<!-- 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-IDK-MRC-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: 1.2692
- Exact Match: 51.4398
- F1: 59.0345
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
---|---|---|---|---|---|
6.2713 | 0.49 | 36 | 2.5468 | 30.3665 | 34.0531 |
3.5101 | 0.98 | 72 | 2.0030 | 26.1780 | 33.6392 |
2.1683 | 1.48 | 108 | 1.7104 | 35.6021 | 43.2542 |
2.1683 | 1.97 | 144 | 1.5149 | 38.7435 | 45.7187 |
1.7142 | 2.46 | 180 | 1.3471 | 42.4084 | 49.3230 |
1.3474 | 2.95 | 216 | 1.3106 | 44.6335 | 51.9284 |
1.2026 | 3.45 | 252 | 1.2716 | 48.2984 | 55.5830 |
1.2026 | 3.94 | 288 | 1.2871 | 45.4188 | 52.6299 |
1.1206 | 4.44 | 324 | 1.2656 | 47.9058 | 55.2204 |
0.978 | 4.93 | 360 | 1.2104 | 48.5602 | 55.8212 |
0.978 | 5.42 | 396 | 1.2160 | 52.3560 | 59.7338 |
0.9386 | 5.91 | 432 | 1.2306 | 50.1309 | 57.1309 |
0.876 | 6.41 | 468 | 1.2227 | 51.5707 | 59.1973 |
0.8186 | 6.9 | 504 | 1.2640 | 51.8325 | 59.8596 |
0.8186 | 7.39 | 540 | 1.2740 | 49.7382 | 57.9164 |
0.7966 | 7.89 | 576 | 1.2344 | 50.5236 | 58.2409 |
0.7632 | 8.38 | 612 | 1.2692 | 51.4398 | 59.0345 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2