xlm_r_base-finetuned_after_mrp-v2-denim-sound-4
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: 0.4251
- Precision 0: 0.8610
- Precision 1: 0.7859
- Recall 0: 0.8512
- Recall 1: 0.7990
- F1 0: 0.8561
- F1 1: 0.7924
- Precision Weighted: 0.8305
- Recall Weighted: 0.83
- F1 Weighted: 0.8302
- Accuracy: 0.83
- F1 Macro: 0.8242
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 | Accuracy | F1 Macro |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.512 | 1.0 | 469 | 0.6133 | 0.6961 | 0.8436 | 0.9502 | 0.3931 | 0.8035 | 0.5363 | 0.7560 | 0.724 | 0.6950 | 0.724 | 0.6699 |
0.5206 | 2.0 | 938 | 0.4096 | 0.8334 | 0.7882 | 0.8626 | 0.7478 | 0.8478 | 0.7674 | 0.8151 | 0.816 | 0.8152 | 0.816 | 0.8076 |
0.4224 | 3.0 | 1407 | 0.3889 | 0.8442 | 0.8122 | 0.8795 | 0.7626 | 0.8615 | 0.7866 | 0.8312 | 0.832 | 0.8311 | 0.832 | 0.8240 |
0.2326 | 4.0 | 1876 | 0.3990 | 0.8451 | 0.8109 | 0.8781 | 0.7645 | 0.8613 | 0.7870 | 0.8312 | 0.832 | 0.8311 | 0.832 | 0.8242 |
0.2544 | 5.0 | 2345 | 0.4251 | 0.8610 | 0.7859 | 0.8512 | 0.7990 | 0.8561 | 0.7924 | 0.8305 | 0.83 | 0.8302 | 0.83 | 0.8242 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1