metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: sentiment-5Epochs
results: []
sentiment-5Epochs
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4947
- Accuracy: 0.8719
- F1: 0.8685
- Precision: 0.8919
- Recall: 0.8463
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.3566 | 1.0 | 7088 | 0.3987 | 0.8627 | 0.8505 | 0.9336 | 0.7810 |
| 0.3468 | 2.0 | 14176 | 0.3861 | 0.8702 | 0.8638 | 0.9085 | 0.8232 |
| 0.335 | 3.0 | 21264 | 0.4421 | 0.8759 | 0.8697 | 0.9154 | 0.8283 |
| 0.3003 | 4.0 | 28352 | 0.4601 | 0.8754 | 0.8696 | 0.9119 | 0.8311 |
| 0.2995 | 5.0 | 35440 | 0.4947 | 0.8719 | 0.8685 | 0.8919 | 0.8463 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0
- Datasets 2.0.0
- Tokenizers 0.11.6