Training in progress, step 100

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "down_proj",
-    "q_proj",
     "gate_proj",
-    "k_proj"
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "k_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:f8ebf80eeeb9fbbe35857103728677b73172ce8f792882917225eb9fa915001e
+oid sha256:b4b6a25bf3ab2e5041738793fc11a64b0e48faeba4db419dba955c6d8f564a5c
 size 39256456

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<eos>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1999,7 +1999,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
+  "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",