Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: w11wo/indonesian-roberta-base-posp-tagger
+tags:
+- generated_from_keras_callback
+model-index:
+- name: tunarebus/indonesian-roberta-base-posp-tagger-finetuned-tweet_pemilu2024
+  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. -->
+
+# tunarebus/indonesian-roberta-base-posp-tagger-finetuned-tweet_pemilu2024
+
+This model is a fine-tuned version of [w11wo/indonesian-roberta-base-posp-tagger](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 12.1843
+- Validation Loss: 11.7533
+- 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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -969, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 12.1843    | 11.7533         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- TensorFlow 2.15.0
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "w11wo/indonesian-roberta-base-posp-tagger",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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-PPO",
+    "1": "B-KUA",
+    "2": "B-ADV",
+    "3": "B-PRN",
+    "4": "B-VBI",
+    "5": "B-PAR",
+    "6": "B-VBP",
+    "7": "B-NNP",
+    "8": "B-UNS",
+    "9": "B-VBT",
+    "10": "B-VBL",
+    "11": "B-NNO",
+    "12": "B-ADJ",
+    "13": "B-PRR",
+    "14": "B-PRK",
+    "15": "B-CCN",
+    "16": "B-$$$",
+    "17": "B-ADK",
+    "18": "B-ART",
+    "19": "B-CSN",
+    "20": "B-NUM",
+    "21": "B-SYM",
+    "22": "B-INT",
+    "23": "B-NEG",
+    "24": "B-PRI",
+    "25": "B-VBE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-$$$": 16,
+    "B-ADJ": 12,
+    "B-ADK": 17,
+    "B-ADV": 2,
+    "B-ART": 18,
+    "B-CCN": 15,
+    "B-CSN": 19,
+    "B-INT": 22,
+    "B-KUA": 1,
+    "B-NEG": 23,
+    "B-NNO": 11,
+    "B-NNP": 7,
+    "B-NUM": 20,
+    "B-PAR": 5,
+    "B-PPO": 0,
+    "B-PRI": 24,
+    "B-PRK": 14,
+    "B-PRN": 3,
+    "B-PRR": 13,
+    "B-SYM": 21,
+    "B-UNS": 8,
+    "B-VBE": 25,
+    "B-VBI": 4,
+    "B-VBL": 10,
+    "B-VBP": 6,
+    "B-VBT": 9
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420a9f8841149a066427833e0be93b0a839887faaa6aa8cbb688aa0b3f06c6c2
+size 655071156

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>"
+}