Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],
@@ -9,7 +9,7 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-LOC",
@@ -22,7 +22,7 @@
     "8": "I-LOC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "B-DATE": 6,
     "B-LOC": 1,
@@ -37,8 +37,8 @@
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c826b79c9ee1c1c178bff515325278a02b7dbeeba93b362e2f9a7a28a93a28
-size 2235535145
+oid sha256:951dd1f66f8e2320691fb20677fa39fa70cfeb803f20258f27ab13fede16b5f5
+size 1109908201

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c68175526951c7c3c68c8dac8d418ca8621dbbe15ed2ac615b1120ff5604d8
+oid sha256:3f7061ba75626d1ecde814d588c2ec7b473d724439eab08102e323867b77a5c5
 size 4091