Training in progress, epoch 1

config.json

@@ -1,165 +1,164 @@
 {
-  "_name_or_path": "/kaggle/working/my_awesome_ner-token_classification_v1.0",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
-    "ElectraForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "embedding_size": 768,
-  "finetuning_task": "ner",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "I-ROLE",
-    "1": "B-LANGUAGE",
-    "2": "B-RANK",
-    "3": "I-PHONE",
-    "4": "I-SONG",
-    "5": "I-DATETIME",
-    "6": "I-RANK",
-    "7": "I-SKILL",
-    "8": "B-COMMUNICATION",
-    "9": "B-LAW",
-    "10": "B-RELIGION",
-    "11": "I-LAW",
-    "12": "B-LOCATION",
-    "13": "B-PRODUCT",
-    "14": "I-MISCELLANEOUS",
-    "15": "I-SPORT",
-    "16": "I-MONEY",
-    "17": "B-MISCELLANEOUS",
-    "18": "B-ORGANIZATION",
-    "19": "B-PHONE",
-    "20": "I-LANGUAGE",
-    "21": "B-DATETIME",
-    "22": "I-EMAIL",
-    "23": "I-FOOD",
-    "24": "B-URL",
-    "25": "I-COMMUNICATION",
-    "26": "I-LOCATION",
-    "27": "B-SONG",
-    "28": "O",
-    "29": "B-PERSON",
-    "30": "I-EVENT",
-    "31": "I-ACTION",
-    "32": "I-EDUCATION",
-    "33": "B-GENDER",
-    "34": "I-COUNTRY",
-    "35": "B-EVENT",
-    "36": "B-AGE",
-    "37": "B-ADDRESS",
-    "38": "I-ADDRESS",
-    "39": "B-ANIMAL",
-    "40": "I-GENDER",
-    "41": "I-PERSON",
-    "42": "B-ROLE",
-    "43": "B-SPORT",
-    "44": "I-DISEASE",
-    "45": "B-MONEY",
-    "46": "I-PRODUCT",
-    "47": "I-RELIGION",
-    "48": "I-TRANSPORTATION",
-    "49": "B-DURATION",
-    "50": "I-QUANTITY",
-    "51": "I-AGE",
-    "52": "B-EMAIL",
-    "53": "B-IP",
-    "54": "I-ORGANIZATION",
-    "55": "B-EDUCATION",
-    "56": "B-QUANTITY",
-    "57": "I-DURATION",
-    "58": "B-COUNTRY",
-    "59": "B-FOOD",
-    "60": "B-DISEASE",
-    "61": "B-TRANSPORTATION",
-    "62": "B-ACTION",
-    "63": "I-ANIMAL",
-    "64": "B-SKILL"
+    "0": "I-IP",
+    "1": "I-ROLE",
+    "2": "B-LANGUAGE",
+    "3": "B-RANK",
+    "4": "I-PHONE",
+    "5": "I-SONG",
+    "6": "I-DATETIME",
+    "7": "I-RANK",
+    "8": "I-SKILL",
+    "9": "B-COMMUNICATION",
+    "10": "B-LAW",
+    "11": "B-RELIGION",
+    "12": "I-LAW",
+    "13": "B-LOCATION",
+    "14": "B-PRODUCT",
+    "15": "I-MISCELLANEOUS",
+    "16": "I-SPORT",
+    "17": "I-MONEY",
+    "18": "B-MISCELLANEOUS",
+    "19": "B-ORGANIZATION",
+    "20": "B-PHONE",
+    "21": "I-LANGUAGE",
+    "22": "B-DATETIME",
+    "23": "I-EMAIL",
+    "24": "I-FOOD",
+    "25": "B-URL",
+    "26": "I-COMMUNICATION",
+    "27": "I-LOCATION",
+    "28": "B-SONG",
+    "29": "O",
+    "30": "B-PERSON",
+    "31": "I-EVENT",
+    "32": "I-ACTION",
+    "33": "I-EDUCATION",
+    "34": "B-GENDER",
+    "35": "I-COUNTRY",
+    "36": "B-EVENT",
+    "37": "B-AGE",
+    "38": "B-ADDRESS",
+    "39": "I-ADDRESS",
+    "40": "B-ANIMAL",
+    "41": "I-GENDER",
+    "42": "I-PERSON",
+    "43": "B-ROLE",
+    "44": "B-SPORT",
+    "45": "I-DISEASE",
+    "46": "B-MONEY",
+    "47": "I-PRODUCT",
+    "48": "I-RELIGION",
+    "49": "I-TRANSPORTATION",
+    "50": "B-DURATION",
+    "51": "I-QUANTITY",
+    "52": "I-AGE",
+    "53": "B-EMAIL",
+    "54": "B-IP",
+    "55": "I-ORGANIZATION",
+    "56": "B-EDUCATION",
+    "57": "B-QUANTITY",
+    "58": "I-DURATION",
+    "59": "B-COUNTRY",
+    "60": "B-FOOD",
+    "61": "B-DISEASE",
+    "62": "B-TRANSPORTATION",
+    "63": "B-ACTION",
+    "64": "I-ANIMAL",
+    "65": "B-SKILL"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-ACTION": 62,
-    "B-ADDRESS": 37,
-    "B-AGE": 36,
-    "B-ANIMAL": 39,
-    "B-COMMUNICATION": 8,
-    "B-COUNTRY": 58,
-    "B-DATETIME": 21,
-    "B-DISEASE": 60,
-    "B-DURATION": 49,
-    "B-EDUCATION": 55,
-    "B-EMAIL": 52,
-    "B-EVENT": 35,
-    "B-FOOD": 59,
-    "B-GENDER": 33,
-    "B-IP": 53,
-    "B-LANGUAGE": 1,
-    "B-LAW": 9,
-    "B-LOCATION": 12,
-    "B-MISCELLANEOUS": 17,
-    "B-MONEY": 45,
-    "B-ORGANIZATION": 18,
-    "B-PERSON": 29,
-    "B-PHONE": 19,
-    "B-PRODUCT": 13,
-    "B-QUANTITY": 56,
-    "B-RANK": 2,
-    "B-RELIGION": 10,
-    "B-ROLE": 42,
-    "B-SKILL": 64,
-    "B-SONG": 27,
-    "B-SPORT": 43,
-    "B-TRANSPORTATION": 61,
-    "B-URL": 24,
-    "I-ACTION": 31,
-    "I-ADDRESS": 38,
-    "I-AGE": 51,
-    "I-ANIMAL": 63,
-    "I-COMMUNICATION": 25,
-    "I-COUNTRY": 34,
-    "I-DATETIME": 5,
-    "I-DISEASE": 44,
-    "I-DURATION": 57,
-    "I-EDUCATION": 32,
-    "I-EMAIL": 22,
-    "I-EVENT": 30,
-    "I-FOOD": 23,
-    "I-GENDER": 40,
-    "I-LANGUAGE": 20,
-    "I-LAW": 11,
-    "I-LOCATION": 26,
-    "I-MISCELLANEOUS": 14,
-    "I-MONEY": 16,
-    "I-ORGANIZATION": 54,
-    "I-PERSON": 41,
-    "I-PHONE": 3,
-    "I-PRODUCT": 46,
-    "I-QUANTITY": 50,
-    "I-RANK": 6,
-    "I-RELIGION": 47,
-    "I-ROLE": 0,
-    "I-SKILL": 7,
-    "I-SONG": 4,
-    "I-SPORT": 15,
-    "I-TRANSPORTATION": 48,
-    "O": 28
+    "B-ACTION": 63,
+    "B-ADDRESS": 38,
+    "B-AGE": 37,
+    "B-ANIMAL": 40,
+    "B-COMMUNICATION": 9,
+    "B-COUNTRY": 59,
+    "B-DATETIME": 22,
+    "B-DISEASE": 61,
+    "B-DURATION": 50,
+    "B-EDUCATION": 56,
+    "B-EMAIL": 53,
+    "B-EVENT": 36,
+    "B-FOOD": 60,
+    "B-GENDER": 34,
+    "B-IP": 54,
+    "B-LANGUAGE": 2,
+    "B-LAW": 10,
+    "B-LOCATION": 13,
+    "B-MISCELLANEOUS": 18,
+    "B-MONEY": 46,
+    "B-ORGANIZATION": 19,
+    "B-PERSON": 30,
+    "B-PHONE": 20,
+    "B-PRODUCT": 14,
+    "B-QUANTITY": 57,
+    "B-RANK": 3,
+    "B-RELIGION": 11,
+    "B-ROLE": 43,
+    "B-SKILL": 65,
+    "B-SONG": 28,
+    "B-SPORT": 44,
+    "B-TRANSPORTATION": 62,
+    "B-URL": 25,
+    "I-ACTION": 32,
+    "I-ADDRESS": 39,
+    "I-AGE": 52,
+    "I-ANIMAL": 64,
+    "I-COMMUNICATION": 26,
+    "I-COUNTRY": 35,
+    "I-DATETIME": 6,
+    "I-DISEASE": 45,
+    "I-DURATION": 58,
+    "I-EDUCATION": 33,
+    "I-EMAIL": 23,
+    "I-EVENT": 31,
+    "I-FOOD": 24,
+    "I-GENDER": 41,
+    "I-IP": 0,
+    "I-LANGUAGE": 21,
+    "I-LAW": 12,
+    "I-LOCATION": 27,
+    "I-MISCELLANEOUS": 15,
+    "I-MONEY": 17,
+    "I-ORGANIZATION": 55,
+    "I-PERSON": 42,
+    "I-PHONE": 4,
+    "I-PRODUCT": 47,
+    "I-QUANTITY": 51,
+    "I-RANK": 7,
+    "I-RELIGION": 48,
+    "I-ROLE": 1,
+    "I-SKILL": 8,
+    "I-SONG": 5,
+    "I-SPORT": 16,
+    "I-TRANSPORTATION": 49,
+    "O": 29
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 62000
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d81a21d2e0cbd7b5630d221ad6cc07e5dbd84224606cc36ec026600ed7c42a
-size 532490884
+oid sha256:efaffc0ad114d65bb28b9f3b3c6d9a7e91ab49e64889ea6735d146f25fcedb05
+size 1110039296

special_tokens_map.json

@@ -1,37 +1,15 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
+    "content": "<mask>",
+    "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5166e09320d5dea01a72734268a6136a5d53f2fe55980b6ba0fc19db6e003f72
-size 1394857
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,40 +25,30 @@
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "max_length": 256,
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "[SEP]",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdc78b473a44c34f1608a33ccf2450f0b2ae50f37d6b0b618bab6bc8079730b
+oid sha256:03eac65ea888e69c8dca7f7c772b61c29227c3029ba2741695d7f5820a6f3e7d
 size 5112