Training in progress, step 5

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
     "v_proj",
-    "up_proj"
+    "gate_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 sha256:492c34ce089793c66bef58ab1a85e15ee11f6bda47da0a1585388b1922af74b5
+oid sha256:45c523e535bb5eab432da370408378bd0959bf6549fdc0b20be0c2ea3658dc30
 size 45118424

config.json

@@ -45,7 +45,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.1",
+  "transformers_version": "4.45.2",
   "use_cache": false,
   "vocab_size": 128256
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256adf7699ab7326b0a85e5d5de013f697d70ba6f2b261b23aec303bc035c096
+oid sha256:5fc628c25d261dd6a2dfdcd2e8f4bb18d9b96223fe41a21c1fef9fba98a3adc6
 size 6648