Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dbmdz/distilbert-base-german-europeana-cased",
+  "_name_or_path": "distilbert-base-multilingual-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForTokenClassification"
@@ -23,12 +23,13 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
+  "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
-  "vocab_size": 32000
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3865032da3cd60b87ea1c59bdce986efe321f19e55dbfc9bf9129e0a63ef5705
-size 270013508
+oid sha256:d0f023ca5cb40c7efbfa470dab19f60fcc7a550c444589513e695d7350de8d71
+size 538957900

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,18 +41,15 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_len": 512,
   "model_max_length": 512,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": false,
+  "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c101b122c1065d5c4848910c31f38bcb1f8d8eb7f4a0d98c8c57d08d45dddac
+oid sha256:4ec21aa80f447bdc48ce063a59fc0c71ad6a5ac58c4895623fd031cb90394fec
 size 5304