Training in progress, epoch 1

config.json

@@ -1,5 +1,11 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],
@@ -7,38 +13,71 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
-    "1": "B-PER",
-    "2": "I-PER",
-    "3": "B-ORG",
-    "4": "I-ORG",
-    "5": "B-LOC",
-    "6": "I-LOC",
-    "7": "B-DATE",
-    "8": "I-DATE"
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "L-PERSON",
+    "4": "U-PERSON",
+    "5": "B-NORP",
+    "6": "I-NORP",
+    "7": "L-NORP",
+    "8": "U-NORP",
+    "9": "B-DATE",
+    "10": "I-DATE",
+    "11": "L-DATE",
+    "12": "U-DATE",
+    "13": "B-USERID",
+    "14": "I-USERID",
+    "15": "L-USERID",
+    "16": "U-USERID",
+    "17": "B-ORG",
+    "18": "I-ORG",
+    "19": "L-ORG",
+    "20": "U-ORG",
+    "21": "B-LOCATION",
+    "22": "I-LOCATION",
+    "23": "L-LOCATION",
+    "24": "U-LOCATION"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
-    "B-DATE": 7,
-    "B-LOC": 5,
-    "B-ORG": 3,
-    "B-PER": 1,
-    "I-DATE": 8,
-    "I-LOC": 6,
-    "I-ORG": 4,
-    "I-PER": 2,
-    "O": 0
+    "B-DATE": 9,
+    "B-LOCATION": 21,
+    "B-NORP": 5,
+    "B-ORG": 17,
+    "B-PERSON": 1,
+    "B-USERID": 13,
+    "I-DATE": 10,
+    "I-LOCATION": 22,
+    "I-NORP": 6,
+    "I-ORG": 18,
+    "I-PERSON": 2,
+    "I-USERID": 14,
+    "L-DATE": 11,
+    "L-LOCATION": 23,
+    "L-NORP": 7,
+    "L-ORG": 19,
+    "L-PERSON": 3,
+    "L-USERID": 15,
+    "O": 0,
+    "U-DATE": 12,
+    "U-LOCATION": 24,
+    "U-NORP": 8,
+    "U-ORG": 20,
+    "U-PERSON": 4,
+    "U-USERID": 16
   },
   "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",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881d8aa9923be7a2ad8e57f345c0ee8e0bb70c0f614f308217fff3188974f1d5
-size 1109863956
+oid sha256:3567d9ae053f9e65c13e836961371e91bd2016ee9418817f0637e91cab8ee95c
+size 2235514364

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2089b6d589478cbe3c770f9d7b1f396435f25b6bdd73dbcc8f23023bc8af6b0
+oid sha256:6311782c7363647e258ddb65ac92557e060679315b94b9c76d7635650e25136f
 size 4536