Training in progress, step 100

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "o_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
     "down_proj",
     "v_proj",
-    "up_proj",
-    "q_proj",
-    "k_proj"
+    "up_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:e7842c403d135b97cca5f568e30dd7f4242ba4ba9bec1ed9c5a4780cab09d7e4
+oid sha256:b5c68bc801e4ae26eac7dca180fb3f29866a92f2677128a850c8aeedf0c33ea1
 size 778096664

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<simple_talk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</simple_talk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<simple_talk>",
+    "</simple_talk>"
   ],
   "bos_token": {
     "content": "<|begin_of_text|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23c93aaa5f8232681180524d7ba766330468eacf5396ac949591b2e3d416e3a
+oid sha256:595af231fb231648d3dcd4842f94d8457ca7b080ec0aa12a37a7eec89bc25092
 size 14136