metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: xlm_r_base-finetuned_after_mrp-v2-lilac-water-12
results: []
xlm_r_base-finetuned_after_mrp-v2-lilac-water-12
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4879
- Precision 0: 0.8632
- Precision 1: 0.8038
- Recall 0: 0.8667
- Recall 1: 0.7990
- F1 0: 0.8649
- F1 1: 0.8014
- Precision Weighted: 0.8391
- Recall Weighted: 0.8392
- F1 Weighted: 0.8391
- F1 Macro: 0.8332
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision 0 | Precision 1 | Recall 0 | Recall 1 | F1 0 | F1 1 | Precision Weighted | Recall Weighted | F1 Weighted | F1 Macro |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5884 | 1.0 | 469 | 0.4450 | 0.8408 | 0.7812 | 0.8539 | 0.7635 | 0.8473 | 0.7723 | 0.8167 | 0.8172 | 0.8169 | 0.8098 |
| 0.3866 | 2.0 | 938 | 0.4053 | 0.8801 | 0.7518 | 0.8108 | 0.8384 | 0.8440 | 0.7927 | 0.8280 | 0.822 | 0.8232 | 0.8184 |
| 0.3641 | 3.0 | 1407 | 0.3683 | 0.8583 | 0.8091 | 0.8727 | 0.7892 | 0.8654 | 0.7990 | 0.8383 | 0.8388 | 0.8385 | 0.8322 |
| 0.282 | 4.0 | 1876 | 0.3963 | 0.8551 | 0.8096 | 0.8741 | 0.7833 | 0.8645 | 0.7962 | 0.8366 | 0.8372 | 0.8367 | 0.8303 |
| 0.2128 | 5.0 | 2345 | 0.4879 | 0.8632 | 0.8038 | 0.8667 | 0.7990 | 0.8649 | 0.8014 | 0.8391 | 0.8392 | 0.8391 | 0.8332 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1