<!-- 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
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: 1.0604
- Exact Match: 69.1099
- F1: 72.5511
- Precision: 73.1008
- Recall: 72.6415
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 |
|---|---|---|---|---|---|---|---|
| 5.5481 | 0.49 | 72 | 3.2112 | 48.4293 | 51.4398 | 51.4398 | 51.4398 |
| 3.5187 | 0.98 | 144 | 2.0492 | 49.8691 | 53.0105 | 53.0105 | 53.0105 |
| 2.1378 | 1.47 | 216 | 1.8265 | 49.6073 | 52.8432 | 52.7883 | 53.0432 |
| 2.0191 | 1.96 | 288 | 1.6413 | 50.0 | 55.3856 | 55.2323 | 56.6140 |
| 1.6485 | 2.45 | 360 | 1.4309 | 57.0681 | 60.8658 | 61.0064 | 61.4124 |
| 1.5878 | 2.94 | 432 | 1.2824 | 59.2932 | 63.1427 | 63.3864 | 63.6375 |
| 1.2111 | 3.43 | 504 | 1.1649 | 62.3037 | 65.7367 | 66.2226 | 65.9932 |
| 1.1951 | 3.92 | 576 | 1.0818 | 64.2670 | 68.3155 | 68.7235 | 68.5007 |
| 1.1498 | 4.41 | 648 | 1.1072 | 63.6126 | 66.9459 | 67.3311 | 67.2027 |
| 0.9706 | 4.89 | 720 | 1.0439 | 66.8848 | 70.6183 | 71.0568 | 70.9028 |
| 0.9326 | 5.39 | 792 | 1.0014 | 68.0628 | 71.3521 | 71.8608 | 71.4544 |
| 0.8384 | 5.87 | 864 | 1.0279 | 65.3141 | 68.8561 | 69.2826 | 69.0155 |
| 0.8171 | 6.37 | 936 | 1.0405 | 68.4555 | 72.0273 | 72.5898 | 72.1179 |
| 0.7371 | 6.85 | 1008 | 1.0032 | 67.1466 | 70.4649 | 70.9701 | 70.6563 |
| 0.6918 | 7.35 | 1080 | 1.0841 | 66.0995 | 69.2320 | 69.6566 | 69.3692 |
| 0.6891 | 7.83 | 1152 | 0.9651 | 69.2408 | 72.6165 | 73.1959 | 72.5760 |
| 0.6171 | 8.33 | 1224 | 1.0881 | 68.4555 | 71.7433 | 72.3149 | 71.7580 |
| 0.5754 | 8.81 | 1296 | 0.9857 | 69.5026 | 73.0417 | 73.6169 | 73.0734 |
| 0.6054 | 9.31 | 1368 | 1.1012 | 68.7173 | 72.1025 | 72.7347 | 72.0089 |
| 0.5516 | 9.79 | 1440 | 1.0517 | 68.0628 | 71.8207 | 72.4355 | 71.8125 |
| 0.5177 | 10.28 | 1512 | 1.0604 | 69.1099 | 72.5511 | 73.1008 | 72.6415 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
