<!-- 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-pre-finetune-gold-silver-div-2-data-smsa-model-xlm-roberta-base
This model is a fine-tuned version of xlm-roberta-base on the smsa dataset. It achieves the following results on the evaluation set:
- Loss: 0.8563
- Accuracy: 0.9198
- F1: 0.8882
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 | 3.1310 | 0.8270 | 0.7450 |
| No log | 0.58 | 200 | 2.0604 | 0.8810 | 0.8322 |
| No log | 0.87 | 300 | 1.8511 | 0.8944 | 0.8397 |
| No log | 1.16 | 400 | 1.7322 | 0.8992 | 0.8595 |
| 2.5788 | 1.45 | 500 | 1.5513 | 0.9040 | 0.8621 |
| 2.5788 | 1.74 | 600 | 1.2492 | 0.9127 | 0.8798 |
| 2.5788 | 2.03 | 700 | 1.2945 | 0.9048 | 0.8708 |
| 2.5788 | 2.33 | 800 | 1.5817 | 0.8992 | 0.8589 |
| 2.5788 | 2.62 | 900 | 1.1143 | 0.9119 | 0.8740 |
| 1.1147 | 2.91 | 1000 | 1.3242 | 0.9087 | 0.8739 |
| 1.1147 | 3.2 | 1100 | 1.1148 | 0.9135 | 0.8721 |
| 1.1147 | 3.49 | 1200 | 1.2345 | 0.9135 | 0.8790 |
| 1.1147 | 3.78 | 1300 | 1.1505 | 0.9127 | 0.8730 |
| 1.1147 | 4.07 | 1400 | 1.1927 | 0.9167 | 0.8736 |
| 0.7747 | 4.36 | 1500 | 1.2222 | 0.9063 | 0.8708 |
| 0.7747 | 4.65 | 1600 | 1.0822 | 0.9175 | 0.8795 |
| 0.7747 | 4.94 | 1700 | 1.2050 | 0.9079 | 0.8650 |
| 0.7747 | 5.23 | 1800 | 1.0231 | 0.9214 | 0.8891 |
| 0.7747 | 5.52 | 1900 | 1.0107 | 0.9127 | 0.8808 |
| 0.6391 | 5.81 | 2000 | 0.9254 | 0.9230 | 0.8896 |
| 0.6391 | 6.1 | 2100 | 0.9551 | 0.9175 | 0.8833 |
| 0.6391 | 6.4 | 2200 | 1.0021 | 0.9143 | 0.8742 |
| 0.6391 | 6.69 | 2300 | 1.2207 | 0.9079 | 0.8553 |
| 0.6391 | 6.98 | 2400 | 0.8913 | 0.9175 | 0.8827 |
| 0.5391 | 7.27 | 2500 | 1.2447 | 0.9032 | 0.8557 |
| 0.5391 | 7.56 | 2600 | 0.9456 | 0.9119 | 0.8777 |
| 0.5391 | 7.85 | 2700 | 0.9517 | 0.9294 | 0.8966 |
| 0.5391 | 8.14 | 2800 | 0.8927 | 0.9206 | 0.8812 |
| 0.5391 | 8.43 | 2900 | 1.0042 | 0.9167 | 0.8780 |
| 0.4633 | 8.72 | 3000 | 0.9702 | 0.9159 | 0.8776 |
| 0.4633 | 9.01 | 3100 | 0.9880 | 0.9167 | 0.8774 |
| 0.4633 | 9.3 | 3200 | 1.0195 | 0.9159 | 0.8768 |
| 0.4633 | 9.59 | 3300 | 1.0196 | 0.9175 | 0.8855 |
| 0.4633 | 9.88 | 3400 | 0.8555 | 0.9214 | 0.8913 |
| 0.4361 | 10.17 | 3500 | 0.9175 | 0.9079 | 0.8734 |
| 0.4361 | 10.47 | 3600 | 0.8892 | 0.9198 | 0.8799 |
| 0.4361 | 10.76 | 3700 | 0.9140 | 0.9238 | 0.8942 |
| 0.4361 | 11.05 | 3800 | 0.8742 | 0.9238 | 0.8901 |
| 0.4361 | 11.34 | 3900 | 0.9916 | 0.9143 | 0.8750 |
| 0.3879 | 11.63 | 4000 | 0.9187 | 0.9175 | 0.8832 |
| 0.3879 | 11.92 | 4100 | 0.8446 | 0.9190 | 0.8818 |
| 0.3879 | 12.21 | 4200 | 0.8563 | 0.9198 | 0.8882 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
