metadata
library_name: transformers
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: emotion_model
results: []
emotion_model
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2936
- Micro F1: 0.7177
- Macro F1: 0.5792
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: 1.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Macro F1 |
|---|---|---|---|---|---|
| 0.4725 | 1.0 | 143 | 0.3610 | 0.5857 | 0.3394 |
| 0.3219 | 2.0 | 286 | 0.3058 | 0.6957 | 0.5022 |
| 0.2892 | 3.0 | 429 | 0.3067 | 0.6814 | 0.4921 |
| 0.263 | 4.0 | 572 | 0.2915 | 0.7037 | 0.5397 |
| 0.2399 | 5.0 | 715 | 0.2911 | 0.7108 | 0.5625 |
| 0.2255 | 6.0 | 858 | 0.2922 | 0.7115 | 0.5833 |
| 0.2147 | 7.0 | 1001 | 0.2877 | 0.7115 | 0.5792 |
| 0.1989 | 8.0 | 1144 | 0.2922 | 0.7176 | 0.5882 |
| 0.1908 | 9.0 | 1287 | 0.2956 | 0.7162 | 0.5816 |
| 0.1851 | 10.0 | 1430 | 0.2970 | 0.7193 | 0.5984 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.3.1.post300
- Datasets 2.2.1
- Tokenizers 0.21.0