<!-- 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. -->
scenario-kd-from-post-finetune-gold-silver-div-4-8000-data-smsa-model-haryoaw-sc
This model is a fine-tuned version of haryoaw/scenario-normal-finetune-clf-data-smsa-model-xlm-roberta-base on the smsa dataset. It achieves the following results on the evaluation set:
- Loss: 1.1325
- Accuracy: 0.9127
- F1: 0.8724
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.4 | 100 | 2.9781 | 0.8365 | 0.7769 |
| No log | 0.8 | 200 | 2.2965 | 0.8587 | 0.8097 |
| No log | 1.2 | 300 | 2.7320 | 0.8444 | 0.8162 |
| No log | 1.6 | 400 | 2.2548 | 0.8627 | 0.8242 |
| 2.6579 | 2.0 | 500 | 1.9153 | 0.8865 | 0.8439 |
| 2.6579 | 2.4 | 600 | 1.8958 | 0.8905 | 0.8481 |
| 2.6579 | 2.8 | 700 | 1.8591 | 0.8921 | 0.8455 |
| 2.6579 | 3.2 | 800 | 1.7154 | 0.8944 | 0.8533 |
| 2.6579 | 3.6 | 900 | 1.6033 | 0.8937 | 0.8557 |
| 1.2089 | 4.0 | 1000 | 1.5786 | 0.8960 | 0.8487 |
| 1.2089 | 4.4 | 1100 | 1.5674 | 0.9016 | 0.8591 |
| 1.2089 | 4.8 | 1200 | 1.4204 | 0.9 | 0.8515 |
| 1.2089 | 5.2 | 1300 | 1.4645 | 0.9040 | 0.8650 |
| 1.2089 | 5.6 | 1400 | 1.5980 | 0.8960 | 0.8560 |
| 0.7739 | 6.0 | 1500 | 1.6732 | 0.8929 | 0.8519 |
| 0.7739 | 6.4 | 1600 | 1.3226 | 0.9063 | 0.8625 |
| 0.7739 | 6.8 | 1700 | 1.2441 | 0.9040 | 0.8600 |
| 0.7739 | 7.2 | 1800 | 1.3860 | 0.8944 | 0.8552 |
| 0.7739 | 7.6 | 1900 | 1.3320 | 0.8968 | 0.8485 |
| 0.6026 | 8.0 | 2000 | 1.3842 | 0.9056 | 0.8615 |
| 0.6026 | 8.4 | 2100 | 1.3240 | 0.9016 | 0.8621 |
| 0.6026 | 8.8 | 2200 | 1.2880 | 0.9063 | 0.8646 |
| 0.6026 | 9.2 | 2300 | 1.3428 | 0.9063 | 0.8639 |
| 0.6026 | 9.6 | 2400 | 1.3725 | 0.9016 | 0.8620 |
| 0.5354 | 10.0 | 2500 | 1.3696 | 0.9024 | 0.8598 |
| 0.5354 | 10.4 | 2600 | 1.3644 | 0.9032 | 0.8571 |
| 0.5354 | 10.8 | 2700 | 1.3189 | 0.9056 | 0.8705 |
| 0.5354 | 11.2 | 2800 | 1.4258 | 0.8984 | 0.8537 |
| 0.5354 | 11.6 | 2900 | 1.3107 | 0.9032 | 0.8614 |
| 0.4787 | 12.0 | 3000 | 1.4494 | 0.9024 | 0.8533 |
| 0.4787 | 12.4 | 3100 | 1.3701 | 0.9071 | 0.8561 |
| 0.4787 | 12.8 | 3200 | 1.1686 | 0.9111 | 0.8711 |
| 0.4787 | 13.2 | 3300 | 1.2147 | 0.9095 | 0.8711 |
| 0.4787 | 13.6 | 3400 | 1.2130 | 0.9056 | 0.8589 |
| 0.4245 | 14.0 | 3500 | 1.2426 | 0.9063 | 0.8623 |
| 0.4245 | 14.4 | 3600 | 1.1548 | 0.9095 | 0.8737 |
| 0.4245 | 14.8 | 3700 | 1.3100 | 0.8984 | 0.8591 |
| 0.4245 | 15.2 | 3800 | 1.2439 | 0.9 | 0.8572 |
| 0.4245 | 15.6 | 3900 | 1.2271 | 0.9048 | 0.8640 |
| 0.3945 | 16.0 | 4000 | 1.2431 | 0.9048 | 0.8603 |
| 0.3945 | 16.4 | 4100 | 1.2223 | 0.9127 | 0.8688 |
| 0.3945 | 16.8 | 4200 | 1.2058 | 0.9056 | 0.8694 |
| 0.3945 | 17.2 | 4300 | 1.1796 | 0.9024 | 0.8609 |
| 0.3945 | 17.6 | 4400 | 1.2383 | 0.9071 | 0.8672 |
| 0.3725 | 18.0 | 4500 | 1.2171 | 0.9040 | 0.8662 |
| 0.3725 | 18.4 | 4600 | 1.2637 | 0.9095 | 0.8721 |
| 0.3725 | 18.8 | 4700 | 1.1956 | 0.9040 | 0.8591 |
| 0.3725 | 19.2 | 4800 | 1.1177 | 0.9095 | 0.8674 |
| 0.3725 | 19.6 | 4900 | 1.0863 | 0.9175 | 0.8819 |
| 0.356 | 20.0 | 5000 | 1.0510 | 0.9143 | 0.8806 |
| 0.356 | 20.4 | 5100 | 1.1132 | 0.9008 | 0.8545 |
| 0.356 | 20.8 | 5200 | 1.2226 | 0.9063 | 0.8639 |
| 0.356 | 21.2 | 5300 | 1.1765 | 0.9048 | 0.8612 |
| 0.356 | 21.6 | 5400 | 1.1246 | 0.9063 | 0.8588 |
| 0.3333 | 22.0 | 5500 | 1.0851 | 0.9127 | 0.8790 |
| 0.3333 | 22.4 | 5600 | 1.0802 | 0.9111 | 0.8692 |
| 0.3333 | 22.8 | 5700 | 1.0567 | 0.9175 | 0.8793 |
| 0.3333 | 23.2 | 5800 | 1.0637 | 0.9119 | 0.8721 |
| 0.3333 | 23.6 | 5900 | 1.2241 | 0.9063 | 0.8612 |
| 0.315 | 24.0 | 6000 | 1.0900 | 0.9095 | 0.8689 |
| 0.315 | 24.4 | 6100 | 1.0571 | 0.9151 | 0.8771 |
| 0.315 | 24.8 | 6200 | 1.1068 | 0.9056 | 0.8611 |
| 0.315 | 25.2 | 6300 | 1.2289 | 0.9056 | 0.8663 |
| 0.315 | 25.6 | 6400 | 1.1325 | 0.9127 | 0.8724 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
