<!-- 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-normal-finetune-clf-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: 0.3511
- Accuracy: 0.9222
- F1: 0.9011
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 | 0.4204 | 0.8397 | 0.6487 |
| No log | 0.58 | 200 | 0.3298 | 0.9095 | 0.8696 |
| No log | 0.87 | 300 | 0.2664 | 0.9214 | 0.8843 |
| No log | 1.16 | 400 | 0.2882 | 0.9151 | 0.8849 |
| 0.3642 | 1.45 | 500 | 0.2531 | 0.9175 | 0.8808 |
| 0.3642 | 1.74 | 600 | 0.2847 | 0.9175 | 0.8820 |
| 0.3642 | 2.03 | 700 | 0.2889 | 0.9294 | 0.9060 |
| 0.3642 | 2.33 | 800 | 0.3066 | 0.9270 | 0.8996 |
| 0.3642 | 2.62 | 900 | 0.3736 | 0.9190 | 0.8914 |
| 0.2064 | 2.91 | 1000 | 0.2706 | 0.9214 | 0.8853 |
| 0.2064 | 3.2 | 1100 | 0.3201 | 0.9190 | 0.8878 |
| 0.2064 | 3.49 | 1200 | 0.2372 | 0.9254 | 0.9007 |
| 0.2064 | 3.78 | 1300 | 0.2534 | 0.9190 | 0.8904 |
| 0.2064 | 4.07 | 1400 | 0.3266 | 0.9214 | 0.8939 |
| 0.1543 | 4.36 | 1500 | 0.3405 | 0.9135 | 0.8815 |
| 0.1543 | 4.65 | 1600 | 0.3485 | 0.9238 | 0.8988 |
| 0.1543 | 4.94 | 1700 | 0.3287 | 0.9270 | 0.9011 |
| 0.1543 | 5.23 | 1800 | 0.3631 | 0.9167 | 0.8866 |
| 0.1543 | 5.52 | 1900 | 0.3714 | 0.9167 | 0.8922 |
| 0.1227 | 5.81 | 2000 | 0.3030 | 0.9119 | 0.8794 |
| 0.1227 | 6.1 | 2100 | 0.3363 | 0.9286 | 0.9046 |
| 0.1227 | 6.4 | 2200 | 0.3511 | 0.9222 | 0.9011 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
