bert for dst model, pretrained

.ipynb_checkpoints/config-checkpoint.json

@@ -1,34 +0,0 @@
-{
-  "_name_or_path": "./checkpoints/checkpoint-11820",
-  "architectures": [
-    "BertForPreTraining"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "directionality": "bidi",
-  "embedding_size": 768,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_name_or_path": "kykim/bert-kor-base",
-  "model_type": "bert",
-  "n_gate": 5,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "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",
-  "proj_dim": null,
-  "transformers_version": "4.5.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 42000
-}

config.json

@@ -1,11 +1,9 @@
 {
-  "_name_or_path": "./checkpoints/checkpoint-11820",
+  "_name_or_path": "./checkpoints/checkpoint-5090",
   "architectures": [
     "BertForPreTraining"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "directionality": "bidi",
-  "embedding_size": 768,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -14,21 +12,16 @@
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_name_or_path": "kykim/bert-kor-base",
+  "model_name_or_path": "dsksd/bert-ko-small-minimal",
   "model_type": "bert",
   "n_gate": 5,
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "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",
   "proj_dim": null,
   "transformers_version": "4.5.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 42000
+  "vocab_size": 35000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e91167831a28bbda235c7dfcbe4d87a187eadfe16d0a5a1913ed5ff67bc5cb
-size 475823670
+oid sha256:bc7a132a5421d504560f167efe9afc16a2f820229a8c8c42a5b504268df2867f
+size 284142038

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "never_split": null,
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "tokenize_chinese_chars": true,
+  "strip_accents": null,
+  "model_max_length": 512
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e161039f77507bb069022547f6196046c0711cd555165dd2e668a525cc084798
+oid sha256:8fc4a9487facf830d41f0759909b54f01966e73e0deb03d28b966015c59cc72d
 size 2351