Steeljin/roberta-base-klue-ynat-classification

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6552
-- Accuracy: 0.859
+- Loss: 0.4957
+- Accuracy: 0.847
 
 ## Model description
 
@@ -42,15 +42,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6135        | 1.0   | 1250 | 0.6673          | 0.833    |
-| 0.39          | 2.0   | 2500 | 0.6715          | 0.838    |
-| 0.2444        | 3.0   | 3750 | 0.7280          | 0.841    |
+| 0.5374        | 1.0   | 1250 | 0.5540          | 0.835    |
 
 
 ### Framework versions

config.json

@@ -12,24 +12,24 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6"
+    "0": "IT\uacfc\ud559",
+    "1": "\uacbd\uc81c",
+    "2": "\uc0ac\ud68c",
+    "3": "\uc0dd\ud65c\ubb38\ud654",
+    "4": "\uc138\uacc4",
+    "5": "\uc2a4\ud3ec\uce20",
+    "6": "\uc815\uce58"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6
+    "IT\uacfc\ud559": 0,
+    "\uacbd\uc81c": 1,
+    "\uc0ac\ud68c": 2,
+    "\uc0dd\ud65c\ubb38\ud654": 3,
+    "\uc138\uacc4": 4,
+    "\uc2a4\ud3ec\uce20": 5,
+    "\uc815\uce58": 6
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd05f58a2f39756a86f78b991d8cd580452faa33efc74257cec98b6ab256b61
+oid sha256:b690bc81281f50da0d0bb008b0c29d72c134a9a4f2af4dbbe8c4301c071bc160
 size 442518124

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f97509d69ab3e3ea84e304cfd673a09f11714044135d0024a22dd2a35e3e28
+oid sha256:4f7d943d51871558513ee86d0d349eb57cca9d6d12f83cffadb173c71666841c
 size 4984