metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: training_dir
results: []
training_dir
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: 0.4296
- Accuracy: 0.8650
- F1: 0.8647
- Precision: 0.8662
- Recall: 0.8650
- Accuracy Label Communication Issue: 0.3878
- Accuracy Label General Query: 0.5135
- Accuracy Label Other: 0.8535
- Accuracy Label Praise: 0.7987
- Accuracy Label Service Issue: 0.9503
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Accuracy Label Communication Issue | Accuracy Label General Query | Accuracy Label Other | Accuracy Label Praise | Accuracy Label Service Issue |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4926 | 1.0 | 220 | 0.4769 | 0.8351 | 0.7977 | 0.7654 | 0.8351 | 0.0 | 0.0 | 0.8479 | 0.7315 | 0.9780 |
| 0.4722 | 2.0 | 440 | 0.4490 | 0.8138 | 0.8335 | 0.8685 | 0.8138 | 0.5918 | 0.2973 | 0.8592 | 0.8523 | 0.8358 |
| 0.1949 | 3.0 | 660 | 0.4296 | 0.8650 | 0.8647 | 0.8662 | 0.8650 | 0.3878 | 0.5135 | 0.8535 | 0.7987 | 0.9503 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1