Training in progress, step 256

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "klue/roberta-base",
+  "_name_or_path": "lemon-mint/LaBSE-EnKo-Nano-Preview-v0.3",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": 0.0,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
@@ -19,18 +18,22 @@
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "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",
   "problem_type": "regression",
-  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.43.3",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 51547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b5e7e2399a6bbf31e687a2b492177005d0cfafb61cef0b202f6bba44c0de2d
-size 442499668
+oid sha256:70c84f3af7ee0adfb42216f02136a2e3db9b2c36f2a116a954527eaaeecf3dbe
+size 502544380

special_tokens_map.json

@@ -1,11 +1,4 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
@@ -13,13 +6,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "mask_token": {
     "content": "[MASK]",
     "lstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[CLS]",
+      "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": "[SEP]",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "[UNK]",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,12 +41,11 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c8cbad2af6c789147145d94979f35047578c60d85338a18f694243fc206a2e
+oid sha256:882520aa2973aae4499f83ada418ae35032cf7e32e286b04afe51bd93d269eee
 size 5176