v1.0

.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

@@ -0,0 +1,90 @@
+---
+license: mit
+base_model: xlm-roberta-base
+metrics:
+- accuracy
+model-index:
+- name: xlm-roberta-base-language-detection-silvanus
+  results: []
+widget:
+- text: >-
+    Kebakaran hutan dan lahan terus terjadi dan semakin meluas di Kota
+    Palangkaraya, Kalimantan Tengah (Kalteng) pada hari Rabu, 15 Nopember 2023
+    20.00 WIB. Bahkan kobaran api mulai membakar pondok warga dan mendekati
+    permukiman. BZK #RCTINews #SeputariNews #News #Karhutla #KebakaranHutan
+    #HutanKalimantan #SILVANUS_Italian_Pilot_Testing
+  example_title: Indonesia
+- text: >-
+    Wildfire rages for a second day in Evia destroying a Natura 2000 protected
+    pine forest. - 5:51 PM Aug 14, 2019
+  example_title: English
+- text: >-
+    3 nov 2023 21:57 - Incendio forestal obliga a la evacuación de hasta 850
+    personas cerca del pueblo de Montichelvo en Valencia.
+  example_title: Spanish
+- text: >-
+    Incendi boschivi nell'est del Paese: 2 morti e oltre 50 case distrutte nello
+    stato del Queensland.
+  example_title: Italian
+- text: >-
+    Lesné požiare na Sicílii si vyžiadali dva ľudské životy a evakuáciu hotela
+    http://dlvr.it/SwW3sC - 23. septembra 2023 20:57
+  example_title: Slovak
+language:
+- id
+- en
+- es
+- it
+- sk
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# xlm-roberta-base-language-detection-silvanus
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the common language and kiviki/SlovakSum datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.0866
+- Accuracy: 0.9868
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.078         | 1.0   | 3188 | 0.1239          | 0.9784   |
+| 0.0703        | 2.0   | 6376 | 0.1035          | 0.9830   |
+| 0.0375        | 3.0   | 9564 | 0.0866          | 0.9868   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,125 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Arabic",
+    "1": "Basque",
+    "2": "Breton",
+    "3": "Catalan",
+    "4": "Chinese_China",
+    "5": "Chinese_Hongkong",
+    "6": "Chinese_Taiwan",
+    "7": "Chuvash",
+    "8": "Czech",
+    "9": "Dhivehi",
+    "10": "Dutch",
+    "11": "English",
+    "12": "Esperanto",
+    "13": "Estonian",
+    "14": "French",
+    "15": "Frisian",
+    "16": "Georgian",
+    "17": "German",
+    "18": "Greek",
+    "19": "Hakha_Chin",
+    "20": "Indonesian",
+    "21": "Interlingua",
+    "22": "Italian",
+    "23": "Japanese",
+    "24": "Kabyle",
+    "25": "Kinyarwanda",
+    "26": "Kyrgyz",
+    "27": "Latvian",
+    "28": "Maltese",
+    "29": "Mangolian",
+    "30": "Persian",
+    "31": "Polish",
+    "32": "Portuguese",
+    "33": "Romanian",
+    "34": "Romansh_Sursilvan",
+    "35": "Russian",
+    "36": "Sakha",
+    "37": "Slovenian",
+    "38": "Spanish",
+    "39": "Swedish",
+    "40": "Tamil",
+    "41": "Tatar",
+    "42": "Turkish",
+    "43": "Ukranian",
+    "44": "Welsh",
+    "45": "Slovak"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arabic": 0,
+    "Basque": 1,
+    "Breton": 2,
+    "Catalan": 3,
+    "Chinese_China": 4,
+    "Chinese_Hongkong": 5,
+    "Chinese_Taiwan": 6,
+    "Chuvash": 7,
+    "Czech": 8,
+    "Dhivehi": 9,
+    "Dutch": 10,
+    "English": 11,
+    "Esperanto": 12,
+    "Estonian": 13,
+    "French": 14,
+    "Frisian": 15,
+    "Georgian": 16,
+    "German": 17,
+    "Greek": 18,
+    "Hakha_Chin": 19,
+    "Indonesian": 20,
+    "Interlingua": 21,
+    "Italian": 22,
+    "Japanese": 23,
+    "Kabyle": 24,
+    "Kinyarwanda": 25,
+    "Kyrgyz": 26,
+    "Latvian": 27,
+    "Maltese": 28,
+    "Mangolian": 29,
+    "Persian": 30,
+    "Polish": 31,
+    "Portuguese": 32,
+    "Romanian": 33,
+    "Romansh_Sursilvan": 34,
+    "Russian": 35,
+    "Sakha": 36,
+    "Slovak": 45,
+    "Slovenian": 37,
+    "Spanish": 38,
+    "Swedish": 39,
+    "Tamil": 40,
+    "Tatar": 41,
+    "Turkish": 42,
+    "Ukranian": 43,
+    "Welsh": 44
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682f2d74fcb5ac4d168cdc0d0514d0304d39d1c841dd7954b72d64f37a89b86b
+size 1112340352

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003498ab0695fbf35aedc8bbbae1e20a6033a1b3914e49c6d2fbe1d54d7d93b9
+size 17082786

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c604139e4a83f290b70282279d18668290438565d95e208956d853d806b90aa
+size 4664