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": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "up_proj",
     "gate_proj",
     "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
     "v_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765066d44432dc7090f036af6595e09ac9d800683350210eaa10405ebb6f89dc
-size 19644912
+oid sha256:62f1cf17ab573085a752c69ad5c48b61e7fda5f2d3d0235bac64f65891f8dac6
+size 78480320

runs/Jun10_19-04-55_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718013909.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.13878.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f8138a73b4dc511d4e6daa52cd47c4d416b39791451d0393f6563af1015180
+size 9980

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:174195be04c6bb2b96cedf1750789af6a677a8d4a180e7ed8dee1a30d12d5e7b
-size 5240
+oid sha256:72fbceb9c377592e441321846e287d76bb73528f2c6479654741d1c35a64df8d
+size 5368