Training in progress, step 100

adapter_config.json

@@ -10,21 +10,21 @@
   "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",
     "q_proj",
-    "down_proj",
-    "up_proj",
     "o_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
     "v_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf020752b7d1b1382c9b71928e7ee85e7e8c494fe1f52c525d9e3eae0aa3c788
-size 19644912
+oid sha256:cf96b1b9d7a5cc39cb84eddc588a71a535f3903fe60b73b82e0112914261b2b0
+size 39256960

runs/Jun10_10-37-10_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717983445.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.72146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa07bca9b3386471b214aa30ac3234ecab0e5611ed90fc3015ec38234b725337
+size 10210

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e693b80f5e674b957ca459dc43344279ea91abfa6a33dc5f9441ed6fa2eb507
+oid sha256:f8ec6b20955f1712c693a9e90c8f9b61569046214f121858301f052f8bc4d73e
 size 5304