apwic's picture
End of training
76dd70d verified
|
raw
history blame
3.34 kB
metadata
language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-lora-r8a1d0.15-0
    results: []

sentiment-lora-r8a1d0.15-0

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3217
  • Accuracy: 0.8622
  • Precision: 0.8326
  • Recall: 0.8375
  • F1: 0.8349

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: 5e-05
  • train_batch_size: 30
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20.0

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.5593 1.0 122 0.5026 0.7268 0.6658 0.6542 0.6589
0.4995 2.0 244 0.4797 0.7544 0.7149 0.7412 0.7226
0.4612 3.0 366 0.4282 0.7644 0.7199 0.7358 0.7262
0.4019 4.0 488 0.3934 0.8296 0.7949 0.7919 0.7934
0.3665 5.0 610 0.4234 0.7970 0.7618 0.7964 0.7720
0.334 6.0 732 0.3723 0.8195 0.7817 0.7973 0.7884
0.3263 7.0 854 0.3704 0.8346 0.7990 0.8230 0.8086
0.3076 8.0 976 0.3521 0.8471 0.8153 0.8168 0.8160
0.298 9.0 1098 0.3522 0.8471 0.8138 0.8243 0.8187
0.2923 10.0 1220 0.3375 0.8571 0.8289 0.8239 0.8264
0.2689 11.0 1342 0.3392 0.8622 0.8319 0.8400 0.8357
0.2686 12.0 1464 0.3484 0.8622 0.8309 0.8450 0.8373
0.2726 13.0 1586 0.3258 0.8596 0.8316 0.8282 0.8298
0.2713 14.0 1708 0.3246 0.8622 0.8333 0.8350 0.8341
0.2577 15.0 1830 0.3307 0.8596 0.8293 0.8357 0.8324
0.2519 16.0 1952 0.3305 0.8622 0.8314 0.8425 0.8365
0.2488 17.0 2074 0.3234 0.8546 0.8246 0.8246 0.8246
0.2546 18.0 2196 0.3247 0.8647 0.8346 0.8442 0.8391
0.2463 19.0 2318 0.3204 0.8596 0.8307 0.8307 0.8307
0.2458 20.0 2440 0.3217 0.8622 0.8326 0.8375 0.8349

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.15.2