metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: deberta-emotion-recognition
results: []
deberta-emotion-recognition
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5153
- Accuracy: 0.9325
- F1: 0.9075
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: 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_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4726 | 1.0 | 1000 | 0.4306 | 0.8585 | 0.8298 |
| 0.237 | 2.0 | 2000 | 0.2473 | 0.927 | 0.9025 |
| 0.2206 | 3.0 | 3000 | 0.1694 | 0.9365 | 0.9126 |
| 0.1654 | 4.0 | 4000 | 0.2024 | 0.934 | 0.9134 |
| 0.1138 | 5.0 | 5000 | 0.2417 | 0.9325 | 0.9082 |
| 0.4768 | 6.0 | 6000 | 0.2855 | 0.9385 | 0.9169 |
| 0.0168 | 7.0 | 7000 | 0.4197 | 0.9385 | 0.9169 |
| 0.0121 | 8.0 | 8000 | 0.4521 | 0.934 | 0.9119 |
| 0.1931 | 9.0 | 9000 | 0.5252 | 0.9335 | 0.9095 |
| 0.0221 | 10.0 | 10000 | 0.5046 | 0.9395 | 0.9160 |
| 0.0112 | 11.0 | 11000 | 0.5153 | 0.9325 | 0.9075 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2