Upload folder using huggingface_hub

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
-    "dense",
     "dense_h_to_4h",
-    "query_key_value"
+    "dense",
+    "query_key_value",
+    "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:ff225d7cd93c9354fe146f6b33e9f90435dbb7291d293690f9dd87ff7d35928f
+oid sha256:60682c0af9f3fd541cd80ee8666eab66077d73f8107e9a7c8be7e909edffe93e
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe1233fbe6e7880347093fdca26f5f414e52348c16039e94627c15ecd4fd308
+oid sha256:04f1c0332a2f1bc5146fc51551ce74af78597f9b37521f92923417ff3d730291
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48d238a5896aebf0de11d918fdfa448e01e704d941b7d64bc881878d172f396
+oid sha256:0cd0cb197f9704e08105e7ec5866b4b909e204f437e856c73b38b61e70f01ff4
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.2963,
+      "loss": 2.1776,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.377,
+      "loss": 2.4224,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.4958,
+      "loss": 2.5657,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.5016,
+      "loss": 2.5934,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.439,
+      "loss": 2.6175,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 2.8349,
+      "loss": 2.8582,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2263,
+      "loss": 2.2232,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.3421,
+      "loss": 2.2464,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.5675,
+      "loss": 2.5335,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.5763,
+      "loss": 2.6144,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.5332,
+      "loss": 2.395,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 2.8075,
+      "loss": 2.8326,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.3415,
+      "loss": 2.3137,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.2512,
+      "loss": 2.4326,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.533,
+      "loss": 2.5481,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.555,
+      "loss": 2.3901,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.6089,
+      "loss": 2.4413,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.5684,
+      "loss": 2.6465,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.1186,
+      "loss": 2.2408,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.3147,
+      "loss": 2.1161,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.4782,
+      "loss": 2.4779,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.25,
+      "loss": 2.3948,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.501,
+      "loss": 2.6741,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.705,
+      "loss": 2.584,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2049661840859136.0,
+  "total_flos": 2045076543504384.0,
   "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 sha256:2304f2bd39d21efc47c500cd5068601045aac2e65032bd864752914da7a71dbf
+oid sha256:9b7c2e8ee1ce9a7a2b3f3bf215f3cac1050303b7acc970ceff11e5960a5a1cce
 size 4728