ehottl/roberta-base-klue-ynat-classification

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 base_model: klue/roberta-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: results
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 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: 0.4633
+- Accuracy: 0.853
 
 ## Model description
 
@@ -40,9 +45,16 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 1
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4189        | 1.0   | 4460 | 0.4998          | 0.855    |
+
+
 ### Framework versions
 
-- Transformers 4.46.2
-- Pytorch 2.3.1.post300
-- Datasets 3.0.2
-- Tokenizers 0.20.3
+- Transformers 4.49.0
+- Pytorch 2.5.1.post306
+- Datasets 3.3.1
+- Tokenizers 0.21.0

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,
@@ -38,9 +38,10 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.49.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 32000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad85116bd28205435ff0d63ac0261835cbdd59033b3abd903c9e4daf550b028
+oid sha256:52534a4e5d38d777b22802991c7aab0f1e86d99d8d1b07d937763af90d127c30
 size 442518124

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c1d5cbfd7d883d9f64f17256b971f34d6354cfb35ffa44aa8057c305fa4023
-size 5240
+oid sha256:fe2515aaeee0c5a37b65275f372c2cad63324918defeaddf0a24e2df0a7e22b9
+size 5304