add model

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- null
+- wikiann
 metrics:
 - precision
 - recall
@@ -14,10 +14,14 @@ model_index:
   - task:
       name: Token Classification
       type: token-classification
+    dataset:
+      name: wikiann
+      type: wikiann
+      args: sr
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.9418150723128973
+      value: 0.95641898994996
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -25,13 +29,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # electra-srb-ner
 
-This model was trained from scratch on the None dataset.
+This model was trained from scratch on the wikiann dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2062
-- Precision: 0.7553
-- Recall: 0.7362
-- F1: 0.7456
-- Accuracy: 0.9418
+- Loss: 0.3017
+- Precision: 0.8911
+- Recall: 0.9081
+- F1: 0.8995
+- Accuracy: 0.9564
 
 ## Model description
 
@@ -56,16 +60,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 207  | 0.2894          | 0.7278    | 0.6252 | 0.6726 | 0.9207   |
-| No log        | 2.0   | 414  | 0.2175          | 0.7463    | 0.6984 | 0.7216 | 0.9352   |
-| 0.3035        | 3.0   | 621  | 0.2189          | 0.7826    | 0.7049 | 0.7417 | 0.9398   |
-| 0.3035        | 4.0   | 828  | 0.2062          | 0.7553    | 0.7362 | 0.7456 | 0.9418   |
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2535        | 1.0   | 1250  | 0.2015          | 0.8494    | 0.8605 | 0.8549 | 0.9376   |
+| 0.1461        | 2.0   | 2500  | 0.1853          | 0.8800    | 0.8681 | 0.8740 | 0.9464   |
+| 0.0914        | 3.0   | 3750  | 0.2022          | 0.8695    | 0.8912 | 0.8802 | 0.9485   |
+| 0.0545        | 4.0   | 5000  | 0.2214          | 0.8758    | 0.8975 | 0.8865 | 0.9514   |
+| 0.0385        | 5.0   | 6250  | 0.2536          | 0.8806    | 0.9010 | 0.8907 | 0.9523   |
+| 0.0266        | 6.0   | 7500  | 0.2506          | 0.8834    | 0.9020 | 0.8926 | 0.9539   |
+| 0.0133        | 7.0   | 8750  | 0.2745          | 0.8910    | 0.9057 | 0.8983 | 0.9562   |
+| 0.0077        | 8.0   | 10000 | 0.2946          | 0.8872    | 0.9065 | 0.8968 | 0.9559   |
+| 0.0043        | 9.0   | 11250 | 0.2931          | 0.8902    | 0.9094 | 0.8997 | 0.9567   |
+| 0.0022        | 10.0  | 12500 | 0.3017          | 0.8911    | 0.9081 | 0.8995 | 0.9564   |
 
 
 ### Framework versions

config.json

@@ -15,10 +15,7 @@
     "3": "LABEL_3",
     "4": "LABEL_4",
     "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9"
+    "6": "LABEL_6"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -29,10 +26,7 @@
     "LABEL_3": 3,
     "LABEL_4": 4,
     "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
+    "LABEL_6": 6
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebe48709174418a5d6b583d89fddf57cdfdb31efd87e93e2574d251afe90a93
-size 435681969
+oid sha256:b7d8a1f36e88c5b01779347014202b894d16581de832b8ffd92fbe47819a491c
+size 435672753

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a005d2ea7afc9ae2800729a104ef88f630e3e3bf4a5b53e98027de77b35740b
+oid sha256:8f81507c71bf9458f8c2acc88833a1e325129d1e0909b54f2b6d8c75619cc011
 size 2671