Upload 12 files

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
+    "down_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739c690ef4eae43186cdf20b6d0b365f9f8aec9ff68e1eb1fc02757f7b36e64b
+oid sha256:76b72116151c2ab64613131dc1acf5548fcca019a2653a920dc613f08be639a7
 size 100059752

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e33d06110cf53a299925654ed15d6eb64b743536c5bffb424426a2eb0ffd5a
+oid sha256:e96c59addde027b8b902d252926469354853f490ed1c57f0f833c5009cd737a2
 size 50545780

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
-size 17477553
+oid sha256:cb7e592b7314175501c7fc56b904d581de569169ac90e5aa2ec11a860c2cbbaa
+size 17477652

trainer_state.json

@@ -10,700 +10,700 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.4236936569213867,
+      "grad_norm": 2.6449337005615234,
       "learning_rate": 0.0001,
       "loss": 1.1597,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.4236936569213867,
+      "grad_norm": 2.6449337005615234,
       "learning_rate": 0.0002,
       "loss": 1.1597,
       "step": 2
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.3299813270568848,
+      "grad_norm": 1.2656898498535156,
       "learning_rate": 0.00019795918367346938,
-      "loss": 0.9809,
+      "loss": 0.9752,
       "step": 3
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.62615966796875,
+      "grad_norm": 1.607674479484558,
       "learning_rate": 0.0001959183673469388,
-      "loss": 0.7416,
+      "loss": 0.7412,
       "step": 4
     },
     {
       "epoch": 5.0,
-      "grad_norm": 1.3189771175384521,
+      "grad_norm": 1.2566553354263306,
       "learning_rate": 0.00019387755102040816,
-      "loss": 0.5219,
+      "loss": 0.523,
       "step": 5
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.062267780303955,
+      "grad_norm": 1.0019608736038208,
       "learning_rate": 0.00019183673469387756,
-      "loss": 0.3376,
+      "loss": 0.3398,
       "step": 6
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.7606938481330872,
+      "grad_norm": 0.7906450033187866,
       "learning_rate": 0.00018979591836734697,
-      "loss": 0.1999,
+      "loss": 0.201,
       "step": 7
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.6657623648643494,
+      "grad_norm": 0.6831750273704529,
       "learning_rate": 0.00018775510204081634,
-      "loss": 0.1314,
+      "loss": 0.1289,
       "step": 8
     },
     {
       "epoch": 9.0,
-      "grad_norm": 0.4108690917491913,
+      "grad_norm": 0.433000773191452,
       "learning_rate": 0.00018571428571428572,
-      "loss": 0.087,
+      "loss": 0.0869,
       "step": 9
     },
     {
       "epoch": 10.0,
-      "grad_norm": 0.25315290689468384,
+      "grad_norm": 0.3084024488925934,
       "learning_rate": 0.00018367346938775512,
-      "loss": 0.0777,
+      "loss": 0.0783,
       "step": 10
     },
     {
       "epoch": 11.0,
-      "grad_norm": 4.897407054901123,
+      "grad_norm": 0.8011140823364258,
       "learning_rate": 0.0001816326530612245,
-      "loss": 0.087,
+      "loss": 0.0769,
       "step": 11
     },
     {
       "epoch": 12.0,
-      "grad_norm": 0.3001738488674164,
+      "grad_norm": 1.9735212326049805,
       "learning_rate": 0.0001795918367346939,
-      "loss": 0.0707,
+      "loss": 0.071,
       "step": 12
     },
     {
       "epoch": 13.0,
-      "grad_norm": 5.1508378982543945,
+      "grad_norm": 4.395259380340576,
       "learning_rate": 0.00017755102040816327,
-      "loss": 0.088,
+      "loss": 0.0986,
       "step": 13
     },
     {
       "epoch": 14.0,
-      "grad_norm": 9.67592716217041,
+      "grad_norm": 2.70194673538208,
       "learning_rate": 0.00017551020408163265,
-      "loss": 0.0799,
+      "loss": 0.0783,
       "step": 14
     },
     {
       "epoch": 15.0,
-      "grad_norm": 2.7876245975494385,
+      "grad_norm": 0.3469013273715973,
       "learning_rate": 0.00017346938775510205,
-      "loss": 0.0967,
+      "loss": 0.0535,
       "step": 15
     },
     {
       "epoch": 16.0,
-      "grad_norm": 1.8201392889022827,
+      "grad_norm": 0.8472123146057129,
       "learning_rate": 0.00017142857142857143,
-      "loss": 0.0601,
+      "loss": 0.0463,
       "step": 16
     },
     {
       "epoch": 17.0,
-      "grad_norm": 1.6338967084884644,
+      "grad_norm": 0.49942201375961304,
       "learning_rate": 0.00016938775510204083,
-      "loss": 0.0512,
+      "loss": 0.0388,
       "step": 17
     },
     {
       "epoch": 18.0,
-      "grad_norm": 0.4770618975162506,
+      "grad_norm": 1.0144060850143433,
       "learning_rate": 0.00016734693877551023,
-      "loss": 0.0373,
+      "loss": 0.0314,
       "step": 18
     },
     {
       "epoch": 19.0,
-      "grad_norm": 0.458904504776001,
+      "grad_norm": 0.4307344853878021,
       "learning_rate": 0.0001653061224489796,
-      "loss": 0.0279,
+      "loss": 0.0171,
       "step": 19
     },
     {
       "epoch": 20.0,
-      "grad_norm": 1.6127618551254272,
+      "grad_norm": 0.29780709743499756,
       "learning_rate": 0.00016326530612244898,
-      "loss": 0.023,
+      "loss": 0.0093,
       "step": 20
     },
     {
       "epoch": 21.0,
-      "grad_norm": 1.090635895729065,
+      "grad_norm": 1.0202921628952026,
       "learning_rate": 0.00016122448979591838,
-      "loss": 0.0105,
+      "loss": 0.0072,
       "step": 21
     },
     {
       "epoch": 22.0,
-      "grad_norm": 0.08737627416849136,
+      "grad_norm": 0.1341150552034378,
       "learning_rate": 0.00015918367346938776,
-      "loss": 0.0061,
+      "loss": 0.0054,
       "step": 22
     },
     {
       "epoch": 23.0,
-      "grad_norm": 0.08030153065919876,
+      "grad_norm": 0.0842108279466629,
       "learning_rate": 0.00015714285714285716,
-      "loss": 0.0051,
+      "loss": 0.0049,
       "step": 23
     },
     {
       "epoch": 24.0,
-      "grad_norm": 0.04834992438554764,
+      "grad_norm": 0.017657078802585602,
       "learning_rate": 0.00015510204081632654,
-      "loss": 0.0048,
+      "loss": 0.0045,
       "step": 24
     },
     {
       "epoch": 25.0,
-      "grad_norm": 0.09552427381277084,
+      "grad_norm": 0.13113492727279663,
       "learning_rate": 0.0001530612244897959,
-      "loss": 0.0048,
+      "loss": 0.005,
       "step": 25
     },
     {
       "epoch": 26.0,
-      "grad_norm": 0.0460357591509819,
+      "grad_norm": 0.08366480469703674,
       "learning_rate": 0.0001510204081632653,
-      "loss": 0.0046,
+      "loss": 0.0048,
       "step": 26
     },
     {
       "epoch": 27.0,
-      "grad_norm": 0.0992983803153038,
+      "grad_norm": 0.029939724132418633,
       "learning_rate": 0.00014897959183673472,
-      "loss": 0.0047,
+      "loss": 0.0045,
       "step": 27
     },
     {
       "epoch": 28.0,
-      "grad_norm": 0.1185307577252388,
+      "grad_norm": 0.016423042863607407,
       "learning_rate": 0.0001469387755102041,
-      "loss": 0.0048,
+      "loss": 0.0044,
       "step": 28
     },
     {
       "epoch": 29.0,
-      "grad_norm": 0.14356577396392822,
+      "grad_norm": 0.08624381572008133,
       "learning_rate": 0.0001448979591836735,
       "loss": 0.0049,
       "step": 29
     },
     {
       "epoch": 30.0,
-      "grad_norm": 0.0876593366265297,
+      "grad_norm": 0.059919197112321854,
       "learning_rate": 0.00014285714285714287,
       "loss": 0.0046,
       "step": 30
     },
     {
       "epoch": 31.0,
-      "grad_norm": 0.08368655294179916,
+      "grad_norm": 0.03369490057229996,
       "learning_rate": 0.00014081632653061224,
-      "loss": 0.0047,
+      "loss": 0.0045,
       "step": 31
     },
     {
       "epoch": 32.0,
-      "grad_norm": 0.042614325881004333,
+      "grad_norm": 0.007869748398661613,
       "learning_rate": 0.00013877551020408165,
-      "loss": 0.0045,
+      "loss": 0.0044,
       "step": 32
     },
     {
       "epoch": 33.0,
-      "grad_norm": 0.00863147247582674,
+      "grad_norm": 0.024808548390865326,
       "learning_rate": 0.00013673469387755102,
       "loss": 0.0044,
       "step": 33
     },
     {
       "epoch": 34.0,
-      "grad_norm": 0.0089035639539361,
+      "grad_norm": 0.07703784108161926,
       "learning_rate": 0.0001346938775510204,
-      "loss": 0.0044,
+      "loss": 0.0047,
       "step": 34
     },
     {
       "epoch": 35.0,
-      "grad_norm": 0.03151445463299751,
+      "grad_norm": 0.05107901617884636,
       "learning_rate": 0.0001326530612244898,
-      "loss": 0.0044,
+      "loss": 0.0045,
       "step": 35
     },
     {
       "epoch": 36.0,
-      "grad_norm": 0.0310219656676054,
+      "grad_norm": 0.02403145283460617,
       "learning_rate": 0.00013061224489795917,
       "loss": 0.0044,
       "step": 36
     },
     {
       "epoch": 37.0,
-      "grad_norm": 0.030537990853190422,
+      "grad_norm": 0.03135854750871658,
       "learning_rate": 0.00012857142857142858,
       "loss": 0.0044,
       "step": 37
     },
     {
       "epoch": 38.0,
-      "grad_norm": 0.03915323689579964,
+      "grad_norm": 0.03122449666261673,
       "learning_rate": 0.00012653061224489798,
       "loss": 0.0044,
       "step": 38
     },
     {
       "epoch": 39.0,
-      "grad_norm": 0.038823168724775314,
+      "grad_norm": 0.031184706836938858,
       "learning_rate": 0.00012448979591836735,
       "loss": 0.0044,
       "step": 39
     },
     {
       "epoch": 40.0,
-      "grad_norm": 0.005813094321638346,
+      "grad_norm": 0.057482823729515076,
       "learning_rate": 0.00012244897959183676,
-      "loss": 0.0044,
+      "loss": 0.0046,
       "step": 40
     },
     {
       "epoch": 41.0,
-      "grad_norm": 0.02931728959083557,
+      "grad_norm": 0.005244183354079723,
       "learning_rate": 0.00012040816326530613,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 41
     },
     {
       "epoch": 42.0,
-      "grad_norm": 0.02919776178896427,
+      "grad_norm": 0.004556509666144848,
       "learning_rate": 0.00011836734693877552,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 42
     },
     {
       "epoch": 43.0,
-      "grad_norm": 0.005404920782893896,
+      "grad_norm": 0.04987052455544472,
       "learning_rate": 0.0001163265306122449,
-      "loss": 0.0044,
+      "loss": 0.0045,
       "step": 43
     },
     {
       "epoch": 44.0,
-      "grad_norm": 0.03844524547457695,
+      "grad_norm": 0.023411056026816368,
       "learning_rate": 0.00011428571428571428,
       "loss": 0.0044,
       "step": 44
     },
     {
       "epoch": 45.0,
-      "grad_norm": 0.005866413004696369,
+      "grad_norm": 0.023280324414372444,
       "learning_rate": 0.00011224489795918367,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 45
     },
     {
       "epoch": 46.0,
-      "grad_norm": 0.028769973665475845,
+      "grad_norm": 0.02315351739525795,
       "learning_rate": 0.00011020408163265306,
       "loss": 0.0044,
       "step": 46
     },
     {
       "epoch": 47.0,
-      "grad_norm": 0.028779389336705208,
+      "grad_norm": 0.0042741685174405575,
       "learning_rate": 0.00010816326530612246,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 47
     },
     {
       "epoch": 48.0,
-      "grad_norm": 0.006406720262020826,
+      "grad_norm": 0.004308342933654785,
       "learning_rate": 0.00010612244897959185,
       "loss": 0.0043,
       "step": 48
     },
     {
       "epoch": 49.0,
-      "grad_norm": 0.03870103508234024,
+      "grad_norm": 0.030576329678297043,
       "learning_rate": 0.00010408163265306123,
       "loss": 0.0044,
       "step": 49
     },
     {
       "epoch": 50.0,
-      "grad_norm": 0.038732465356588364,
+      "grad_norm": 0.03056076355278492,
       "learning_rate": 0.00010204081632653062,
       "loss": 0.0044,
       "step": 50
     },
     {
       "epoch": 51.0,
-      "grad_norm": 0.00536749605089426,
+      "grad_norm": 0.030563408508896828,
       "learning_rate": 0.0001,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 51
     },
     {
       "epoch": 52.0,
-      "grad_norm": 0.028795704245567322,
+      "grad_norm": 0.004566062707453966,
       "learning_rate": 9.79591836734694e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 52
     },
     {
       "epoch": 53.0,
-      "grad_norm": 0.02882838249206543,
+      "grad_norm": 0.022832510992884636,
       "learning_rate": 9.591836734693878e-05,
       "loss": 0.0044,
       "step": 53
     },
     {
       "epoch": 54.0,
-      "grad_norm": 0.02882484346628189,
+      "grad_norm": 0.02288009785115719,
       "learning_rate": 9.387755102040817e-05,
       "loss": 0.0044,
       "step": 54
     },
     {
       "epoch": 55.0,
-      "grad_norm": 0.00502988463267684,
+      "grad_norm": 0.02284756489098072,
       "learning_rate": 9.183673469387756e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 55
     },
     {
       "epoch": 56.0,
-      "grad_norm": 0.005017813295125961,
+      "grad_norm": 0.022797992452979088,
       "learning_rate": 8.979591836734695e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 56
     },
     {
       "epoch": 57.0,
-      "grad_norm": 0.005218982230871916,
+      "grad_norm": 0.022721149027347565,
       "learning_rate": 8.775510204081632e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 57
     },
     {
       "epoch": 58.0,
-      "grad_norm": 0.038150474429130554,
+      "grad_norm": 0.00404245825484395,
       "learning_rate": 8.571428571428571e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 58
     },
     {
       "epoch": 59.0,
-      "grad_norm": 0.03801121190190315,
+      "grad_norm": 0.030218880623579025,
       "learning_rate": 8.367346938775511e-05,
       "loss": 0.0044,
       "step": 59
     },
     {
       "epoch": 60.0,
-      "grad_norm": 0.004977047443389893,
+      "grad_norm": 0.030180249363183975,
       "learning_rate": 8.163265306122449e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 60
     },
     {
       "epoch": 61.0,
-      "grad_norm": 0.0602005235850811,
+      "grad_norm": 0.03016875684261322,
       "learning_rate": 7.959183673469388e-05,
-      "loss": 0.0045,
+      "loss": 0.0044,
       "step": 61
     },
     {
       "epoch": 62.0,
-      "grad_norm": 0.0284713264554739,
+      "grad_norm": 0.004292755853384733,
       "learning_rate": 7.755102040816327e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 62
     },
     {
       "epoch": 63.0,
-      "grad_norm": 0.004900462459772825,
+      "grad_norm": 0.00451462808996439,
       "learning_rate": 7.551020408163266e-05,
       "loss": 0.0043,
       "step": 63
     },
     {
       "epoch": 64.0,
-      "grad_norm": 0.0048695337027311325,
+      "grad_norm": 0.004491481464356184,
       "learning_rate": 7.346938775510205e-05,
       "loss": 0.0043,
       "step": 64
     },
     {
       "epoch": 65.0,
-      "grad_norm": 0.004841310903429985,
+      "grad_norm": 0.02254634164273739,
       "learning_rate": 7.142857142857143e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 65
     },
     {
       "epoch": 66.0,
-      "grad_norm": 0.004835947882384062,
+      "grad_norm": 0.022601598873734474,
       "learning_rate": 6.938775510204082e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 66
     },
     {
       "epoch": 67.0,
-      "grad_norm": 0.03715803846716881,
+      "grad_norm": 0.022533219307661057,
       "learning_rate": 6.73469387755102e-05,
       "loss": 0.0044,
       "step": 67
     },
     {
       "epoch": 68.0,
-      "grad_norm": 0.004820631351321936,
+      "grad_norm": 0.022499827668070793,
       "learning_rate": 6.530612244897959e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 68
     },
     {
       "epoch": 69.0,
-      "grad_norm": 0.004830862861126661,
+      "grad_norm": 0.02238309197127819,
       "learning_rate": 6.326530612244899e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 69
     },
     {
       "epoch": 70.0,
-      "grad_norm": 0.02773592434823513,
+      "grad_norm": 0.004698493983596563,
       "learning_rate": 6.122448979591838e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 70
     },
     {
       "epoch": 71.0,
-      "grad_norm": 0.02766617201268673,
+      "grad_norm": 0.03000456467270851,
       "learning_rate": 5.918367346938776e-05,
       "loss": 0.0044,
       "step": 71
     },
     {
       "epoch": 72.0,
-      "grad_norm": 0.027592068538069725,
+      "grad_norm": 0.029959533363580704,
       "learning_rate": 5.714285714285714e-05,
       "loss": 0.0044,
       "step": 72
     },
     {
       "epoch": 73.0,
-      "grad_norm": 0.004762730095535517,
+      "grad_norm": 0.029947014525532722,
       "learning_rate": 5.510204081632653e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 73
     },
     {
       "epoch": 74.0,
-      "grad_norm": 0.004771250765770674,
+      "grad_norm": 0.029971199110150337,
       "learning_rate": 5.3061224489795926e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 74
     },
     {
       "epoch": 75.0,
-      "grad_norm": 0.004748388193547726,
+      "grad_norm": 0.0047256131656467915,
       "learning_rate": 5.102040816326531e-05,
       "loss": 0.0043,
       "step": 75
     },
     {
       "epoch": 76.0,
-      "grad_norm": 0.03664989769458771,
+      "grad_norm": 0.022311007604002953,
       "learning_rate": 4.89795918367347e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 76
     },
     {
       "epoch": 77.0,
-      "grad_norm": 0.004758178256452084,
+      "grad_norm": 0.02232247218489647,
       "learning_rate": 4.6938775510204086e-05,
       "loss": 0.0043,
       "step": 77
     },
     {
       "epoch": 78.0,
-      "grad_norm": 0.03650437667965889,
+      "grad_norm": 0.022320913150906563,
       "learning_rate": 4.4897959183673474e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 78
     },
     {
       "epoch": 79.0,
-      "grad_norm": 0.004723742604255676,
+      "grad_norm": 0.022281426936388016,
       "learning_rate": 4.2857142857142856e-05,
       "loss": 0.0043,
       "step": 79
     },
     {
       "epoch": 80.0,
-      "grad_norm": 0.027179496362805367,
+      "grad_norm": 0.004078465048223734,
       "learning_rate": 4.0816326530612245e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 80
     },
     {
       "epoch": 81.0,
-      "grad_norm": 0.027180835604667664,
+      "grad_norm": 0.022234855219721794,
       "learning_rate": 3.8775510204081634e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 81
     },
     {
       "epoch": 82.0,
-      "grad_norm": 0.027134299278259277,
+      "grad_norm": 0.004209673032164574,
       "learning_rate": 3.673469387755102e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 82
     },
     {
       "epoch": 83.0,
-      "grad_norm": 0.027070023119449615,
+      "grad_norm": 0.004030004143714905,
       "learning_rate": 3.469387755102041e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 83
     },
     {
       "epoch": 84.0,
-      "grad_norm": 0.004842973779886961,
+      "grad_norm": 0.004146768245846033,
       "learning_rate": 3.265306122448979e-05,
       "loss": 0.0043,
       "step": 84
     },
     {
       "epoch": 85.0,
-      "grad_norm": 0.004742528777569532,
+      "grad_norm": 0.029780622571706772,
       "learning_rate": 3.061224489795919e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 85
     },
     {
       "epoch": 86.0,
-      "grad_norm": 0.004724172409623861,
+      "grad_norm": 0.02978537231683731,
       "learning_rate": 2.857142857142857e-05,
-      "loss": 0.0043,
+      "loss": 0.0044,
       "step": 86
     },
     {
       "epoch": 87.0,
-      "grad_norm": 0.03628339245915413,
+      "grad_norm": 0.003935360349714756,
       "learning_rate": 2.6530612244897963e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 87
     },
     {
       "epoch": 88.0,
-      "grad_norm": 0.036234479397535324,
+      "grad_norm": 0.0040387483313679695,
       "learning_rate": 2.448979591836735e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 88
     },
     {
       "epoch": 89.0,
-      "grad_norm": 0.004697797354310751,
+      "grad_norm": 0.004038290120661259,
       "learning_rate": 2.2448979591836737e-05,
       "loss": 0.0043,
       "step": 89
     },
     {
       "epoch": 90.0,
-      "grad_norm": 0.004719586111605167,
+      "grad_norm": 0.003925453871488571,
       "learning_rate": 2.0408163265306123e-05,
       "loss": 0.0043,
       "step": 90
     },
     {
       "epoch": 91.0,
-      "grad_norm": 0.004701649770140648,
+      "grad_norm": 0.00405112886801362,
       "learning_rate": 1.836734693877551e-05,
       "loss": 0.0043,
       "step": 91
     },
     {
       "epoch": 92.0,
-      "grad_norm": 0.026852702721953392,
+      "grad_norm": 0.004041624255478382,
       "learning_rate": 1.6326530612244897e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 92
     },
     {
       "epoch": 93.0,
-      "grad_norm": 0.02685590460896492,
+      "grad_norm": 0.022224921733140945,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 93
     },
     {
       "epoch": 94.0,
-      "grad_norm": 0.0047478387132287025,
+      "grad_norm": 0.022291233763098717,
       "learning_rate": 1.2244897959183674e-05,
       "loss": 0.0043,
       "step": 94
     },
     {
       "epoch": 95.0,
-      "grad_norm": 0.026850329712033272,
+      "grad_norm": 0.004063317086547613,
       "learning_rate": 1.0204081632653061e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 95
     },
     {
       "epoch": 96.0,
-      "grad_norm": 0.00475778803229332,
+      "grad_norm": 0.0040570334531366825,
       "learning_rate": 8.163265306122448e-06,
       "loss": 0.0043,
       "step": 96
     },
     {
       "epoch": 97.0,
-      "grad_norm": 0.004756512586027384,
+      "grad_norm": 0.004056213889271021,
       "learning_rate": 6.122448979591837e-06,
       "loss": 0.0043,
       "step": 97
     },
     {
       "epoch": 98.0,
-      "grad_norm": 0.004749584477394819,
+      "grad_norm": 0.022241706028580666,
       "learning_rate": 4.081632653061224e-06,
       "loss": 0.0043,
       "step": 98
     },
     {
       "epoch": 99.0,
-      "grad_norm": 0.004759279545396566,
+      "grad_norm": 0.022222261875867844,
       "learning_rate": 2.040816326530612e-06,
       "loss": 0.0043,
       "step": 99
     },
     {
       "epoch": 100.0,
-      "grad_norm": 0.004726547747850418,
+      "grad_norm": 0.02224196493625641,
       "learning_rate": 0.0,
       "loss": 0.0043,
       "step": 100

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700afa88f3f25a9108feb30e33c64c29aca41d329b79f230609b2023fa359c16
+oid sha256:88c1ac92c45e5daa6934f6550b7e9b92214c2a7189659aea3017fb00f7052e4f
 size 4984