metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-finetuned-WebClassification-v2-smalllinguaMultiv2
results: []
roberta-finetuned-WebClassification-v2-smalllinguaMultiv2
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: 1.0950
- Accuracy: 0.7742
- F1: 0.7742
- Precision: 0.7742
- Recall: 0.7742
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 | 48 | 2.8245 | 0.2796 | 0.2796 | 0.2796 | 0.2796 |
| No log | 2.0 | 96 | 2.2338 | 0.4301 | 0.4301 | 0.4301 | 0.4301 |
| No log | 3.0 | 144 | 1.9060 | 0.5269 | 0.5269 | 0.5269 | 0.5269 |
| No log | 4.0 | 192 | 1.5349 | 0.6022 | 0.6022 | 0.6022 | 0.6022 |
| No log | 5.0 | 240 | 1.4208 | 0.6882 | 0.6882 | 0.6882 | 0.6882 |
| No log | 6.0 | 288 | 1.3330 | 0.7204 | 0.7204 | 0.7204 | 0.7204 |
| No log | 7.0 | 336 | 1.2037 | 0.7097 | 0.7097 | 0.7097 | 0.7097 |
| No log | 8.0 | 384 | 1.1414 | 0.7419 | 0.7419 | 0.7419 | 0.7419 |
| No log | 9.0 | 432 | 1.0950 | 0.7742 | 0.7742 | 0.7742 | 0.7742 |
| No log | 10.0 | 480 | 1.0883 | 0.7634 | 0.7634 | 0.7634 | 0.7634 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3