<!-- 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. -->
mlner-mlwptok-muril
This model is a fine-tuned version of google/muril-base-cased on the mlner2021 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8331
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.8113
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
1.447 | 1.0 | 1389 | 0.9396 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.898 | 2.0 | 2778 | 0.8883 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.859 | 3.0 | 4167 | 0.8721 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.8302 | 4.0 | 5556 | 0.8666 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.8165 | 5.0 | 6945 | 0.8403 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.8143 | 6.0 | 8334 | 0.8376 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.8034 | 7.0 | 9723 | 0.8393 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.7766 | 8.0 | 11112 | 0.8383 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.794 | 9.0 | 12501 | 0.8346 | 0.0 | 0.0 | 0.0 | 0.8113 |
0.7858 | 10.0 | 13890 | 0.8331 | 0.0 | 0.0 | 0.0 | 0.8113 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6