Training in progress, step 828

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "k_proj",
-    "o_proj",
+    "q_proj",
     "down_proj",
+    "o_proj",
     "v_proj",
-    "gate_proj",
-    "q_proj",
-    "up_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2538bbc75c4a43d1ba2c640dee2156989546d870732e18158c5499beba3bf201
+oid sha256:459055fd7c4d4b96d529b8078fb28501c5cbaeb0e2d2e7efe2754780cb46b1cf
 size 5398674440

tokenizer_config.json

@@ -2000,12 +2000,13 @@
     "<end_of_turn>"
   ],
   "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "extra_special_tokens": {},
-  "model_max_length": 8192,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "right",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e37639a25379ea645e4d5735081501cb989251c6caaea5633f17169f3782ba
+oid sha256:3d0cc08bc3e87b2dcad83314f2ac4e1801177e709d894a9e37da215293bb6b2e
 size 5624