metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: xlm-roberta-sentiment-tweets-8bs
results: []
xlm-roberta-sentiment-tweets-8bs
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6661
- Accuracy: 0.7170
- Precision: 0.7162
- Recall: 0.7051
- F1: 0.7042
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.0299 | 1.0 | 363 | 0.8129 | 0.6618 | 0.6556 | 0.6661 | 0.6493 |
| 0.7514 | 2.0 | 726 | 0.6661 | 0.7170 | 0.7162 | 0.7051 | 0.7042 |
| 0.6169 | 3.0 | 1089 | 0.7025 | 0.7129 | 0.7058 | 0.7077 | 0.7036 |
| 0.4881 | 4.0 | 1452 | 0.7650 | 0.6991 | 0.7074 | 0.6881 | 0.6934 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2