|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-finetuned-pos |
|
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. --> |
|
|
|
# xlm-roberta-base-finetuned-pos |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/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 |
|
|
