Upload folder using huggingface_hub

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda2e7eeb2e05558aad305b947d18e40371994273b1eed16695539b04dacdb9a
+oid sha256:56408c2ec49ba9e4484688a0b921dd667fb6d209333935c9df51ff0e397f71cc
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf51aaab65bdb12c34dad1d8d2f1759991d05f3e3ead5314308860be6212404
+oid sha256:55a0cef79cb0217c66b96785c9b983eaa0c47531361233305cfd5b6e5be094ad
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b772e495c0a15affc6564a65138b0f1afe44b783339b26b29aff2f39cc64c0f
+oid sha256:5dd6d270a779be8e669e4b188078f38308064c9b18edae78c223f89d5b0c5e5a
 size 14244

trainer_state.json

@@ -11,559 +11,559 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.7597,
+      "loss": 1.9875,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.7691,
+      "loss": 1.6222,
       "step": 4
     },
     {
       "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.7391,
+      "loss": 1.7088,
       "step": 6
     },
     {
       "epoch": 0.13,
       "learning_rate": 0.0002,
-      "loss": 1.8441,
+      "loss": 1.624,
       "step": 8
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.8435,
+      "loss": 1.4983,
       "step": 10
     },
     {
       "epoch": 0.19,
       "learning_rate": 0.0002,
-      "loss": 1.946,
+      "loss": 1.7191,
       "step": 12
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 1.8873,
+      "loss": 2.3085,
       "step": 14
     },
     {
       "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 1.7255,
+      "loss": 2.4811,
       "step": 16
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 1.5998,
+      "loss": 1.7176,
       "step": 18
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.5016,
+      "loss": 1.6774,
       "step": 20
     },
     {
       "epoch": 0.35,
       "learning_rate": 0.0002,
-      "loss": 1.3951,
+      "loss": 1.6692,
       "step": 22
     },
     {
       "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.4886,
+      "loss": 1.3514,
       "step": 24
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.4517,
+      "loss": 1.4799,
       "step": 26
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.4721,
+      "loss": 2.0934,
       "step": 28
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.541,
+      "loss": 2.4565,
       "step": 30
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 1.2211,
+      "loss": 1.734,
       "step": 32
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.3493,
+      "loss": 1.8199,
       "step": 34
     },
     {
       "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.369,
+      "loss": 1.614,
       "step": 36
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 1.3797,
+      "loss": 1.3391,
       "step": 38
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 1.3887,
+      "loss": 1.3939,
       "step": 40
     },
     {
       "epoch": 0.67,
       "learning_rate": 0.0002,
-      "loss": 1.3289,
+      "loss": 1.661,
       "step": 42
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 1.2585,
+      "loss": 1.9097,
       "step": 44
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 1.5215,
+      "loss": 2.2357,
       "step": 46
     },
     {
       "epoch": 0.77,
       "learning_rate": 0.0002,
-      "loss": 1.3621,
+      "loss": 1.5075,
       "step": 48
     },
     {
       "epoch": 0.8,
       "learning_rate": 0.0002,
-      "loss": 1.3361,
+      "loss": 1.6559,
       "step": 50
     },
     {
       "epoch": 0.83,
       "learning_rate": 0.0002,
-      "loss": 1.1277,
+      "loss": 1.4698,
       "step": 52
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.3098,
+      "loss": 1.425,
       "step": 54
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 1.2836,
+      "loss": 1.4822,
       "step": 56
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 1.3276,
+      "loss": 1.7588,
       "step": 58
     },
     {
       "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 1.2232,
+      "loss": 1.8205,
       "step": 60
     },
     {
       "epoch": 0.99,
       "learning_rate": 0.0002,
-      "loss": 1.3009,
+      "loss": 1.5478,
       "step": 62
     },
     {
       "epoch": 1.02,
       "learning_rate": 0.0002,
-      "loss": 1.3459,
+      "loss": 1.9213,
       "step": 64
     },
     {
       "epoch": 1.06,
       "learning_rate": 0.0002,
-      "loss": 1.2756,
+      "loss": 1.3823,
       "step": 66
     },
     {
       "epoch": 1.09,
       "learning_rate": 0.0002,
-      "loss": 1.2275,
+      "loss": 1.5282,
       "step": 68
     },
     {
       "epoch": 1.12,
       "learning_rate": 0.0002,
-      "loss": 1.266,
+      "loss": 1.3108,
       "step": 70
     },
     {
       "epoch": 1.15,
       "learning_rate": 0.0002,
-      "loss": 1.3021,
+      "loss": 1.2504,
       "step": 72
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.0002,
-      "loss": 1.3212,
+      "loss": 1.2357,
       "step": 74
     },
     {
       "epoch": 1.22,
       "learning_rate": 0.0002,
-      "loss": 1.0714,
+      "loss": 1.7761,
       "step": 76
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0002,
-      "loss": 1.2865,
+      "loss": 1.5256,
       "step": 78
     },
     {
       "epoch": 1.28,
       "learning_rate": 0.0002,
-      "loss": 1.1694,
+      "loss": 1.7673,
       "step": 80
     },
     {
       "epoch": 1.31,
       "learning_rate": 0.0002,
-      "loss": 1.2996,
+      "loss": 1.669,
       "step": 82
     },
     {
       "epoch": 1.34,
       "learning_rate": 0.0002,
-      "loss": 1.185,
+      "loss": 1.5903,
       "step": 84
     },
     {
       "epoch": 1.38,
       "learning_rate": 0.0002,
-      "loss": 1.2625,
+      "loss": 1.0959,
       "step": 86
     },
     {
       "epoch": 1.41,
       "learning_rate": 0.0002,
-      "loss": 1.2019,
+      "loss": 1.2544,
       "step": 88
     },
     {
       "epoch": 1.44,
       "learning_rate": 0.0002,
-      "loss": 1.2313,
+      "loss": 1.5317,
       "step": 90
     },
     {
       "epoch": 1.47,
       "learning_rate": 0.0002,
-      "loss": 1.1451,
+      "loss": 1.789,
       "step": 92
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0002,
-      "loss": 1.2957,
+      "loss": 1.6952,
       "step": 94
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0002,
-      "loss": 1.1715,
+      "loss": 1.6499,
       "step": 96
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.0002,
-      "loss": 1.2473,
+      "loss": 1.4369,
       "step": 98
     },
     {
       "epoch": 1.6,
       "learning_rate": 0.0002,
-      "loss": 1.1796,
+      "loss": 1.3262,
       "step": 100
     },
     {
       "epoch": 1.63,
       "learning_rate": 0.0002,
-      "loss": 1.211,
+      "loss": 1.2666,
       "step": 102
     },
     {
       "epoch": 1.66,
       "learning_rate": 0.0002,
-      "loss": 1.1733,
+      "loss": 1.3001,
       "step": 104
     },
     {
       "epoch": 1.7,
       "learning_rate": 0.0002,
-      "loss": 1.156,
+      "loss": 1.592,
       "step": 106
     },
     {
       "epoch": 1.73,
       "learning_rate": 0.0002,
-      "loss": 1.124,
+      "loss": 1.7889,
       "step": 108
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0002,
-      "loss": 1.2058,
+      "loss": 1.6086,
       "step": 110
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0002,
-      "loss": 1.2686,
+      "loss": 1.5085,
       "step": 112
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0002,
-      "loss": 1.1246,
+      "loss": 1.4875,
       "step": 114
     },
     {
       "epoch": 1.86,
       "learning_rate": 0.0002,
-      "loss": 1.1836,
+      "loss": 1.282,
       "step": 116
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0002,
-      "loss": 1.1491,
+      "loss": 1.188,
       "step": 118
     },
     {
       "epoch": 1.92,
       "learning_rate": 0.0002,
-      "loss": 1.2865,
+      "loss": 1.373,
       "step": 120
     },
     {
       "epoch": 1.95,
       "learning_rate": 0.0002,
-      "loss": 1.1011,
+      "loss": 1.477,
       "step": 122
     },
     {
       "epoch": 1.98,
       "learning_rate": 0.0002,
-      "loss": 1.267,
+      "loss": 1.6242,
       "step": 124
     },
     {
       "epoch": 2.02,
       "learning_rate": 0.0002,
-      "loss": 1.128,
+      "loss": 1.6837,
       "step": 126
     },
     {
       "epoch": 2.05,
       "learning_rate": 0.0002,
-      "loss": 1.1364,
+      "loss": 1.4979,
       "step": 128
     },
     {
       "epoch": 2.08,
       "learning_rate": 0.0002,
-      "loss": 1.0983,
+      "loss": 1.4929,
       "step": 130
     },
     {
       "epoch": 2.11,
       "learning_rate": 0.0002,
-      "loss": 1.0923,
+      "loss": 1.3345,
       "step": 132
     },
     {
       "epoch": 2.14,
       "learning_rate": 0.0002,
-      "loss": 1.142,
+      "loss": 1.1678,
       "step": 134
     },
     {
       "epoch": 2.18,
       "learning_rate": 0.0002,
-      "loss": 1.1277,
+      "loss": 1.0854,
       "step": 136
     },
     {
       "epoch": 2.21,
       "learning_rate": 0.0002,
-      "loss": 1.0157,
+      "loss": 1.2597,
       "step": 138
     },
     {
       "epoch": 2.24,
       "learning_rate": 0.0002,
-      "loss": 0.9849,
+      "loss": 1.2452,
       "step": 140
     },
     {
       "epoch": 2.27,
       "learning_rate": 0.0002,
-      "loss": 1.2084,
+      "loss": 1.8322,
       "step": 142
     },
     {
       "epoch": 2.3,
       "learning_rate": 0.0002,
-      "loss": 1.1842,
+      "loss": 1.5011,
       "step": 144
     },
     {
       "epoch": 2.34,
       "learning_rate": 0.0002,
-      "loss": 1.2013,
+      "loss": 1.4569,
       "step": 146
     },
     {
       "epoch": 2.37,
       "learning_rate": 0.0002,
-      "loss": 1.1305,
+      "loss": 1.1229,
       "step": 148
     },
     {
       "epoch": 2.4,
       "learning_rate": 0.0002,
-      "loss": 1.1419,
+      "loss": 1.0178,
       "step": 150
     },
     {
       "epoch": 2.43,
       "learning_rate": 0.0002,
-      "loss": 1.1472,
+      "loss": 0.9499,
       "step": 152
     },
     {
       "epoch": 2.46,
       "learning_rate": 0.0002,
-      "loss": 0.9259,
+      "loss": 1.3877,
       "step": 154
     },
     {
       "epoch": 2.5,
       "learning_rate": 0.0002,
-      "loss": 1.1574,
+      "loss": 1.4279,
       "step": 156
     },
     {
       "epoch": 2.53,
       "learning_rate": 0.0002,
-      "loss": 1.2082,
+      "loss": 1.5053,
       "step": 158
     },
     {
       "epoch": 2.56,
       "learning_rate": 0.0002,
-      "loss": 1.2029,
+      "loss": 1.4945,
       "step": 160
     },
     {
       "epoch": 2.59,
       "learning_rate": 0.0002,
-      "loss": 1.1883,
+      "loss": 1.4151,
       "step": 162
     },
     {
       "epoch": 2.62,
       "learning_rate": 0.0002,
-      "loss": 1.1662,
+      "loss": 1.0512,
       "step": 164
     },
     {
       "epoch": 2.66,
       "learning_rate": 0.0002,
-      "loss": 1.1388,
+      "loss": 1.2224,
       "step": 166
     },
     {
       "epoch": 2.69,
       "learning_rate": 0.0002,
-      "loss": 1.0185,
+      "loss": 1.4344,
       "step": 168
     },
     {
       "epoch": 2.72,
       "learning_rate": 0.0002,
-      "loss": 0.9262,
+      "loss": 1.2874,
       "step": 170
     },
     {
       "epoch": 2.75,
       "learning_rate": 0.0002,
-      "loss": 1.2859,
+      "loss": 1.845,
       "step": 172
     },
     {
       "epoch": 2.78,
       "learning_rate": 0.0002,
-      "loss": 1.2683,
+      "loss": 1.5317,
       "step": 174
     },
     {
       "epoch": 2.82,
       "learning_rate": 0.0002,
-      "loss": 1.0533,
+      "loss": 1.3465,
       "step": 176
     },
     {
       "epoch": 2.85,
       "learning_rate": 0.0002,
-      "loss": 1.095,
+      "loss": 1.1323,
       "step": 178
     },
     {
       "epoch": 2.88,
       "learning_rate": 0.0002,
-      "loss": 1.0904,
+      "loss": 1.1242,
       "step": 180
     },
     {
       "epoch": 2.91,
       "learning_rate": 0.0002,
-      "loss": 1.0844,
+      "loss": 1.3615,
       "step": 182
     },
     {
       "epoch": 2.94,
       "learning_rate": 0.0002,
-      "loss": 0.9657,
+      "loss": 1.2473,
       "step": 184
     },
     {
       "epoch": 2.98,
       "learning_rate": 0.0002,
-      "loss": 1.0686,
+      "loss": 1.4774,
       "step": 186
     }
   ],
@@ -572,7 +572,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4225580494577664.0,
+  "total_flos": 6327817773293568.0,
   "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 sha256:0c2ca62d8b872f5570f8734b5af327cc6ba8c68f65662987fd2a2703a05c01fc
+oid sha256:899688d04ff97d2aaa081138b17e41596da543004cd3455e1d859e127c0719b2
 size 4728