metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: indobertweet-finetuned-ijelid
results: []
widget:
- text: Productnya bagus bgt guys, nek bales chat cepet tur pelayanane apik.
indobertweet-finetuned-ijelid
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5301
- Precision: 0.9246
- Recall: 0.9344
- F1: 0.9293
- Accuracy: 0.9513
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.5141 | 0.9216 | 0.9326 | 0.9268 | 0.9508 |
| No log | 2.0 | 98 | 0.5187 | 0.9222 | 0.9356 | 0.9285 | 0.9512 |
| No log | 3.0 | 147 | 0.5307 | 0.9256 | 0.9341 | 0.9296 | 0.9516 |
| No log | 4.0 | 196 | 0.5307 | 0.9251 | 0.9343 | 0.9295 | 0.9512 |
| No log | 5.0 | 245 | 0.5301 | 0.9246 | 0.9344 | 0.9293 | 0.9513 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu102
- Datasets 2.5.1
- Tokenizers 0.12.1