Upload folder using huggingface_hub

adapter_config.json

@@ -14,7 +14,7 @@
   "loftq_config": {},
   "lora_alpha": 96,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f59fd7c6f0dfbc9b0c3934ce3a7cd21eb7528d5d973cdfcd58aa59d88ccc39f
+oid sha256:f38f6c7cc699891d33b43936e13424bf4f5c79f2e529aeddd1d38cb2b4e18803
 size 359270696

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74c663e8652398e356aaca1501eb4cca823029856401927eb69158c2c246999
+oid sha256:d10e91706fa7e2ba3d059b9c546fae7154a67c360412992451723c1d1fe5cc02
 size 718831691

trainer_state.json

@@ -11,422 +11,422 @@
   "log_history": [
     {
       "epoch": 0.05063291139240506,
-      "grad_norm": 22.15937042236328,
+      "grad_norm": 23.053184509277344,
       "learning_rate": 0.0,
       "loss": 3.0474,
       "step": 1
     },
     {
       "epoch": 0.10126582278481013,
-      "grad_norm": 36.183231353759766,
+      "grad_norm": 37.69414520263672,
       "learning_rate": 3.3333333333333335e-05,
       "loss": 3.2925,
       "step": 2
     },
     {
       "epoch": 0.1518987341772152,
-      "grad_norm": 5.320329189300537,
+      "grad_norm": 5.540323734283447,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 3.0096,
+      "loss": 3.0089,
       "step": 3
     },
     {
       "epoch": 0.20253164556962025,
-      "grad_norm": 4.796537399291992,
+      "grad_norm": 4.970560073852539,
       "learning_rate": 0.0001,
-      "loss": 2.6045,
+      "loss": 2.6052,
       "step": 4
     },
     {
       "epoch": 0.25316455696202533,
-      "grad_norm": 2.9281771183013916,
+      "grad_norm": 3.1140971183776855,
       "learning_rate": 0.00013333333333333334,
-      "loss": 2.1625,
+      "loss": 2.1661,
       "step": 5
     },
     {
       "epoch": 0.3037974683544304,
-      "grad_norm": 7.840775012969971,
+      "grad_norm": 5.0788140296936035,
       "learning_rate": 0.00016666666666666666,
-      "loss": 2.7606,
+      "loss": 2.7634,
       "step": 6
     },
     {
       "epoch": 0.35443037974683544,
-      "grad_norm": 3.6150004863739014,
+      "grad_norm": 3.610426425933838,
       "learning_rate": 0.0002,
-      "loss": 2.5675,
+      "loss": 2.5581,
       "step": 7
     },
     {
       "epoch": 0.4050632911392405,
-      "grad_norm": 3.3033154010772705,
+      "grad_norm": 3.3719804286956787,
       "learning_rate": 0.00023333333333333333,
-      "loss": 2.3897,
+      "loss": 2.3932,
       "step": 8
     },
     {
       "epoch": 0.45569620253164556,
-      "grad_norm": 4.086965560913086,
+      "grad_norm": 3.6790554523468018,
       "learning_rate": 0.0002666666666666667,
-      "loss": 2.755,
+      "loss": 2.7487,
       "step": 9
     },
     {
       "epoch": 0.5063291139240507,
-      "grad_norm": 3.734769105911255,
+      "grad_norm": 3.152188301086426,
       "learning_rate": 0.0003,
-      "loss": 2.5837,
+      "loss": 2.5796,
       "step": 10
     },
     {
       "epoch": 0.5569620253164557,
-      "grad_norm": 3.2234697341918945,
+      "grad_norm": 3.6318979263305664,
       "learning_rate": 0.0003333333333333333,
-      "loss": 2.6353,
+      "loss": 2.6359,
       "step": 11
     },
     {
       "epoch": 0.6075949367088608,
-      "grad_norm": 2.629314422607422,
+      "grad_norm": 2.668596029281616,
       "learning_rate": 0.00036666666666666667,
-      "loss": 2.732,
+      "loss": 2.7351,
       "step": 12
     },
     {
       "epoch": 0.6582278481012658,
-      "grad_norm": 3.710653066635132,
+      "grad_norm": 5.233928680419922,
       "learning_rate": 0.0004,
-      "loss": 2.4126,
+      "loss": 2.4318,
       "step": 13
     },
     {
       "epoch": 0.7088607594936709,
-      "grad_norm": 3.1855616569519043,
+      "grad_norm": 3.2564899921417236,
       "learning_rate": 0.00043333333333333337,
-      "loss": 2.0725,
+      "loss": 2.0882,
       "step": 14
     },
     {
       "epoch": 0.759493670886076,
-      "grad_norm": 3.34596848487854,
+      "grad_norm": 3.2959020137786865,
       "learning_rate": 0.00046666666666666666,
-      "loss": 2.3351,
+      "loss": 2.3181,
       "step": 15
     },
     {
       "epoch": 0.810126582278481,
-      "grad_norm": 3.2423255443573,
+      "grad_norm": 3.4378912448883057,
       "learning_rate": 0.0005,
-      "loss": 2.7354,
+      "loss": 2.7332,
       "step": 16
     },
     {
       "epoch": 0.8607594936708861,
-      "grad_norm": 3.6997056007385254,
+      "grad_norm": 3.6707003116607666,
       "learning_rate": 0.0004998292650357557,
-      "loss": 2.6154,
+      "loss": 2.5919,
       "step": 17
     },
     {
       "epoch": 0.9113924050632911,
-      "grad_norm": 3.3852779865264893,
+      "grad_norm": 3.861492872238159,
       "learning_rate": 0.0004993172933464471,
-      "loss": 2.9623,
+      "loss": 2.9812,
       "step": 18
     },
     {
       "epoch": 0.9620253164556962,
-      "grad_norm": 5.298639297485352,
+      "grad_norm": 5.971181869506836,
       "learning_rate": 0.0004984647842238185,
-      "loss": 2.7019,
+      "loss": 2.7555,
       "step": 19
     },
     {
       "epoch": 1.0,
-      "grad_norm": 4.402466773986816,
+      "grad_norm": 4.519949436187744,
       "learning_rate": 0.0004972729020927865,
-      "loss": 2.4495,
+      "loss": 2.4604,
       "step": 20
     },
     {
       "epoch": 1.0506329113924051,
-      "grad_norm": 3.915959358215332,
+      "grad_norm": 6.372091770172119,
       "learning_rate": 0.0004957432749209755,
-      "loss": 1.9027,
+      "loss": 1.9803,
       "step": 21
     },
     {
       "epoch": 1.1012658227848102,
-      "grad_norm": 2.6463258266448975,
+      "grad_norm": 3.0549910068511963,
       "learning_rate": 0.0004938779919951092,
-      "loss": 1.6182,
+      "loss": 1.7481,
       "step": 22
     },
     {
       "epoch": 1.1518987341772151,
-      "grad_norm": 3.179638385772705,
+      "grad_norm": 3.166491746902466,
       "learning_rate": 0.0004916796010672969,
-      "loss": 1.6585,
+      "loss": 1.7108,
       "step": 23
     },
     {
       "epoch": 1.2025316455696202,
-      "grad_norm": 5.375019550323486,
+      "grad_norm": 5.136909008026123,
       "learning_rate": 0.0004891511048751102,
-      "loss": 1.9379,
+      "loss": 1.9706,
       "step": 24
     },
     {
       "epoch": 1.2531645569620253,
-      "grad_norm": 3.4863626956939697,
+      "grad_norm": 3.662278413772583,
       "learning_rate": 0.00048629595704020493,
-      "loss": 1.5123,
+      "loss": 1.451,
       "step": 25
     },
     {
       "epoch": 1.3037974683544304,
-      "grad_norm": 2.945317506790161,
+      "grad_norm": 3.243025302886963,
       "learning_rate": 0.00048311805735108893,
-      "loss": 1.8359,
+      "loss": 1.882,
       "step": 26
     },
     {
       "epoch": 1.3544303797468356,
-      "grad_norm": 4.178781986236572,
+      "grad_norm": 4.813160419464111,
       "learning_rate": 0.0004796217464364808,
-      "loss": 1.8808,
+      "loss": 1.9157,
       "step": 27
     },
     {
       "epoch": 1.4050632911392404,
-      "grad_norm": 3.691697597503662,
+      "grad_norm": 3.516997814178467,
       "learning_rate": 0.0004758117998365322,
-      "loss": 1.7988,
+      "loss": 1.8105,
       "step": 28
     },
     {
       "epoch": 1.4556962025316456,
-      "grad_norm": 3.262970447540283,
+      "grad_norm": 3.336134672164917,
       "learning_rate": 0.00047169342148001547,
-      "loss": 1.8361,
+      "loss": 1.7735,
       "step": 29
     },
     {
       "epoch": 1.5063291139240507,
-      "grad_norm": 3.550689220428467,
+      "grad_norm": 3.748394727706909,
       "learning_rate": 0.0004672722365763821,
-      "loss": 1.609,
+      "loss": 1.6359,
       "step": 30
     },
     {
       "epoch": 1.5569620253164556,
-      "grad_norm": 3.615360736846924,
+      "grad_norm": 4.215877056121826,
       "learning_rate": 0.0004625542839324036,
-      "loss": 1.5563,
+      "loss": 1.557,
       "step": 31
     },
     {
       "epoch": 1.6075949367088609,
-      "grad_norm": 2.8636770248413086,
+      "grad_norm": 3.181777000427246,
       "learning_rate": 0.00045754600770388763,
-      "loss": 1.5551,
+      "loss": 1.6716,
       "step": 32
     },
     {
       "epoch": 1.6582278481012658,
-      "grad_norm": 4.557415962219238,
+      "grad_norm": 5.638424873352051,
       "learning_rate": 0.0004522542485937369,
-      "loss": 1.7539,
+      "loss": 1.8503,
       "step": 33
     },
     {
       "epoch": 1.7088607594936709,
-      "grad_norm": 3.1868419647216797,
+      "grad_norm": 3.092801570892334,
       "learning_rate": 0.0004466862345083708,
-      "loss": 1.7852,
+      "loss": 1.7874,
       "step": 34
     },
     {
       "epoch": 1.759493670886076,
-      "grad_norm": 3.380448818206787,
+      "grad_norm": 3.7433102130889893,
       "learning_rate": 0.0004408495706852758,
-      "loss": 1.7807,
+      "loss": 1.8509,
       "step": 35
     },
     {
       "epoch": 1.810126582278481,
-      "grad_norm": 4.706411838531494,
+      "grad_norm": 5.199512004852295,
       "learning_rate": 0.00043475222930516476,
-      "loss": 1.9616,
+      "loss": 1.9676,
       "step": 36
     },
     {
       "epoch": 1.8607594936708862,
-      "grad_norm": 2.568176031112671,
+      "grad_norm": 2.9524500370025635,
       "learning_rate": 0.0004284025386029381,
-      "loss": 1.5545,
+      "loss": 1.6064,
       "step": 37
     },
     {
       "epoch": 1.9113924050632911,
-      "grad_norm": 3.263295888900757,
+      "grad_norm": 3.5136239528656006,
       "learning_rate": 0.00042180917149231567,
-      "loss": 1.7313,
+      "loss": 1.7605,
       "step": 38
     },
     {
       "epoch": 1.9620253164556962,
-      "grad_norm": 5.326169967651367,
+      "grad_norm": 4.008464813232422,
       "learning_rate": 0.0004149811337196807,
-      "loss": 1.6959,
+      "loss": 1.6991,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "grad_norm": 4.056178569793701,
+      "grad_norm": 3.3913097381591797,
       "learning_rate": 0.00040792775156331276,
-      "loss": 1.9885,
+      "loss": 1.9957,
       "step": 40
     },
     {
       "epoch": 2.050632911392405,
-      "grad_norm": 2.816775321960449,
+      "grad_norm": 3.1906797885894775,
       "learning_rate": 0.0004006586590948141,
-      "loss": 1.079,
+      "loss": 1.1241,
       "step": 41
     },
     {
       "epoch": 2.1012658227848102,
-      "grad_norm": 3.266395330429077,
+      "grad_norm": 72.32931518554688,
       "learning_rate": 0.0003931837850201263,
-      "loss": 1.021,
+      "loss": 1.0448,
       "step": 42
     },
     {
       "epoch": 2.151898734177215,
-      "grad_norm": 4.753467559814453,
+      "grad_norm": 8.60446548461914,
       "learning_rate": 0.00038551333911811237,
-      "loss": 1.0574,
+      "loss": 1.2111,
       "step": 43
     },
     {
       "epoch": 2.2025316455696204,
-      "grad_norm": 4.696927547454834,
+      "grad_norm": 111.643798828125,
       "learning_rate": 0.00037765779829522674,
-      "loss": 1.1594,
+      "loss": 1.2316,
       "step": 44
     },
     {
       "epoch": 2.2531645569620253,
-      "grad_norm": 3.3051199913024902,
+      "grad_norm": 69.01380157470703,
       "learning_rate": 0.00036962789227532164,
-      "loss": 1.0123,
+      "loss": 1.1394,
       "step": 45
     },
     {
       "epoch": 2.3037974683544302,
-      "grad_norm": 3.196387767791748,
+      "grad_norm": 49.87290573120117,
       "learning_rate": 0.0003614345889441346,
-      "loss": 1.2621,
+      "loss": 1.5392,
       "step": 46
     },
     {
       "epoch": 2.3544303797468356,
-      "grad_norm": 3.5468530654907227,
+      "grad_norm": 6.338498115539551,
       "learning_rate": 0.0003530890793684759,
-      "loss": 1.0165,
+      "loss": 1.3349,
       "step": 47
     },
     {
       "epoch": 2.4050632911392404,
-      "grad_norm": 2.5015392303466797,
+      "grad_norm": 3.9022185802459717,
       "learning_rate": 0.0003446027625105776,
-      "loss": 1.216,
+      "loss": 1.4879,
       "step": 48
     },
     {
       "epoch": 2.4556962025316453,
-      "grad_norm": 2.7021989822387695,
+      "grad_norm": 3.2077016830444336,
       "learning_rate": 0.00033598722965848206,
-      "loss": 1.2118,
+      "loss": 1.3891,
       "step": 49
     },
     {
       "epoch": 2.5063291139240507,
-      "grad_norm": 3.0691046714782715,
+      "grad_norm": 3.5117242336273193,
       "learning_rate": 0.00032725424859373687,
-      "loss": 0.9781,
+      "loss": 1.0252,
       "step": 50
     },
     {
       "epoch": 2.5569620253164556,
-      "grad_norm": 2.657027244567871,
+      "grad_norm": 2.9290771484375,
       "learning_rate": 0.0003184157475180208,
-      "loss": 0.9974,
+      "loss": 1.1663,
       "step": 51
     },
     {
       "epoch": 2.607594936708861,
-      "grad_norm": 3.9573814868927,
+      "grad_norm": 3.6337857246398926,
       "learning_rate": 0.00030948379876065467,
-      "loss": 0.8675,
+      "loss": 0.8949,
       "step": 52
     },
     {
       "epoch": 2.6582278481012658,
-      "grad_norm": 2.825610876083374,
+      "grad_norm": 3.0574092864990234,
       "learning_rate": 0.00030047060228925254,
-      "loss": 1.0503,
+      "loss": 1.0849,
       "step": 53
     },
     {
       "epoch": 2.708860759493671,
-      "grad_norm": 4.903167724609375,
+      "grad_norm": 4.709362983703613,
       "learning_rate": 0.0002913884690460325,
-      "loss": 1.4037,
+      "loss": 1.5214,
       "step": 54
     },
     {
       "epoch": 2.759493670886076,
-      "grad_norm": 2.883190393447876,
+      "grad_norm": 2.733558416366577,
       "learning_rate": 0.00028224980413255084,
-      "loss": 0.9242,
+      "loss": 0.9746,
       "step": 55
     },
     {
       "epoch": 2.810126582278481,
-      "grad_norm": 2.112745523452759,
+      "grad_norm": 2.5984580516815186,
       "learning_rate": 0.0002730670898658255,
-      "loss": 0.8504,
+      "loss": 0.9218,
       "step": 56
     },
     {
       "epoch": 2.8607594936708862,
-      "grad_norm": 2.8920631408691406,
+      "grad_norm": 3.3489749431610107,
       "learning_rate": 0.0002638528687289925,
-      "loss": 0.8863,
+      "loss": 0.9848,
       "step": 57
     },
     {
       "epoch": 2.911392405063291,
-      "grad_norm": 2.817871570587158,
+      "grad_norm": 3.0495173931121826,
       "learning_rate": 0.0002546197262397825,
-      "loss": 1.0101,
+      "loss": 1.0627,
       "step": 58
     },
     {
       "epoch": 2.962025316455696,
-      "grad_norm": 3.5625603199005127,
+      "grad_norm": 3.800489664077759,
       "learning_rate": 0.0002453802737602176,
-      "loss": 1.138,
+      "loss": 1.193,
       "step": 59
     },
     {
       "epoch": 3.0,
-      "grad_norm": 2.3167858123779297,
+      "grad_norm": 2.3720569610595703,
       "learning_rate": 0.00023614713127100752,
-      "loss": 0.5741,
+      "loss": 0.5813,
       "step": 60
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba1f2914799e90728253ee6efdcfb4b949f06f16db0ce9229e365f91a8f35af
+oid sha256:9f5ae345297f057409c6b6f6ef86d9a3c968bc42d4f072f03acde8898bbe3f0d
 size 6033