Training in progress, epoch 1

config.json

@@ -1,11 +1,13 @@
 {
-  "_name_or_path": "bert-base-multilingual-uncased",
+  "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
   "architectures": [
-    "BertForTokenClassification"
+    "RobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -29,21 +31,17 @@
     "OTH": 1,
     "VAR": 3
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "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",
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.33.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 105879
+  "vocab_size": 40000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17487b1a168845291213188bf3462215651f66e47429f2f92d6ff238d8b78cf7
-size 667152553
+oid sha256:6576bae791a541a24ee27f256729cfddf6d7183dfc4a92259ac1105a4ca3f2aa
+size 464775913

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49dfca8775caf8e72d0d0eb788857c49497d1635e1a01294fdf744d690c02fe
+oid sha256:dd7dd697122beb80ea626d92cdbaf2e8f1c834c2f7043fe1e66171571aff88a8
 size 4027