Training in progress epoch 0

.gitattributes

@@ -33,3 +33,5 @@ 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
+variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+variables/variables.index filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: monologg/koelectra-small-finetuned-sentiment
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # CYONG/v1
 
-This model is a fine-tuned version of [monologg/koelectra-small-finetuned-sentiment](https://huggingface.co/monologg/koelectra-small-finetuned-sentiment) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.0855
-- Validation Loss: 3.0577
-- Train Accuracy: 0.5960
+- Train Loss: 2.9202
+- Validation Loss: 2.0632
+- Train Accuracy: 0.7748
 - Epoch: 0
 
 ## Model description
@@ -43,7 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 3.0855     | 3.0577          | 0.5960         | 0     |
+| 2.9202     | 2.0632          | 0.7748         | 0     |
 
 
 ### Framework versions

config.json

@@ -1,15 +1,14 @@
 {
-  "_name_or_path": "monologg/koelectra-small-finetuned-sentiment",
-  "_num_labels": 2,
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "embedding_size": 128,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "hidden_size": 768,
   "id2label": {
     "0": "quota",
     "1": "\uae30\ubd80 \uc694\uccad",
@@ -35,7 +34,7 @@
     "21": "\ubb38\uc790\uc778\uc2dd"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 3072,
   "label2id": {
     "AI\ubaa8\ub4dc": 11,
     "quota": 0,
@@ -62,18 +61,18 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "electra",
-  "num_attention_heads": 4,
+  "model_type": "bert",
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "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",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
   "transformers_version": "4.31.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32200
+  "vocab_size": 105879
 }

fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda638924df760b2db8a62cf79ddf2135952f256574edec7b85434188b0db675
+size 58

keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e76dc41cfef9e8f4a4e74a09586ef5bcc68407b51f1d6bd6c89506f156ee1e
+size 84588

saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daedea18b795b49006693b716950ed258a9070f37c504b0dd6228af1da7b350d
+size 4085763

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918c3f48c33ab46ed9021023d1a40b072ba410ab54449705bfa2e1f31b5f5568
-size 55349584
+oid sha256:25df8f021138759f852f6cf2a86e8546a3285f8562eaf23dc1f50346383ef318
+size 669764024

tokenizer_config.json

@@ -2,10 +2,8 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "from_pt": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_len": 512,
   "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",

variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df47e9a15c58e02c891fd03c1c9dddfd6171af97464264f8eb881d179c4f3f2
+size 803761150

variables/variables.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1aa69f346359a7578e48bd12eecbfce990076f505f65515f649e9431a8f0e59
+size 18432