<!-- 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-non-kd-from-post-finetune-div-2-data-smsa-model-haryoaw-scenario-normal
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: 0.5768
- Accuracy: 0.9143
- F1: 0.8831
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 | 0.2456 | 0.9143 | 0.8805 |
| No log | 0.58 | 200 | 0.3334 | 0.9032 | 0.8496 |
| No log | 0.87 | 300 | 0.2942 | 0.9198 | 0.8774 |
| No log | 1.16 | 400 | 0.2682 | 0.9167 | 0.8800 |
| 0.2418 | 1.45 | 500 | 0.3193 | 0.9056 | 0.8587 |
| 0.2418 | 1.74 | 600 | 0.3491 | 0.9063 | 0.8631 |
| 0.2418 | 2.03 | 700 | 0.3188 | 0.9143 | 0.8806 |
| 0.2418 | 2.33 | 800 | 0.3215 | 0.9222 | 0.8864 |
| 0.2418 | 2.62 | 900 | 0.3786 | 0.9183 | 0.8914 |
| 0.1482 | 2.91 | 1000 | 0.3338 | 0.9135 | 0.8783 |
| 0.1482 | 3.2 | 1100 | 0.3397 | 0.9143 | 0.8773 |
| 0.1482 | 3.49 | 1200 | 0.3981 | 0.9127 | 0.8821 |
| 0.1482 | 3.78 | 1300 | 0.3516 | 0.9167 | 0.8750 |
| 0.1482 | 4.07 | 1400 | 0.3778 | 0.9198 | 0.8945 |
| 0.0951 | 4.36 | 1500 | 0.4304 | 0.9087 | 0.8750 |
| 0.0951 | 4.65 | 1600 | 0.4327 | 0.9183 | 0.8915 |
| 0.0951 | 4.94 | 1700 | 0.3671 | 0.9254 | 0.8938 |
| 0.0951 | 5.23 | 1800 | 0.4241 | 0.9302 | 0.9035 |
| 0.0951 | 5.52 | 1900 | 0.4366 | 0.9206 | 0.8944 |
| 0.0708 | 5.81 | 2000 | 0.4122 | 0.9103 | 0.8789 |
| 0.0708 | 6.1 | 2100 | 0.4829 | 0.9206 | 0.8930 |
| 0.0708 | 6.4 | 2200 | 0.4174 | 0.9238 | 0.8920 |
| 0.0708 | 6.69 | 2300 | 0.4631 | 0.9151 | 0.8830 |
| 0.0708 | 6.98 | 2400 | 0.4153 | 0.9159 | 0.8899 |
| 0.0545 | 7.27 | 2500 | 0.5217 | 0.9159 | 0.8867 |
| 0.0545 | 7.56 | 2600 | 0.4447 | 0.9214 | 0.8855 |
| 0.0545 | 7.85 | 2700 | 0.3846 | 0.9302 | 0.9027 |
| 0.0545 | 8.14 | 2800 | 0.4613 | 0.9143 | 0.8824 |
| 0.0545 | 8.43 | 2900 | 0.5693 | 0.9183 | 0.8807 |
| 0.0423 | 8.72 | 3000 | 0.5215 | 0.9159 | 0.8899 |
| 0.0423 | 9.01 | 3100 | 0.5503 | 0.9111 | 0.8774 |
| 0.0423 | 9.3 | 3200 | 0.5958 | 0.9119 | 0.8840 |
| 0.0423 | 9.59 | 3300 | 0.5768 | 0.9143 | 0.8831 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
