End of training

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [monologg/koelectra-base-v3-discriminator](https://huggingface.co/monologg/koelectra-base-v3-discriminator) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6564
-- Accuracy: 0.5676
-- F1: 0.6406
+- Loss: 2.5286
+- Accuracy: 0.1898
+- F1: 0.1547
 
 ## Model description
 
@@ -40,25 +40,41 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4e-05
+- learning_rate: 3e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 4
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
-| 0.6612        | 0.0669 | 200  | 0.6585          | 0.4970   | 0.4306 |
-| 0.6569        | 0.1339 | 400  | 0.6563          | 0.4951   | 0.4099 |
-| 0.6547        | 0.2008 | 600  | 0.6564          | 0.5676   | 0.6406 |
-| 0.653         | 0.2677 | 800  | 0.6533          | 0.5289   | 0.5172 |
-| 0.6554        | 0.3347 | 1000 | 0.6524          | 0.5400   | 0.5435 |
-| 0.6558        | 0.4016 | 1200 | 0.6552          | 0.5416   | 0.4878 |
-| 0.6516        | 0.4685 | 1400 | 0.6549          | 0.5438   | 0.4847 |
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|
+| 2.6213        | 0.1673 | 500   | 2.6180          | 0.1142   | 0.0241 |
+| 2.6412        | 0.3347 | 1000  | 2.6167          | 0.1318   | 0.0336 |
+| 2.5861        | 0.5020 | 1500  | 2.6111          | 0.1320   | 0.0385 |
+| 2.6183        | 0.6693 | 2000  | 2.6133          | 0.1222   | 0.0461 |
+| 2.5954        | 0.8367 | 2500  | 2.5958          | 0.1411   | 0.0607 |
+| 2.5828        | 1.0040 | 3000  | 2.5822          | 0.1479   | 0.0703 |
+| 2.5803        | 1.1714 | 3500  | 2.5685          | 0.1553   | 0.0826 |
+| 2.5615        | 1.3387 | 4000  | 2.5566          | 0.1645   | 0.0977 |
+| 2.5463        | 1.5060 | 4500  | 2.5531          | 0.1687   | 0.1111 |
+| 2.5511        | 1.6734 | 5000  | 2.5446          | 0.1679   | 0.1170 |
+| 2.5242        | 1.8407 | 5500  | 2.5342          | 0.1726   | 0.1215 |
+| 2.5191        | 2.0080 | 6000  | 2.5246          | 0.1825   | 0.1384 |
+| 2.4866        | 2.1754 | 6500  | 2.5306          | 0.1834   | 0.1428 |
+| 2.5005        | 2.3427 | 7000  | 2.5325          | 0.1803   | 0.1399 |
+| 2.5131        | 2.5100 | 7500  | 2.5195          | 0.1877   | 0.1473 |
+| 2.4918        | 2.6774 | 8000  | 2.5204          | 0.1876   | 0.1489 |
+| 2.4755        | 2.8447 | 8500  | 2.5218          | 0.1877   | 0.1568 |
+| 2.4223        | 3.0120 | 9000  | 2.5286          | 0.1898   | 0.1547 |
+| 2.4297        | 3.1794 | 9500  | 2.5364          | 0.1874   | 0.1599 |
+| 2.4213        | 3.3467 | 10000 | 2.5432          | 0.1866   | 0.1584 |
+| 2.4619        | 3.5141 | 10500 | 2.5393          | 0.1879   | 0.1585 |
+| 2.4383        | 3.6814 | 11000 | 2.5424          | 0.1849   | 0.1590 |
+| 2.4368        | 3.8487 | 11500 | 2.5414          | 0.1866   | 0.1599 |
 
 
 ### Framework versions

config.json

@@ -3,30 +3,48 @@
     "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "axis_names": [
-    "IE",
-    "SN",
-    "TF",
-    "JP"
-  ],
   "classifier_dropout": null,
   "embedding_size": 768,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "IE",
-    "1": "SN",
-    "2": "TF",
-    "3": "JP"
+    "0": "enfj",
+    "1": "enfp",
+    "2": "entj",
+    "3": "entp",
+    "4": "esfj",
+    "5": "esfp",
+    "6": "estj",
+    "7": "estp",
+    "8": "infj",
+    "9": "infp",
+    "10": "intj",
+    "11": "intp",
+    "12": "isfj",
+    "13": "isfp",
+    "14": "istj",
+    "15": "istp"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "IE": 0,
-    "JP": 3,
-    "SN": 1,
-    "TF": 2
+    "enfj": 0,
+    "enfp": 1,
+    "entj": 2,
+    "entp": 3,
+    "esfj": 4,
+    "esfp": 5,
+    "estj": 6,
+    "estp": 7,
+    "infj": 8,
+    "infp": 9,
+    "intj": 10,
+    "intp": 11,
+    "isfj": 12,
+    "isfp": 13,
+    "istj": 14,
+    "istp": 15
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -35,12 +53,11 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "problem_type": "multi_label_classification",
+  "problem_type": "single_label_classification",
   "summary_activation": "gelu",
   "summary_last_dropout": 0.1,
   "summary_type": "first",
   "summary_use_proj": true,
-  "task_type": "multilabel_4axis",
   "torch_dtype": "float32",
   "transformers_version": "4.55.2",
   "type_vocab_size": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eac4d6bde09291ae691e27527969fba10a06eb4b13409899a89a41711444e5a
-size 451721824
+oid sha256:abdac44a84793448c9d631c70eb5524bbf060e53252826af4449b3356f55a29f
+size 451758736

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf668bbab69941c0ced64b8a84b99b1af55159f6b0ee1a0bac514355441169b
+oid sha256:9912277088bd43b0b741b48b2a53ac2c354bdb06d0d2003e35416bf20e33283f
 size 5713