Training in progress, epoch 1

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "mrm8488/TinyBERT-spanish-uncased-finetuned-ner",
+  "base_model_name_or_path": "roberta-large",
   "bias": "all",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6413772851e993811224973a7b9ee1c6a67679fc398a9f41891408ca2dc60f8
-size 403533
+oid sha256:f6fc78f225580ac648c70a0c8b03cb48fc08eb567cec3115291582a8f470eef1
+size 7519645

added_tokens.json

@@ -1,7 +1,7 @@
 {
-  "[CLS]": 4,
-  "[MASK]": 0,
-  "[PAD]": 1,
-  "[SEP]": 5,
-  "[UNK]": 3
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
 }

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,7 +1,8 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[MASK]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,32 +10,32 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[CLS]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "[SEP]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
@@ -42,19 +43,18 @@
     }
   },
   "additional_special_tokens": [],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
   "padding": true,
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "truncation": true,
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }