metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: 2-finetuned-xlm-r-masakhaner-swa-whole-word-phonetic
results: []
2-finetuned-xlm-r-masakhaner-swa-whole-word-phonetic
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 38.6651
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-08
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 61 | 39.9450 |
| No log | 2.0 | 122 | 39.5738 |
| No log | 3.0 | 183 | 40.0065 |
| No log | 4.0 | 244 | 39.2715 |
| No log | 5.0 | 305 | 38.7492 |
| No log | 6.0 | 366 | 38.8567 |
| No log | 7.0 | 427 | 38.7596 |
| No log | 8.0 | 488 | 38.6652 |
| 42.1342 | 9.0 | 549 | 38.6603 |
| 42.1342 | 10.0 | 610 | 38.6651 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1