146c455ab49e27b0da02ba4fb6ef4ea9a6eb84c6fd062fcfdd2080a085a56
+oid sha256:5aa00eb920dd18ab8c143c1abbb8a44aab6dd17b40c8b862bafbade0591c2912
 size 6417