<!-- 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-no_kd_weight_reset-data-indolem_sentiment-model-xlm-roberta-base
This model is a fine-tuned version of xlm-roberta-base on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 1.4015
- Accuracy: 0.8095
- F1: 0.6667
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 | 0.88 | 100 | 0.5951 | 0.6692 | 0.5875 |
| No log | 1.75 | 200 | 0.4701 | 0.8095 | 0.6415 |
| No log | 2.63 | 300 | 0.5323 | 0.7769 | 0.6740 |
| No log | 3.51 | 400 | 0.4689 | 0.8246 | 0.6392 |
| 0.3239 | 4.39 | 500 | 0.8579 | 0.7995 | 0.6970 |
| 0.3239 | 5.26 | 600 | 0.8613 | 0.8170 | 0.6096 |
| 0.3239 | 6.14 | 700 | 1.0303 | 0.8221 | 0.6537 |
| 0.3239 | 7.02 | 800 | 0.9862 | 0.8346 | 0.7080 |
| 0.3239 | 7.89 | 900 | 1.2705 | 0.7744 | 0.6739 |
| 0.082 | 8.77 | 1000 | 1.1303 | 0.8271 | 0.6960 |
| 0.082 | 9.65 | 1100 | 1.3476 | 0.8020 | 0.6802 |
| 0.082 | 10.53 | 1200 | 1.3277 | 0.8120 | 0.6914 |
| 0.082 | 11.4 | 1300 | 1.4394 | 0.7769 | 0.6691 |
| 0.082 | 12.28 | 1400 | 1.1989 | 0.8221 | 0.6635 |
| 0.0363 | 13.16 | 1500 | 1.2330 | 0.8221 | 0.6698 |
| 0.0363 | 14.04 | 1600 | 1.2604 | 0.8095 | 0.5914 |
| 0.0363 | 14.91 | 1700 | 1.3383 | 0.8045 | 0.5714 |
| 0.0363 | 15.79 | 1800 | 1.3164 | 0.8145 | 0.6838 |
| 0.0363 | 16.67 | 1900 | 1.0465 | 0.8346 | 0.6916 |
| 0.0317 | 17.54 | 2000 | 1.0505 | 0.8120 | 0.6914 |
| 0.0317 | 18.42 | 2100 | 1.2285 | 0.8170 | 0.6920 |
| 0.0317 | 19.3 | 2200 | 1.5450 | 0.7669 | 0.6910 |
| 0.0317 | 20.18 | 2300 | 1.4015 | 0.8095 | 0.6667 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
