Training in progress epoch 0

README.md

@@ -0,0 +1,58 @@
+---
+license: mit
+base_model: flax-community/indonesian-roberta-base
+tags:
+- generated_from_keras_callback
+model-index:
+- name: aadhistii/roberta-base-indonesian-ner
+  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. -->
+
+# aadhistii/roberta-base-indonesian-ner
+
+This model is a fine-tuned version of [flax-community/indonesian-roberta-base](https://huggingface.co/flax-community/indonesian-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.4384
+- Validation Loss: 0.1839
+- Train Precision: 0.7954
+- Train Recall: 0.8247
+- Train F1: 0.8098
+- Train Accuracy: 0.9459
+- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2349, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.4384     | 0.1839          | 0.7954          | 0.8247       | 0.8098   | 0.9459         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- TensorFlow 2.15.0
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "flax-community/indonesian-roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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",
+    "36": "I-TIM",
+    "37": "I-WOA",
+    "38": "O"
+  },
+  "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,
+    "I-TIM": 36,
+    "I-WOA": 37,
+    "O": 38
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142145ba88306b0340ce8301f0a3db095e1df8143c9a2e0f0b065eb7f85056c0
+size 496627792

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}