Training in progress, epoch 1

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-multilingual-cased",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BertForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -33,21 +34,17 @@
     "I-PERSON": 2,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-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": "4.48.3",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7255a0d9989f074c0e90b4649de680c3d32dac573a25b88b6221ed7cfc64f49c
-size 709102436
+oid sha256:130337c4bebd0eccb6e72bf13a69dcc6b97b259da9c1ba6f0a6b5231e797b4c4
+size 1109863956

runs/Feb26_12-19-49_9c672336c1e1/events.out.tfevents.1740572392.9c672336c1e1.1001.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897d0539f34abad08fd30ff66f86106b002daa8e4c19ec263f380c3e1a078504
+size 6199

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d35b2092427eb68b5a62e65d71bfd30604861905eadd0290160715bd0a1339
+oid sha256:a574e24f1584974967d5163806810d1d1c1e55766976546a9fa2f67607809bce
 size 5368