<!-- 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-base-uncased-with-ITTL-without-freeze-LR-1e-05
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0444
- Exact Match: 67.9319
- F1: 73.5776
- Precision: 75.1324
- Recall: 76.1210
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
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
5.7583 | 0.49 | 73 | 3.4717 | 48.6911 | 48.7120 | 48.7565 | 48.7036 |
3.8675 | 0.99 | 146 | 2.0063 | 49.8691 | 49.8691 | 49.8691 | 49.8691 |
2.1019 | 1.49 | 219 | 1.7934 | 43.5864 | 48.7113 | 47.9108 | 55.2027 |
1.9506 | 1.98 | 292 | 1.5978 | 52.4869 | 55.5648 | 55.8810 | 58.4501 |
1.582 | 2.48 | 365 | 1.4043 | 56.5445 | 61.2297 | 61.9432 | 64.9738 |
1.5478 | 2.98 | 438 | 1.2214 | 61.6492 | 66.1051 | 66.6829 | 69.1297 |
1.2069 | 3.47 | 511 | 1.1363 | 62.1728 | 67.2788 | 68.1474 | 70.3092 |
1.2033 | 3.97 | 584 | 1.0647 | 64.1361 | 69.5232 | 70.4180 | 72.9446 |
1.0169 | 4.47 | 657 | 1.0578 | 66.4921 | 72.1170 | 73.7120 | 74.5930 |
0.9691 | 4.96 | 730 | 1.0995 | 63.4817 | 69.3250 | 70.7996 | 71.9125 |
0.8492 | 5.46 | 803 | 1.0184 | 67.2775 | 72.1515 | 73.4105 | 75.0396 |
0.8327 | 5.96 | 876 | 1.1143 | 65.5759 | 71.0294 | 72.7764 | 73.1126 |
0.8248 | 6.45 | 949 | 1.0151 | 68.3246 | 73.9214 | 75.4324 | 76.0018 |
0.7498 | 6.95 | 1022 | 1.0034 | 68.8482 | 74.2840 | 76.1810 | 75.9452 |
0.6847 | 7.45 | 1095 | 1.0601 | 68.0628 | 73.5761 | 75.3716 | 75.4001 |
0.7117 | 7.94 | 1168 | 1.0448 | 68.0628 | 74.0368 | 75.6591 | 75.9829 |
0.6365 | 8.44 | 1241 | 1.0444 | 67.9319 | 73.5776 | 75.1324 | 76.1210 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2