<!-- 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-6-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: 1.6242
- Accuracy: 0.8873
- F1: 0.8533
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 | 4.5429 | 0.75 | 0.5044 |
| No log | 0.58 | 200 | 3.8045 | 0.7897 | 0.6798 |
| No log | 0.87 | 300 | 2.5030 | 0.8579 | 0.8122 |
| No log | 1.16 | 400 | 2.5163 | 0.8579 | 0.8178 |
| 3.6314 | 1.45 | 500 | 2.2567 | 0.8706 | 0.8363 |
| 3.6314 | 1.74 | 600 | 2.1203 | 0.8722 | 0.8317 |
| 3.6314 | 2.03 | 700 | 2.0120 | 0.8746 | 0.8343 |
| 3.6314 | 2.33 | 800 | 2.1335 | 0.8754 | 0.8290 |
| 3.6314 | 2.62 | 900 | 2.0003 | 0.8794 | 0.8457 |
| 1.794 | 2.91 | 1000 | 1.7672 | 0.8810 | 0.8445 |
| 1.794 | 3.2 | 1100 | 1.9169 | 0.8802 | 0.8445 |
| 1.794 | 3.49 | 1200 | 1.9258 | 0.8833 | 0.8452 |
| 1.794 | 3.78 | 1300 | 1.7938 | 0.8897 | 0.8406 |
| 1.794 | 4.07 | 1400 | 1.7968 | 0.8865 | 0.8459 |
| 1.2751 | 4.36 | 1500 | 1.8488 | 0.8913 | 0.8587 |
| 1.2751 | 4.65 | 1600 | 1.6383 | 0.8944 | 0.8620 |
| 1.2751 | 4.94 | 1700 | 1.7449 | 0.8937 | 0.8585 |
| 1.2751 | 5.23 | 1800 | 1.8031 | 0.8849 | 0.8475 |
| 1.2751 | 5.52 | 1900 | 1.6505 | 0.8905 | 0.8508 |
| 0.9575 | 5.81 | 2000 | 1.6162 | 0.8984 | 0.8612 |
| 0.9575 | 6.1 | 2100 | 1.4955 | 0.8992 | 0.8577 |
| 0.9575 | 6.4 | 2200 | 1.6451 | 0.8976 | 0.8602 |
| 0.9575 | 6.69 | 2300 | 1.7084 | 0.8889 | 0.8428 |
| 0.9575 | 6.98 | 2400 | 1.5918 | 0.8976 | 0.8613 |
| 0.8105 | 7.27 | 2500 | 1.5149 | 0.8984 | 0.8601 |
| 0.8105 | 7.56 | 2600 | 1.6106 | 0.8913 | 0.8497 |
| 0.8105 | 7.85 | 2700 | 1.5165 | 0.8960 | 0.8577 |
| 0.8105 | 8.14 | 2800 | 1.8248 | 0.8841 | 0.8491 |
| 0.8105 | 8.43 | 2900 | 1.5287 | 0.8952 | 0.8601 |
| 0.6661 | 8.72 | 3000 | 1.6404 | 0.8921 | 0.8535 |
| 0.6661 | 9.01 | 3100 | 1.6242 | 0.8873 | 0.8533 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
