Training in progress epoch 0

README.md

@@ -13,8 +13,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: nan
-- Validation Loss: nan
+- Train Loss: 2.1016
+- Validation Loss: 1.8401
 - Epoch: 0
 
 ## Model description
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| nan        | nan             | 0     |
+| 2.1016     | 1.8401          | 0     |
 
 
 ### Framework versions

config.json

@@ -11,8 +11,28 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
@@ -20,6 +40,7 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
   "tokenizer_class": "BertTokenizer",
   "transformers_version": "4.19.2",
   "type_vocab_size": 1,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7757df9898b81b2ba94921e0143a3bb190724a71231680ba725124cdaf9473e7
-size 1347187352
+oid sha256:367263510d918f93df0dabbe849d017daab6fc2b7f962d858174d64f2c048ce8
+size 1347211928