Update README.md

README.md

@@ -1,3 +1,42 @@
 ---
 license: cc-by-nc-4.0
+metrics:
+- accuracy
+- f1
+datasets:
+- orai-nlp/basqueGLUE
+language:
+- eu
+pipeline_tag: token-classification
+tags:
+- NERC
 ---
+
+
+
+ [ElhBERTeu](https://huggingface.co/orai-nlp/ElhBERTeu) model finetuned for NERC BasqueGlue dataset. 
+ In Domain and Out-of-domain tasks' train and dev datasets were merge for training. Reported performance results are tested on the merged test dataset after training for 10 epochs (batch size 32, learning rate  3e-5).
+
+Results on test set:
+
+* accuracy = 0.9785551028520322
+* f1 = 0.8665899340797322
+* loss = 0.11313809949144367
+* precision = 0.8650511802799248
+* recall = 0.8681341719077568
+
+Per class results: 
+
+accuracy:  97.86%; precision:  86.51%; recall:  86.81%; FB1:  86.66
+              LOC: precision:  89.43%; recall:  87.95%; FB1:  88.68  1844
+             MISC: precision:  70.72%; recall:  67.75%; FB1:  69.20  502
+              ORG: precision:  80.04%; recall:  84.32%; FB1:  82.12  1082
+              PER: precision:  93.52%; recall:  94.57%; FB1:  94.04  1359
+
+
+
+Tagset: 
+["O", "B-ORG", "B-PER", "I-PER", "I-ORG", "B-LOC", "I-LOC", "B-MISC", "I-MISC",]
+
+
+Finetuning details: 10 epochs, batch size 32, learning rate  3e-5.