<!-- 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-silver-div-2-data-smsa-model-haryoaw-scenario-nor
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: 0.5818
- Accuracy: 0.9127
- F1: 0.8727
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 | 0.29 | 100 | 1.0281 | 0.9127 | 0.8821 |
No log | 0.58 | 200 | 0.8653 | 0.9016 | 0.8649 |
No log | 0.87 | 300 | 0.9940 | 0.9135 | 0.8666 |
No log | 1.16 | 400 | 0.9911 | 0.9032 | 0.8562 |
1.1328 | 1.45 | 500 | 0.7262 | 0.9167 | 0.8802 |
1.1328 | 1.74 | 600 | 0.7373 | 0.9111 | 0.8688 |
1.1328 | 2.03 | 700 | 0.6964 | 0.9087 | 0.8738 |
1.1328 | 2.33 | 800 | 0.7581 | 0.9119 | 0.8745 |
1.1328 | 2.62 | 900 | 0.6310 | 0.9127 | 0.8819 |
0.5496 | 2.91 | 1000 | 0.7035 | 0.9079 | 0.8736 |
0.5496 | 3.2 | 1100 | 0.8224 | 0.9071 | 0.8776 |
0.5496 | 3.49 | 1200 | 0.7693 | 0.9063 | 0.8673 |
0.5496 | 3.78 | 1300 | 0.6196 | 0.9206 | 0.8823 |
0.5496 | 4.07 | 1400 | 0.6537 | 0.9190 | 0.8797 |
0.4194 | 4.36 | 1500 | 0.7571 | 0.9079 | 0.8708 |
0.4194 | 4.65 | 1600 | 0.5997 | 0.9135 | 0.8795 |
0.4194 | 4.94 | 1700 | 0.5831 | 0.9254 | 0.8966 |
0.4194 | 5.23 | 1800 | 0.5490 | 0.9222 | 0.8868 |
0.4194 | 5.52 | 1900 | 0.5633 | 0.9167 | 0.8860 |
0.3324 | 5.81 | 2000 | 0.6259 | 0.9127 | 0.8759 |
0.3324 | 6.1 | 2100 | 0.5049 | 0.9206 | 0.8830 |
0.3324 | 6.4 | 2200 | 0.7568 | 0.9103 | 0.8585 |
0.3324 | 6.69 | 2300 | 0.7457 | 0.9143 | 0.8822 |
0.3324 | 6.98 | 2400 | 0.7096 | 0.9175 | 0.8837 |
0.3011 | 7.27 | 2500 | 0.5641 | 0.9206 | 0.8871 |
0.3011 | 7.56 | 2600 | 0.6250 | 0.9175 | 0.8768 |
0.3011 | 7.85 | 2700 | 0.5925 | 0.9119 | 0.8636 |
0.3011 | 8.14 | 2800 | 0.4954 | 0.9222 | 0.8812 |
0.3011 | 8.43 | 2900 | 0.5270 | 0.9175 | 0.8844 |
0.2544 | 8.72 | 3000 | 0.5161 | 0.9103 | 0.8733 |
0.2544 | 9.01 | 3100 | 0.5674 | 0.9214 | 0.8893 |
0.2544 | 9.3 | 3200 | 0.5818 | 0.9127 | 0.8727 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3