Training in progress, step 100

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:b93b8bceba00a022f719e9a55897bea86fc38ce97ed69308bb9c5ba89422bae9
-size 12859872
+oid sha256:be0d26d5d7fecb32d62d21463fba562efa57d2b57c9bd335175f6f113a11f763
+size 102775544

runs/Nov16_02-36-23_main-lora-gemma7b-alpaca-0-0/events.out.tfevents.1731743352.main-lora-gemma7b-alpaca-0-0.457.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e55ac36072ca9d21f694d60f8663537da56d6413986e3a385f83e18f0e426f
+size 11005

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fb4acb53aa0a48daf5c3bf6f0fb132cf2bce8896fba91fa5fb88d24766fa9a
+oid sha256:b4773dfb4d177b1524b5364b69730e03bb8c54e7ada87d05e6e9b4981e8b8307
 size 6328