metadata
library_name: transformers
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mindmate-emotion-classifier
results: []
mindmate-emotion-classifier
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5719
- Accuracy: 0.7976
- F1 Weighted: 0.7962
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: 32
- eval_batch_size: 64
- 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: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted |
|---|---|---|---|---|---|
| 0.6452 | 1.0 | 2268 | 0.6177 | 0.7778 | 0.7804 |
| 0.5152 | 2.0 | 4536 | 0.5764 | 0.7867 | 0.7849 |
| 0.4566 | 3.0 | 6804 | 0.5719 | 0.7976 | 0.7962 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2