Training in progress, step 200

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 12,
+  "lora_alpha": 24,
   "lora_bias": false,
   "lora_dropout": 0.25,
   "megatron_config": null,
@@ -21,17 +21,17 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 12,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
+    "q_proj",
     "up_proj",
-    "gate_proj",
+    "k_proj",
+    "o_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "gate_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe58d3c03518659248e48a169ce5f7ad1fd9fcba3b7ff3fbc00f64781e12c93e
-size 5544448
+oid sha256:cb7edc022a38beb145ffb51c73bf9826a63972fa7eb7866f4c9659074c1a8c43
+size 8297288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c67ac096c206b245d26f775afa3fb8ffa810038da5c0f227d1b18811d5d602b
+oid sha256:a5e19188bdca9ed7ec3f5485c2058b4803117cec11f54ee11e729dcda3bd5b01
 size 5905