<!-- 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_weight_reset-data-smsa-model-xlmr_base_trained
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: 1.9943
- Accuracy: 0.8714
- F1: 0.8306
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 | 5.2516 | 0.7111 | 0.4696 |
| No log | 0.58 | 200 | 4.1679 | 0.7738 | 0.5320 |
| No log | 0.87 | 300 | 3.6960 | 0.7849 | 0.5396 |
| No log | 1.16 | 400 | 3.7163 | 0.8040 | 0.7322 |
| 4.4612 | 1.45 | 500 | 2.9986 | 0.8492 | 0.8040 |
| 4.4612 | 1.74 | 600 | 2.3529 | 0.8667 | 0.8147 |
| 4.4612 | 2.03 | 700 | 2.3724 | 0.8619 | 0.8197 |
| 4.4612 | 2.33 | 800 | 2.6005 | 0.8556 | 0.8003 |
| 4.4612 | 2.62 | 900 | 3.0561 | 0.8460 | 0.8074 |
| 2.24 | 2.91 | 1000 | 2.2566 | 0.8690 | 0.8292 |
| 2.24 | 3.2 | 1100 | 2.2290 | 0.8746 | 0.8264 |
| 2.24 | 3.49 | 1200 | 3.1429 | 0.8365 | 0.7894 |
| 2.24 | 3.78 | 1300 | 1.9892 | 0.8873 | 0.8465 |
| 2.24 | 4.07 | 1400 | 2.1988 | 0.8706 | 0.8289 |
| 1.6098 | 4.36 | 1500 | 2.0279 | 0.8794 | 0.8376 |
| 1.6098 | 4.65 | 1600 | 2.2940 | 0.8587 | 0.8052 |
| 1.6098 | 4.94 | 1700 | 2.5064 | 0.8643 | 0.8200 |
| 1.6098 | 5.23 | 1800 | 2.3622 | 0.8619 | 0.7967 |
| 1.6098 | 5.52 | 1900 | 2.1670 | 0.8698 | 0.8206 |
| 1.2931 | 5.81 | 2000 | 2.4944 | 0.8611 | 0.8260 |
| 1.2931 | 6.1 | 2100 | 2.5436 | 0.8667 | 0.8283 |
| 1.2931 | 6.4 | 2200 | 2.2876 | 0.8722 | 0.8348 |
| 1.2931 | 6.69 | 2300 | 2.1152 | 0.8698 | 0.8169 |
| 1.2931 | 6.98 | 2400 | 2.1041 | 0.8722 | 0.8232 |
| 1.1499 | 7.27 | 2500 | 2.9629 | 0.8421 | 0.8075 |
| 1.1499 | 7.56 | 2600 | 2.2516 | 0.8659 | 0.8242 |
| 1.1499 | 7.85 | 2700 | 2.1008 | 0.8754 | 0.8385 |
| 1.1499 | 8.14 | 2800 | 1.9943 | 0.8714 | 0.8306 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
