metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: XMLRoberta_Dataset9kMeta
results: []
XMLRoberta_Dataset9kMeta
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2475
- Accuracy: 0.9498
- F1: 0.9499
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|---|
| No log | 1.6461 | 200 | 0.2426 | 0.9319 | 0.9192 |
| 0.4716 | 3.2922 | 400 | 0.2306 | 0.9226 | 0.9152 |
| 0.1801 | 4.9383 | 600 | 0.2223 | 0.9464 | 0.9457 |
| 0.118 | 6.5844 | 800 | 0.2062 | 0.9498 | 0.9492 |
| 0.0819 | 8.2305 | 1000 | 0.2399 | 0.9498 | 0.9504 |
| 0.0819 | 9.8765 | 1200 | 0.2475 | 0.9498 | 0.9499 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1