metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- massive
metrics:
- accuracy
model-index:
- name: distilroberta-base-Massive-intent
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: massive
type: massive
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.8937530742744713
distilroberta-base-Massive-intent
This model is a fine-tuned version of distilroberta-base on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.6618
- Accuracy: 0.8938
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.41 | 1.0 | 720 | 0.6742 | 0.8288 |
| 0.4978 | 2.0 | 1440 | 0.5150 | 0.8751 |
| 0.3009 | 3.0 | 2160 | 0.5705 | 0.8790 |
| 0.1953 | 4.0 | 2880 | 0.5887 | 0.8795 |
| 0.127 | 5.0 | 3600 | 0.6123 | 0.8810 |
| 0.0914 | 6.0 | 4320 | 0.6575 | 0.8834 |
| 0.0583 | 7.0 | 5040 | 0.6618 | 0.8938 |
| 0.0355 | 8.0 | 5760 | 0.7591 | 0.8864 |
| 0.0259 | 9.0 | 6480 | 0.8087 | 0.8780 |
| 0.02 | 10.0 | 7200 | 0.7964 | 0.8888 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1