xlmr-ro-en-no_shuffled-orig-test1000
This model is a fine-tuned version of xlm-roberta-base on the wmt20_mlqe_task1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3291
- R Squared: 0.6391
- Mae: 0.4085
- Pearson R: 0.8424
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | R Squared | Mae | Pearson R |
|---|---|---|---|---|---|---|
| No log | 1.0 | 438 | 0.5117 | 0.4388 | 0.5424 | 0.7976 |
| 0.5683 | 2.0 | 876 | 0.3039 | 0.6668 | 0.4056 | 0.8488 |
| 0.3309 | 3.0 | 1314 | 0.3115 | 0.6584 | 0.4003 | 0.8459 |
| 0.2277 | 4.0 | 1752 | 0.3937 | 0.5682 | 0.4485 | 0.8330 |
| 0.1565 | 5.0 | 2190 | 0.3291 | 0.6391 | 0.4085 | 0.8424 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for patpizio/xlmr-ro-en-no_shuffled-orig-test1000
Base model
FacebookAI/xlm-roberta-base