Training complete

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: cahya/bert-base-indonesian-1.5G
+license: afl-3.0
+base_model: Davlan/bert-base-multilingual-cased-ner-hrl
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # belajarner_bert_case
 
-This model is a fine-tuned version of [cahya/bert-base-indonesian-1.5G](https://huggingface.co/cahya/bert-base-indonesian-1.5G) on an unknown dataset.
+This model is a fine-tuned version of [Davlan/bert-base-multilingual-cased-ner-hrl](https://huggingface.co/Davlan/bert-base-multilingual-cased-ner-hrl) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3302
-- Precision: 0.8314
-- Recall: 0.8484
-- F1: 0.8398
-- Accuracy: 0.9471
+- Loss: 0.3367
+- Precision: 0.8139
+- Recall: 0.8422
+- F1: 0.8278
+- Accuracy: 0.9420
 
 ## Model description
 
@@ -55,19 +55,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1904        | 1.0   | 1567  | 0.2090          | 0.7825    | 0.8298 | 0.8054 | 0.9385   |
-| 0.1195        | 2.0   | 3134  | 0.2141          | 0.8312    | 0.8237 | 0.8274 | 0.9446   |
-| 0.0772        | 3.0   | 4701  | 0.2200          | 0.8220    | 0.8427 | 0.8322 | 0.9457   |
-| 0.0463        | 4.0   | 6268  | 0.2636          | 0.8158    | 0.8498 | 0.8324 | 0.9446   |
-| 0.0342        | 5.0   | 7835  | 0.2878          | 0.8351    | 0.8392 | 0.8372 | 0.9456   |
-| 0.0223        | 6.0   | 9402  | 0.3066          | 0.8267    | 0.8414 | 0.8340 | 0.9454   |
-| 0.0139        | 7.0   | 10969 | 0.3250          | 0.8302    | 0.8476 | 0.8388 | 0.9466   |
-| 0.0096        | 8.0   | 12536 | 0.3302          | 0.8314    | 0.8484 | 0.8398 | 0.9471   |
+| 0.2503        | 1.0   | 1567  | 0.2331          | 0.7484    | 0.8148 | 0.7802 | 0.9294   |
+| 0.1645        | 2.0   | 3134  | 0.2307          | 0.7987    | 0.8158 | 0.8072 | 0.9363   |
+| 0.1097        | 3.0   | 4701  | 0.2588          | 0.7764    | 0.8334 | 0.8039 | 0.9360   |
+| 0.0822        | 4.0   | 6268  | 0.2624          | 0.8056    | 0.8389 | 0.8219 | 0.9409   |
+| 0.061         | 5.0   | 7835  | 0.2927          | 0.8183    | 0.8275 | 0.8229 | 0.9414   |
+| 0.0407        | 6.0   | 9402  | 0.3156          | 0.8021    | 0.8350 | 0.8182 | 0.9399   |
+| 0.0315        | 7.0   | 10969 | 0.3257          | 0.8102    | 0.8381 | 0.8239 | 0.9413   |
+| 0.0238        | 8.0   | 12536 | 0.3367          | 0.8139    | 0.8422 | 0.8278 | 0.9420   |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.0
+- Datasets 2.17.1
 - Tokenizers 0.15.2

config.json

@@ -1,97 +1,98 @@
 {
-  "_name_or_path": "cahya/bert-base-indonesian-1.5G",
+  "_name_or_path": "Davlan/bert-base-multilingual-cased-ner-hrl",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "B-CRD",
-    "1": "B-DAT",
-    "2": "B-EVT",
-    "3": "B-FAC",
-    "4": "B-GPE",
-    "5": "B-LAN",
-    "6": "B-LAW",
-    "7": "B-LOC",
-    "8": "B-MON",
-    "9": "B-NOR",
-    "10": "B-ORD",
-    "11": "B-ORG",
-    "12": "B-PER",
-    "13": "B-PRC",
-    "14": "B-PRD",
-    "15": "B-QTY",
-    "16": "B-REG",
-    "17": "B-TIM",
-    "18": "B-WOA",
-    "19": "I-CRD",
-    "20": "I-DAT",
-    "21": "I-EVT",
-    "22": "I-FAC",
-    "23": "I-GPE",
-    "24": "I-LAN",
-    "25": "I-LAW",
-    "26": "I-LOC",
-    "27": "I-MON",
-    "28": "I-NOR",
-    "29": "I-ORD",
-    "30": "I-ORG",
-    "31": "I-PER",
-    "32": "I-PRC",
-    "33": "I-PRD",
-    "34": "I-QTY",
-    "35": "I-REG",
+    "0": "O",
+    "1": "B-CRD",
+    "2": "I-CRD",
+    "3": "B-DAT",
+    "4": "I-DAT",
+    "5": "B-EVT",
+    "6": "I-EVT",
+    "7": "B-FAC",
+    "8": "I-FAC",
+    "9": "B-GPE",
+    "10": "I-GPE",
+    "11": "B-LAN",
+    "12": "I-LAN",
+    "13": "B-LAW",
+    "14": "I-LAW",
+    "15": "B-LOC",
+    "16": "I-LOC",
+    "17": "B-MON",
+    "18": "I-MON",
+    "19": "B-NOR",
+    "20": "I-NOR",
+    "21": "B-ORD",
+    "22": "I-ORD",
+    "23": "B-ORG",
+    "24": "I-ORG",
+    "25": "B-PER",
+    "26": "I-PER",
+    "27": "B-PRC",
+    "28": "I-PRC",
+    "29": "B-PRD",
+    "30": "I-PRD",
+    "31": "B-QTY",
+    "32": "I-QTY",
+    "33": "B-REG",
+    "34": "I-REG",
+    "35": "B-TIM",
     "36": "I-TIM",
-    "37": "I-WOA",
-    "38": "O"
+    "37": "B-WOA",
+    "38": "I-WOA"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-CRD": 0,
-    "B-DAT": 1,
-    "B-EVT": 2,
-    "B-FAC": 3,
-    "B-GPE": 4,
-    "B-LAN": 5,
-    "B-LAW": 6,
-    "B-LOC": 7,
-    "B-MON": 8,
-    "B-NOR": 9,
-    "B-ORD": 10,
-    "B-ORG": 11,
-    "B-PER": 12,
-    "B-PRC": 13,
-    "B-PRD": 14,
-    "B-QTY": 15,
-    "B-REG": 16,
-    "B-TIM": 17,
-    "B-WOA": 18,
-    "I-CRD": 19,
-    "I-DAT": 20,
-    "I-EVT": 21,
-    "I-FAC": 22,
-    "I-GPE": 23,
-    "I-LAN": 24,
-    "I-LAW": 25,
-    "I-LOC": 26,
-    "I-MON": 27,
-    "I-NOR": 28,
-    "I-ORD": 29,
-    "I-ORG": 30,
-    "I-PER": 31,
-    "I-PRC": 32,
-    "I-PRD": 33,
-    "I-QTY": 34,
-    "I-REG": 35,
+    "B-CRD": 1,
+    "B-DAT": 3,
+    "B-EVT": 5,
+    "B-FAC": 7,
+    "B-GPE": 9,
+    "B-LAN": 11,
+    "B-LAW": 13,
+    "B-LOC": 15,
+    "B-MON": 17,
+    "B-NOR": 19,
+    "B-ORD": 21,
+    "B-ORG": 23,
+    "B-PER": 25,
+    "B-PRC": 27,
+    "B-PRD": 29,
+    "B-QTY": 31,
+    "B-REG": 33,
+    "B-TIM": 35,
+    "B-WOA": 37,
+    "I-CRD": 2,
+    "I-DAT": 4,
+    "I-EVT": 6,
+    "I-FAC": 8,
+    "I-GPE": 10,
+    "I-LAN": 12,
+    "I-LAW": 14,
+    "I-LOC": 16,
+    "I-MON": 18,
+    "I-NOR": 20,
+    "I-ORD": 22,
+    "I-ORG": 24,
+    "I-PER": 26,
+    "I-PRC": 28,
+    "I-PRD": 30,
+    "I-QTY": 32,
+    "I-REG": 34,
     "I-TIM": 36,
-    "I-WOA": 37,
-    "O": 38
+    "I-WOA": 38,
+    "O": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -99,10 +100,15 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f48a4068dfc6c563caa3269fa4354d48b78e054e08c560b9d28fa3c9b46343dc
-size 440250324
+oid sha256:3c5ff0211f38026f5243f61a377f5e7f5d8e834144928cff583aa6dfd93a67de
+size 709194716

runs/Feb20_02-50-19_21f700017ff9/events.out.tfevents.1708397421.21f700017ff9.191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98dd95f9bd184fed07eca29f126ee7a893236f569fd66035cb7ce48927970d8
+size 13914

tokenizer_config.json

@@ -1,38 +1,38 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[UNK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[SEP]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[PAD]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[CLS]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -44,10 +44,9 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "full_tokenizer_file": null,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089227e81d92fd690978c5ba0e6b83d332833d004b1e9c55aab1b9fbaff3fc02
+oid sha256:aa0914b1da1ced7966de88c48803983604e5c535c3c6a4412d9e069e170a0add
 size 4600