Training in progress, step 150

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 2048,
+  "lora_alpha": 16,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "up_proj",
     "k_proj",
-    "o_proj",
+    "down_proj",
     "q_proj",
-    "gate_proj"
+    "gate_proj",
+    "o_proj",
+    "up_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 sha256:9a7b37af4adadcbb0be30995b61958227a95de02aa828295f69b69e8e688de80
+oid sha256:09928a665cafa00e26c4ea0a5e78f9777fc8954718ff41170f95bb98325c7656
 size 5368770952

runs/Sep07_19-53-19_50254c7077a1/events.out.tfevents.1725738812.50254c7077a1.2978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36f0b57ec0629b331de0d27095ef319f38d98f309a4be6eef87053ad87034f3
+size 11468

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ac11d0d2b491c0474c3fa4a6f303e018d228d70be0e5d7df1c27b27ca2429d
+oid sha256:76e90cc15fa237b6422cb6b683ceea528432fbb0266acf485134aa12341b4da4
 size 5496