Training in progress, epoch 1

.gitattributes

@@ -32,3 +32,4 @@ 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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,236 @@
+{
+  "_name_or_path": "facebook/xlm-v-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": "Afrikaans",
+    "1": "Amharic",
+    "2": "Arabic",
+    "3": "Assamese",
+    "4": "Asturian",
+    "5": "Azerbaijani",
+    "6": "Belarusian",
+    "7": "Bulgarian",
+    "8": "Bengali",
+    "9": "Bosnian",
+    "10": "Catalan",
+    "11": "Cebuano",
+    "12": "Sorani-Kurdish",
+    "13": "Mandarin Chinese",
+    "14": "Czech",
+    "15": "Welsh",
+    "16": "Danish",
+    "17": "German",
+    "18": "Greek",
+    "19": "English",
+    "20": "Spanish",
+    "21": "Estonian",
+    "22": "Persian",
+    "23": "Fula",
+    "24": "Finnish",
+    "25": "Filipino",
+    "26": "French",
+    "27": "Irish",
+    "28": "Galician",
+    "29": "Gujarati",
+    "30": "Hausa",
+    "31": "Hebrew",
+    "32": "Hindi",
+    "33": "Croatian",
+    "34": "Hungarian",
+    "35": "Armenian",
+    "36": "Indonesian",
+    "37": "Igbo",
+    "38": "Icelandic",
+    "39": "Italian",
+    "40": "Japanese",
+    "41": "Javanese",
+    "42": "Georgian",
+    "43": "Kamba",
+    "44": "Kabuverdianu",
+    "45": "Kazakh",
+    "46": "Khmer",
+    "47": "Kannada",
+    "48": "Korean",
+    "49": "Kyrgyz",
+    "50": "Luxembourgish",
+    "51": "Ganda",
+    "52": "Lingala",
+    "53": "Lao",
+    "54": "Lithuanian",
+    "55": "Luo",
+    "56": "Latvian",
+    "57": "Maori",
+    "58": "Macedonian",
+    "59": "Malayalam",
+    "60": "Mongolian",
+    "61": "Marathi",
+    "62": "Malay",
+    "63": "Maltese",
+    "64": "Burmese",
+    "65": "Norwegian",
+    "66": "Nepali",
+    "67": "Dutch",
+    "68": "Northern-Sotho",
+    "69": "Nyanja",
+    "70": "Occitan",
+    "71": "Oromo",
+    "72": "Oriya",
+    "73": "Punjabi",
+    "74": "Polish",
+    "75": "Pashto",
+    "76": "Portuguese",
+    "77": "Romanian",
+    "78": "Russian",
+    "79": "Sindhi",
+    "80": "Slovak",
+    "81": "Slovenian",
+    "82": "Shona",
+    "83": "Somali",
+    "84": "Serbian",
+    "85": "Swedish",
+    "86": "Swahili",
+    "87": "Tamil",
+    "88": "Telugu",
+    "89": "Tajik",
+    "90": "Thai",
+    "91": "Turkish",
+    "92": "Ukrainian",
+    "93": "Umbundu",
+    "94": "Urdu",
+    "95": "Uzbek",
+    "96": "Vietnamese",
+    "97": "Wolof",
+    "98": "Xhosa",
+    "99": "Yoruba",
+    "100": "Cantonese Chinese",
+    "101": "Zulu"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Afrikaans": 0,
+    "Amharic": 1,
+    "Arabic": 2,
+    "Armenian": 35,
+    "Assamese": 3,
+    "Asturian": 4,
+    "Azerbaijani": 5,
+    "Belarusian": 6,
+    "Bengali": 8,
+    "Bosnian": 9,
+    "Bulgarian": 7,
+    "Burmese": 64,
+    "Cantonese Chinese": 100,
+    "Catalan": 10,
+    "Cebuano": 11,
+    "Croatian": 33,
+    "Czech": 14,
+    "Danish": 16,
+    "Dutch": 67,
+    "English": 19,
+    "Estonian": 21,
+    "Filipino": 25,
+    "Finnish": 24,
+    "French": 26,
+    "Fula": 23,
+    "Galician": 28,
+    "Ganda": 51,
+    "Georgian": 42,
+    "German": 17,
+    "Greek": 18,
+    "Gujarati": 29,
+    "Hausa": 30,
+    "Hebrew": 31,
+    "Hindi": 32,
+    "Hungarian": 34,
+    "Icelandic": 38,
+    "Igbo": 37,
+    "Indonesian": 36,
+    "Irish": 27,
+    "Italian": 39,
+    "Japanese": 40,
+    "Javanese": 41,
+    "Kabuverdianu": 44,
+    "Kamba": 43,
+    "Kannada": 47,
+    "Kazakh": 45,
+    "Khmer": 46,
+    "Korean": 48,
+    "Kyrgyz": 49,
+    "Lao": 53,
+    "Latvian": 56,
+    "Lingala": 52,
+    "Lithuanian": 54,
+    "Luo": 55,
+    "Luxembourgish": 50,
+    "Macedonian": 58,
+    "Malay": 62,
+    "Malayalam": 59,
+    "Maltese": 63,
+    "Mandarin Chinese": 13,
+    "Maori": 57,
+    "Marathi": 61,
+    "Mongolian": 60,
+    "Nepali": 66,
+    "Northern-Sotho": 68,
+    "Norwegian": 65,
+    "Nyanja": 69,
+    "Occitan": 70,
+    "Oriya": 72,
+    "Oromo": 71,
+    "Pashto": 75,
+    "Persian": 22,
+    "Polish": 74,
+    "Portuguese": 76,
+    "Punjabi": 73,
+    "Romanian": 77,
+    "Russian": 78,
+    "Serbian": 84,
+    "Shona": 82,
+    "Sindhi": 79,
+    "Slovak": 80,
+    "Slovenian": 81,
+    "Somali": 83,
+    "Sorani-Kurdish": 12,
+    "Spanish": 20,
+    "Swahili": 86,
+    "Swedish": 85,
+    "Tajik": 89,
+    "Tamil": 87,
+    "Telugu": 88,
+    "Thai": 90,
+    "Turkish": 91,
+    "Ukrainian": 92,
+    "Umbundu": 93,
+    "Urdu": 94,
+    "Uzbek": 95,
+    "Vietnamese": 96,
+    "Welsh": 15,
+    "Wolof": 97,
+    "Xhosa": 98,
+    "Yoruba": 99,
+    "Zulu": 101
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 901629
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130f9a1c098b9f9d137297b53e4d63c46c17de44564d9c338b90009d5ce9b8db
+size 3114359925

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:ab892eef4554b6ef5a5289833a4dcb99b9001472a939160299a7d0fa603e27ad
+size 61333547

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "facebook/xlm-v-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d425c6ef778369a06302e6e97593ebb8cd22a365f759bdac3b78813603f78e5
+size 3515