Training in progress, step 50

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 512,
+  "lora_alpha": 256,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "o_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550d328a31b440aa6464048d02ac975c6a0a634ae113901f3393090eb2240aa1
-size 3611357976
+oid sha256:d2071a4dc9a52f3aab3899ac6a736667921981490e2e95d1d9dd7ae96484f9cc
+size 2332095256

runs/Apr02_06-14-33_1f3fbe1ee1c0/events.out.tfevents.1712038481.1f3fbe1ee1c0.16839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e307eb0fa5845fd3dfdfa973e627397e440899f9b2ca270ec55e01b377c8937
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcbaa9e0c85cfabcfcb328cfdf2cf920c56178cee9b246cdd4a0bb41c090cae
+oid sha256:f9c93f4241534784d984a7e3b976dec8e33542a9bd517c3b2795bd4e33062913
 size 4984