Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "o_proj",
     "up_proj",
+    "gate_proj",
+    "v_proj",
     "down_proj",
-    "k_proj",
-    "v_proj"
+    "q_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7824785b77388bdacbd438b6940d2e36888c73f044b90f65f3e52ea1d3c98100
-size 1342238560
+oid sha256:a6eb8a9f8b466ff0ce908f0ccad75fba05d4418dd4615298da9fa1f34e0bac5a
+size 335605144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ed2902ee88ca639467bbb931d791a178b5c0f00781bdda6df7648779e8d5d0
+oid sha256:7306f0a34fe582d4c5bc7891f992e296a8271864c660bc6d4579a90d606fc1f4
 size 5112