Upload folder using huggingface_hub

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
+    "dense_h_to_4h",
     "dense",
     "dense_4h_to_h",
-    "dense_h_to_4h"
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156947125904fc15345a796ddebb5d29a0c200da64a794d4d18eee53c52ecf33
+oid sha256:1029352956f41c995bbab514c89a7bda865d44520c44c983e40e90195e4165fd
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef1522bb078d5fbae65a850ced5b1eac93f5801c6e3a548a3ee2c03da64317d
+oid sha256:33bee878c8e06c3007394de1644c785cba41e3e01fa63f2aac8666f21c94b53b
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36036b8e9cb8bf1908ccee95412415e841201c79e48dfc95f6c2d397b24a1f3
+oid sha256:cdc263226150a1c504bd2ca4fcc02f23de94da18ea54442257a548ed801dda45
 size 14244

trainer_state.json

@@ -11,601 +11,601 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.7288,
+      "loss": 2.4072,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 2.1485,
+      "loss": 1.9622,
       "step": 4
     },
     {
       "epoch": 0.09,
       "learning_rate": 0.0002,
-      "loss": 1.8821,
+      "loss": 1.8757,
       "step": 6
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.986,
+      "loss": 1.8847,
       "step": 8
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 1.8129,
+      "loss": 1.7333,
       "step": 10
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.5467,
+      "loss": 1.8547,
       "step": 12
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 1.837,
+      "loss": 2.0118,
       "step": 14
     },
     {
       "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 1.7176,
+      "loss": 1.8139,
       "step": 16
     },
     {
       "epoch": 0.27,
       "learning_rate": 0.0002,
-      "loss": 2.2534,
+      "loss": 2.3062,
       "step": 18
     },
     {
       "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.6446,
+      "loss": 2.1489,
       "step": 20
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 1.6897,
+      "loss": 1.7783,
       "step": 22
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.7913,
+      "loss": 1.661,
       "step": 24
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 1.3692,
+      "loss": 1.4785,
       "step": 26
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.5104,
+      "loss": 1.5294,
       "step": 28
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.7339,
+      "loss": 1.8193,
       "step": 30
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.3308,
+      "loss": 1.6798,
       "step": 32
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.1892,
+      "loss": 2.3295,
       "step": 34
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.7639,
+      "loss": 1.9608,
       "step": 36
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 1.683,
+      "loss": 1.6603,
       "step": 38
     },
     {
       "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.5708,
+      "loss": 1.6115,
       "step": 40
     },
     {
       "epoch": 0.63,
       "learning_rate": 0.0002,
-      "loss": 1.4114,
+      "loss": 1.3979,
       "step": 42
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 1.5305,
+      "loss": 1.7217,
       "step": 44
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.0002,
-      "loss": 1.5418,
+      "loss": 1.6246,
       "step": 46
     },
     {
       "epoch": 0.72,
       "learning_rate": 0.0002,
-      "loss": 1.2955,
+      "loss": 1.4965,
       "step": 48
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 2.4863,
+      "loss": 2.4293,
       "step": 50
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 1.8446,
+      "loss": 1.651,
       "step": 52
     },
     {
       "epoch": 0.81,
       "learning_rate": 0.0002,
-      "loss": 1.6516,
+      "loss": 1.7392,
       "step": 54
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.0002,
-      "loss": 1.5209,
+      "loss": 1.7796,
       "step": 56
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.3298,
+      "loss": 1.5059,
       "step": 58
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 1.4544,
+      "loss": 1.5211,
       "step": 60
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0002,
-      "loss": 1.5177,
+      "loss": 1.4616,
       "step": 62
     },
     {
       "epoch": 0.95,
       "learning_rate": 0.0002,
-      "loss": 1.3454,
+      "loss": 1.4818,
       "step": 64
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 1.5538,
+      "loss": 1.6473,
       "step": 66
     },
     {
       "epoch": 1.01,
       "learning_rate": 0.0002,
-      "loss": 1.905,
+      "loss": 2.0672,
       "step": 68
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0002,
-      "loss": 2.016,
+      "loss": 1.747,
       "step": 70
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0002,
-      "loss": 1.5493,
+      "loss": 1.6798,
       "step": 72
     },
     {
       "epoch": 1.1,
       "learning_rate": 0.0002,
-      "loss": 1.5867,
+      "loss": 1.5336,
       "step": 74
     },
     {
       "epoch": 1.13,
       "learning_rate": 0.0002,
-      "loss": 1.6154,
+      "loss": 1.478,
       "step": 76
     },
     {
       "epoch": 1.16,
       "learning_rate": 0.0002,
-      "loss": 1.2208,
+      "loss": 1.3612,
       "step": 78
     },
     {
       "epoch": 1.19,
       "learning_rate": 0.0002,
-      "loss": 1.3932,
+      "loss": 1.4822,
       "step": 80
     },
     {
       "epoch": 1.22,
       "learning_rate": 0.0002,
-      "loss": 1.4372,
+      "loss": 1.5777,
       "step": 82
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0002,
-      "loss": 1.7286,
+      "loss": 1.5267,
       "step": 84
     },
     {
       "epoch": 1.28,
       "learning_rate": 0.0002,
-      "loss": 2.019,
+      "loss": 2.09,
       "step": 86
     },
     {
       "epoch": 1.31,
       "learning_rate": 0.0002,
-      "loss": 1.6197,
+      "loss": 1.5577,
       "step": 88
     },
     {
       "epoch": 1.34,
       "learning_rate": 0.0002,
-      "loss": 1.6878,
+      "loss": 1.6998,
       "step": 90
     },
     {
       "epoch": 1.37,
       "learning_rate": 0.0002,
-      "loss": 1.4629,
+      "loss": 1.4994,
       "step": 92
     },
     {
       "epoch": 1.4,
       "learning_rate": 0.0002,
-      "loss": 1.2949,
+      "loss": 1.1934,
       "step": 94
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.0002,
-      "loss": 1.4003,
+      "loss": 1.3973,
       "step": 96
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0002,
-      "loss": 1.4388,
+      "loss": 1.457,
       "step": 98
     },
     {
       "epoch": 1.49,
       "learning_rate": 0.0002,
-      "loss": 1.179,
+      "loss": 1.4781,
       "step": 100
     },
     {
       "epoch": 1.52,
       "learning_rate": 0.0002,
-      "loss": 2.1112,
+      "loss": 2.1705,
       "step": 102
     },
     {
       "epoch": 1.55,
       "learning_rate": 0.0002,
-      "loss": 1.7006,
+      "loss": 1.5827,
       "step": 104
     },
     {
       "epoch": 1.58,
       "learning_rate": 0.0002,
-      "loss": 1.4977,
+      "loss": 1.6973,
       "step": 106
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0002,
-      "loss": 1.6462,
+      "loss": 1.5756,
       "step": 108
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0002,
-      "loss": 1.3297,
+      "loss": 1.228,
       "step": 110
     },
     {
       "epoch": 1.67,
       "learning_rate": 0.0002,
-      "loss": 1.3384,
+      "loss": 1.3241,
       "step": 112
     },
     {
       "epoch": 1.7,
       "learning_rate": 0.0002,
-      "loss": 1.356,
+      "loss": 1.5305,
       "step": 114
     },
     {
       "epoch": 1.73,
       "learning_rate": 0.0002,
-      "loss": 1.4641,
+      "loss": 1.6581,
       "step": 116
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0002,
-      "loss": 2.0829,
+      "loss": 2.3319,
       "step": 118
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0002,
-      "loss": 1.5826,
+      "loss": 1.6531,
       "step": 120
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0002,
-      "loss": 1.4997,
+      "loss": 1.5482,
       "step": 122
     },
     {
       "epoch": 1.85,
       "learning_rate": 0.0002,
-      "loss": 1.4314,
+      "loss": 1.6534,
       "step": 124
     },
     {
       "epoch": 1.88,
       "learning_rate": 0.0002,
-      "loss": 1.2322,
+      "loss": 1.2656,
       "step": 126
     },
     {
       "epoch": 1.91,
       "learning_rate": 0.0002,
-      "loss": 1.2579,
+      "loss": 1.462,
       "step": 128
     },
     {
       "epoch": 1.94,
       "learning_rate": 0.0002,
-      "loss": 1.4243,
+      "loss": 1.4357,
       "step": 130
     },
     {
       "epoch": 1.97,
       "learning_rate": 0.0002,
-      "loss": 1.4007,
+      "loss": 1.4769,
       "step": 132
     },
     {
       "epoch": 2.0,
       "learning_rate": 0.0002,
-      "loss": 1.3165,
+      "loss": 1.5089,
       "step": 134
     },
     {
       "epoch": 2.03,
       "learning_rate": 0.0002,
-      "loss": 2.2527,
+      "loss": 2.6047,
       "step": 136
     },
     {
       "epoch": 2.06,
       "learning_rate": 0.0002,
-      "loss": 1.7019,
+      "loss": 1.9267,
       "step": 138
     },
     {
       "epoch": 2.09,
       "learning_rate": 0.0002,
-      "loss": 1.5064,
+      "loss": 1.552,
       "step": 140
     },
     {
       "epoch": 2.12,
       "learning_rate": 0.0002,
-      "loss": 1.5758,
+      "loss": 1.5174,
       "step": 142
     },
     {
       "epoch": 2.15,
       "learning_rate": 0.0002,
-      "loss": 1.4431,
+      "loss": 1.1909,
       "step": 144
     },
     {
       "epoch": 2.18,
       "learning_rate": 0.0002,
-      "loss": 1.1322,
+      "loss": 1.1614,
       "step": 146
     },
     {
       "epoch": 2.21,
       "learning_rate": 0.0002,
-      "loss": 1.1932,
+      "loss": 1.306,
       "step": 148
     },
     {
       "epoch": 2.24,
       "learning_rate": 0.0002,
-      "loss": 0.8962,
+      "loss": 1.0872,
       "step": 150
     },
     {
       "epoch": 2.27,
       "learning_rate": 0.0002,
-      "loss": 2.2722,
+      "loss": 2.2395,
       "step": 152
     },
     {
       "epoch": 2.3,
       "learning_rate": 0.0002,
-      "loss": 1.9434,
+      "loss": 1.7894,
       "step": 154
     },
     {
       "epoch": 2.33,
       "learning_rate": 0.0002,
-      "loss": 1.5319,
+      "loss": 1.6281,
       "step": 156
     },
     {
       "epoch": 2.36,
       "learning_rate": 0.0002,
-      "loss": 1.4101,
+      "loss": 1.6183,
       "step": 158
     },
     {
       "epoch": 2.39,
       "learning_rate": 0.0002,
-      "loss": 1.3388,
+      "loss": 1.3153,
       "step": 160
     },
     {
       "epoch": 2.42,
       "learning_rate": 0.0002,
-      "loss": 1.2689,
+      "loss": 1.2935,
       "step": 162
     },
     {
       "epoch": 2.45,
       "learning_rate": 0.0002,
-      "loss": 1.1449,
+      "loss": 1.3173,
       "step": 164
     },
     {
       "epoch": 2.48,
       "learning_rate": 0.0002,
-      "loss": 0.8975,
+      "loss": 0.9721,
       "step": 166
     },
     {
       "epoch": 2.51,
       "learning_rate": 0.0002,
-      "loss": 2.0784,
+      "loss": 1.8607,
       "step": 168
     },
     {
       "epoch": 2.53,
       "learning_rate": 0.0002,
-      "loss": 1.46,
+      "loss": 1.598,
       "step": 170
     },
     {
       "epoch": 2.56,
       "learning_rate": 0.0002,
-      "loss": 1.6374,
+      "loss": 1.5441,
       "step": 172
     },
     {
       "epoch": 2.59,
       "learning_rate": 0.0002,
-      "loss": 1.5981,
+      "loss": 1.5628,
       "step": 174
     },
     {
       "epoch": 2.62,
       "learning_rate": 0.0002,
-      "loss": 1.1474,
+      "loss": 1.3187,
       "step": 176
     },
     {
       "epoch": 2.65,
       "learning_rate": 0.0002,
-      "loss": 1.2735,
+      "loss": 1.2027,
       "step": 178
     },
     {
       "epoch": 2.68,
       "learning_rate": 0.0002,
-      "loss": 1.1469,
+      "loss": 1.3727,
       "step": 180
     },
     {
       "epoch": 2.71,
       "learning_rate": 0.0002,
-      "loss": 1.0846,
+      "loss": 1.1875,
       "step": 182
     },
     {
       "epoch": 2.74,
       "learning_rate": 0.0002,
-      "loss": 2.048,
+      "loss": 1.9715,
       "step": 184
     },
     {
       "epoch": 2.77,
       "learning_rate": 0.0002,
-      "loss": 1.628,
+      "loss": 1.6918,
       "step": 186
     },
     {
       "epoch": 2.8,
       "learning_rate": 0.0002,
-      "loss": 1.5144,
+      "loss": 1.6092,
       "step": 188
     },
     {
       "epoch": 2.83,
       "learning_rate": 0.0002,
-      "loss": 1.5147,
+      "loss": 1.4727,
       "step": 190
     },
     {
       "epoch": 2.86,
       "learning_rate": 0.0002,
-      "loss": 1.169,
+      "loss": 1.4236,
       "step": 192
     },
     {
       "epoch": 2.89,
       "learning_rate": 0.0002,
-      "loss": 1.1152,
+      "loss": 1.2674,
       "step": 194
     },
     {
       "epoch": 2.92,
       "learning_rate": 0.0002,
-      "loss": 1.2723,
+      "loss": 1.1127,
       "step": 196
     },
     {
       "epoch": 2.95,
       "learning_rate": 0.0002,
-      "loss": 0.9781,
+      "loss": 1.0309,
       "step": 198
     },
     {
       "epoch": 2.98,
       "learning_rate": 0.0002,
-      "loss": 1.5831,
+      "loss": 1.5248,
       "step": 200
     }
   ],
@@ -614,7 +614,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 9208470057197568.0,
+  "total_flos": 9019630437408768.0,
   "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 sha256:16b6b67553fc11ab749e3fb148bfbcd92169a909fd51905d3b409fd3c1d9396c
+oid sha256:814ed334932763a139ba3f72ece77cd8ba7084fb47f41613bb0e6fe31f432fe8
 size 4728