Training in progress, epoch 1

.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

config.json

@@ -0,0 +1,123 @@
+{
+  "_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",
+    "10": "Dutch",
+    "11": "English",
+    "12": "Esperanto",
+    "13": "Estonian",
+    "14": "French",
+    "15": "Frisian",
+    "16": "Georgian",
+    "17": "German",
+    "18": "Greek",
+    "19": "Hakha_Chin",
+    "2": "Breton",
+    "20": "Indonesian",
+    "21": "Interlingua",
+    "22": "Italian",
+    "23": "Japanese",
+    "24": "Kabyle",
+    "25": "Kinyarwanda",
+    "26": "Kyrgyz",
+    "27": "Latvian",
+    "28": "Maltese",
+    "29": "Mangolian",
+    "3": "Catalan",
+    "30": "Persian",
+    "31": "Polish",
+    "32": "Portuguese",
+    "33": "Romanian",
+    "34": "Romansh_Sursilvan",
+    "35": "Russian",
+    "36": "Sakha",
+    "37": "Slovenian",
+    "38": "Spanish",
+    "39": "Swedish",
+    "4": "Chinese_China",
+    "40": "Tamil",
+    "41": "Tatar",
+    "42": "Turkish",
+    "43": "Ukranian",
+    "44": "Welsh",
+    "5": "Chinese_Hongkong",
+    "6": "Chinese_Taiwan",
+    "7": "Chuvash",
+    "8": "Czech",
+    "9": "Dhivehi"
+  },
+  "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",
+    "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": "4.33.2",
+  "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 sha256:1cfa5e40ba3601ca072f21b21399b32f16275ba176b199da81000d3b63facde9
+size 1112381937

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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:79456675143c872b154cd09eb77acaef6a51aa5967ae4db213e5bcb5d0e3f475
+size 4091