End of training

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-base_model: klue/roberta-large
+license: mit
+base_model: joeddav/xlm-roberta-large-xnli
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta_fine_simile
 
-This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the None dataset.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1035
+- Loss: 0.6860
 
 ## Model description
 
@@ -34,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -47,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 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          |
+| 0.7328        | 1.0   | 225  | 0.7291          |
+| 0.7723        | 2.0   | 450  | 0.6914          |
+| 0.7069        | 3.0   | 675  | 0.7188          |
+| 0.6843        | 4.0   | 900  | 0.6874          |
+| 0.699         | 5.0   | 1125 | 0.6860          |
 
 
 ### Framework versions

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "RobertaForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "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": "roberta",
+  "model_type": "xlm-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": 32000
+  "vocab_size": 250002
 }

logs/events.out.tfevents.1765780997.1613b95ee668.660.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308bde78fda4ab77605cf9268c6cc1d067d1a1a9e64f6157e80f221fae584210
+size 30537

logs/events.out.tfevents.1765783400.1613b95ee668.660.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7127a21e6ba52b822cd0fe1ec32b3f47523467bee514d90cc2c9c7904f462d8c
+size 359

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd61f957ece46698e46dbbe9ac6726532f3b848ace45c32e0e3c4aae9582eee
-size 1346681920
+oid sha256:a87ca4b4c6f8aaf27a43e8439936d9722a23cfbe74fb410f0bb70d6164f62d80
+size 2239618672

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850babe403e02c9968d4ef98de81ed26a9c5abfcac2ccee067f15c7e84f2fb79
+oid sha256:1790549f3dc76c3dcba74d2023ed2c5335f5760843b58ec42fc1f5b3c2c098ca
 size 5841