<!-- 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. -->
test661146
This model is a fine-tuned version of haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 8.3091
- Accuracy: 0.8020
- F1: 0.6030
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.75 | 200 | 8.7798 | 0.7143 | 0.1739 |
| No log | 3.51 | 400 | 8.0431 | 0.7293 | 0.6029 |
| 8.5498 | 5.26 | 600 | 13.2550 | 0.7569 | 0.3022 |
| 8.5498 | 7.02 | 800 | 8.4359 | 0.7845 | 0.6446 |
| 3.1288 | 8.77 | 1000 | 9.0490 | 0.8045 | 0.61 |
| 3.1288 | 10.53 | 1200 | 8.6164 | 0.7970 | 0.5371 |
| 3.1288 | 12.28 | 1400 | 8.2125 | 0.8045 | 0.6609 |
| 1.1523 | 14.04 | 1600 | 8.4612 | 0.7920 | 0.6438 |
| 1.1523 | 15.79 | 1800 | 8.2375 | 0.7970 | 0.6267 |
| 0.5946 | 17.54 | 2000 | 9.3369 | 0.7920 | 0.5464 |
| 0.5946 | 19.3 | 2200 | 8.3727 | 0.7995 | 0.5745 |
| 0.5946 | 21.05 | 2400 | 8.1460 | 0.7995 | 0.6190 |
| 0.3501 | 22.81 | 2600 | 7.7445 | 0.7920 | 0.6140 |
| 0.3501 | 24.56 | 2800 | 7.9872 | 0.7945 | 0.5941 |
| 0.2206 | 26.32 | 3000 | 8.2333 | 0.7895 | 0.5962 |
| 0.2206 | 28.07 | 3200 | 8.1668 | 0.7920 | 0.6140 |
| 0.2206 | 29.82 | 3400 | 8.3289 | 0.8020 | 0.5864 |
| 0.1204 | 31.58 | 3600 | 8.4234 | 0.7995 | 0.5789 |
| 0.1204 | 33.33 | 3800 | 7.8834 | 0.8020 | 0.6326 |
| 0.0848 | 35.09 | 4000 | 8.3675 | 0.8020 | 0.5949 |
| 0.0848 | 36.84 | 4200 | 8.0341 | 0.8045 | 0.6176 |
| 0.0848 | 38.6 | 4400 | 8.3091 | 0.8020 | 0.6030 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
