Upload folder using huggingface_hub

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj",
     "k_proj",
-    "up_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd67baec71aece20a60155a6101783007b9913a5959740bb42fb8d6b6630984
+oid sha256:a111c948bdfc4e0385c1cefccdad91a853056d6403f1cc698b68117ddc5fe324
 size 276869160

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8077feaa96893fb650dcb9656796c694c4648b7c916165b633cde8bf4e155f95
+oid sha256:1730dc203bcae94b33bc3dcbf9a722804120e24cbe9c1029ec1450ca0880bec3
 size 553854714

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d7c7f54fc5396598b8785e4b837226cd9d977162fd91a5dbb7b9db4b5e5932
+oid sha256:d839c288abf2b3689142bcb7f27a1ac0e84df0da29746c6b101fea61b5c09bf9
 size 14244

trainer_state.json

@@ -11,433 +11,433 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0,
-      "loss": 1.8359,
+      "loss": 1.9175,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0,
-      "loss": 2.0644,
+      "loss": 2.1462,
       "step": 4
     },
     {
       "epoch": 0.12,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 2.265,
+      "learning_rate": 0.0,
+      "loss": 2.2927,
       "step": 6
     },
     {
       "epoch": 0.16,
-      "learning_rate": 1.2e-05,
-      "loss": 2.2443,
+      "learning_rate": 0.0,
+      "loss": 2.2939,
       "step": 8
     },
     {
       "epoch": 0.21,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.4286,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.3964,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.704,
+      "loss": 2.5863,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 1.999744599547812e-05,
-      "loss": 1.9173,
+      "loss": 1.8329,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 1.99770217861636e-05,
-      "loss": 2.1814,
+      "loss": 2.1592,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 1.9936215093023884e-05,
-      "loss": 2.3203,
+      "loss": 2.2509,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 1.9875109281794828e-05,
-      "loss": 2.1449,
+      "loss": 2.1665,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 1.9793829188147406e-05,
-      "loss": 2.2452,
+      "loss": 2.3913,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 1.9692540862655587e-05,
-      "loss": 2.4673,
+      "loss": 2.5814,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 1.9571451231564523e-05,
-      "loss": 1.9931,
+      "loss": 1.8951,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 1.9430807674052092e-05,
-      "loss": 2.2818,
+      "loss": 2.1537,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 1.9270897516847406e-05,
-      "loss": 2.1631,
+      "loss": 2.1855,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.9092047447238775e-05,
-      "loss": 2.1008,
+      "loss": 2.1352,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.8894622845670282e-05,
-      "loss": 2.1732,
+      "loss": 2.1292,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 1.86790270392905e-05,
-      "loss": 2.4445,
+      "loss": 2.3216,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.8445700477978207e-05,
-      "loss": 1.7119,
+      "loss": 1.8196,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 1.8195119834528535e-05,
-      "loss": 2.056,
+      "loss": 2.123,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 1.792779703083777e-05,
-      "loss": 2.1947,
+      "loss": 2.17,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 1.764427819207624e-05,
-      "loss": 2.2409,
+      "loss": 2.1112,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 1.734514253098589e-05,
-      "loss": 2.0962,
+      "loss": 2.101,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 1.7031001164581828e-05,
-      "loss": 2.347,
+      "loss": 2.2077,
       "step": 48
     },
     {
       "epoch": 1.03,
       "learning_rate": 1.670249586567531e-05,
-      "loss": 1.9654,
+      "loss": 1.9385,
       "step": 50
     },
     {
       "epoch": 1.07,
       "learning_rate": 1.636029775176862e-05,
-      "loss": 1.918,
+      "loss": 2.0721,
       "step": 52
     },
     {
       "epoch": 1.11,
       "learning_rate": 1.6005105914000508e-05,
-      "loss": 2.0105,
+      "loss": 2.1402,
       "step": 54
     },
     {
       "epoch": 1.15,
       "learning_rate": 1.5637645988943008e-05,
-      "loss": 2.2175,
+      "loss": 2.3016,
       "step": 56
     },
     {
       "epoch": 1.19,
       "learning_rate": 1.5258668676167548e-05,
-      "loss": 1.8879,
+      "loss": 2.1148,
       "step": 58
     },
     {
       "epoch": 1.23,
       "learning_rate": 1.48689482046087e-05,
-      "loss": 2.2379,
+      "loss": 2.1329,
       "step": 60
     },
     {
       "epoch": 1.27,
       "learning_rate": 1.4469280750858854e-05,
-      "loss": 1.9181,
+      "loss": 2.0325,
       "step": 62
     },
     {
       "epoch": 1.31,
       "learning_rate": 1.4060482812625055e-05,
-      "loss": 1.9695,
+      "loss": 2.0027,
       "step": 64
     },
     {
       "epoch": 1.35,
       "learning_rate": 1.3643389540670963e-05,
-      "loss": 2.1585,
+      "loss": 2.067,
       "step": 66
     },
     {
       "epoch": 1.39,
       "learning_rate": 1.3218853032651719e-05,
-      "loss": 2.2469,
+      "loss": 1.9725,
       "step": 68
     },
     {
       "epoch": 1.44,
       "learning_rate": 1.2787740592327232e-05,
-      "loss": 2.158,
+      "loss": 2.1139,
       "step": 70
     },
     {
       "epoch": 1.48,
       "learning_rate": 1.2350932957710322e-05,
-      "loss": 2.1121,
+      "loss": 2.1837,
       "step": 72
     },
     {
       "epoch": 1.52,
       "learning_rate": 1.1909322501769407e-05,
-      "loss": 1.9493,
+      "loss": 1.956,
       "step": 74
     },
     {
       "epoch": 1.56,
       "learning_rate": 1.1463811409361667e-05,
-      "loss": 1.9611,
+      "loss": 1.8643,
       "step": 76
     },
     {
       "epoch": 1.6,
       "learning_rate": 1.1015309834121083e-05,
-      "loss": 2.182,
+      "loss": 2.1062,
       "step": 78
     },
     {
       "epoch": 1.64,
       "learning_rate": 1.05647340390667e-05,
-      "loss": 2.0111,
+      "loss": 2.1883,
       "step": 80
     },
     {
       "epoch": 1.68,
       "learning_rate": 1.01130045247298e-05,
-      "loss": 2.2589,
+      "loss": 1.999,
       "step": 82
     },
     {
       "epoch": 1.72,
       "learning_rate": 9.661044148624038e-06,
-      "loss": 2.0812,
+      "loss": 2.0649,
       "step": 84
     },
     {
       "epoch": 1.76,
       "learning_rate": 9.209776239900453e-06,
-      "loss": 2.0365,
+      "loss": 1.7508,
       "step": 86
     },
     {
       "epoch": 1.81,
       "learning_rate": 8.76012271303888e-06,
-      "loss": 2.09,
+      "loss": 2.0394,
       "step": 88
     },
     {
       "epoch": 1.85,
       "learning_rate": 8.313002184429529e-06,
-      "loss": 2.0565,
+      "loss": 2.0459,
       "step": 90
     },
     {
       "epoch": 1.89,
       "learning_rate": 7.869328095692313e-06,
-      "loss": 2.1456,
+      "loss": 2.1346,
       "step": 92
     },
     {
       "epoch": 1.93,
       "learning_rate": 7.430006847567972e-06,
-      "loss": 1.9832,
+      "loss": 2.1252,
       "step": 94
     },
     {
       "epoch": 1.97,
       "learning_rate": 6.995935948193294e-06,
-      "loss": 2.1603,
+      "loss": 2.0431,
       "step": 96
     },
     {
       "epoch": 2.01,
       "learning_rate": 6.568002179543409e-06,
-      "loss": 2.0932,
+      "loss": 2.1634,
       "step": 98
     },
     {
       "epoch": 2.05,
       "learning_rate": 6.147079785787038e-06,
-      "loss": 2.0403,
+      "loss": 1.8052,
       "step": 100
     },
     {
       "epoch": 2.09,
       "learning_rate": 5.7340286872557515e-06,
-      "loss": 1.9059,
+      "loss": 2.0465,
       "step": 102
     },
     {
       "epoch": 2.13,
       "learning_rate": 5.329692723675994e-06,
-      "loss": 2.1737,
+      "loss": 2.0533,
       "step": 104
     },
     {
       "epoch": 2.17,
       "learning_rate": 4.934897930252887e-06,
-      "loss": 2.0443,
+      "loss": 2.1753,
       "step": 106
     },
     {
       "epoch": 2.22,
       "learning_rate": 4.550450850127626e-06,
-      "loss": 2.0404,
+      "loss": 2.1203,
       "step": 108
     },
     {
       "epoch": 2.26,
       "learning_rate": 4.177136886656067e-06,
-      "loss": 1.9976,
+      "loss": 1.9635,
       "step": 110
     },
     {
       "epoch": 2.3,
       "learning_rate": 3.815718698874672e-06,
-      "loss": 1.8335,
+      "loss": 1.9614,
       "step": 112
     },
     {
       "epoch": 2.34,
       "learning_rate": 3.466934643431795e-06,
-      "loss": 2.2607,
+      "loss": 2.0104,
       "step": 114
     },
     {
       "epoch": 2.38,
       "learning_rate": 3.1314972661673572e-06,
-      "loss": 2.098,
+      "loss": 2.0814,
       "step": 116
     },
     {
       "epoch": 2.42,
       "learning_rate": 2.8100918464225304e-06,
-      "loss": 1.9934,
+      "loss": 2.1685,
       "step": 118
     },
     {
       "epoch": 2.46,
       "learning_rate": 2.5033749970533015e-06,
-      "loss": 2.0058,
+      "loss": 1.914,
       "step": 120
     },
     {
       "epoch": 2.5,
       "learning_rate": 2.211973323008041e-06,
-      "loss": 2.0931,
+      "loss": 2.0804,
       "step": 122
     },
     {
       "epoch": 2.54,
       "learning_rate": 1.936482141209486e-06,
-      "loss": 1.763,
+      "loss": 1.9071,
       "step": 124
     },
     {
       "epoch": 2.58,
       "learning_rate": 1.6774642643563955e-06,
-      "loss": 1.9877,
+      "loss": 2.1307,
       "step": 126
     },
     {
       "epoch": 2.63,
       "learning_rate": 1.4354488511294418e-06,
-      "loss": 2.2412,
+      "loss": 2.1478,
       "step": 128
     },
     {
       "epoch": 2.67,
       "learning_rate": 1.2109303251503434e-06,
-      "loss": 2.067,
+      "loss": 1.9693,
       "step": 130
     },
     {
       "epoch": 2.71,
       "learning_rate": 1.0043673649027519e-06,
-      "loss": 2.123,
+      "loss": 1.9913,
       "step": 132
     },
     {
       "epoch": 2.75,
       "learning_rate": 8.161819666783888e-07,
-      "loss": 2.0428,
+      "loss": 1.9936,
       "step": 134
     },
     {
       "epoch": 2.79,
       "learning_rate": 6.467585824627886e-07,
-      "loss": 1.8645,
+      "loss": 1.8671,
       "step": 136
     },
     {
       "epoch": 2.83,
       "learning_rate": 4.964433345219354e-07,
-      "loss": 2.1057,
+      "loss": 2.1326,
       "step": 138
     },
     {
       "epoch": 2.87,
       "learning_rate": 3.6554330829429716e-07,
-      "loss": 2.0721,
+      "loss": 2.1233,
       "step": 140
     },
     {
       "epoch": 2.91,
       "learning_rate": 2.5432592503288e-07,
-      "loss": 2.1623,
+      "loss": 2.0922,
       "step": 142
     },
     {
       "epoch": 2.95,
       "learning_rate": 1.630183954789233e-07,
-      "loss": 2.2136,
+      "loss": 2.0815,
       "step": 144
     }
   ],
@@ -446,7 +446,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.275170572624896e+16,
+  "total_flos": 1.2751629349782528e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52b3fc8b85d6cfe69705aad5966ccce8b92bad58312e1a1a9c7566b8df64b99
+oid sha256:ef422f322db7c57192c86b04e279604e2fec5f74b9f7720451b6bcd47fa7d026
 size 4728