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 +1,160 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "I-PERSON",
+    "1": "B-TRANSPORTATION",
+    "2": "I-ROLE",
+    "3": "B-EVENT",
+    "4": "I-TIME",
+    "5": "I-TRANSPORTATION",
+    "6": "I-COUNTRY",
+    "7": "I-LANGUAGE",
+    "8": "B-LANGUAGE",
+    "9": "I-LOCATION",
+    "10": "B-DEGREE",
+    "11": "I-DOCUMENT",
+    "12": "B-PERSON",
+    "13": "B-SOCIAL_MEDIA",
+    "14": "B-COUNTRY",
+    "15": "B-SCHOOL",
+    "16": "I-ORGANIZATION",
+    "17": "I-QUANTITY",
+    "18": "I-SONG",
+    "19": "I-NUMBER",
+    "20": "I-FOOD",
+    "21": "B-TEMPERATURE",
+    "22": "I-TOTAL_AREA",
+    "23": "I-TOTAL_VOLUME",
+    "24": "I-DISEASE",
+    "25": "B-RELATIONSHIP",
+    "26": "I-EVENT",
+    "27": "B-GENDER",
+    "28": "B-QUANTITY",
+    "29": "I-TEMPERATURE",
+    "30": "I-DEGREE",
+    "31": "B-EDUCATION",
+    "32": "B-LOCATION",
+    "33": "B-NUMBER",
+    "34": "I-RELATIONSHIP",
+    "35": "I-EDUCATION",
+    "36": "I-ORDINAL",
+    "37": "I-SCHOOL",
+    "38": "B-NATIONALITY",
+    "39": "I-AGE",
+    "40": "O",
+    "41": "B-MONEY",
+    "42": "B-FOOD",
+    "43": "I-MONEY",
+    "44": "B-SONG",
+    "45": "B-TOTAL_AREA",
+    "46": "I-NATIONALITY",
+    "47": "I-RANK",
+    "48": "B-ROLE",
+    "49": "B-ORDINAL",
+    "50": "B-PRODUCT",
+    "51": "B-TIME",
+    "52": "B-AGE",
+    "53": "B-ORGANIZATION",
+    "54": "I-DATE",
+    "55": "B-DISEASE",
+    "56": "B-SPORT",
+    "57": "B-TOTAL_VOLUME",
+    "58": "I-PRODUCT",
+    "59": "B-RANK",
+    "60": "B-DATE",
+    "61": "I-GENDER",
+    "62": "B-DOCUMENT",
+    "63": "I-SPORT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 52,
+    "B-COUNTRY": 14,
+    "B-DATE": 60,
+    "B-DEGREE": 10,
+    "B-DISEASE": 55,
+    "B-DOCUMENT": 62,
+    "B-EDUCATION": 31,
+    "B-EVENT": 3,
+    "B-FOOD": 42,
+    "B-GENDER": 27,
+    "B-LANGUAGE": 8,
+    "B-LOCATION": 32,
+    "B-MONEY": 41,
+    "B-NATIONALITY": 38,
+    "B-NUMBER": 33,
+    "B-ORDINAL": 49,
+    "B-ORGANIZATION": 53,
+    "B-PERSON": 12,
+    "B-PRODUCT": 50,
+    "B-QUANTITY": 28,
+    "B-RANK": 59,
+    "B-RELATIONSHIP": 25,
+    "B-ROLE": 48,
+    "B-SCHOOL": 15,
+    "B-SOCIAL_MEDIA": 13,
+    "B-SONG": 44,
+    "B-SPORT": 56,
+    "B-TEMPERATURE": 21,
+    "B-TIME": 51,
+    "B-TOTAL_AREA": 45,
+    "B-TOTAL_VOLUME": 57,
+    "B-TRANSPORTATION": 1,
+    "I-AGE": 39,
+    "I-COUNTRY": 6,
+    "I-DATE": 54,
+    "I-DEGREE": 30,
+    "I-DISEASE": 24,
+    "I-DOCUMENT": 11,
+    "I-EDUCATION": 35,
+    "I-EVENT": 26,
+    "I-FOOD": 20,
+    "I-GENDER": 61,
+    "I-LANGUAGE": 7,
+    "I-LOCATION": 9,
+    "I-MONEY": 43,
+    "I-NATIONALITY": 46,
+    "I-NUMBER": 19,
+    "I-ORDINAL": 36,
+    "I-ORGANIZATION": 16,
+    "I-PERSON": 0,
+    "I-PRODUCT": 58,
+    "I-QUANTITY": 17,
+    "I-RANK": 47,
+    "I-RELATIONSHIP": 34,
+    "I-ROLE": 2,
+    "I-SCHOOL": 37,
+    "I-SONG": 18,
+    "I-SPORT": 63,
+    "I-TEMPERATURE": 29,
+    "I-TIME": 4,
+    "I-TOTAL_AREA": 22,
+    "I-TOTAL_VOLUME": 23,
+    "I-TRANSPORTATION": 5,
+    "O": 40
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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:ceb6e807201e37388cff4842a480eb250b29e088b58b6d16b829314a0ce1a7e4
+size 1111599872

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

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": 1024,
+  "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:ed412e3b7d5c79ad1a609616575077894eef777ce7778762a30748af474cb61d
+size 5112