Training complete

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: indolem/indobert-base-uncased
+base_model: cahya/bert-base-indonesian-NER
 tags:
 - generated_from_trainer
 datasets:
@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.7905982905982906
+      value: 0.7716312056737589
     - name: Recall
       type: recall
-      value: 0.8383685800604229
+      value: 0.8217522658610272
     - name: F1
       type: f1
-      value: 0.8137829912023461
+      value: 0.7959034381858083
     - name: Accuracy
       type: accuracy
-      value: 0.9516761543327008
+      value: 0.9477048970719857
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # belajarner
 
-This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indonlu_nergrit dataset.
+This model is a fine-tuned version of [cahya/bert-base-indonesian-NER](https://huggingface.co/cahya/bert-base-indonesian-NER) on the indonlu_nergrit dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2235
-- Precision: 0.7906
-- Recall: 0.8384
-- F1: 0.8138
-- Accuracy: 0.9517
+- Loss: 0.2621
+- Precision: 0.7716
+- Recall: 0.8218
+- F1: 0.7959
+- Accuracy: 0.9477
 
 ## Model description
 
@@ -79,14 +79,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 209  | 0.1750          | 0.7418    | 0.8157 | 0.7770 | 0.9469   |
-| No log        | 2.0   | 418  | 0.1590          | 0.7677    | 0.8338 | 0.7994 | 0.9491   |
-| 0.2398        | 3.0   | 627  | 0.1720          | 0.7817    | 0.8112 | 0.7961 | 0.9476   |
-| 0.2398        | 4.0   | 836  | 0.1812          | 0.7948    | 0.8248 | 0.8095 | 0.9510   |
-| 0.0753        | 5.0   | 1045 | 0.1934          | 0.7872    | 0.8384 | 0.8120 | 0.9545   |
-| 0.0753        | 6.0   | 1254 | 0.2178          | 0.7805    | 0.8323 | 0.8056 | 0.9497   |
-| 0.0753        | 7.0   | 1463 | 0.2199          | 0.7943    | 0.8459 | 0.8193 | 0.9522   |
-| 0.0374        | 8.0   | 1672 | 0.2235          | 0.7906    | 0.8384 | 0.8138 | 0.9517   |
+| No log        | 1.0   | 209  | 0.1633          | 0.7678    | 0.8142 | 0.7903 | 0.9476   |
+| No log        | 2.0   | 418  | 0.1623          | 0.7631    | 0.8127 | 0.7871 | 0.9462   |
+| 0.1633        | 3.0   | 627  | 0.1978          | 0.7535    | 0.8172 | 0.7841 | 0.9459   |
+| 0.1633        | 4.0   | 836  | 0.2103          | 0.7573    | 0.8202 | 0.7875 | 0.9460   |
+| 0.0423        | 5.0   | 1045 | 0.2236          | 0.7757    | 0.8097 | 0.7923 | 0.9487   |
+| 0.0423        | 6.0   | 1254 | 0.2529          | 0.7843    | 0.8293 | 0.8062 | 0.9474   |
+| 0.0423        | 7.0   | 1463 | 0.2559          | 0.77      | 0.8142 | 0.7915 | 0.9467   |
+| 0.0136        | 8.0   | 1672 | 0.2621          | 0.7716    | 0.8218 | 0.7959 | 0.9477   |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "indolem/indobert-base-uncased",
+  "_name_or_path": "cahya/bert-base-indonesian-NER",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_ids": 0,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -35,12 +34,11 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 31923
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfff3039d4cddf8b238e162b9c970f03f8fedd66952cfad1842bc5790bdad899
-size 439915340
+oid sha256:c91e35db013f96ddb47572c0bfbad876fb17a171656a56d2961e52aebf1d61b1
+size 440151884

runs/Feb19_02-09-05_51cb7f447e43/events.out.tfevents.1708308548.51cb7f447e43.919.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fa2a3aa31dba2bbf2782631a3eb5b1297551d349341d71845d8d63c260422b
+size 9135

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[MASK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,7 +33,7 @@
       "special": true
     },
     "4": {
-      "content": "[SEP]",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ed29da338e3530fe523346f79bf0087cdb1f41c81618a56fb4712afb10311d
+oid sha256:1ea1fcab412f0bd86e96dcf5c086dbfbbdb78863f4bc80a9f8e9fd9187208469
 size 4536