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": [
     "up_proj",
-    "q_proj",
-    "gate_proj",
-    "down_proj",
     "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
     "o_proj",
-    "v_proj"
+    "gate_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:a9087fa1bb83829ae295ab3613a7241125ca8071426aea9e9d36caa432da8207
-size 19644912
+oid sha256:d321a2938a6c4a228473b8a6a912d8aae9f033574f4a5a2c0b52c8027c734127
+size 78480320

runs/Jun11_02-05-02_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718039128.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.18115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d40bfde9ae59e288953567fb66219b0d625951dc78d238c07805ebbc81f6fae
+size 9980

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740c45c5229a63c1e016512f9de4508a8df9dc335e19089a6885c51d6bb4230f
-size 5240
+oid sha256:75ec3a6870fe803573a05bb18448cff8e23af8dcd6dc487404aeb473b7065ff2
+size 5368