metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- simplification
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: dar-ai_emotions
results: []
dar-ai_emotions
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2181
- Precision: 0.9316
- Recall: 0.9275
- F1: 0.9284
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.4349 | 1.0 | 1000 | 0.2899 | 0.9129 | 0.9045 | 0.9059 |
| 0.2468 | 2.0 | 2000 | 0.2258 | 0.9368 | 0.9305 | 0.9318 |
| 0.1648 | 3.0 | 3000 | 0.2181 | 0.9316 | 0.9275 | 0.9284 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1