metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
model-index:
- name: bert_emo_classifier
results: []
bert_emo_classifier
This model is a fine-tuned version of bert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2715
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.888 | 0.25 | 500 | 0.4122 |
| 0.338 | 0.5 | 1000 | 0.2967 |
| 0.2527 | 0.75 | 1500 | 0.2798 |
| 0.2389 | 1.0 | 2000 | 0.2554 |
| 0.161 | 1.25 | 2500 | 0.2172 |
| 0.1687 | 1.5 | 3000 | 0.1868 |
| 0.136 | 1.75 | 3500 | 0.1909 |
| 0.1733 | 2.0 | 4000 | 0.2073 |
| 0.1088 | 2.25 | 4500 | 0.2176 |
| 0.1109 | 2.5 | 5000 | 0.2136 |
| 0.1241 | 2.75 | 5500 | 0.2356 |
| 0.1232 | 3.0 | 6000 | 0.2241 |
| 0.074 | 3.25 | 6500 | 0.2542 |
| 0.0761 | 3.5 | 7000 | 0.2682 |
| 0.0751 | 3.75 | 7500 | 0.2674 |
| 0.0652 | 4.0 | 8000 | 0.2715 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.10.3