<!-- 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-6-8000-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: 1.6304
- Accuracy: 0.8944
- F1: 0.8526
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 | 4.2992 | 0.7762 | 0.5297 |
| No log | 0.8 | 200 | 3.5734 | 0.8302 | 0.7818 |
| No log | 1.2 | 300 | 2.7835 | 0.8611 | 0.8248 |
| No log | 1.6 | 400 | 2.7938 | 0.8444 | 0.7982 |
| 3.7756 | 2.0 | 500 | 2.5710 | 0.8492 | 0.8107 |
| 3.7756 | 2.4 | 600 | 2.2901 | 0.8706 | 0.8248 |
| 3.7756 | 2.8 | 700 | 2.0957 | 0.8722 | 0.8290 |
| 3.7756 | 3.2 | 800 | 1.9684 | 0.8738 | 0.8342 |
| 3.7756 | 3.6 | 900 | 2.2273 | 0.8651 | 0.8283 |
| 1.672 | 4.0 | 1000 | 1.9168 | 0.8714 | 0.8255 |
| 1.672 | 4.4 | 1100 | 1.9733 | 0.8754 | 0.8416 |
| 1.672 | 4.8 | 1200 | 1.8184 | 0.8857 | 0.8473 |
| 1.672 | 5.2 | 1300 | 1.8946 | 0.8794 | 0.8363 |
| 1.672 | 5.6 | 1400 | 1.8216 | 0.8849 | 0.8458 |
| 1.1148 | 6.0 | 1500 | 1.7989 | 0.8937 | 0.8549 |
| 1.1148 | 6.4 | 1600 | 1.8477 | 0.8841 | 0.8425 |
| 1.1148 | 6.8 | 1700 | 1.6685 | 0.8897 | 0.8524 |
| 1.1148 | 7.2 | 1800 | 1.8290 | 0.8897 | 0.8512 |
| 1.1148 | 7.6 | 1900 | 1.7970 | 0.8857 | 0.8403 |
| 0.8332 | 8.0 | 2000 | 1.6670 | 0.8889 | 0.8481 |
| 0.8332 | 8.4 | 2100 | 1.8573 | 0.8865 | 0.8438 |
| 0.8332 | 8.8 | 2200 | 1.7962 | 0.8881 | 0.8481 |
| 0.8332 | 9.2 | 2300 | 1.7305 | 0.8849 | 0.8393 |
| 0.8332 | 9.6 | 2400 | 1.6553 | 0.8897 | 0.8497 |
| 0.6674 | 10.0 | 2500 | 1.6846 | 0.8921 | 0.8519 |
| 0.6674 | 10.4 | 2600 | 1.6563 | 0.8944 | 0.8529 |
| 0.6674 | 10.8 | 2700 | 1.6125 | 0.8905 | 0.8513 |
| 0.6674 | 11.2 | 2800 | 1.7804 | 0.8841 | 0.8369 |
| 0.6674 | 11.6 | 2900 | 1.6885 | 0.8913 | 0.8528 |
| 0.595 | 12.0 | 3000 | 1.6304 | 0.8944 | 0.8526 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
