Training in progress, step 800

adapter_config.json

@@ -24,9 +24,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "dense_h_to_4h",
     "query_key_value",
+    "dense_h_to_4h",
+    "dense",
     "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:43cfd0c15ba328b56422f37bdcfed8d13b491959ec26a469f3730a8af7304010
+size 159266376

config.json

@@ -22,7 +22,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_parallel_residual": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0169f40afff071e757b0e090b369d1620ba5cf0efeaea3a91b4e744854f175d1
+oid sha256:284561e178ca9f12bc2078a56657cb3d6c3e31da872309722b17260f608a55a5
 size 6072