update model

README.md

@@ -6,21 +6,21 @@ metrics:
 - accuracy
 
 model-index:
-- name: distilbert-base-multilingual-cased-finetuned-conll2003-ner
+- name: gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# distilbert-base-multilingual-cased-finetuned-conll2003-ner
+# gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
 
 This model was trained from scratch on an unkown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0635
-- Precision: 0.9269
-- Recall: 0.9337
-- F1: 0.9303
-- Accuracy: 0.9835
+- Loss: 0.0484
+- Precision: 0.9340
+- Recall: 0.9413
+- F1: 0.9376
+- Accuracy: 0.9875
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2338        | 1.0   | 878  | 0.0753          | 0.9188    | 0.9089 | 0.9138 | 0.9795   |
-| 0.0541        | 2.0   | 1756 | 0.0681          | 0.9362    | 0.9278 | 0.9320 | 0.9830   |
-| 0.031         | 3.0   | 2634 | 0.0635          | 0.9269    | 0.9337 | 0.9303 | 0.9835   |
+| 0.1931        | 1.0   | 878  | 0.0518          | 0.9146    | 0.9276 | 0.9210 | 0.9852   |
+| 0.0389        | 2.0   | 1756 | 0.0470          | 0.9261    | 0.9389 | 0.9325 | 0.9870   |
+| 0.0228        | 3.0   | 2634 | 0.0484          | 0.9340    | 0.9413 | 0.9376 | 0.9875   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-multilingual-cased",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForTokenClassification"
@@ -35,12 +35,11 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "transformers_version": "4.6.1",
-  "vocab_size": 119547
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790c1d8f79c4a1b09b3836462f3be2a7a741284977d99a353812d499693d61c7
-size 539006405
+oid sha256:76b8f43b516f5f0340d896894e4aa0f3f903752bac218e5c8d1b8477a853a7c3
+size 265521605

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-multilingual-cased"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased"}