|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: FacebookAI/xlm-roberta-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
- recall |
|
|
model-index: |
|
|
- name: xlmr_synset_classifier_pair |
|
|
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. --> |
|
|
|
|
|
# xlmr_synset_classifier_pair |
|
|
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4819 |
|
|
- Accuracy: 0.8520 |
|
|
- F1: 0.8428 |
|
|
- Precision: 0.8474 |
|
|
- Recall: 0.8520 |
|
|
- F1 Macro: 0.6767 |
|
|
- Precision Macro: 0.6791 |
|
|
- Recall Macro: 0.6942 |
|
|
- F1 Micro: 0.8520 |
|
|
- Precision Micro: 0.8520 |
|
|
- Recall Micro: 0.8520 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 128 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- num_epochs: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:| |
|
|
| 3.5852 | 0.6221 | 100 | 2.1752 | 0.5101 | 0.4039 | 0.3639 | 0.5101 | 0.1413 | 0.1482 | 0.1624 | 0.5101 | 0.5101 | 0.5101 | |
|
|
| 1.332 | 1.2442 | 200 | 0.7470 | 0.7936 | 0.7645 | 0.7729 | 0.7936 | 0.4907 | 0.4864 | 0.5309 | 0.7936 | 0.7936 | 0.7936 | |
|
|
| 0.7141 | 1.8663 | 300 | 0.5803 | 0.8291 | 0.8145 | 0.8311 | 0.8291 | 0.5873 | 0.5801 | 0.6215 | 0.8291 | 0.8291 | 0.8291 | |
|
|
| 0.5558 | 2.4883 | 400 | 0.5548 | 0.8398 | 0.8264 | 0.8336 | 0.8398 | 0.6228 | 0.6142 | 0.6467 | 0.8398 | 0.8398 | 0.8398 | |
|
|
| 0.5017 | 3.1104 | 500 | 0.5036 | 0.8448 | 0.8315 | 0.8398 | 0.8448 | 0.6279 | 0.6192 | 0.6553 | 0.8448 | 0.8448 | 0.8448 | |
|
|
| 0.4131 | 3.7325 | 600 | 0.4765 | 0.8457 | 0.8365 | 0.8368 | 0.8457 | 0.6435 | 0.6397 | 0.6586 | 0.8457 | 0.8457 | 0.8457 | |
|
|
| 0.3848 | 4.3546 | 700 | 0.4845 | 0.8497 | 0.8398 | 0.8457 | 0.8497 | 0.6779 | 0.6796 | 0.6972 | 0.8497 | 0.8497 | 0.8497 | |
|
|
| 0.3476 | 4.9767 | 800 | 0.4819 | 0.8520 | 0.8428 | 0.8474 | 0.8520 | 0.6767 | 0.6791 | 0.6942 | 0.8520 | 0.8520 | 0.8520 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.2 |
|
|
- Pytorch 2.3.1+cu121 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
