Training in progress, step 20

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "query_key_value",
-    "dense",
-    "dense_4h_to_h"
+    "dense_h_to_4h",
+    "dense_4h_to_h",
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3f23ca4c7178a2d425e48352c6cb8e0b06cbf7492cf6c1da34ae774fd590f3
+oid sha256:0d9f3ea130cefd724abb217edac6d36fa46f44529f6d25e4890e266b965d8d57
 size 261131840

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 2048
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 11,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8eb10bdf58e32007ec613f3b36fa00a2a3853a4d48c90310a9297de20df2ea1
+oid sha256:09ae5e58b3e2fc5a20dc550e7d624f95b4d03751a69672ba71402fa3c0f68591
 size 5624