Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "cis-lmu/glot500-base",
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],
@@ -64,5 +64,5 @@
   "transformers_version": "4.48.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 401145
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f7fb72db1d1c7f0e1583e16b600fe8dff5872aa76d2fbc59ad068aa2b8cdcdd
-size 1109891640
+oid sha256:a77bf33ab44a076e7e17683f9477710ea47786f42a97fe0a17de42e9f2000dbb
+size 1574203208

runs/Feb17_20-55-13_ed4ad4a957af/events.out.tfevents.1739825715.ed4ad4a957af.3044.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b552a6ab65f9a6a2cecf9712f24ab2f5847deec8d322ec5cefc178a27914e4a5
+size 6307

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051
+oid sha256:7a313a26470baedaede322622492f2a542aa41527ddc5d40de444e945ad3c613
+size 7658320

special_tokens_map.json

@@ -5,7 +5,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
-size 17082999
+oid sha256:db2eadcc9c4d85bc62828f79f5b3cc05c409d958a1ed506f2835e1d38165e7fe
+size 26910556

tokenizer_config.json

@@ -32,10 +32,10 @@
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "401144": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -50,6 +50,8 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "unk_token": "<unk>",
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5445d7c7d113df1eb4221b86c8cb6f67fbcbc607e316971f5ebee913fd1afb2e
+oid sha256:84a4716cd8707ea3a538881acff4beaffba0b4feb7d5d8a2d586eac9a4e35f6b
 size 5368