Training in progress, step 200

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "vilm/vinallama-7b-chat",
+  "base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26265c8f1022859fd0a2ac06f980e611beab902cf3c3f1e74220bea9941237f3
-size 134264202
+oid sha256:82e8df30fa0d5ec2a7fe2dbc474f4765c43c5d8162cdbb91e670b7a9bbfca58c
+size 109098378

special_tokens_map.json

@@ -2,11 +2,10 @@
   "additional_special_tokens": [
     "<unk>",
     "<s>",
-    "</s>",
-    "<|im_end|>"
+    "</s>"
   ],
   "bos_token": "<s>",
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "pad_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -24,16 +24,32 @@
       "single_word": false,
       "special": true
     },
-    "46303": {
-      "content": "<|im_end|>",
+    "38365": {
+      "content": "<<SYS>>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
+    },
+    "38366": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38367": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     },
-    "46304": {
-      "content": "<|im_start|>",
+    "38368": {
+      "content": "[/INST]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -44,22 +60,23 @@
   "additional_special_tokens": [
     "<unk>",
     "<s>",
-    "</s>",
-    "<|im_end|>"
+    "</s>"
   ],
   "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": false,
+  "eos_token": "</s>",
+  "legacy": true,
   "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true,
+  "use_default_system_prompt": false,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0dfc5b24acd4af6b7ddd04bb6f82970de8ccd0d21c99043a23b7909340d3cd0
+oid sha256:be6399431ca53f26a0719f0dc33d090bdca93be9426bf30d7f1c5cd5ff6cd04d
 size 4536