xlm_r_base-finetuned_after_mrp-v2-winter-morning-8
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: 0.3928
- Precision 0: 0.8692
- Precision 1: 0.8174
- Recall 0: 0.8768
- Recall 1: 0.8069
- F1 0: 0.8729
- F1 1: 0.8121
- Precision Weighted: 0.8481
- Recall Weighted: 0.8484
- F1 Weighted: 0.8482
- F1 Macro: 0.8425
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.5435 | 1.0 | 469 | 0.4939 | 0.7696 | 0.9088 | 0.9603 | 0.5793 | 0.8544 | 0.7076 | 0.8261 | 0.8056 | 0.7948 | 0.7810 |
0.383 | 2.0 | 938 | 0.3987 | 0.8647 | 0.7743 | 0.8391 | 0.8079 | 0.8517 | 0.7907 | 0.8280 | 0.8264 | 0.8269 | 0.8212 |
0.376 | 3.0 | 1407 | 0.3737 | 0.8511 | 0.8220 | 0.8855 | 0.7734 | 0.8680 | 0.7970 | 0.8393 | 0.84 | 0.8391 | 0.8325 |
0.2841 | 4.0 | 1876 | 0.3928 | 0.8692 | 0.8174 | 0.8768 | 0.8069 | 0.8729 | 0.8121 | 0.8481 | 0.8484 | 0.8482 | 0.8425 |
0.225 | 5.0 | 2345 | 0.4836 | 0.8597 | 0.8026 | 0.8667 | 0.7931 | 0.8632 | 0.7978 | 0.8365 | 0.8368 | 0.8366 | 0.8305 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 1