Training in progress, step 24

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj"
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_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 sha256:53a2614816cd11b0707713a912603dea5c45df8d043512ca7c5ae3eddba4fc5a
-size 167832240
+oid sha256:9924d60ce44dc29c6625c2cf520090a4c9f3531328557a7757afb92eb22e6642
+size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3833977106fac48f5d71407b1a01067110c5fbf699342151524802ba318de1
+oid sha256:92fbacf34900b96125f66b74fbc4090efcbcc2109c24b84e33ad287aa6e0cd0a
 size 6776