metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
results: []
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: 1.0515
- Exact Match: 65.9686
- F1: 71.4684
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 |
---|---|---|---|---|---|
6.1822 | 0.49 | 36 | 2.5004 | 49.8691 | 49.8691 |
3.6893 | 0.98 | 72 | 1.9896 | 49.8691 | 49.8691 |
2.2116 | 1.48 | 108 | 1.8516 | 49.2147 | 49.7070 |
2.2116 | 1.97 | 144 | 1.7367 | 50.1309 | 52.0399 |
1.9945 | 2.46 | 180 | 1.5956 | 51.7016 | 56.3444 |
1.7443 | 2.95 | 216 | 1.4508 | 54.9738 | 59.4030 |
1.5782 | 3.45 | 252 | 1.3234 | 59.9476 | 65.0857 |
1.5782 | 3.94 | 288 | 1.2652 | 58.1152 | 63.9949 |
1.4004 | 4.44 | 324 | 1.1784 | 62.0419 | 67.5268 |
1.241 | 4.93 | 360 | 1.1573 | 60.4712 | 66.5284 |
1.241 | 5.42 | 396 | 1.1217 | 62.4346 | 67.8923 |
1.1603 | 5.91 | 432 | 1.0997 | 63.3508 | 68.7351 |
1.0849 | 6.41 | 468 | 1.0832 | 64.3979 | 69.5781 |
1.0209 | 6.9 | 504 | 1.0773 | 64.0052 | 69.3072 |
1.0209 | 7.4 | 540 | 1.0500 | 65.0524 | 70.4355 |
0.9802 | 7.89 | 576 | 1.0644 | 65.3141 | 70.7507 |
0.9536 | 8.38 | 612 | 1.0516 | 65.5759 | 70.9704 |
0.9536 | 8.87 | 648 | 1.0395 | 65.4450 | 71.2117 |
0.9319 | 9.37 | 684 | 1.0411 | 65.8377 | 71.3692 |
0.9091 | 9.86 | 720 | 1.0515 | 65.9686 | 71.4684 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2