metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-finetuned-pos
results: []
xlm-roberta-base-finetuned-pos
This model is a fine-tuned version of xlm-roberta-base on the Sajjad's dataset. It achieves the following results on the evaluation set:
- Loss: 0.5350
- Precision: 0.8992
- Recall: 0.9129
- F1: 0.9060
- Accuracy: 0.8979
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 457 | 0.3629 | 0.8779 | 0.8952 | 0.8865 | 0.8904 |
| 0.5823 | 2.0 | 914 | 0.3986 | 0.8870 | 0.9036 | 0.8952 | 0.8879 |
| 0.2312 | 3.0 | 1371 | 0.4127 | 0.8891 | 0.9044 | 0.8967 | 0.8887 |
| 0.1651 | 4.0 | 1828 | 0.4374 | 0.8885 | 0.9030 | 0.8957 | 0.8870 |
| 0.1265 | 5.0 | 2285 | 0.4622 | 0.8923 | 0.9068 | 0.8995 | 0.8912 |
| 0.1036 | 6.0 | 2742 | 0.4752 | 0.8962 | 0.9088 | 0.9025 | 0.8946 |
| 0.0806 | 7.0 | 3199 | 0.5058 | 0.8950 | 0.9093 | 0.9020 | 0.8933 |
| 0.0727 | 8.0 | 3656 | 0.5232 | 0.8996 | 0.9123 | 0.9059 | 0.8976 |
| 0.0603 | 9.0 | 4113 | 0.5360 | 0.8970 | 0.9106 | 0.9037 | 0.8952 |
| 0.0548 | 10.0 | 4570 | 0.5350 | 0.8992 | 0.9129 | 0.9060 | 0.8979 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2