Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+base_model: indolem/indobert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: apwic/indobert-base-uncased-lora-nergrit
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# apwic/indobert-base-uncased-lora-nergrit
+
+This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.4709
+- Validation Loss: 0.2069
+- Train Accuracy: 0.9399
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2352, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 0.4709     | 0.2069          | 0.9399         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- TensorFlow 2.12.0
+- Datasets 2.14.6
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "indolem/indobert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "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-LAW",
+    "12": "I-LAW",
+    "13": "B-LOC",
+    "14": "I-LOC",
+    "15": "B-MON",
+    "16": "I-MON",
+    "17": "B-NOR",
+    "18": "I-NOR",
+    "19": "B-ORD",
+    "20": "I-ORD",
+    "21": "B-ORG",
+    "22": "I-ORG",
+    "23": "B-PER",
+    "24": "I-PER",
+    "25": "B-PRC",
+    "26": "I-PRC",
+    "27": "B-PRD",
+    "28": "I-PRD",
+    "29": "B-QTY",
+    "30": "I-QTY",
+    "31": "B-REG",
+    "32": "I-REG",
+    "33": "B-TIM",
+    "34": "I-TIM",
+    "35": "B-WOA",
+    "36": "I-WOA",
+    "37": "B-LAN",
+    "38": "I-LAN"
+  },
+  "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": 37,
+    "B-LAW": 11,
+    "B-LOC": 13,
+    "B-MON": 15,
+    "B-NOR": 17,
+    "B-ORD": 19,
+    "B-ORG": 21,
+    "B-PER": 23,
+    "B-PRC": 25,
+    "B-PRD": 27,
+    "B-QTY": 29,
+    "B-REG": 31,
+    "B-TIM": 33,
+    "B-WOA": 35,
+    "I-CRD": 2,
+    "I-DAT": 4,
+    "I-EVT": 6,
+    "I-FAC": 8,
+    "I-GPE": 10,
+    "I-LAN": 38,
+    "I-LAW": 12,
+    "I-LOC": 14,
+    "I-MON": 16,
+    "I-NOR": 18,
+    "I-ORD": 20,
+    "I-ORG": 22,
+    "I-PER": 24,
+    "I-PRC": 26,
+    "I-PRD": 28,
+    "I-QTY": 30,
+    "I-REG": 32,
+    "I-TIM": 34,
+    "I-WOA": 36,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31923
+}

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc24d5e7ef6756489f0b830ea286d1f9b82b45c5edd13ebe620853cdb1f4fba
+size 440263780

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}