fine_tuned_rte_sloberta

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
-license: cc-by-sa-4.0
-base_model: EMBEDDIA/sloberta
+license: mit
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine_tuned_rte_sloberta
 
-This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6653
+- Loss: 1.4763
 - Accuracy: 0.6207
-- F1: 0.5750
+- F1: 0.5951
 
 ## Model description
 
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
-| 0.6985        | 1.7241  | 50   | 0.7540          | 0.4138   | 0.2422 |
-| 0.7058        | 3.4483  | 100  | 0.6912          | 0.5862   | 0.4333 |
-| 0.6993        | 5.1724  | 150  | 0.6980          | 0.4138   | 0.2422 |
-| 0.7003        | 6.8966  | 200  | 0.6806          | 0.5862   | 0.4333 |
-| 0.6968        | 8.6207  | 250  | 0.6730          | 0.5862   | 0.4333 |
-| 0.6736        | 10.3448 | 300  | 0.6726          | 0.6897   | 0.6801 |
-| 0.6339        | 12.0690 | 350  | 0.6580          | 0.6207   | 0.6090 |
-| 0.6005        | 13.7931 | 400  | 0.6653          | 0.6207   | 0.5750 |
+| 0.7117        | 1.7241  | 50   | 0.7129          | 0.4138   | 0.2422 |
+| 0.7033        | 3.4483  | 100  | 0.6997          | 0.4138   | 0.2422 |
+| 0.6845        | 5.1724  | 150  | 0.6933          | 0.4828   | 0.4828 |
+| 0.6378        | 6.8966  | 200  | 0.8005          | 0.4828   | 0.4668 |
+| 0.4579        | 8.6207  | 250  | 0.9656          | 0.6207   | 0.5951 |
+| 0.2521        | 10.3448 | 300  | 1.2302          | 0.6552   | 0.6018 |
+| 0.1196        | 12.0690 | 350  | 1.4679          | 0.5862   | 0.5789 |
+| 0.0653        | 13.7931 | 400  | 1.4763          | 0.6207   | 0.5951 |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "EMBEDDIA/sloberta",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "CamembertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -23,9 +22,10 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "camembert",
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -33,5 +33,5 @@
   "transformers_version": "4.40.2",
   "type_vocab_size": 1,
   "use_cache": false,
-  "vocab_size": 32005
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29cb0af14d650db1d9f022cffc1845fc4ee8af8e2c6bd824f93d035c81ac5f10
-size 442518104
+oid sha256:5eabd24fea607f51753c670732cbff70b9cf98944aaa48ee857d18940d30c1c9
+size 1112205008

runs/May22_19-18-31_DESKTOP-22QTFDR/events.out.tfevents.1716398312.DESKTOP-22QTFDR.19492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0be47c1bdcc7a74bba35cd0aa128b18b0e1b782a27fafd330b55e18f3fdfa8
+size 9842

runs/May22_19-18-31_DESKTOP-22QTFDR/events.out.tfevents.1716398560.DESKTOP-22QTFDR.19492.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c818036a42d96e675cab730bcfc6918b5e012088f9c7c3a285fc357ee15ce3fd
+size 457

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b589385a2320549143ab23b0ccf82cc99a82685701cdabe0fad847bd0479ff
-size 800013
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,55 +1,15 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "</s>",
-    "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_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>NOTUSED",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>NOTUSED",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -32,45 +32,23 @@
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
+    "250001": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": false,
   "eos_token": "</s>",
   "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "CamembertTokenizer",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc80e643402c7ee6d9d8ca8f6132e33e609f3728a236a07b663529646f673f88
+oid sha256:36dd1dd9f5c346ceaa1b3d7782066fd60c5d48c515089da4fb6079288a85a7c7
 size 5048