Training in progress, step 4626

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "uitnlp/visobert",
+  "_name_or_path": "NlpHUST/ner-vietnamese-electra-base",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "ElectraForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "embedding_size": 768,
+  "finetuning_task": "ner",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -67,15 +67,19 @@
     "O": 13
   },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "max_position_embeddings": 512,
+  "model_type": "electra",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 15004
+  "vocab_size": 62000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351522b6cd567a68fab3fc7262542a275c1d727b60de9820a9f7480d918972a6
-size 388002212
+oid sha256:50dbbf7e026e41d44d27cef246b3481759c53a7d0f949ab5f662b3a76420eb1f
+size 532367844

special_tokens_map.json

@@ -1,15 +1,37 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec0ca8948acb11682e26487719297f9ea011756fd24d5564b8f51cf01ea7c8a
-size 1095547
+oid sha256:5166e09320d5dea01a72734268a6136a5d53f2fe55980b6ba0fc19db6e003f72
+size 1394857

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,31 +25,40 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "15001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34335c839fe62015899e0e7278a9b1f4c9f5e0b07a3694ba42aa35bf8c572b9f
+oid sha256:5c1c91f5116dea19622c55409073080a460d7e8ebc02cc10e05d35edff8c08da
 size 5112