metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-xlm-roberta-base-label_vector
results: []
edos-2023-baseline-xlm-roberta-base-label_vector
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: 1.1101
- F1: 0.3846
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 2.1158 | 1.18 | 100 | 1.8798 | 0.1060 |
| 1.8474 | 2.35 | 200 | 1.6564 | 0.1666 |
| 1.7147 | 3.53 | 300 | 1.5267 | 0.2450 |
| 1.5738 | 4.71 | 400 | 1.4163 | 0.2523 |
| 1.5035 | 5.88 | 500 | 1.2823 | 0.3144 |
| 1.397 | 7.06 | 600 | 1.2035 | 0.3422 |
| 1.3436 | 8.24 | 700 | 1.1409 | 0.3740 |
| 1.2812 | 9.41 | 800 | 1.1101 | 0.3846 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2