Training in progress, step 4

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "MistralForCausalLM",
-    "parent_library": "transformers.models.mistral.modeling_mistral"
+    "base_model_class": "MptForCausalLM",
+    "parent_library": "transformers.models.mpt.modeling_mpt"
   },
-  "base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
+  "base_model_name_or_path": "vinai/PhoGPT-4B-Chat",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,15 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "up_proj",
+    "Wqkv",
+    "out_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": null,
-  "use_dora": false,
+  "use_dora": true,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242a6af7b5a0ff82aac7c6f0ea6478bdb5e5d47ef8141a536fcf1fc2645dba0e
-size 83945296
+oid sha256:a015d9c73adc8761a6c0f966efbb7beed52acd3356e5f2d9b35506487e525327
+size 53923248

special_tokens_map.json

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

tokenizer_config.json

@@ -1,6 +1,5 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -26,55 +25,22 @@
       "single_word": false,
       "special": true
     },
-    "38365": {
-      "content": "<<SYS>>",
+    "3": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "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
+      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</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 %}",
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "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
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258ce3f2c30f2dd5d61b0c55898095fdd50b3ffd6fee97143d267e6748468c48
+oid sha256:a258901ba7183b5b37b37dcd95dce7f77bab35551eae7e7edec705146e6e24ff
 size 5368