Training in progress, step 200

adapter_config.json

@@ -10,8 +10,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
-  "lora_dropout": 0,
+  "lora_alpha": 128,
+  "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "up_proj",
     "q_proj",
-    "o_proj",
+    "down_proj",
+    "up_proj",
     "gate_proj",
-    "down_proj"
+    "v_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0af59d551d2db519eb35dfa43e01c3e22b9fd5430eae359316fb5e416bee8c
+oid sha256:0fa66be3d4a7311d3014a87414186c20b18271fd81cc360432ce349307f6365b
 size 41581360

runs/Nov07_11-35-42_987d39284a3d/events.out.tfevents.1730979363.987d39284a3d.2294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773476059ab0ebfdf7eedb2ead7c0deafb3424cd97548814dbe83ba9e8139afb
+size 5666

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c951826726a61cb3c0add037215ead129d9f0b2d14a572d23a6f9f0f66c5508
+oid sha256:9d7ab6529b5acd4d2436094471dbe8bdf63005a567296c84841228f1af628e0f
 size 5176