<!-- 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-2-4000-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: 1.0114
- Accuracy: 0.9111
- F1: 0.8737
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 | 0.8 | 100 | 1.5812 | 0.8952 | 0.8464 |
| No log | 1.6 | 200 | 1.6038 | 0.8944 | 0.8475 |
| No log | 2.4 | 300 | 1.2158 | 0.9071 | 0.8684 |
| No log | 3.2 | 400 | 1.2230 | 0.9087 | 0.8686 |
| 1.2555 | 4.0 | 500 | 1.2893 | 0.9048 | 0.8725 |
| 1.2555 | 4.8 | 600 | 1.2173 | 0.9048 | 0.8725 |
| 1.2555 | 5.6 | 700 | 1.0754 | 0.9071 | 0.8704 |
| 1.2555 | 6.4 | 800 | 1.1436 | 0.9103 | 0.8780 |
| 1.2555 | 7.2 | 900 | 1.4197 | 0.8984 | 0.8489 |
| 0.5649 | 8.0 | 1000 | 1.2034 | 0.8992 | 0.8546 |
| 0.5649 | 8.8 | 1100 | 1.2230 | 0.9119 | 0.8795 |
| 0.5649 | 9.6 | 1200 | 1.1023 | 0.9087 | 0.8711 |
| 0.5649 | 10.4 | 1300 | 1.0464 | 0.9079 | 0.8711 |
| 0.5649 | 11.2 | 1400 | 1.1144 | 0.9063 | 0.8700 |
| 0.4271 | 12.0 | 1500 | 1.0885 | 0.9048 | 0.8705 |
| 0.4271 | 12.8 | 1600 | 1.0620 | 0.9127 | 0.8723 |
| 0.4271 | 13.6 | 1700 | 1.1287 | 0.9056 | 0.8691 |
| 0.4271 | 14.4 | 1800 | 0.9505 | 0.9183 | 0.8802 |
| 0.4271 | 15.2 | 1900 | 0.9078 | 0.9135 | 0.8784 |
| 0.3663 | 16.0 | 2000 | 1.1429 | 0.9222 | 0.8856 |
| 0.3663 | 16.8 | 2100 | 1.1455 | 0.9095 | 0.8703 |
| 0.3663 | 17.6 | 2200 | 0.9608 | 0.9159 | 0.8795 |
| 0.3663 | 18.4 | 2300 | 0.9918 | 0.9063 | 0.8752 |
| 0.3663 | 19.2 | 2400 | 1.0393 | 0.9103 | 0.8681 |
| 0.318 | 20.0 | 2500 | 0.9410 | 0.9087 | 0.8698 |
| 0.318 | 20.8 | 2600 | 1.0046 | 0.9111 | 0.8755 |
| 0.318 | 21.6 | 2700 | 1.0051 | 0.9071 | 0.8647 |
| 0.318 | 22.4 | 2800 | 0.9527 | 0.9103 | 0.8738 |
| 0.318 | 23.2 | 2900 | 1.0086 | 0.9095 | 0.8760 |
| 0.2909 | 24.0 | 3000 | 1.0873 | 0.9111 | 0.8748 |
| 0.2909 | 24.8 | 3100 | 0.9875 | 0.9143 | 0.8796 |
| 0.2909 | 25.6 | 3200 | 0.9676 | 0.9095 | 0.8736 |
| 0.2909 | 26.4 | 3300 | 0.9236 | 0.9079 | 0.8735 |
| 0.2909 | 27.2 | 3400 | 0.9956 | 0.9087 | 0.8712 |
| 0.2671 | 28.0 | 3500 | 1.0114 | 0.9111 | 0.8737 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
