Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vonewman/xlm-roberta-base-finetuned-wolof",
+  "_name_or_path": "vonewman/xlm-roberta-large-finetuned-wolof",
   "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 sha256:2c3f86dfdb4e687b035d88632437c912f8b1366bc810787c85ddb86d71c0486a
-size 1109908201
+oid sha256:b17c58f4cbd8870d47d5a228ffa2e9660b4c7e301646445e661a20c25b74b499
+size 2235535145

tokenizer_config.json

@@ -11,9 +11,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770786e6a012dc40e05706a67cd4dbf265ef3820b01992c2643a28a04c7ad2ed
+oid sha256:5ddc6169707df442a4d8787c211d8ee8d6355b988112705c3a26701cf7e234ab
 size 4027