metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: xlm_r_large-baseline_model-v2-fallen-oath-3
results: []
xlm_r_large-baseline_model-v2-fallen-oath-3
This model is a fine-tuned version of xlm-roberta-large on SOLD dataset. It achieves the following results on the evaluation set:
- Loss: 0.5036
- Precision 0: 0.8766
- Precision 1: 0.7911
- Recall 0: 0.8512
- Recall 1: 0.8246
- F1 0: 0.8637
- F1 1: 0.8075
- Precision Weighted: 0.8419
- Recall Weighted: 0.8404
- F1 Weighted: 0.8409
- F1 Macro: 0.8356
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4937 | 1.0 | 469 | 0.4268 | 0.8346 | 0.7933 | 0.8667 | 0.7488 | 0.8503 | 0.7704 | 0.8179 | 0.8188 | 0.8179 | 0.8104 |
| 0.3945 | 2.0 | 938 | 0.3987 | 0.9083 | 0.7168 | 0.7603 | 0.8877 | 0.8277 | 0.7931 | 0.8305 | 0.812 | 0.8137 | 0.8104 |
| 0.3721 | 3.0 | 1407 | 0.3612 | 0.8654 | 0.7992 | 0.8620 | 0.8039 | 0.8637 | 0.8016 | 0.8386 | 0.8384 | 0.8385 | 0.8326 |
| 0.2721 | 4.0 | 1876 | 0.4191 | 0.8514 | 0.8246 | 0.8875 | 0.7734 | 0.8691 | 0.7982 | 0.8405 | 0.8412 | 0.8403 | 0.8336 |
| 0.2144 | 5.0 | 2345 | 0.5036 | 0.8766 | 0.7911 | 0.8512 | 0.8246 | 0.8637 | 0.8075 | 0.8419 | 0.8404 | 0.8409 | 0.8356 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1