metadata
license: mit
tags:
- generated_from_keras_callback
datasets:
- go_emotions
- emotion
base_model: microsoft/xtremedistil-l6-h256-uncased
model-index:
- name: jonaskoenig/xtremedistil-l6-h256-uncased-go-emotion
results: []
jonaskoenig/xtremedistil-l6-h256-uncased-go-emotion
This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on go_emotions and emotion. It achieves the following results on the evaluation set:
- Train Loss: 0.0282
- Train Binary Crossentropy: 0.4836
- Epoch: 8
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:
- optimizer: {'name': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Binary Crossentropy | Epoch |
|---|---|---|
| 0.0487 | 0.6401 | 0 |
| 0.0348 | 0.5925 | 1 |
| 0.0319 | 0.5393 | 2 |
| 0.0306 | 0.5168 | 3 |
| 0.0298 | 0.5045 | 4 |
| 0.0292 | 0.4970 | 5 |
| 0.0288 | 0.4916 | 6 |
| 0.0284 | 0.4878 | 7 |
| 0.0282 | 0.4836 | 8 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.9.1
- Datasets 2.3.2
- Tokenizers 0.12.1