<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuned-DatasetQAS-TYDI-QA-ID-with-indobert-large-p2-without-ITTL-without-freeze-LR-1e-05
This model is a fine-tuned version of indobenchmark/indobert-large-p2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3674
- Exact Match: 61.6056
- F1: 75.5602
- Precision: 77.4368
- Recall: 81.6689
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 6.0141 | 0.49 | 38 | 2.9934 | 18.3246 | 28.5746 | 29.9986 | 38.5826 |
| 3.7088 | 0.99 | 76 | 2.2203 | 26.8761 | 39.4873 | 41.1034 | 53.1907 |
| 2.2959 | 1.48 | 114 | 1.6080 | 44.8517 | 57.3435 | 59.1495 | 67.1641 |
| 1.6372 | 1.97 | 152 | 1.3376 | 51.8325 | 64.2537 | 66.2962 | 72.3325 |
| 1.6372 | 2.47 | 190 | 1.2596 | 54.4503 | 68.1380 | 70.6221 | 74.2239 |
| 1.22 | 2.96 | 228 | 1.1852 | 56.8935 | 70.9543 | 73.3635 | 75.8557 |
| 1.0455 | 3.45 | 266 | 1.1563 | 57.5916 | 71.5590 | 73.6178 | 77.8050 |
| 0.9065 | 3.95 | 304 | 1.1665 | 59.6859 | 73.4100 | 75.5409 | 78.9196 |
| 0.9065 | 4.44 | 342 | 1.1836 | 60.7330 | 74.8281 | 76.8589 | 79.7466 |
| 0.7931 | 4.94 | 380 | 1.1379 | 60.7330 | 74.7075 | 76.7252 | 79.6857 |
| 0.6928 | 5.43 | 418 | 1.2231 | 60.3839 | 74.8252 | 77.1086 | 79.3933 |
| 0.6134 | 5.92 | 456 | 1.2237 | 61.0820 | 75.0180 | 76.8374 | 80.0757 |
| 0.6134 | 6.42 | 494 | 1.2708 | 62.4782 | 75.6353 | 77.9711 | 80.0176 |
| 0.5184 | 6.91 | 532 | 1.2351 | 62.1291 | 75.4447 | 77.4664 | 80.9526 |
| 0.4996 | 7.4 | 570 | 1.2836 | 61.9546 | 75.7055 | 77.5004 | 80.8263 |
| 0.4253 | 7.9 | 608 | 1.2907 | 61.9546 | 75.7304 | 77.4574 | 81.1694 |
| 0.4253 | 8.39 | 646 | 1.3289 | 62.3037 | 75.8263 | 77.7220 | 80.7753 |
| 0.4077 | 8.88 | 684 | 1.3006 | 61.6056 | 75.4850 | 77.2571 | 80.4104 |
| 0.3478 | 9.38 | 722 | 1.3455 | 61.2565 | 74.7989 | 76.8151 | 80.0213 |
| 0.3074 | 9.87 | 760 | 1.3674 | 61.6056 | 75.5602 | 77.4368 | 81.6689 |
Framework versions
- Transformers 4.27.0
- Pytorch 2.0.0+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
