Training in progress, epoch 1

config.json

@@ -1,83 +1,46 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.2,
+  "hidden_dropout_prob": 0.3,
   "hidden_size": 768,
   "id2label": {
-    "0": "ADMINISTRACION PUBLICA",
-    "1": "ARTE",
-    "2": "AUTOMOCION",
-    "3": "BANCA Y FINANCIERO",
-    "4": "BIOLOGIA",
-    "5": "COMERCIO-E",
-    "6": "DEPORTES",
-    "7": "ECONOMIA Y FINANZAS",
-    "8": "EDUCACION",
-    "9": "EMPRESA Y MARKETING",
-    "10": "ENERGIA,PETROLEO Y GAS",
-    "11": "GASTRONOMIA Y ALIMENTACION",
-    "12": "INDUSTRIA Y EQUIPAMIENTOS",
-    "13": "INMOBILIARIA",
-    "14": "JUGUETES",
-    "15": "LEGAL Y SEGUROS",
-    "16": "LOGISTICA",
-    "17": "MEDICINA",
-    "18": "MEDIO AMBIENTE",
-    "19": "MODA",
-    "20": "RECURSOS HUMANOS",
-    "21": "SOFTWARE",
-    "22": "TELECOMUNICACIONES",
-    "23": "TRANSPORTE Y LOGISTICA",
-    "24": "TURISMO Y VIAJES"
+    "0": "B",
+    "1": "E",
+    "2": "P",
+    "3": "S",
+    "4": "T"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "ADMINISTRACION PUBLICA": 0,
-    "ARTE": 1,
-    "AUTOMOCION": 2,
-    "BANCA Y FINANCIERO": 3,
-    "BIOLOGIA": 4,
-    "COMERCIO-E": 5,
-    "DEPORTES": 6,
-    "ECONOMIA Y FINANZAS": 7,
-    "EDUCACION": 8,
-    "EMPRESA Y MARKETING": 9,
-    "ENERGIA,PETROLEO Y GAS": 10,
-    "GASTRONOMIA Y ALIMENTACION": 11,
-    "INDUSTRIA Y EQUIPAMIENTOS": 12,
-    "INMOBILIARIA": 13,
-    "JUGUETES": 14,
-    "LEGAL Y SEGUROS": 15,
-    "LOGISTICA": 16,
-    "MEDICINA": 17,
-    "MEDIO AMBIENTE": 18,
-    "MODA": 19,
-    "RECURSOS HUMANOS": 20,
-    "SOFTWARE": 21,
-    "TELECOMUNICACIONES": 22,
-    "TRANSPORTE Y LOGISTICA": 23,
-    "TURISMO Y VIAJES": 24
+    "B": 0,
+    "E": 1,
+    "P": 2,
+    "S": 3,
+    "T": 4
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0",
-  "type_vocab_size": 1,
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a939f785348a57a92cc98f4f88272c21ce6a722b2f207bc555c1cae2c47a5207
-size 1112275756
+oid sha256:2c54e37c4dd10a0c538110596ac78a1757a5dcad8b8b53c0976021b700ae91cf
+size 711452684

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4147c7d8584d679fcabb10e7c63ac96de865feb8a5e2b6bc9308acf93cacdb
-size 17082953
+oid sha256:4e8d2533b6e39afe137ac1ff84390ef303f71f9c257aab2df09f4c6a62d08bf3
+size 2919627

tokenizer_config.json

@@ -1,54 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "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>",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6c615cb937919b60858b4410773db6e7f6877d21d6d7543f4909c5d6ff1d08
-size 4155
+oid sha256:4445c2643d242e58c09052dc49bff30352ee40acf7af330028cd6f72955f5843
+size 4219