Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "../input/my-model/xlm_roberta_base_pretrained_wolof_model_pytorch",
+  "_name_or_path": "xlm_roberta_large_wolof_pretrained_model_pytorch",
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],
@@ -9,7 +9,7 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-LOC",
@@ -22,7 +22,7 @@
     "8": "I-LOC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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:cc5da34755a3927db1c804c4ac6ec68cfc4c1ee351f28ab3cfd55640fb80eda5
-size 1109908201
+oid sha256:b17c58f4cbd8870d47d5a228ffa2e9660b4c7e301646445e661a20c25b74b499
+size 2235535145

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43cb66d6df6c86021c2ad630f0214930b280cdc6bfb33fe05a555bd4d180fa71
-size 17082925
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95611591d4c53aef85b03271ca9b472cc61f9ac292089113fa2b403fccbb3010
+oid sha256:b2438b2561612d82b80dde2f705af0567bf0697cdcc288270593af9a7e966db1
 size 4027