Training in progress, step 250

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "up_proj",
     "v_proj",
+    "o_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj"
+    "k_proj",
+    "q_proj",
+    "up_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:cabc45bc5aabf5322e1457c48a8249842187fe818ccb132b79bde3bb088086f7
+oid sha256:2df5ad8f357b1110470257ee2447f8d59de6cd9afce0a6c15e47f153dada020c
 size 97728

config.json

@@ -13,7 +13,7 @@
   "hidden_size": 16,
   "initializer_range": 0.02,
   "intermediate_size": 64,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4366489b38b3c2792811c00b5d117d6d4e235e0d37a068173ff8d5b1642069b3
+oid sha256:269943fdbb6079fe98aea09b1ba0ad9effab69ac6b899d73428616ee9d738342
 size 6776