<!-- 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-pre-finetune-gold-silver-div-2-data-indolem_sentiment-model-xlm
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: 6.4046
- Accuracy: 0.8571
- F1: 0.7220
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 | 10.0069 | 0.6917 | 0.6144 |
| No log | 1.75 | 200 | 5.0701 | 0.8271 | 0.7064 |
| No log | 2.63 | 300 | 7.8096 | 0.7920 | 0.7224 |
| No log | 3.51 | 400 | 5.1337 | 0.8647 | 0.7840 |
| 5.3086 | 4.39 | 500 | 6.1924 | 0.8296 | 0.6699 |
| 5.3086 | 5.26 | 600 | 6.2006 | 0.8371 | 0.6948 |
| 5.3086 | 6.14 | 700 | 5.1451 | 0.8396 | 0.6952 |
| 5.3086 | 7.02 | 800 | 5.6337 | 0.8446 | 0.752 |
| 5.3086 | 7.89 | 900 | 6.3927 | 0.8346 | 0.6972 |
| 1.5213 | 8.77 | 1000 | 5.7591 | 0.8421 | 0.6957 |
| 1.5213 | 9.65 | 1100 | 6.2614 | 0.8471 | 0.7240 |
| 1.5213 | 10.53 | 1200 | 5.1968 | 0.8421 | 0.7273 |
| 1.5213 | 11.4 | 1300 | 7.3645 | 0.8321 | 0.7509 |
| 1.5213 | 12.28 | 1400 | 5.6387 | 0.8622 | 0.7511 |
| 0.8014 | 13.16 | 1500 | 5.1675 | 0.8772 | 0.8048 |
| 0.8014 | 14.04 | 1600 | 5.4952 | 0.8722 | 0.7671 |
| 0.8014 | 14.91 | 1700 | 5.3757 | 0.8647 | 0.7652 |
| 0.8014 | 15.79 | 1800 | 5.3607 | 0.8546 | 0.7339 |
| 0.8014 | 16.67 | 1900 | 5.7929 | 0.8396 | 0.6893 |
| 0.616 | 17.54 | 2000 | 6.4679 | 0.8521 | 0.7401 |
| 0.616 | 18.42 | 2100 | 5.2358 | 0.8521 | 0.7552 |
| 0.616 | 19.3 | 2200 | 5.5126 | 0.8371 | 0.7670 |
| 0.616 | 20.18 | 2300 | 6.7347 | 0.8421 | 0.7014 |
| 0.616 | 21.05 | 2400 | 6.3595 | 0.8346 | 0.6887 |
| 0.4313 | 21.93 | 2500 | 5.3087 | 0.8622 | 0.7755 |
| 0.4313 | 22.81 | 2600 | 5.3043 | 0.8521 | 0.7552 |
| 0.4313 | 23.68 | 2700 | 5.7201 | 0.8622 | 0.7925 |
| 0.4313 | 24.56 | 2800 | 5.9307 | 0.8521 | 0.7511 |
| 0.4313 | 25.44 | 2900 | 5.5064 | 0.8622 | 0.7291 |
| 0.3434 | 26.32 | 3000 | 6.4046 | 0.8571 | 0.7220 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
