Training in progress, step 15

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 24,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj",
     "v_proj",
+    "o_proj",
+    "up_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d259edcf51a6e65a5e5aa8f076d5bc4bf480fc4b4c59350991263774074d7ea
-size 67662840
+oid sha256:5f5168c85d041eb40b539ed1ea4fa405f9e14109cf8ce608d3eac8f26f627745
+size 45118424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441f7463c0db2e1253eb6ddf59c934fab68dc0782a39afd6c59cfb134e8542f9
+oid sha256:7c62cd4a5f5b5d98624b05b91ea66842c68cee52403c2495c0459cf13d17cfcc
 size 6648