metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-finetuned-WebClassification-v2-smalllinguaENv2
results: []
roberta-finetuned-WebClassification-v2-smalllinguaENv2
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: 1.8560
- Accuracy: 0.525
- F1: 0.525
- Precision: 0.525
- Recall: 0.525
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 20 | 2.9637 | 0.1 | 0.1000 | 0.1 | 0.1 |
| No log | 2.0 | 40 | 2.7821 | 0.225 | 0.225 | 0.225 | 0.225 |
| No log | 3.0 | 60 | 2.5523 | 0.4 | 0.4000 | 0.4 | 0.4 |
| No log | 4.0 | 80 | 2.3580 | 0.4 | 0.4000 | 0.4 | 0.4 |
| No log | 5.0 | 100 | 2.2043 | 0.375 | 0.375 | 0.375 | 0.375 |
| No log | 6.0 | 120 | 2.0265 | 0.475 | 0.4750 | 0.475 | 0.475 |
| No log | 7.0 | 140 | 1.9271 | 0.5 | 0.5 | 0.5 | 0.5 |
| No log | 8.0 | 160 | 1.8560 | 0.525 | 0.525 | 0.525 | 0.525 |
| No log | 9.0 | 180 | 1.8013 | 0.525 | 0.525 | 0.525 | 0.525 |
| No log | 10.0 | 200 | 1.7784 | 0.525 | 0.525 | 0.525 | 0.525 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3