|
--- |
|
license: mit |
|
base_model: FacebookAI/xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: XMLRoberta_Dataset59KBoDuoi |
|
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. --> |
|
|
|
# XMLRoberta_Dataset59KBoDuoi |
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4792 |
|
- Accuracy: 0.8964 |
|
- F1: 0.8969 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.5115 | 200 | 0.4025 | 0.8084 | 0.8111 | |
|
| No log | 1.0230 | 400 | 0.3500 | 0.8424 | 0.8451 | |
|
| No log | 1.5345 | 600 | 0.3312 | 0.8637 | 0.8612 | |
|
| 0.4018 | 2.0460 | 800 | 0.3394 | 0.8580 | 0.8610 | |
|
| 0.4018 | 2.5575 | 1000 | 0.2938 | 0.8747 | 0.8760 | |
|
| 0.4018 | 3.0691 | 1200 | 0.2903 | 0.8829 | 0.8841 | |
|
| 0.4018 | 3.5806 | 1400 | 0.2871 | 0.8854 | 0.8859 | |
|
| 0.2576 | 4.0921 | 1600 | 0.2955 | 0.8864 | 0.8873 | |
|
| 0.2576 | 4.6036 | 1800 | 0.2831 | 0.8887 | 0.8894 | |
|
| 0.2576 | 5.1151 | 2000 | 0.2952 | 0.8885 | 0.8898 | |
|
| 0.2576 | 5.6266 | 2200 | 0.2947 | 0.8872 | 0.8881 | |
|
| 0.2036 | 6.1381 | 2400 | 0.3086 | 0.8887 | 0.8902 | |
|
| 0.2036 | 6.6496 | 2600 | 0.2939 | 0.8924 | 0.8931 | |
|
| 0.2036 | 7.1611 | 2800 | 0.3368 | 0.8879 | 0.8895 | |
|
| 0.2036 | 7.6726 | 3000 | 0.3162 | 0.8924 | 0.8932 | |
|
| 0.1616 | 8.1841 | 3200 | 0.3423 | 0.8909 | 0.8919 | |
|
| 0.1616 | 8.6957 | 3400 | 0.3475 | 0.8940 | 0.8945 | |
|
| 0.1616 | 9.2072 | 3600 | 0.3546 | 0.8914 | 0.8923 | |
|
| 0.1616 | 9.7187 | 3800 | 0.3505 | 0.8941 | 0.8947 | |
|
| 0.1291 | 10.2302 | 4000 | 0.3850 | 0.8934 | 0.8941 | |
|
| 0.1291 | 10.7417 | 4200 | 0.3718 | 0.8957 | 0.8963 | |
|
| 0.1291 | 11.2532 | 4400 | 0.3893 | 0.8916 | 0.8924 | |
|
| 0.1291 | 11.7647 | 4600 | 0.3923 | 0.8949 | 0.8955 | |
|
| 0.1047 | 12.2762 | 4800 | 0.4213 | 0.8959 | 0.8968 | |
|
| 0.1047 | 12.7877 | 5000 | 0.3877 | 0.8951 | 0.8961 | |
|
| 0.1047 | 13.2992 | 5200 | 0.3972 | 0.8990 | 0.8992 | |
|
| 0.1047 | 13.8107 | 5400 | 0.3896 | 0.8928 | 0.8937 | |
|
| 0.0865 | 14.3223 | 5600 | 0.4290 | 0.8961 | 0.8964 | |
|
| 0.0865 | 14.8338 | 5800 | 0.4360 | 0.8977 | 0.8979 | |
|
| 0.0865 | 15.3453 | 6000 | 0.4398 | 0.8958 | 0.8963 | |
|
| 0.0865 | 15.8568 | 6200 | 0.4357 | 0.8951 | 0.8955 | |
|
| 0.0726 | 16.3683 | 6400 | 0.4662 | 0.8952 | 0.8953 | |
|
| 0.0726 | 16.8798 | 6600 | 0.4608 | 0.8945 | 0.8955 | |
|
| 0.0726 | 17.3913 | 6800 | 0.4714 | 0.8952 | 0.8954 | |
|
| 0.0726 | 17.9028 | 7000 | 0.4638 | 0.8967 | 0.8971 | |
|
| 0.0612 | 18.4143 | 7200 | 0.4783 | 0.8969 | 0.8971 | |
|
| 0.0612 | 18.9258 | 7400 | 0.4856 | 0.8962 | 0.8967 | |
|
| 0.0612 | 19.4373 | 7600 | 0.4779 | 0.8958 | 0.8963 | |
|
| 0.0612 | 19.9488 | 7800 | 0.4792 | 0.8964 | 0.8969 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
