metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased__subj__all-train
results: []
distilbert-base-uncased__subj__all-train
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3193
- Accuracy: 0.9485
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1992 | 1.0 | 500 | 0.1236 | 0.963 |
| 0.084 | 2.0 | 1000 | 0.1428 | 0.963 |
| 0.0333 | 3.0 | 1500 | 0.1906 | 0.965 |
| 0.0159 | 4.0 | 2000 | 0.3193 | 0.9485 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu102
- Datasets 1.17.0
- Tokenizers 0.10.3