metadata
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: []
tunarebus/indonesian-roberta-base-posp-tagger-finetuned-tweet_pemilu2024
This model is a fine-tuned version of w11wo/indonesian-roberta-base-posp-tagger on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.4664
- Validation Loss: 5.3607
- Epoch: 19
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 |
---|---|---|
11.7870 | 11.4348 | 0 |
10.8383 | 10.1366 | 1 |
9.6098 | 9.0621 | 2 |
8.7602 | 8.2954 | 3 |
8.0949 | 7.7276 | 4 |
7.6334 | 7.2756 | 5 |
7.3192 | 7.0363 | 6 |
7.1297 | 6.8447 | 7 |
6.8798 | 6.6169 | 8 |
6.6715 | 6.4639 | 9 |
6.5429 | 6.3752 | 10 |
6.4095 | 6.2620 | 11 |
6.2638 | 6.1581 | 12 |
6.1540 | 5.9689 | 13 |
6.0265 | 5.8920 | 14 |
5.8897 | 5.7454 | 15 |
5.8217 | 5.6647 | 16 |
5.6666 | 5.4978 | 17 |
5.5835 | 5.4511 | 18 |
5.4664 | 5.3607 | 19 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.0
- Tokenizers 0.15.0