|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: finetuned-xlm-r-masakhaner-swa-whole-word-phonetic |
|
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. --> |
|
|
|
# finetuned-xlm-r-masakhaner-swa-whole-word-phonetic |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 11.2301 |
|
|
|
## 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-07 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 62 | 38.7304 | |
|
| No log | 2.0 | 124 | 37.1806 | |
|
| No log | 3.0 | 186 | 33.3488 | |
|
| No log | 4.0 | 248 | 28.7715 | |
|
| No log | 5.0 | 310 | 24.8965 | |
|
| No log | 6.0 | 372 | 21.4066 | |
|
| No log | 7.0 | 434 | 19.1665 | |
|
| No log | 8.0 | 496 | 17.3087 | |
|
| 29.5022 | 9.0 | 558 | 15.5323 | |
|
| 29.5022 | 10.0 | 620 | 14.4497 | |
|
| 29.5022 | 11.0 | 682 | 14.1622 | |
|
| 29.5022 | 12.0 | 744 | 13.7512 | |
|
| 29.5022 | 13.0 | 806 | 13.3941 | |
|
| 29.5022 | 14.0 | 868 | 13.0215 | |
|
| 29.5022 | 15.0 | 930 | 12.8363 | |
|
| 29.5022 | 16.0 | 992 | 12.6596 | |
|
| 13.2409 | 17.0 | 1054 | 12.5914 | |
|
| 13.2409 | 18.0 | 1116 | 12.2895 | |
|
| 13.2409 | 19.0 | 1178 | 12.2700 | |
|
| 13.2409 | 20.0 | 1240 | 12.1427 | |
|
| 13.2409 | 21.0 | 1302 | 12.1344 | |
|
| 13.2409 | 22.0 | 1364 | 12.0623 | |
|
| 13.2409 | 23.0 | 1426 | 12.0630 | |
|
| 13.2409 | 24.0 | 1488 | 12.0983 | |
|
| 11.0242 | 25.0 | 1550 | 11.7902 | |
|
| 11.0242 | 26.0 | 1612 | 11.8626 | |
|
| 11.0242 | 27.0 | 1674 | 11.9154 | |
|
| 11.0242 | 28.0 | 1736 | 11.6483 | |
|
| 11.0242 | 29.0 | 1798 | 11.8620 | |
|
| 11.0242 | 30.0 | 1860 | 11.5987 | |
|
| 11.0242 | 31.0 | 1922 | 11.7633 | |
|
| 11.0242 | 32.0 | 1984 | 11.7000 | |
|
| 10.5931 | 33.0 | 2046 | 11.6631 | |
|
| 10.5931 | 34.0 | 2108 | 11.4315 | |
|
| 10.5931 | 35.0 | 2170 | 11.5619 | |
|
| 10.5931 | 36.0 | 2232 | 11.5930 | |
|
| 10.5931 | 37.0 | 2294 | 11.5537 | |
|
| 10.5931 | 38.0 | 2356 | 11.6703 | |
|
| 10.5931 | 39.0 | 2418 | 11.5488 | |
|
| 10.5931 | 40.0 | 2480 | 11.4440 | |
|
| 10.4503 | 41.0 | 2542 | 11.3210 | |
|
| 10.4503 | 42.0 | 2604 | 11.4373 | |
|
| 10.4503 | 43.0 | 2666 | 11.4868 | |
|
| 10.4503 | 44.0 | 2728 | 11.3895 | |
|
| 10.4503 | 45.0 | 2790 | 11.4097 | |
|
| 10.4503 | 46.0 | 2852 | 11.5567 | |
|
| 10.4503 | 47.0 | 2914 | 11.3519 | |
|
| 10.4503 | 48.0 | 2976 | 11.3263 | |
|
| 10.4239 | 49.0 | 3038 | 11.4049 | |
|
| 10.4239 | 50.0 | 3100 | 11.2301 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
