End of training

README.md

@@ -35,7 +35,7 @@ This model was trained with SFT.
 
 - TRL: 0.12.1
 - Transformers: 4.46.2
-- Pytorch: 2.5.1+cu124
+- Pytorch: 2.6.0+cu124
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "qkv_proj",
     "gate_up_proj",
-    "down_proj"
+    "qkv_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c556edf1b70885cb081bd27bfc8ab0339adf8374deecd2c805bd9e752195d1
+oid sha256:122b30ac2da9f0bbeb01f8231dfa836c359d9d8513fb9f4f8d3a9d25e84dfcf9
 size 50365768

special_tokens_map.json

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

tokenizer_config.json

@@ -122,7 +122,7 @@
   "eos_token": "<|endoftext|>",
   "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<unk>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",