Upload folder using huggingface_hub

adapter_config.json

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
-    "o_proj",
+    "q_proj",
     "gate_proj",
-    "k_proj",
+    "o_proj",
+    "down_proj",
     "v_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f0584a9fdecad22b26d4b43b9759f406a5219824727c031f1c8d8557e8792f
+oid sha256:cc805562df8d1ecadb0c7ceffd216b6ce1fc1b37b12c12a52bb95c28b1936981
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cbf7903fa258b793125361ef6b4c1b93c52baafc3b11c52784b5bac1e483d4
+oid sha256:dbc845a86ea49fcb13768bd2e1dffa9c405dc1c7d0f7bd8eff6b9a03d0a4e377
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619dbcc06b74b236aa1e4a20235db3ddb6093a74fe192b6d650a68dea86629c7
+oid sha256:97c1c57b943500bdd422828e26395d31b84f5a9794fe4c32c901ecbc4e90724e
 size 14244

trainer_state.json

@@ -11,187 +11,187 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.8763,
+      "loss": 1.6044,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.6551,
+      "loss": 1.5881,
       "step": 4
     },
     {
       "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.6117,
+      "loss": 1.5893,
       "step": 6
     },
     {
       "epoch": 0.13,
       "learning_rate": 0.0002,
-      "loss": 1.4364,
+      "loss": 1.6713,
       "step": 8
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.3856,
+      "loss": 1.6675,
       "step": 10
     },
     {
       "epoch": 0.19,
       "learning_rate": 0.0002,
-      "loss": 1.888,
+      "loss": 1.728,
       "step": 12
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.7773,
+      "loss": 2.0484,
       "step": 14
     },
     {
       "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 2.7147,
+      "loss": 1.6691,
       "step": 16
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 1.6225,
+      "loss": 1.2777,
       "step": 18
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.4844,
+      "loss": 1.3286,
       "step": 20
     },
     {
       "epoch": 0.35,
       "learning_rate": 0.0002,
-      "loss": 1.2329,
+      "loss": 1.2907,
       "step": 22
     },
     {
       "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.0668,
+      "loss": 1.2286,
       "step": 24
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.0695,
+      "loss": 1.3034,
       "step": 26
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.8005,
+      "loss": 1.2253,
       "step": 28
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 2.2701,
+      "loss": 1.398,
       "step": 30
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 1.7467,
+      "loss": 1.1233,
       "step": 32
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.416,
+      "loss": 1.181,
       "step": 34
     },
     {
       "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.3106,
+      "loss": 1.1303,
       "step": 36
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 0.8445,
+      "loss": 1.12,
       "step": 38
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 1.0193,
+      "loss": 1.191,
       "step": 40
     },
     {
       "epoch": 0.67,
       "learning_rate": 0.0002,
-      "loss": 1.5088,
+      "loss": 1.1562,
       "step": 42
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 1.7339,
+      "loss": 1.1221,
       "step": 44
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.137,
+      "loss": 1.2625,
       "step": 46
     },
     {
       "epoch": 0.77,
       "learning_rate": 0.0002,
-      "loss": 1.3696,
+      "loss": 1.0936,
       "step": 48
     },
     {
       "epoch": 0.8,
       "learning_rate": 0.0002,
-      "loss": 1.338,
+      "loss": 1.048,
       "step": 50
     },
     {
       "epoch": 0.83,
       "learning_rate": 0.0002,
-      "loss": 1.2948,
+      "loss": 0.9645,
       "step": 52
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 0.9147,
+      "loss": 1.0299,
       "step": 54
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 1.1057,
+      "loss": 1.0774,
       "step": 56
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 1.4985,
+      "loss": 1.1457,
       "step": 58
     },
     {
       "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 1.9006,
+      "loss": 1.1011,
       "step": 60
     },
     {
       "epoch": 0.99,
       "learning_rate": 0.0002,
-      "loss": 1.1481,
+      "loss": 1.0221,
       "step": 62
     }
   ],
@@ -200,7 +200,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3204864602185728.0,
+  "total_flos": 2179055645245440.0,
   "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 sha256:0681cd1910c2b08abb29c099e64819599db5cbd9791249e18d756090b563b039
+oid sha256:085df06261844d8e43666229030657ce5dd5cc1aac22d14d759f080cd507fb4e
 size 4728