metadata
library_name: transformers
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-emotion-predictor
results: []
roberta-emotion-predictor
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2439
- Macro F1: 0.3485
- Weighted F1: 0.3644
- Accuracy: 0.3689
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: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Weighted F1 | Accuracy |
|---|---|---|---|---|---|---|
| 2.4474 | 1.0 | 1625 | 2.4144 | 0.2943 | 0.3186 | 0.3269 |
| 2.261 | 2.0 | 3250 | 2.2982 | 0.3330 | 0.3523 | 0.3577 |
| 2.1515 | 3.0 | 4875 | 2.2638 | 0.3393 | 0.3567 | 0.3625 |
| 2.0117 | 4.0 | 6500 | 2.2536 | 0.3456 | 0.3634 | 0.3684 |
| 1.9649 | 5.0 | 8125 | 2.2569 | 0.3443 | 0.3630 | 0.3687 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 2.14.7
- Tokenizers 0.22.2