Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "k_proj",
-    "q_proj",
-    "v_proj",
     "up_proj",
-    "down_proj",
-    "gate_proj"
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f139adb91a18f1e822ae65ccd548390a891e48007e6fbcd1d5663c9e8775cb1
+oid sha256:1734d5eba28316a65c28d0c8e9814b2a27dfc3773ec16e919c78a679c065bc6b
 size 2332095256

runs/Apr02_08-16-15_1f3fbe1ee1c0/events.out.tfevents.1712045782.1f3fbe1ee1c0.49623.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81b123f9609bf1c1c0c22f6621ce6be870260014449da25ab1bc51951e79102
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114b4cb8725f1816f2141e390e912ce51e3d5062aad6e9e02174514a5a238740
+oid sha256:7429726cd8d2c5c6d4f0cc837af40995e4af7e7154a174cf10b52ff0a9a8b26d
 size 4984