Upload 8 files

config.json

@@ -1,28 +1,31 @@
 {
-  "_name_or_path": "/data/10/qiyuw/sentence_pairs/20221004-checkpoint",
+  "_name_or_path": "qiyuw/WSPAlign-mbert-base",
   "architectures": [
-    "XLMRobertaForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.21.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980206780b06edbd92bc027a1138871a61b8c4de0df71590849ec10baeb92142
-size 2219752165
+oid sha256:6411f5d06f2fb5c743c1b0da8cdffa090bd2d1c1fbb51a04d16d8dae854cf20e
+size 1418231813

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:009efc8e82c7cfb74e1a99946d46f9c0fc908ed390fd424718147c8cf941e76f
-size 1109889457
+oid sha256:693bb1f981bcf53c6b2bc35a1956b7e9dbd3aecc1f95d7f1022ae4a7a7e0dbf2
+size 709129709

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253e31fcca8e2f4d29a301fffed4693e38ef531fc5892f73b3c32622061e7a52
-size 623
+oid sha256:631ea08acf301fa9ca40faaf4c9fa70ccacf5e60387a660ca000e7e7ad0bea66
+size 627

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,22 +1,16 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "/data/10/qiyuw/sentence_pairs/20221004-checkpoint",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
+  "name_or_path": "qiyuw/WSPAlign-mbert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b76cfb35e1ef5cff79e25a7b989734554c8d476180aa32b449f3de9d16f50d
-size 1903
+oid sha256:fdf603ca54f0fa767e48fd6a738450ad333d423e2c24dda89d87f713b8318b9e
+size 1915