Training in progress, step 4

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "MptForCausalLM",
-    "parent_library": "transformers.models.mpt.modeling_mpt"
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
   },
-  "base_model_name_or_path": "vinai/PhoGPT-4B-Chat",
+  "base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,9 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
-    "down_proj"
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48fdc8d91871ab678a84b4b3e96ef8a09058e341b027e071b6e04bd6eb4a0d0c
-size 40147760
+oid sha256:35dcf7be987c4656918c01d7f8278cad6ee0ff43eff398fbcfe5ce535ba8222b
+size 89481280

special_tokens_map.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -14,7 +19,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,5 +1,6 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,22 +26,55 @@
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<pad>",
+    "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
+    },
+    "38368": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' and loop.first %}{{ '### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '\n### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '\n### Trả lời: ' + message['content'] + eos_token }}{% endif %}{% if loop.last %}{% if message['role'] == 'user' and add_generation_prompt %}{{ '\n### Trả lời:' }}{% endif %}{% endif %}{% endfor %}",
+  "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": "</s>",
-  "model_max_length": 8192,
-  "pad_token": "<pad>",
-  "padding_side": "right",
-  "tokenizer_class": "BloomTokenizer",
-  "unk_token": "<unk>"
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f63c3f4f3abcfc1da4f12624b5e92d18b65bc877d8a9cc61f75b9e0e477d79
+oid sha256:7665efa84289db8691dafd78e33e2ce23cba58c5370f5c6154c485994d9a201f
 size 5368