Training in progress, step 250

adapter_config.json

@@ -15,26 +15,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 1,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "q_proj",
+    "gate_proj",
+    "k_proj",
     "down_proj",
+    "o_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": null,
-  "use_dora": false,
+  "use_dora": true,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1730c68af776d55c9a34711b9c256a590c8dfc1eca55ea607fcab3b799628b0
-size 76621264
+oid sha256:1b6eb004d2abd5116ef05e347d09b2c3cd31b231197e96cc2c84de0517ca4593
+size 154423432

runs/Mar03_04-08-34_49fec54f04df/events.out.tfevents.1740974915.49fec54f04df.17.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c91285370fa3104289174e0e8590a9521d03c24de8a0da7427f2c794cc0983
+size 10361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8300baf6e1d4779440b8026613918699e31335c37f4ba181ebe197c65e4e1239
-size 5368
+oid sha256:0d9f65f1c950f3cf9b5a0506527beab3a77b63f0328d2dde24f6b053de20cd59
+size 5432