Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "k_proj",
     "up_proj",
-    "o_proj",
-    "down_proj",
     "v_proj",
-    "k_proj",
-    "q_proj"
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2c2d17c5a93a5d7d4bb2cf165f327db8c660c1433f24a1514fe1f345583238
-size 19644912
+oid sha256:e05cec8fd53f4b2a0e509bebcc6ad92f1f237ac0f6ea2d3f365e159e942ad99c
+size 39256960

runs/Jun10_10-58-48_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717984754.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.2790.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98bede091089136c9f338ecea3e3a5cb56eb3c4662eeaa53ce978825715ed78
+size 9976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92ca1c3c2f398289fef9b9cef09a653686f550bbd615f971cf725b3dc192ad4
-size 5240
+oid sha256:43cbf465a2c5205d37fe33b12900f53e0cb88c69da1bd121b342eb3f7a856026
+size 5368