Training complete

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: belajarner
+  results: []
+---
+
+<!-- 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. -->
+
+# belajarner
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2832
+- Precision: 0.8019
+- Recall: 0.8379
+- F1: 0.8195
+- Accuracy: 0.9411
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2947        | 1.0   | 1567  | 0.2493          | 0.7364    | 0.7978 | 0.7658 | 0.9276   |
+| 0.1966        | 2.0   | 3134  | 0.2276          | 0.7717    | 0.8150 | 0.7927 | 0.9351   |
+| 0.1486        | 3.0   | 4701  | 0.2354          | 0.7773    | 0.8293 | 0.8025 | 0.9366   |
+| 0.1183        | 4.0   | 6268  | 0.2468          | 0.8001    | 0.8388 | 0.8190 | 0.9396   |
+| 0.096         | 5.0   | 7835  | 0.2539          | 0.8093    | 0.8296 | 0.8193 | 0.9407   |
+| 0.0772        | 6.0   | 9402  | 0.2717          | 0.8000    | 0.8382 | 0.8187 | 0.9395   |
+| 0.0648        | 7.0   | 10969 | 0.2822          | 0.8010    | 0.8400 | 0.8201 | 0.9412   |
+| 0.0556        | 8.0   | 12536 | 0.2832          | 0.8019    | 0.8379 | 0.8195 | 0.9411   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,113 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "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": "B-WOA",
+    "38": "I-WOA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "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": 38,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "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": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2403ff9da46121da482aec13408aab17ad2708238deded83a3db2991a21e442d
+size 709194716

runs/Mar26_02-31-42_e3f97316e80a/events.out.tfevents.1711420312.e3f97316e80a.155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd936b6eaba6c1276be1018625bb435785852be72fcd542211db11c8fc046ea
+size 13884

runs/Mar26_02-31-42_e3f97316e80a/events.out.tfevents.1711423085.e3f97316e80a.155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7324be7aacb4ff4f3a8da5c774fef4f570fb62d25fa473e570c9ca98c7658665
+size 560

runs/Mar26_03-25-17_e3f97316e80a/events.out.tfevents.1711423521.e3f97316e80a.155.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f61001cc414d3ae95a22cdfa2f5eaad790ee1e87e45a3ecaeef0aa615dd6e1
+size 13835

runs/Mar26_04-09-24_e3f97316e80a/events.out.tfevents.1711426167.e3f97316e80a.155.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c7680d9c194b992b97725fab8ced3547d0b93100a980f4f2816c384ac31ef8
+size 13837

runs/Mar26_04-09-24_e3f97316e80a/events.out.tfevents.1711428742.e3f97316e80a.155.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6088502ef8c1f069c3d4f8803a48fbcc5ccde579661b4d91e542362725af18d3
+size 560

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739810f8ea16ffb5da42d3899982469e618b75c6e8b88e316f8836a2e9ef55fe
+size 4536