metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: xlm-roberta-base-Final_Mixed-aug_insert_w2v-1
results: []
xlm-roberta-base-Final_Mixed-aug_insert_w2v-1
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3222
- Accuracy: 0.75
- F1: 0.7494
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: 41
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.9974 | 1.0 | 86 | 0.7220 | 0.7 | 0.6853 |
| 0.6771 | 2.0 | 172 | 0.5830 | 0.75 | 0.7414 |
| 0.4881 | 3.0 | 258 | 0.7321 | 0.73 | 0.7233 |
| 0.3431 | 4.0 | 344 | 0.8026 | 0.76 | 0.7555 |
| 0.2209 | 5.0 | 430 | 0.9511 | 0.75 | 0.7443 |
| 0.1558 | 6.0 | 516 | 1.2518 | 0.72 | 0.7046 |
| 0.1311 | 7.0 | 602 | 1.2975 | 0.74 | 0.7397 |
| 0.1027 | 8.0 | 688 | 1.3222 | 0.75 | 0.7494 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3