<!-- 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-4-6000-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: 1.3371
- Accuracy: 0.8992
- F1: 0.8584
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 | 0.53 | 100 | 2.7477 | 0.8579 | 0.8247 |
| No log | 1.06 | 200 | 2.2651 | 0.8635 | 0.8129 |
| No log | 1.6 | 300 | 2.1842 | 0.8722 | 0.8230 |
| No log | 2.13 | 400 | 2.2843 | 0.8683 | 0.8248 |
| 2.5002 | 2.66 | 500 | 2.2342 | 0.8706 | 0.8273 |
| 2.5002 | 3.19 | 600 | 1.9496 | 0.8857 | 0.8480 |
| 2.5002 | 3.72 | 700 | 1.8901 | 0.8817 | 0.8401 |
| 2.5002 | 4.26 | 800 | 1.8914 | 0.8746 | 0.8296 |
| 2.5002 | 4.79 | 900 | 1.9103 | 0.8881 | 0.8398 |
| 1.0417 | 5.32 | 1000 | 1.8576 | 0.8825 | 0.8314 |
| 1.0417 | 5.85 | 1100 | 1.6300 | 0.8889 | 0.8517 |
| 1.0417 | 6.38 | 1200 | 1.7720 | 0.8944 | 0.8580 |
| 1.0417 | 6.91 | 1300 | 1.5597 | 0.9032 | 0.8679 |
| 1.0417 | 7.45 | 1400 | 1.8633 | 0.8778 | 0.8297 |
| 0.686 | 7.98 | 1500 | 1.5350 | 0.9 | 0.8649 |
| 0.686 | 8.51 | 1600 | 1.5335 | 0.8937 | 0.8526 |
| 0.686 | 9.04 | 1700 | 1.6360 | 0.8968 | 0.8606 |
| 0.686 | 9.57 | 1800 | 1.6797 | 0.8992 | 0.8568 |
| 0.686 | 10.11 | 1900 | 1.4661 | 0.9008 | 0.8623 |
| 0.5508 | 10.64 | 2000 | 1.4232 | 0.9008 | 0.8619 |
| 0.5508 | 11.17 | 2100 | 1.4547 | 0.8984 | 0.8611 |
| 0.5508 | 11.7 | 2200 | 1.3803 | 0.9024 | 0.8609 |
| 0.5508 | 12.23 | 2300 | 1.5724 | 0.8960 | 0.8529 |
| 0.5508 | 12.77 | 2400 | 1.5670 | 0.8929 | 0.8493 |
| 0.4573 | 13.3 | 2500 | 1.4456 | 0.9008 | 0.8622 |
| 0.4573 | 13.83 | 2600 | 1.5091 | 0.8960 | 0.8534 |
| 0.4573 | 14.36 | 2700 | 1.4223 | 0.9 | 0.8604 |
| 0.4573 | 14.89 | 2800 | 1.3371 | 0.8992 | 0.8584 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
