Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "vlsp-2023-vllm/hoa-7b",
+  "base_model_name_or_path": "vilm/vietcuna-7b-v3",
   "inference_mode": true,
   "num_attention_heads": 32,
   "num_layers": 30,
@@ -12,5 +12,5 @@
   "revision": null,
   "task_type": "CAUSAL_LM",
   "token_dim": 4096,
-  "tokenizer_name_or_path": "vlsp-2023-vllm/hoa-7b"
+  "tokenizer_name_or_path": "vilm/vietcuna-7b-v3"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b1949fd423319a05fa045f473d07ebfedfc4109c946fbb7c8f8963f66febae
+oid sha256:bcae2b04283ed2a779b8537e0d4c95dec71e9ffdba45965817af0e1efcf39d75
 size 131837

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -2,7 +2,7 @@
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,23 +26,7 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<mask>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<|endoftext|>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -51,10 +35,11 @@
     }
   },
   "additional_special_tokens": [],
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "pad_token": "<pad>",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf0f2bc46559fc693b33b37ffb1366470864e767c9a7dd624219c4126a3866c1
+oid sha256:328bc5b681b07840e8c11652366f27a95f1370e98a882f74449971459e3a68d8
 size 4091