End of training

README.md

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: mit
-base_model: joeddav/xlm-roberta-large-xnli
+base_model: klue/roberta-large
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta_fine_simile
 
-This model is a fine-tuned version of [joeddav/xlm-roberta-large-xnli](https://huggingface.co/joeddav/xlm-roberta-large-xnli) on the None dataset.
+This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6936
+- Loss: 0.1035
 
 ## Model description
 
@@ -35,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.003
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -48,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.7215        | 1.0   | 225  | 0.7191          |
-| 1.4954        | 2.0   | 450  | 1.4224          |
-| 0.7847        | 3.0   | 675  | 0.6952          |
-| 0.6903        | 4.0   | 900  | 0.6936          |
-| 0.7235        | 5.0   | 1125 | 0.7039          |
+| 0.084         | 1.0   | 225  | 0.1656          |
+| 0.4257        | 2.0   | 450  | 0.1035          |
+| 0.6882        | 3.0   | 675  | 0.6996          |
+| 0.7057        | 4.0   | 900  | 0.6892          |
+| 0.695         | 5.0   | 1125 | 0.6860          |
 
 
 ### Framework versions

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -23,15 +23,15 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
   "transformers_version": "4.57.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 32000
 }

logs/events.out.tfevents.1765781819.f7d3e96ea34b.385.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da87247e4d9c80de46f14c5c767324551d4ed8cba62e8acc56ac17d591822a2
+size 30529

logs/events.out.tfevents.1765782831.f7d3e96ea34b.385.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d8457bbb5222eecebefeb04d8cfa93d18c8d0f62a345270370cb906d6fdeae
+size 359

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788ce5cb2cbc8c9890ef733942bd41113069938eb0c54a4ea9bbceb3eb1e9d6f
-size 2239618672
+oid sha256:cdd61f957ece46698e46dbbe9ac6726532f3b848ace45c32e0e3c4aae9582eee
+size 1346681920

special_tokens_map.json

@@ -1,15 +1,51 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74659c780d49afad7a7b9799868f75cbd3014fb6c34956e85a793028d38094a
-size 17098251
+oid sha256:4a45131245e310d1650c760a22038de8180f7311ace3575ad96b24f85ef38e1b
+size 751999

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,32 +25,36 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c722bee15913dea1fd5122591d6d71f26aad63615acf2c00d178272700a6810
+oid sha256:850babe403e02c9968d4ef98de81ed26a9c5abfcac2ccee067f15c7e84f2fb79
 size 5841