Upload folder using huggingface_hub

checkpoint-135/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-135/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891fa0e06a90d3689146f789b56c3510f79ba5ada17d67af2a0dcc3ff70d90be
+oid sha256:7718f0634ac3bef02f52aafadd54cbe41a58d8e96b9e31705f4a760bd23c2958
 size 59933632

checkpoint-135/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb3288b293aa0fcdeeb9d049c15669c4aa12f78d9d60f91534c19d0e68843eb
+oid sha256:07bfca53f041d8a86cbd449fcd4aef50bee88a9868b59cb3bea9255e019a2358
 size 120166091

checkpoint-135/trainer_state.json

@@ -46,912 +46,912 @@
     },
     {
       "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
     }
   ],

checkpoint-135/training_args.bin

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