<!-- 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-data-smsa-model-haryoaw-scenari
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: 0.9124
- Accuracy: 0.9206
- F1: 0.8870
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 | 1.4293 | 0.9048 | 0.8658 |
No log | 0.58 | 200 | 1.3922 | 0.9032 | 0.8602 |
No log | 0.87 | 300 | 1.2611 | 0.9143 | 0.8759 |
No log | 1.16 | 400 | 1.5672 | 0.8984 | 0.8453 |
1.4388 | 1.45 | 500 | 1.0477 | 0.9167 | 0.8786 |
1.4388 | 1.74 | 600 | 1.3537 | 0.9079 | 0.8747 |
1.4388 | 2.03 | 700 | 1.3946 | 0.8976 | 0.8482 |
1.4388 | 2.33 | 800 | 1.1872 | 0.9127 | 0.8630 |
1.4388 | 2.62 | 900 | 0.9847 | 0.9230 | 0.8925 |
0.7688 | 2.91 | 1000 | 1.0218 | 0.9127 | 0.8722 |
0.7688 | 3.2 | 1100 | 1.0574 | 0.9103 | 0.8723 |
0.7688 | 3.49 | 1200 | 0.9755 | 0.9087 | 0.8699 |
0.7688 | 3.78 | 1300 | 1.0600 | 0.9198 | 0.8833 |
0.7688 | 4.07 | 1400 | 0.9060 | 0.9214 | 0.8863 |
0.6111 | 4.36 | 1500 | 1.2306 | 0.9119 | 0.8736 |
0.6111 | 4.65 | 1600 | 0.9943 | 0.9119 | 0.8775 |
0.6111 | 4.94 | 1700 | 0.9418 | 0.9143 | 0.8822 |
0.6111 | 5.23 | 1800 | 0.8809 | 0.9222 | 0.8925 |
0.6111 | 5.52 | 1900 | 0.8965 | 0.9159 | 0.8789 |
0.5221 | 5.81 | 2000 | 1.0321 | 0.9135 | 0.8762 |
0.5221 | 6.1 | 2100 | 0.8426 | 0.9206 | 0.8849 |
0.5221 | 6.4 | 2200 | 0.8672 | 0.9206 | 0.8892 |
0.5221 | 6.69 | 2300 | 0.8808 | 0.9190 | 0.8806 |
0.5221 | 6.98 | 2400 | 0.9124 | 0.9206 | 0.8870 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3