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": [
+    "up_proj",
     "q_proj",
+    "down_proj",
     "v_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj"
+    "o_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 sha256:3caec7cf7cfc25de5f85d3a629c6929e390c7c48b85546c19f0589510a3ab2d7
-size 19644912
+oid sha256:175c4ae4482407e27e4f1aab77580c912c52f99541381caf65e5c86bcdabcf97
+size 39256960

runs/Jun10_11-43-03_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717987400.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.73754.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44a3aa272e621c20581b6e8384faa1b154539643b0d6424d62cbcbe27dc937b
+size 9944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a096b6af6930227ee47276d82859871a167cf72e3c2b01fad1399f27dcda745
+oid sha256:9701d374006488c3c752f343e751a9352e46b8cc32754ddb0a8fe6f15b6bcfc7
 size 5304