Training complete

.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 +1,49 @@
+---
+license: cc-by-4.0
+base_model: qanastek/51-languages-classifier
+tags:
+- classification
+- generated_from_trainer
+model-index:
+- name: ClassificationLanguage
+  results: []
+---
+
+<!-- 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. -->
+
+# ClassificationLanguage
+
+This model is a fine-tuned version of [qanastek/51-languages-classifier](https://huggingface.co/qanastek/51-languages-classifier) on an unknown dataset.
+
+## 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: 5e-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: 3.0
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "qanastek/51-languages-classifier",
+  "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": "af-ZA",
+    "1": "am-ET",
+    "2": "ar-SA",
+    "3": "az-AZ",
+    "4": "bn-BD",
+    "5": "cy-GB",
+    "6": "da-DK",
+    "7": "de-DE",
+    "8": "el-GR",
+    "9": "en-US",
+    "10": "es-ES",
+    "11": "fa-IR",
+    "12": "fi-FI",
+    "13": "fr-FR",
+    "14": "he-IL",
+    "15": "hi-IN",
+    "16": "hu-HU",
+    "17": "hy-AM",
+    "18": "id-ID",
+    "19": "is-IS",
+    "20": "it-IT",
+    "21": "ja-JP",
+    "22": "jv-ID",
+    "23": "ka-GE",
+    "24": "km-KH",
+    "25": "kn-IN",
+    "26": "ko-KR",
+    "27": "lv-LV",
+    "28": "ml-IN",
+    "29": "mn-MN",
+    "30": "ms-MY",
+    "31": "my-MM",
+    "32": "nb-NO",
+    "33": "nl-NL",
+    "34": "pl-PL",
+    "35": "pt-PT",
+    "36": "ro-RO",
+    "37": "ru-RU",
+    "38": "sl-SL",
+    "39": "sq-AL",
+    "40": "sv-SE",
+    "41": "sw-KE",
+    "42": "ta-IN",
+    "43": "te-IN",
+    "44": "th-TH",
+    "45": "tl-PH",
+    "46": "tr-TR",
+    "47": "ur-PK",
+    "48": "vi-VN",
+    "49": "zh-CN",
+    "50": "zh-TW"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "af-ZA": 0,
+    "am-ET": 1,
+    "ar-SA": 2,
+    "az-AZ": 3,
+    "bn-BD": 4,
+    "cy-GB": 5,
+    "da-DK": 6,
+    "de-DE": 7,
+    "el-GR": 8,
+    "en-US": 9,
+    "es-ES": 10,
+    "fa-IR": 11,
+    "fi-FI": 12,
+    "fr-FR": 13,
+    "he-IL": 14,
+    "hi-IN": 15,
+    "hu-HU": 16,
+    "hy-AM": 17,
+    "id-ID": 18,
+    "is-IS": 19,
+    "it-IT": 20,
+    "ja-JP": 21,
+    "jv-ID": 22,
+    "ka-GE": 23,
+    "km-KH": 24,
+    "kn-IN": 25,
+    "ko-KR": 26,
+    "lv-LV": 27,
+    "ml-IN": 28,
+    "mn-MN": 29,
+    "ms-MY": 30,
+    "my-MM": 31,
+    "nb-NO": 32,
+    "nl-NL": 33,
+    "pl-PL": 34,
+    "pt-PT": 35,
+    "ro-RO": 36,
+    "ru-RU": 37,
+    "sl-SL": 38,
+    "sq-AL": 39,
+    "sv-SE": 40,
+    "sw-KE": 41,
+    "ta-IN": 42,
+    "te-IN": 43,
+    "th-TH": 44,
+    "tl-PH": 45,
+    "tr-TR": 46,
+    "ur-PK": 47,
+    "vi-VN": 48,
+    "zh-CN": 49,
+    "zh-TW": 50
+  },
+  "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": "4.33.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3442e56e0fbc62d5c4b9a3b2ecb33f39375f51fac2564beffd4f58966089bf
+size 1112400433

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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "label": 51,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b9f19e810f1bcd9659d6c169371e6f859e7e662db29b0ba5fd8bfd360a715f
+size 4027