|
|
--- |
|
|
license: mit |
|
|
base_model: roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: results |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# results |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.8299 |
|
|
- Accuracy: 0.6038 |
|
|
- F1: 0.5980 |
|
|
|
|
|
## 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: 2e-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 |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 50 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
|
| No log | 1.0 | 24 | 1.1029 | 0.1772 | 0.0627 | |
|
|
| No log | 2.0 | 48 | 1.0290 | 0.5063 | 0.3404 | |
|
|
| No log | 3.0 | 72 | 0.9006 | 0.5949 | 0.5268 | |
|
|
| No log | 4.0 | 96 | 0.8745 | 0.6013 | 0.6014 | |
|
|
| No log | 5.0 | 120 | 0.8370 | 0.5696 | 0.5730 | |
|
|
| No log | 6.0 | 144 | 0.8020 | 0.6709 | 0.6623 | |
|
|
| No log | 7.0 | 168 | 0.8105 | 0.6835 | 0.6759 | |
|
|
| No log | 8.0 | 192 | 0.9875 | 0.6329 | 0.6251 | |
|
|
| No log | 9.0 | 216 | 1.1282 | 0.6266 | 0.6317 | |
|
|
| No log | 10.0 | 240 | 1.2444 | 0.5949 | 0.5950 | |
|
|
| No log | 11.0 | 264 | 1.1916 | 0.6456 | 0.6394 | |
|
|
| No log | 12.0 | 288 | 1.5230 | 0.5886 | 0.5905 | |
|
|
| No log | 13.0 | 312 | 1.4544 | 0.6456 | 0.6381 | |
|
|
| No log | 14.0 | 336 | 1.6109 | 0.6076 | 0.6093 | |
|
|
| No log | 15.0 | 360 | 1.6181 | 0.6203 | 0.6213 | |
|
|
| No log | 16.0 | 384 | 1.6836 | 0.6392 | 0.6382 | |
|
|
| No log | 17.0 | 408 | 1.7056 | 0.6709 | 0.6648 | |
|
|
| No log | 18.0 | 432 | 1.9027 | 0.5949 | 0.5968 | |
|
|
| No log | 19.0 | 456 | 1.7156 | 0.6835 | 0.6695 | |
|
|
| No log | 20.0 | 480 | 1.8976 | 0.6392 | 0.6376 | |
|
|
| 0.3619 | 21.0 | 504 | 1.8731 | 0.6139 | 0.6172 | |
|
|
| 0.3619 | 22.0 | 528 | 1.8723 | 0.6709 | 0.6570 | |
|
|
| 0.3619 | 23.0 | 552 | 2.1482 | 0.5886 | 0.5921 | |
|
|
| 0.3619 | 24.0 | 576 | 1.8633 | 0.6203 | 0.6198 | |
|
|
| 0.3619 | 25.0 | 600 | 1.7921 | 0.6392 | 0.6373 | |
|
|
| 0.3619 | 26.0 | 624 | 1.8867 | 0.6203 | 0.6229 | |
|
|
| 0.3619 | 27.0 | 648 | 1.8571 | 0.6646 | 0.6535 | |
|
|
| 0.3619 | 28.0 | 672 | 1.9876 | 0.6266 | 0.6295 | |
|
|
| 0.3619 | 29.0 | 696 | 1.8853 | 0.6519 | 0.6452 | |
|
|
| 0.3619 | 30.0 | 720 | 2.0321 | 0.6266 | 0.6315 | |
|
|
| 0.3619 | 31.0 | 744 | 1.8590 | 0.6646 | 0.6553 | |
|
|
| 0.3619 | 32.0 | 768 | 2.2514 | 0.6266 | 0.6297 | |
|
|
| 0.3619 | 33.0 | 792 | 1.8813 | 0.6646 | 0.6647 | |
|
|
| 0.3619 | 34.0 | 816 | 2.1837 | 0.6139 | 0.6158 | |
|
|
| 0.3619 | 35.0 | 840 | 1.8851 | 0.6709 | 0.6682 | |
|
|
| 0.3619 | 36.0 | 864 | 2.0150 | 0.6329 | 0.6346 | |
|
|
| 0.3619 | 37.0 | 888 | 1.9542 | 0.6709 | 0.6703 | |
|
|
| 0.3619 | 38.0 | 912 | 2.0234 | 0.6582 | 0.6551 | |
|
|
| 0.3619 | 39.0 | 936 | 2.1399 | 0.6329 | 0.6350 | |
|
|
| 0.3619 | 40.0 | 960 | 2.1121 | 0.6329 | 0.6357 | |
|
|
| 0.3619 | 41.0 | 984 | 2.0931 | 0.6266 | 0.6291 | |
|
|
| 0.0321 | 42.0 | 1008 | 1.9945 | 0.6772 | 0.6757 | |
|
|
| 0.0321 | 43.0 | 1032 | 2.0745 | 0.6646 | 0.6652 | |
|
|
| 0.0321 | 44.0 | 1056 | 2.0226 | 0.6835 | 0.6795 | |
|
|
| 0.0321 | 45.0 | 1080 | 2.1174 | 0.6582 | 0.6589 | |
|
|
| 0.0321 | 46.0 | 1104 | 2.1243 | 0.6456 | 0.6467 | |
|
|
| 0.0321 | 47.0 | 1128 | 2.1506 | 0.6203 | 0.6226 | |
|
|
| 0.0321 | 48.0 | 1152 | 2.1542 | 0.6329 | 0.6350 | |
|
|
| 0.0321 | 49.0 | 1176 | 2.1295 | 0.6582 | 0.6580 | |
|
|
| 0.0321 | 50.0 | 1200 | 2.1290 | 0.6582 | 0.6580 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.0 |
|
|
- Pytorch 2.0.0 |
|
|
- Datasets 2.1.0 |
|
|
- Tokenizers 0.14.1 |
|
|
|
